{
  "status": "partial",
  "completed_count": 66,
  "applicable_count": 66,
  "failed_count": 0,
  "schema_version": 7,
  "config_hash": "dc07cd5433bf681a",
  "data": {
    "scenes": [
      {
        "scene_index": 1,
        "heading": "S#1. 숲속 / 해 질 무렵",
        "beat_title": "이빨 자국이 선명한 허벅지 상처",
        "representative_moment": "핏방울이 흘러내리는 남자의 맨살 허벅지가 클로즈업된 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up, low angle at knee height, cold blue-gray dusk lighting with sharp crimson accent",
            "t2i_prompt": "Photorealistic cinematic still. An extreme close-up low angle at knee height, focusing on the exposed bare thigh of a middle-aged East Asian man, captured mid-stride stumbling toward the right. A deep bite mark sits center-left on the clammy skin, with fresh crimson blood drops tracking downward. Cold blue-gray dusk ambient light reflects on the leg surface, rendering the blood as a sharp crimson accent. The rolled-up edge of a fluorescent hiking pant leg enters the top frame edge. [L01: Blurred dark wet undergrowth scrapes across the lower and side frame boundaries. The background behind the leg is cropped into soft fragments, revealing a narrow muddy forest floor and dark vertical tree trunks swallowed by chilling, deep pervasive shadows.]",
            "outfit_assignments": [],
            "source_facts": [
              "Scene text: 허벅지에 커다란 이빨 자국. 피가 흐르고.",
              "Shot 3: 한국인 남자의 맨살 허벅지에 선명하게 파인 커다란 이빨 자국과 핏방울의 클로즈업."
            ],
            "visual_inferences": [
              "fixed_element dusk_forest_lighting: deep pervasive shadows and cold blue-gray dusk light.",
              "Mid-stride stumbling motion indicated by blood tracking downward and tense leg muscles.",
              "A slice of the hiking pant leg (from outlook O09) is visible at the top edge to anchor the character's clothing without breaking the extreme close-up framing."
            ],
            "creative_decisions": [
              "Utilizing a tight body-part focus framing that isolates the wound, strictly adhering to the body_part_focus_rule by using a common noun and omitting the face/full body.",
              "Using blurred foreground foliage at the edges to simulate the frantic, scraping movement through the dense forest."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "847110684b30acfa",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "6aaacd9d20465357",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "No dependent scene",
        "_shot_index": 3,
        "visible_entities": [
          "C07",
          "P01",
          "L01"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 1,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view holds an extreme close-up (ECU) low angle beside the 한국인 남자's bare thigh at knee height, handheld and shaking as brush scrapes across the frame edges. The bite mark sits center-left with blood drops tracking downward, while the rest of the body and forest are cropped into blurred fragments so the wound becomes the only readable point of panic.",
            "lighting_mood": "Cold blue-gray dusk light leaks through foliage, with the blood rendered as a sharp crimson accent against clammy skin.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C07",
              "P01",
              "L01"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C07",
                "outlook_id": "O09"
              },
              {
                "character_id": "C15",
                "outlook_id": "O15"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_forest_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A dense, overgrown forest environment enveloped in cold, fading blue-gray dusk light. The surrounding foliage and tree trunks are partially obscured by deep, pervasive shadows, creating a chilling and eerie atmosphere.",
                "applies_to_shots": [
                  3,
                  4,
                  5
                ],
                "source_facts": [
                  "Scene text: 숲속 / 해 질 무렵 (Forest / Dusk)",
                  "Shot 3: Cold blue-gray dusk light leaks through foliage",
                  "Shot 4: Fading coastal-blue dusk",
                  "Shot 5: cold dusk tones, using the last gray sky"
                ],
                "visual_inferences": [
                  "Deep, pervasive shadows swallowing the background elements due to the extremely low light level"
                ],
                "creative_decisions": [
                  "Applying a consistent cold blue-gray color palette across extreme close-ups and wide shots to anchor the visual timeline right before nightfall"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C07O09",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C15O15",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "98876b93167416ec"
      },
      {
        "scene_index": 1,
        "heading": "S#1. 숲속 / 해 질 무렵",
        "beat_title": "정체불명의 위협을 피해 달아나는 공포",
        "representative_moment": "겁에 질려 동공이 확장된 C07의 땀에 젖은 얼굴 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level handheld tight framing with shallow depth of field, fading coastal-blue dusk lighting",
            "t2i_prompt": "Photorealistic cinematic still. C07O09 in a fluorescent hiking jacket, a young East Asian man, tight framing on his terrified expression, shoulder visible at the lower frame edge, stumbling forward in mid-stumble, body angled in three-quarter left. His head is turned slightly, eyes fixed on the dark trees past the camera right. Focus on his wide, dilated pupils and sweat-slicked skin. Cold, fading blue-gray dusk light washes across his damp cheek and jaw, body volume preserved against the dim ambient fill. The background is composed of [L01: soft streaked narrow forest path just below his shoulder level, dark negative space of dense shadowed trees beside his eyeline, occasional blurred thin swaying branches near the frame edges]. Eye-level handheld shot, shallow depth of field turning the background foliage into streaks.",
            "outfit_assignments": [
              {
                "character_id": "C07",
                "outlook_id": "O09"
              }
            ],
            "source_facts": [
              "Scene text: 잔뜩 겁에 질린 남자 표정(T.S)",
              "Shot description: sweat-slick face, pupils blown wide, gaze snapping past camera right toward the unseen darkness",
              "DP instruction: three_quarter_left, stumbling forward panting, eyes on dark trees"
            ],
            "visual_inferences": [
              "fixed_element dusk_forest_lighting: cold fading blue-gray dusk light, deep shadows",
              "mid-stumble posture freezing the motion of his frantic escape",
              "fluorescent hiking jacket derived from O09 outlook"
            ],
            "creative_decisions": [
              "Used 'tight framing on his terrified expression, shoulder visible at the lower frame edge' to comply with close framing face rules, preventing the floating head artifact",
              "Light 'washes across his damp cheek' instead of cutting, to safely highlight the sweat-slicked texture without unintended physical bisection",
              "Described the immediate surroundings inside the L01 block to support the skipped_close_framing background binding policy"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "f32f7471a33e207e",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "0d9873c7e50d66b8",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 1,
        "dependency_reason": "동일 씬 내 이전 샷의 푸른빛이 도는 해 질 무렵 숲속 조명(dusk_forest_lighting) 연속성 유지",
        "_shot_index": 4,
        "visible_entities": [
          "C07",
          "P01",
          "L01"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 1,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view shifts to a face-filling close-up (CU) eye-level handheld shot from the 한국인 남자's front-left, backing away just ahead of him on the forest path. His sweat-slick face occupies nearly the whole frame, pupils blown wide and gaze snapping past camera right toward the unseen darkness, with shallow DOF turning the trees into streaks.",
            "lighting_mood": "Fading coastal-blue dusk and damp skin highlights create a cold, breathless panic, with shadows swallowing the background.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C07",
              "P01",
              "L01"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C07",
                "outlook_id": "O09"
              },
              {
                "character_id": "C15",
                "outlook_id": "O15"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_forest_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A dense, overgrown forest environment enveloped in cold, fading blue-gray dusk light. The surrounding foliage and tree trunks are partially obscured by deep, pervasive shadows, creating a chilling and eerie atmosphere.",
                "applies_to_shots": [
                  3,
                  4,
                  5
                ],
                "source_facts": [
                  "Scene text: 숲속 / 해 질 무렵 (Forest / Dusk)",
                  "Shot 3: Cold blue-gray dusk light leaks through foliage",
                  "Shot 4: Fading coastal-blue dusk",
                  "Shot 5: cold dusk tones, using the last gray sky"
                ],
                "visual_inferences": [
                  "Deep, pervasive shadows swallowing the background elements due to the extremely low light level"
                ],
                "creative_decisions": [
                  "Applying a consistent cold blue-gray color palette across extreme close-ups and wide shots to anchor the visual timeline right before nightfall"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 1,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C07O09",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C15O15",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "fb5b08f9419d0736"
      },
      {
        "scene_index": 1,
        "heading": "S#1. 숲속 / 해 질 무렵",
        "beat_title": "공중에서 덮쳐오는 검은 형상",
        "representative_moment": "어두운 숲속에서 C15가 공중으로 뛰어올라 C07을 향해 덮치는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "underexposed low angle composition aimed upward, cold blue-gray dusk lighting, backlit silhouette effect with rim lighting",
            "t2i_prompt": "Photorealistic cinematic still. Underexposed low angle composition aimed upward. Focus on the airborne attacker in the upper center of the frame. C15O15 in a ragged black cloak, an East Asian figure, facing the camera, suspended mid-leap in the upper center. He appears as a predatory backlit figure, rim light catching on his shoulders and outstretched arms, body volume preserved against the dim ambient fill, face in deep shadow but jaw contour visible, eyes fixed on the man below. His cloak trails upward in the direction opposite to his downward lunge. Occupying the lower frame and sharing the muddy forest clearing anchor, C07O09 in a neon hiking jacket, a middle-aged East Asian man, recoils on his back foot. He is positioned with his back to the camera but his head is turned to show a terrified side profile, eyes fixed on the attacker above. [L01: A dense, overgrown forest clearing with muddy, uneven ground scattered with leaves, enveloped in cold, fading blue-gray dusk light. A clouded gray sky forms a dim backdrop, framed by a nearly featureless black tree canopy above.] Deep, pervasive shadows swallow the surrounding foliage.",
            "outfit_assignments": [
              {
                "character_id": "C07",
                "outlook_id": "O09"
              },
              {
                "character_id": "C15",
                "outlook_id": "O15"
              }
            ],
            "source_facts": [
              "Scene text: 우거진 수풀을 헤치며 도망치는. 벗겨진 한쪽 신발. 잔뜩 겁에 질린 남자 표정(T.S) 그때 어디선가 쏜살같이 달려온 검은 인영이 남자를 덮친다.",
              "Shot 5: 짙은 어둠 속에서 나타난 검은 형상이 한국인 남자를 덮치기 위해 공중으로 뛰어올라 양팔을 뻗은 채 허공에 떠 있는 찰나의 순간."
            ],
            "visual_inferences": [
              "fixed_element dusk_forest_lighting: A dense, overgrown forest environment enveloped in cold, fading blue-gray dusk light with deep shadows.",
              "C15 mid-leap action frozen with clothing trailing in the opposite direction of motion.",
              "C15 and C07 sharing the muddy forest ground as a spatial anchor to enforce fg/bg physical consistency."
            ],
            "creative_decisions": [
              "Low angle composition aimed upward to place the airborne attacker in the upper frame and the recoiling victim in the lower frame, adhering to the camera frame rule.",
              "Adding rim light and jaw contour visibility to the attacker to prevent a flat, featureless cutout while maintaining the occult silhouette effect.",
              "Slight profile turn for C07 to satisfy both the 'back to camera' instruction and the 'face identifiability' requirement for using the C07 ID."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "5804929a5f1b02bf",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "d7231eb8d11090b0",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 1,
        "dependency_reason": "같은 숲속 배경에서의 연속적인 도주 및 피습 시퀀스 (dusk_forest_lighting 환경 상태 공유)",
        "_shot_index": 5,
        "visible_entities": [
          "C07",
          "C15",
          "P01",
          "L01"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 1,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view locks into a wide shot (WS) low angle from the dark clearing, static and aimed upward as 검은 형상 bursts out of the upper center of frame. The 한국인 남자 stays small and lower in the frame, recoiling beneath it, while the black figure is held at the apex of its leap as a silhouette against the dim sky.",
            "lighting_mood": "The scene is underexposed in cold dusk tones, using the last gray sky as backlight to carve the attacker into a black occult silhouette.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C07",
              "C15",
              "P01",
              "L01"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C07",
                "outlook_id": "O09"
              },
              {
                "character_id": "C15",
                "outlook_id": "O15"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_forest_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A dense, overgrown forest environment enveloped in cold, fading blue-gray dusk light. The surrounding foliage and tree trunks are partially obscured by deep, pervasive shadows, creating a chilling and eerie atmosphere.",
                "applies_to_shots": [
                  3,
                  4,
                  5
                ],
                "source_facts": [
                  "Scene text: 숲속 / 해 질 무렵 (Forest / Dusk)",
                  "Shot 3: Cold blue-gray dusk light leaks through foliage",
                  "Shot 4: Fading coastal-blue dusk",
                  "Shot 5: cold dusk tones, using the last gray sky"
                ],
                "visual_inferences": [
                  "Deep, pervasive shadows swallowing the background elements due to the extremely low light level"
                ],
                "creative_decisions": [
                  "Applying a consistent cold blue-gray color palette across extreme close-ups and wide shots to anchor the visual timeline right before nightfall"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 1,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C07O09",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C15O15",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "9d062b0ddd86aa82"
      },
      {
        "scene_index": 2,
        "heading": "S#2. 도시 뒷골목 / N",
        "beat_title": "목을 무는 남자",
        "representative_moment": "남자의 이빨이 여자의 창백한 목에 닿은 극단적인 클로즈업 정지 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up (ECU) eye-level side profile, abstract bokeh background",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up eye-level side profile. C08O10 in a black hoodie, a young East Asian man, in right profile, jaw pressed against the pale throat of a young East Asian woman in a dark coat, in left profile. Her head tilted back, eyes looking up, while his eyes are fixed on her neck. Tight framing on the lower faces, with the neck and shoulder edges visible. Focus on his teeth touching the bloodless skin at dead center. Sickly sodium-green light grazes the pale skin, washing the neck with a cold, corpse-like tone. Behind them, [L03: abstract blurred yellow-green streetlight bokeh and the soft vertical shadow of a utility pole frame the background].",
            "outfit_assignments": [
              {
                "character_id": "C08",
                "outlook_id": "O10"
              }
            ],
            "source_facts": [
              "Scene text: '남자의 붉은 눈동자, 목의 살점을 뜯는 이빨...'",
              "Shot 4 description: '한국인 남자의 치아가 여자의 핏기 없는 목 피부에 닿은 정지 순간'",
              "Shot 4 camera: 'extreme close-up (ECU) eye-level side profile at neck height... teeth touch skin at dead center'"
            ],
            "visual_inferences": [
              "fixed_element wet_alleyway_night: sickly sodium-green and muted fluorescent streetlights",
              "Woman's dark coat added to provide realistic clothing boundary at the frame edge",
              "Abstract bokeh applies the alleyway lights to a shallow depth of field"
            ],
            "creative_decisions": [
              "Framed as a tight profile composition (faces and shoulder edges visible) rather than an isolated neck close-up, to safely bind the C08O10 face and preserve physical body volume",
              "Sickly green light 'grazes' and 'washes' the skin to convey horror tone without using physically slicing lighting verbs"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "f3524bb3f38f0453",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "e80ec516404894be",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 4,
        "visible_entities": [
          "C08",
          "L03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 2,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view freezes into an extreme close-up (ECU) eye-level side profile at neck height, only inches from the 한국인 여자's pale throat and the 한국인 남자's mouth. The teeth touch skin at dead center, with the background dissolved into abstract streetlight bokeh and the frame held almost unnaturally still.",
            "lighting_mood": "Sickly sodium-green alley light grazes the skin, making the bloodless neck cold and corpse-like before the crimson break.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C08",
              "L03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C08",
                "outlook_id": "O10"
              },
              {
                "character_id": "C09",
                "outlook_id": "O11"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "wet_alleyway_night",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A cold, dark city alleyway at night. The space is illuminated by weak, sickly sodium-green and muted fluorescent streetlights, casting a gloomy and chilling atmosphere. The ground consists of wet, dark pavement reflecting the dim urban light.",
                "applies_to_shots": [
                  4,
                  5
                ],
                "source_facts": [
                  "Scene text: '도시 뒷골목 / N', '도심 희미한 가로등 불빛'",
                  "Shot 4: 'Sickly sodium-green alley light grazes the skin'",
                  "Shot 5: 'wet pavement and trash-lined walls', 'Muted blue-black night tones mix with weak fluorescent street spill'"
                ],
                "visual_inferences": [
                  "The overall dampness and wet pavement persist throughout the scene, even when blurred in the close-up shot."
                ],
                "creative_decisions": [
                  "Anchoring the color palette to a mix of sickly sodium-green and muted blue-black to unify the extreme close-up and the wide shot under the same eerie urban night atmosphere."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C08O10",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C09O11",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "720ec68ad96204f9"
      },
      {
        "scene_index": 2,
        "heading": "S#2. 도시 뒷골목 / N",
        "beat_title": "쓰러진 여자",
        "representative_moment": "피를 흘린 C09가 차가운 뒷골목 바닥에 눈을 감은 채 쓰러져 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle wide shot from ground level, muted blue-black night tones mixed with sickly green spill",
            "t2i_prompt": "Photorealistic cinematic still. A low angle from ground level, the wet pavement occupying the lower frame. C09O11 in a white blouse, a young East Asian woman, lies motionless across the center of the dark alley floor, positioned at a three-quarter angle from the right with eyes closed. Focus on the fresh blood at her neck, standing out as a sharp red note. Muted blue-black night tones mix with weak fluorescent street spill pooling on the ground. A gloomy, chilling atmosphere permeates the space, illuminated by faint, sickly sodium-green light reflecting off the wet, dark pavement and the stained concrete walls extending into the background. Discarded trash bags and damp cardboard sit along the distant wall edges.",
            "outfit_assignments": [
              {
                "character_id": "C09",
                "outlook_id": "O11"
              }
            ],
            "source_facts": [
              "Scene text: '도심 희미한 가로등 불빛', '푹 힘없이 쓰러지는 여자'",
              "Shot description: observer at ground level, Korean woman bleeding from the neck lying on cold alley floor"
            ],
            "visual_inferences": [
              "fixed_element wet_alleyway_night: wet, dark pavement reflecting dim urban light, sickly sodium-green ambient",
              "Prone body occupies the lower to mid frame due to ground-level low angle",
              "Trash bags and cardboard add gritty texture to the cold negative space"
            ],
            "creative_decisions": [
              "Wide composition using the wet pavement as a foreground plane to anchor the low-angle perspective",
              "Contrasting the sharp red blood against the muted blue-black and sodium-green environment to establish the visual anchor"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "829c6896f1e88743",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "9b5c8fad97d94811",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 2,
        "dependency_reason": "같은 씬(도시 뒷골목) 내 사건의 직후 순간이므로 바닥의 질감과 조명(가로등 불빛 등)의 연속성 유지",
        "_shot_index": 5,
        "visible_entities": [
          "C09",
          "L03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 2,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view pulls back into a wide shot (WS) low angle from ground level, dollying away until the 한국인 여자's full body lies across the center of the alley floor. Her neck wound remains the visual anchor near the upper third of her body, while wet pavement and trash-lined walls stretch around her as cold negative space.",
            "lighting_mood": "Muted blue-black night tones mix with weak fluorescent street spill, leaving the blood at her neck as the only sharp red note.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C09",
              "L03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C08",
                "outlook_id": "O10"
              },
              {
                "character_id": "C09",
                "outlook_id": "O11"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "wet_alleyway_night",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A cold, dark city alleyway at night. The space is illuminated by weak, sickly sodium-green and muted fluorescent streetlights, casting a gloomy and chilling atmosphere. The ground consists of wet, dark pavement reflecting the dim urban light.",
                "applies_to_shots": [
                  4,
                  5
                ],
                "source_facts": [
                  "Scene text: '도시 뒷골목 / N', '도심 희미한 가로등 불빛'",
                  "Shot 4: 'Sickly sodium-green alley light grazes the skin'",
                  "Shot 5: 'wet pavement and trash-lined walls', 'Muted blue-black night tones mix with weak fluorescent street spill'"
                ],
                "visual_inferences": [
                  "The overall dampness and wet pavement persist throughout the scene, even when blurred in the close-up shot."
                ],
                "creative_decisions": [
                  "Anchoring the color palette to a mix of sickly sodium-green and muted blue-black to unify the extreme close-up and the wide shot under the same eerie urban night atmosphere."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 2,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C08O10",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C09O11",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "e886df3821db8f2c"
      },
      {
        "scene_index": 3,
        "heading": "S#3. 현장 / D",
        "beat_title": "현장 지휘와 참혹한 변사체 흔적 (뉴스 보도)",
        "representative_moment": "혜수(C02)가 뉴스 화면의 흐린 빛 속에서 턱을 괸 채 폴리스 라인 너머 바닥의 핏자국을 무겁게 응시하고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "A broadcast-news observer MCU high angle, flat overcast daylight filtered through dense fog",
            "t2i_prompt": "Photorealistic cinematic still. A broadcast-news observer medium close-up, high angle from slightly above and beside the subject. C02O03 in a gray leather jacket, a young East Asian woman, at three-quarter angle from the right, chin resting on her fist, eyes fixed down on a dark bloodstain. The figure occupies the right middle ground, neck and upper chest in frame. Focus on her expression and the stain sharing the composition. The lower left frame is anchored by a dried, black-red irregular bloodstain on [L02: damp, trampled muddy forest ground]. In the soft, out-of-focus background, a stretched P02 yellow police line sags slightly, with hazy silhouettes of forensic officers moving faintly. Flat overcast daylight filtered through dense fog washes over the scene, muted grays and desaturated greens, subtle digital broadcast texture, cold forensic stillness.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "S#3 action: '경찰, 폴리스 라인을 치고 시신을 수거한다. 형사무리 속에 사건을 지휘하는 혜수의 모습이 보인다.'",
              "shot description: 혜수가 턱을 괸 채 바닥의 검붉은 핏자국을 응시하는 정지 구도"
            ],
            "visual_inferences": [
              "C02 body_pose: chin resting on fist, eyes directed downwards at the stain",
              "broadcast news context interpreted as a subtle digital noise/texture over the image",
              "background forensics blurred to keep MCU focus on Hye-su and the stain"
            ],
            "creative_decisions": [
              "anchored the dark stain in the lower left and Hye-su in the right middle ground to create a shared visual tension",
              "used muted grays and desaturated greens to emphasize the cold, forensic tone of the broadcast"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "e7fd65aff4f73896",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "aebd9b965ca5cfa2",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "독립적으로 묘사되는 뉴스 보도 화면 내 현장 상황",
        "_shot_index": 3,
        "visible_entities": [
          "C02",
          "P02",
          "P03",
          "L02"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 3,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "A broadcast-news observer view holds a medium close-up (MCU) high angle from low beside 혜수, locked off about one meter away and angled slightly down so her chin-resting profile and the bloodstain share the frame. 혜수 occupies the right middle ground, the dark red-black stain anchors the lower left, and hazy police activity remains softened behind the line.",
            "lighting_mood": "Flat overcast daylight is filtered through fog, with muted grays and desaturated greens giving the news image a cold, forensic stillness.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "P02",
              "P03",
              "L02"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "db8a52a656f4bcd1"
      },
      {
        "scene_index": 4,
        "heading": "S#4. 옥탑방 / D",
        "beat_title": "적막한 옥탑방 전경과 뉴스 보도",
        "representative_moment": "회색빛 하늘 아래 인천 변두리 빌라의 낡은 옥탑방과 파란 물탱크가 정적으로 내려다보이는 부감 전경.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "omniscient extreme wide shot high angle, diffuse gray daylight",
            "t2i_prompt": "Photorealistic cinematic still. An omniscient extreme wide shot from a high oblique aerial position above the [L04: Incheon villa rooftops]. Focus on the worn rooftop room and the faded blue water tank from the reference, sitting slightly right of center. The old tile roof and the parapet wall from the reference are held in a static frame, surrounded by overcast gray sky and cluttered neighboring rooflines. Diffuse gray daylight flattens the buildings into muted blues and concrete grays, making the water tank's color feel strangely ominous.",
            "outfit_assignments": [],
            "source_facts": [
              "S#4 action: '인천 변두리 부감, 오래된 빌라 옥탑방 전경.'",
              "shot description: EWS high angle from a high oblique aerial position above the Incheon villa rooftops."
            ],
            "visual_inferences": [
              "empty roof terrace emphasizes the isolated, ominous mood while news V.O. plays",
              "diffuse daylight flattens the contrast, highlighting the faded blue of the water tank against concrete grays"
            ],
            "creative_decisions": [
              "anchored specific objects ('water tank from the reference', 'parapet wall from the reference') to comply with background binding constraints",
              "used 'Focus on the worn rooftop room...' to establish the clear camera target for this empty establishing shot"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "072412a2eab2a606",
              "owned_hash": "c9ee8c218343e53d",
              "camera_direction_hash": "84e6d0b7360fb128",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "water tank",
                  "violating_phrase": "the faded blue water tank from the reference",
                  "reason": "The phrase explicitly references an owned background object and keeps it as part of the composition rather than creating a new one.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "parapet wall",
                  "violating_phrase": "the parapet wall from the reference",
                  "reason": "The phrase explicitly references an owned background object already present in the reference scene.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "voiceover",
        "dependent_scene_index": -1,
        "dependency_reason": "전경(Establishing)을 보여주는 독립적인 배경 샷",
        "_shot_index": 1,
        "visible_entities": [
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 4,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An omniscient direct view settles into an extreme wide shot (EWS) high angle from a high oblique aerial position above the Incheon villa rooftops. The worn rooftop room sits slightly right of center, its old tile roof and blue water tank held in a static frame with enough surrounding gray sky and neighboring rooflines to make it feel isolated.",
            "lighting_mood": "Diffuse gray daylight flattens the buildings into muted blues and concrete grays, making the water tank's faded blue feel strangely ominous.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "L04"
            ],
            "allowed_outlook_pairs": [],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_rooftop_day_overcast_establishing",
            "reference_usage": "exact_background",
            "owned_objects": [
              "access door",
              "laundry line",
              "parapet wall",
              "post",
              "roof drain",
              "roof terrace",
              "sliding window",
              "stairwell",
              "wall light",
              "water tank",
              "window sill"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "background",
                "id": "bg_rooftop_day_overcast_establishing",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "de06949218c8423d"
      },
      {
        "scene_index": 5,
        "heading": "S#5. 옥탑방 안 / 실내",
        "beat_title": "불안한 뉴스 시청",
        "representative_moment": "C05가 부엌 앞치마를 쥔 채, 끓는 약초물 김을 뒤로 하고 굳은 표정으로 TV 뉴스를 응시한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level tight head-and-shoulder composition, blending sickly blue TV spill with soft pale window light to emphasize tension.",
            "t2i_prompt": "Photorealistic cinematic still. A head-and-shoulder composition. C05O06 in a beige cardigan and apron, a middle-aged East Asian woman, facing the camera. Her face occupies the center frame, shoulders held tight at the lower edge, hands gripping the apron fabric near her chest at the bottom boundary. Her eyes are fixed on an unseen TV off-camera, her expression tense. A sickly cool blue spill washes across her face and collar, mixing with pale ambient light. [L07: Soft misty haze of steam rising directly behind her shoulders, reducing the immediate surroundings into an out-of-focus blurred background edge].",
            "outfit_assignments": [
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "source_facts": [
              "S#5 action: '앞치마를 두른 채 TV 뉴스를 뚫어지게 바라보는 민숙(수리영 엄마. 40세) 표정이 어둡다.'",
              "Shot 4 description: 굳은 표정의 40대 한국인 여성 앞모습."
            ],
            "visual_inferences": [
              "fixed_element steamy_kitchen_background: misty haze of steam behind her",
              "sickly TV-blue spill reflecting on her face to emphasize the unseen news source"
            ],
            "creative_decisions": [
              "Head-and-shoulder framing to focus on her anxious expression while keeping the pose (gripping apron) barely visible at the frame edge",
              "Using the steam to create an out-of-focus background edge, isolating her figure without fully rendering the room"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "906bae6bb93258d9",
              "owned_hash": "cb1d462ffc515e90",
              "camera_direction_hash": "23afcc72051db611",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 4,
        "visible_entities": [
          "C05",
          "P04",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 5,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view pushes into a close-up (CU) eye-level frontal portrait of 40대 한국인 여성 from the living-room side, keeping the TV just off her eyeline rather than visible head-on. Her face fills most of the center frame, shoulders tight beneath the apron, while the sink steam and small window are minimized into soft domestic haze behind her.",
            "lighting_mood": "Pale window light mixes with sickly TV-blue spill, draining her face into anxious gray while the kitchen steam softens the room.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C05",
              "P04",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              },
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_day_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "steamy_kitchen_background",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The kitchen sink area is enveloped in a soft, misty haze of steam rising from a recently boiled pot. The surrounding space is dimly lit by pale natural light from a small window, creating a muted, slightly hazy domestic atmosphere in the background.",
                "applies_to_shots": [
                  4,
                  9
                ],
                "source_facts": [
                  "S#5 scene text: 냄비의 물이 끓어 달그락거리는 소리… 김이 피어오르고",
                  "Shot 4 description: sink steam and small window are minimized into soft domestic haze behind her",
                  "Shot 9 description: blurred sink and shut-off TV behind her... leftover kitchen steam create a muted domestic calm"
                ],
                "visual_inferences": [
                  "The steam from the boiling medicinal herbs consistently permeates the kitchen area, visibly affecting the background clarity and atmosphere."
                ],
                "creative_decisions": [
                  "Using the lingering steam as a continuous environmental texture to spatially connect the separate close-up shots of the mother and daughter."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O01",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "2cec06233eb02d92"
      },
      {
        "scene_index": 5,
        "heading": "S#5. 옥탑방 안 / 실내",
        "beat_title": "약초물을 마시며 투정부리는 수리영",
        "representative_moment": "C01 sips the herbal water with a slight frown, framed tightly against the hazy kitchen background.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Close-up (CU) eye-level three-quarter angle, soft gray daylight",
            "t2i_prompt": "Photorealistic cinematic still. C01O01 in gray homewear, a young East Asian woman, shown in three-quarter left profile. Tight framing on her face, upper body in frame. She holds a small cup, filled with faint brown-green herbal water, resting against her lips in the lower center of the frame, the rim angled toward the camera. Her eyes look down at the cup with a slight frown and narrowed eyes. Focus on her expression and the cup at her lips. [L07: In the blurred background, soft misty steam envelops a wet kitchen sink and a dark shut-off TV screen angled away from the camera, illuminated by muted soft gray daylight falling across the rear space, creating a hazy, calm domestic atmosphere].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              }
            ],
            "source_facts": [
              "S#5 scene text: (식탁에 앉으며) ... (마시고 나서) 아, 진짜 맛 없어...(투정)",
              "Shot 9 description: blurred sink and shut-off TV behind her... leftover kitchen steam create a muted domestic calm"
            ],
            "visual_inferences": [
              "fixed_element steamy_kitchen_background: soft, misty haze of steam rising from a recently boiled pot permeates the kitchen area",
              "C01 is in homewear since she just woke up and hasn't changed into her outdoor clothes yet"
            ],
            "creative_decisions": [
              "Used 'tight framing on her face, upper body in frame' to avoid floating head generation",
              "Shallow depth of field effectively blurs the TV and sink to emphasize her subtle narrowed-eye expression",
              "Cup placed in the lower center to naturally anchor her downward gaze"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "1e6f94f777f3773a",
              "owned_hash": "cb1d462ffc515e90",
              "camera_direction_hash": "8dc827d854edf684",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 5,
        "dependency_reason": "Occurs in the same kitchen environment as S5_Shot4, but utilizes skipped_close_framing to focus entirely on the subject, carrying over only the environmental steam texture.",
        "_shot_index": 9,
        "visible_entities": [
          "C01",
          "P04",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 5,
            "shot_index": 9
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view resolves the table dolly into a close-up (CU) eye-level three-quarter angle on 수리영 at the dining table. The cup rests against her lips in the lower center of frame, taking less than a third of the image, while her slight frown and narrowed eyes hold focus against a blurred sink and shut-off TV behind her.",
            "lighting_mood": "Soft gray daylight and leftover kitchen steam create a muted domestic calm, with the herbal water tinted a faint medicinal brown-green.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P04",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              },
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_day_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "steamy_kitchen_background",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The kitchen sink area is enveloped in a soft, misty haze of steam rising from a recently boiled pot. The surrounding space is dimly lit by pale natural light from a small window, creating a muted, slightly hazy domestic atmosphere in the background.",
                "applies_to_shots": [
                  4,
                  9
                ],
                "source_facts": [
                  "S#5 scene text: 냄비의 물이 끓어 달그락거리는 소리… 김이 피어오르고",
                  "Shot 4 description: sink steam and small window are minimized into soft domestic haze behind her",
                  "Shot 9 description: blurred sink and shut-off TV behind her... leftover kitchen steam create a muted domestic calm"
                ],
                "visual_inferences": [
                  "The steam from the boiling medicinal herbs consistently permeates the kitchen area, visibly affecting the background clarity and atmosphere."
                ],
                "creative_decisions": [
                  "Using the lingering steam as a continuous environmental texture to spatially connect the separate close-up shots of the mother and daughter."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 5,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O01",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "29ed7ffd61db873a"
      },
      {
        "scene_index": 5,
        "heading": "S#5. 옥탑방 안 / 실내",
        "beat_title": "민숙의 손목에 선명해진 표식 인지",
        "representative_moment": "Focus on the distinct circular mark on 's bare wrist, glowing faintly with a reddish tint.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "close-up high angle focused on the wrist, dim daylight falling into bluish entryway shadow",
            "t2i_prompt": "Photorealistic cinematic still. Focus on a small circular mark on the bare wrist of a middle-aged East Asian woman in a pushed-back sleeve. An observer's close-up high angle, angled down onto the wrist held near chest height. The forearm stretches diagonally across the frame. The circular mark sits just right of center on the skin, catching a faint crimson tint that feels unnaturally vivid. Dim indoor daylight falls off into bluish shadow along the arm and fabric. [L07: A softly blurred, worn entryway floor, the lower edge of a closed door, and the side of a shoe rack] occupy the background below the hand to provide physical depth.",
            "outfit_assignments": [],
            "source_facts": [
              "S#5 action: '힐끗, 민숙 손목에 보이는 작은 원(이하 표식)을 본다.'",
              "shot description: close-up of a small circular mark with a reddish glow on a Korean woman's bare wrist"
            ],
            "visual_inferences": [
              "dim indoor daylight contrasting with the red glow heightens the ominous tension",
              "wrist positioned diagonally across the frame to lead the eye toward the circular mark"
            ],
            "creative_decisions": [
              "high-angle close framing looks down onto the wrist, placing the entryway floor as a soft background to anchor depth without distracting from the primary subject",
              "omitted the character's face entirely to strictly adhere to the body-part focus rule and maximize the impact of the detail"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "c159173af4757b4d",
              "owned_hash": "cb1d462ffc515e90",
              "camera_direction_hash": "d02853eff15fec09",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 5,
        "dependency_reason": "preserves the entryway lighting and floor context from the previous S#5 shots, maintaining spatial continuity during the close-up detail",
        "_shot_index": 14,
        "visible_entities": [
          "P04",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 5,
            "shot_index": 14
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "An observer's direct view drops into a close-up (CU) high angle from beside 40대 한국인 여성 at chest-to-waist height, angled down onto her bare wrist as the dolly-in settles. The small circular mark sits just right of center on the skin with a faint red glow, while the edge of her sleeve and the entryway floor remain visible as scale references.",
            "lighting_mood": "Dim indoor daylight falls off into bluish entryway shadow, making the mark's crimson tint feel unnaturally vivid against ordinary skin.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P04",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              },
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_day_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 5,
                "shot_index": 9,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O01",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "7950d7d661b86493"
      },
      {
        "scene_index": 6,
        "heading": "S#6. 해안가 도로 / D",
        "beat_title": "해안가를 달리며 바람을 느끼는 수리영",
        "representative_moment": "C01O02 rides a bicycle along the coastal road, her eyes closed and white earphones in, breathing in the sea air.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Observer perspective tight eye-level close-up tracking parallel, muted blue-gray bokeh",
            "t2i_prompt": "Photorealistic cinematic still. Observer perspective, tight eye-level close-up tracking parallel. C01O02 in a navy windbreaker, a young East Asian woman, positioned in the right half of the frame in left profile, leaning forward into the ride. Tight framing on her expression, neck and upper shoulder in frame. Her eyes are closed, with white earphones in her ears. Her hair flows gently back in the direction opposite to motion. A slice of the bicycle handlebar is visible at the lower frame edge, slightly blurred. Cold coastal daylight diffused through sea fog washes her skin and jacket in a pale blue-gray softness. [L08: damp coastal road and sea smearing into a muted blue-gray bokeh behind her].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#6 action: '수리영 자전거를 타고 해안가 도로를 달린다. 이어폰을 끼고...'",
              "shot description: '양 귀에 하얀 이어폰을 꽂고 지긋이 눈을 감은 수리영의 옆얼굴 클로즈업.'",
              "DP instruction: 'tight eye-level CU tracks parallel about two feet from 수리영's left side'"
            ],
            "visual_inferences": [
              "Hair flowing back to indicate the mid-action forward motion of the bicycle without using blur on the subject",
              "Neck and upper shoulder included in the frame to prevent a floating head composite",
              "Handlebar slice included at the bottom edge to anchor the bicycle prop within the close-up"
            ],
            "creative_decisions": [
              "Subject positioned in the right half of the frame to give space for the left-facing profile and the tracking motion",
              "Diffused pale blue-gray lighting washing over the skin to emphasize the cold, hazy coastal atmosphere"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "829aab7b2f5f51b8",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "9c82441cf3ab8c61",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "No direct visual dependency on a prior shot is required for this isolated tracking close-up.",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "L08"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 6,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision. A tight eye-level CU tracks parallel about two feet from 수리영's left side, holding her calm side-profile in the right half of frame while both white earphones and her closed eyelids stay crisp; the bicycle motion is implied only by a faint tremor at the frame edge. The foggy coastal road and sea smear into muted blue-gray bokeh behind her, with no independent camera shift beyond the flow’s close side observation.",
            "lighting_mood": "Cold coastal daylight is diffused through sea fog, washing her skin in pale blue-gray softness with a quiet, almost premonitory calm.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L08"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "8d5fbc1a693fbfa9"
      },
      {
        "scene_index": 7,
        "heading": "S#7. 유기견 보호원 / D",
        "beat_title": "사납게 짖어대는 로트와일러",
        "representative_moment": "철장 너머로 이빨을 드러내며 거칠게 짖는 로트와일러(C11)의 머리 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low-angle close-up from observer POV, harsh cool green-gray fluorescent lighting",
            "t2i_prompt": "Photorealistic cinematic still. A low-angle close-up at muzzle height from an observer's perspective. C11O00, a massive black Rottweiler, is facing the camera, snarling fiercely with open jaws, a wet black nose, and exposed teeth. The dog's head and thick neck push forward toward the lens, eyes fixed on the camera. Thick vertical metallic cage bars slice the immediate foreground, creating a stark rigid barrier. [L09: A dim, stained, cramped enclosure immediately behind the dog's head, with wet dirty concrete floor patches visible below the muzzle]. Harsh overhead sterile fluorescent lights illuminate the space, casting a cool waxy green-gray wash across the black fur and dripping saliva. Deep green-gray shadows obscure the frame edges, while stark highlights catch sharply on the exposed fangs. Focus on the dog's aggressive expression pushing toward the foreground bars.",
            "outfit_assignments": [
              {
                "character_id": "C11",
                "outlook_id": "O00"
              }
            ],
            "source_facts": [
              "Shot 1 description: 철장 안에서 이빨을 거칠게 드러내고 입을 벌린 거대한 검은색 로트와일러의 머리.",
              "DP direction: Observer perspective, direct vision from just inside the kennel gate. A low angle CU sits at the Rottweiler's muzzle height."
            ],
            "visual_inferences": [
              "fixed_element kennel_cage_bars: Thick, vertical metallic cage bars dividing the space",
              "fixed_element sterile_fluorescent_lighting: harsh overhead fluorescent lights, casting a cool, sterile wash with subtle waxy, green-gray tones",
              "Observer (수리영) is implied behind the camera, looking at the dog through the cage bars."
            ],
            "creative_decisions": [
              "Used a tight through-bars composition to make the kennel feel too narrow and immediate, enhancing the Rottweiler's aggressive presence.",
              "Applied a sickly green-gray fluorescent cast to emphasize the unglamorous and slightly unnerving clinical atmosphere of the shelter."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "efec95bad95ffc50",
              "owned_hash": "24cb3d73858cd4a8",
              "camera_direction_hash": "0c33098dee57ef72",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 1,
        "visible_entities": [
          "C11",
          "L09"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 7,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision from just inside the kennel gate. A low angle CU sits at the 로트와일러’s muzzle height, tighter than the flow default so the open jaws, wet black nose, and exposed teeth occupy most of the center while vertical cage bars slice the foreground without exceeding the frame. The dog’s head pushes toward camera as a through-bars composition, making the kennel feel too narrow and immediate.",
            "lighting_mood": "Sickly shelter fluorescents flicker over black fur and saliva, leaving the kennel corners in green-gray shadow with harsh highlights on the teeth.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C11",
              "L09"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C11",
                "outlook_id": "O00"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_kennel_aisle_day_vaccination_busy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "kennel_cage_bars",
                "element_type": "environment_state",
                "character_name": "",
                "description": "Thick, vertical metallic cage bars divide the space, acting as a stark architectural element that forms the animal enclosure. The dull metal surfaces create a rigid vertical pattern that visually separates the subjects.",
                "applies_to_shots": [
                  1,
                  4
                ],
                "source_facts": [
                  "Shot 1 description: 'vertical cage bars slice the foreground without exceeding the frame.'",
                  "Shot 4 description: 'The kennel bars are now a soft peripheral pattern'"
                ],
                "visual_inferences": [
                  "Heavy-duty steel or aluminum bars with a slightly worn metallic finish, typical of enclosures holding large aggressive dogs."
                ],
                "creative_decisions": [
                  "Maintaining the vertical bars across both shots to establish the physical barrier of the kennel, while shifting their depth of field from foreground to background to match the camera's focus."
                ],
                "confidence": "high"
              },
              {
                "element_id": "sterile_fluorescent_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior is illuminated by harsh overhead fluorescent lights, casting a cool, sterile wash with subtle waxy, green-gray tones across the surfaces. This lighting creates an unglamorous and slightly unnerving clinical atmosphere uniformly throughout the facility.",
                "applies_to_shots": [
                  1,
                  4,
                  8
                ],
                "source_facts": [
                  "Shot 1: 'Sickly shelter fluorescents flicker... leaving the kennel corners in green-gray shadow.'",
                  "Shot 4: 'Flat fluorescent light turns the fur and skin waxy, with a faint green cast.'",
                  "Shot 8: 'Cool fluorescent wash reflects off water and steel... tender but still sterile.'"
                ],
                "visual_inferences": [
                  "Industrial fluorescent tube lighting mounted on the shelter ceiling, emitting a consistently harsh spectrum."
                ],
                "creative_decisions": [
                  "Using the consistent cool, green-tinted lighting to visually unify the different areas of the shelter (the kennel and the bathing station), reinforcing an unglamorous mood."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C11O00",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "a38ca704fde925fc"
      },
      {
        "scene_index": 7,
        "heading": "S#7. 유기견 보호원 / D",
        "beat_title": "맹견의 제압과 주사",
        "representative_moment": "50대 의사의 손이 얌전해진 로트와일러의 엉덩이에 주삿바늘을 꽂고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up with a slight Dutch angle, low observer perspective, waxy green-gray fluorescent cast",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up with a slight Dutch angle, low observer perspective. Focus on the rough hand of an East Asian man in his 50s, his arm entering the frame from above, steadily holding a syringe. The needle is angled directly into the pinched skin of the rear flank of a subdued dark-furred Rottweiler lying prone facing right. The man's face and the dog's eyes are positioned entirely beyond the frame edges to maintain isolated focus on the injection. The dog's dark fur occupies the peripheral edges of the central frame. [L09: A soft peripheral background of thick, out-of-focus vertical metallic cage bars angled away from the camera, and a damp, scuffed concrete floor visible at the lower edge]. Harsh overhead fluorescent lighting casts a cool, waxy green-gray sterile wash across the skin, hand, and fur, creating an unnerving clinical atmosphere.",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 4 description: '엎드린 개의 엉덩이에 주사기 바늘을 꽂은 50대 한국인 남성의 손 클로즈업'",
              "Scene text: '맹견의 엉덩이에 주사를 놓고 빠지는 50대 의사'",
              "Camera instruction: 'ECU with a slight Dutch angle pushes in low beside the prone dog’s rear flank, isolating the syringe needle, pinched skin, and rough hand'"
            ],
            "visual_inferences": [
              "fixed_element: kennel_cage_bars acting as a soft out-of-focus background",
              "fixed_element: sterile_fluorescent_lighting casting a green-gray clinical wash",
              "Due to ECU framing, the man's head and dog's head are implied out of frame to avoid view mixing",
              "The dog is identified as a Rottweiler based on the scene text, with dark fur providing scale at the edges"
            ],
            "creative_decisions": [
              "Using a slight Dutch angle to heighten the clinical tension of the injection moment.",
              "Limiting the background description strictly to the immediate frame-edge surfaces ([L09]) since it is a skipped_close_framing shot."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "03202eb22749b7b8",
              "owned_hash": "24cb3d73858cd4a8",
              "camera_direction_hash": "a15e56e9b1456eba",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 7,
        "dependency_reason": "Shares the same kennel location, lighting, and cage bar elements established in Shot 1.",
        "_shot_index": 4,
        "visible_entities": [
          "L09"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 7,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision continuing the lateral medical-action flow. An ECU with a slight Dutch angle pushes in low beside the prone dog’s rear flank, isolating the syringe needle, pinched skin, and 50대 한국인 남성’s rough hand in the central third while the dog’s fur provides scale around the edges. The kennel bars are now a soft peripheral pattern, keeping the action grounded without pulling focus from the injection point.",
            "lighting_mood": "Flat fluorescent light turns the fur and skin waxy, with a faint green cast that makes the routine injection feel unnervingly surgical.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "L09"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C11",
                "outlook_id": "O00"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_kennel_aisle_day_vaccination_busy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "kennel_cage_bars",
                "element_type": "environment_state",
                "character_name": "",
                "description": "Thick, vertical metallic cage bars divide the space, acting as a stark architectural element that forms the animal enclosure. The dull metal surfaces create a rigid vertical pattern that visually separates the subjects.",
                "applies_to_shots": [
                  1,
                  4
                ],
                "source_facts": [
                  "Shot 1 description: 'vertical cage bars slice the foreground without exceeding the frame.'",
                  "Shot 4 description: 'The kennel bars are now a soft peripheral pattern'"
                ],
                "visual_inferences": [
                  "Heavy-duty steel or aluminum bars with a slightly worn metallic finish, typical of enclosures holding large aggressive dogs."
                ],
                "creative_decisions": [
                  "Maintaining the vertical bars across both shots to establish the physical barrier of the kennel, while shifting their depth of field from foreground to background to match the camera's focus."
                ],
                "confidence": "high"
              },
              {
                "element_id": "sterile_fluorescent_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior is illuminated by harsh overhead fluorescent lights, casting a cool, sterile wash with subtle waxy, green-gray tones across the surfaces. This lighting creates an unglamorous and slightly unnerving clinical atmosphere uniformly throughout the facility.",
                "applies_to_shots": [
                  1,
                  4,
                  8
                ],
                "source_facts": [
                  "Shot 1: 'Sickly shelter fluorescents flicker... leaving the kennel corners in green-gray shadow.'",
                  "Shot 4: 'Flat fluorescent light turns the fur and skin waxy, with a faint green cast.'",
                  "Shot 8: 'Cool fluorescent wash reflects off water and steel... tender but still sterile.'"
                ],
                "visual_inferences": [
                  "Industrial fluorescent tube lighting mounted on the shelter ceiling, emitting a consistently harsh spectrum."
                ],
                "creative_decisions": [
                  "Using the consistent cool, green-tinted lighting to visually unify the different areas of the shelter (the kennel and the bathing station), reinforcing an unglamorous mood."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 7,
                "shot_index": 1,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C11O00",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "f59192ed301e6bbb"
      },
      {
        "scene_index": 7,
        "heading": "S#7. 유기견 보호원 / D",
        "beat_title": "작업에 몰입하는 수리영의 손길",
        "representative_moment": "수리영(C01)이 작은 강아지의 젖은 등에 비누 거품을 묻힌 채 양손을 얹고 내려다보는 정지된 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Observer perspective, slightly overhead medium shot detail at arm level, cool waxy green-gray fluorescent wash",
            "t2i_prompt": "Photorealistic cinematic still. Observer perspective, a slightly overhead medium shot from arm level, looking down at the wet stainless tub from the reference. C01O02 in a navy windbreaker, a young East Asian woman, with her head and upper torso occupying the upper frame. She is looking away from the camera, eyes fixed down on a small puppy standing inside the tub. Her forearms extend downward, symmetrically framing the dog, both hands resting on the puppy's foamy wet back. Fresh white foam spreads across the wet fur. The pale, damp, slightly stained tile wall occupies the background behind her. Cool, sterile light from the overhead fluorescent light from the reference washes over the scene with faint waxy green-gray tones, reflecting off the water streaks and steel surfaces. A wet sprayer from the reference rests near the rear edge, its coiled nozzle pointing away from the camera, bringing a quiet, tender pause to the clinical atmosphere.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#7 action: '달려가 털깍고, 연고 바르고, 목욕시키고 등'",
              "Shot description: 작은 강아지의 젖은 등에 비누 거품을 묻힌 채 양손을 얹은 수리영의 정지 구도"
            ],
            "visual_inferences": [
              "fixed_element sterile_fluorescent_lighting: harsh overhead fluorescent lights casting a cool, sterile wash with subtle waxy, green-gray tones",
              "Slightly overhead MS angle showing the upper body and arms symmetrically framing the puppy inside the tub"
            ],
            "creative_decisions": [
              "Explicitly anchored background elements (tub, sprayer, fluorescent light) using 'from the reference' to avoid generating duplicate objects",
              "Placed C01O02's head and torso in the upper frame to geometrically align with the overhead downward camera angle",
              "Symmetrical hand placement to emphasize a quiet, caring pause over the foamy puppy"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "e82c9cca02e158b6",
              "owned_hash": "bc6a99e389261123",
              "camera_direction_hash": "0a3525d363e46e4e",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "tub",
                  "violating_phrase": "wet stainless tub",
                  "reason": "The tub is directly named and framed as a visible scene element without an explicit anchor-only reference beyond \"from the reference,\" which still describes it as present in-frame.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "the overhead fluorescent light from the reference",
                  "reason": "The light is explicitly referenced as coming from the reference, indicating an existing background object rather than a new one to create.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "sprayer",
                  "violating_phrase": "A wet sprayer from the reference rests near the rear edge",
                  "reason": "The sprayer is explicitly identified as already existing in the reference background and only positioned by location.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 7,
        "dependency_reason": "S7_Shot4의 동일한 공간(유기견 보호원 목욕실) 배경 및 조명 연속성 유지 (exact_background)",
        "_shot_index": 8,
        "visible_entities": [
          "C01",
          "L09"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 7,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision at the end of the care-close-observation flow. A slightly overhead MS detail holds static at arm level above the bathing station, with 수리영’s two hands placed symmetrically from left and right on the small puppy’s foamy wet back in the center; her forearms frame the dog without letting any prop overwhelm the image. The composition settles into a quiet long-take implied pause, shifting the scene’s rhythm from threat to care.",
            "lighting_mood": "Cool fluorescent wash reflects off water and steel, softened by white foam so the horror palette briefly becomes tender but still sterile.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L09"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C11",
                "outlook_id": "O00"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_wash_grooming_area_day_bathing",
            "reference_usage": "exact_background",
            "owned_objects": [
              "bottle",
              "counter",
              "door",
              "drain",
              "dryer blower",
              "drying rack",
              "faucet",
              "fluorescent light",
              "grooming table",
              "ramp",
              "shelf",
              "shelving",
              "sink",
              "sprayer",
              "stool",
              "towel",
              "tub",
              "ventilation fan",
              "washer dryer",
              "waste bin",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "sterile_fluorescent_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior is illuminated by harsh overhead fluorescent lights, casting a cool, sterile wash with subtle waxy, green-gray tones across the surfaces. This lighting creates an unglamorous and slightly unnerving clinical atmosphere uniformly throughout the facility.",
                "applies_to_shots": [
                  1,
                  4,
                  8
                ],
                "source_facts": [
                  "Shot 1: 'Sickly shelter fluorescents flicker... leaving the kennel corners in green-gray shadow.'",
                  "Shot 4: 'Flat fluorescent light turns the fur and skin waxy, with a faint green cast.'",
                  "Shot 8: 'Cool fluorescent wash reflects off water and steel... tender but still sterile.'"
                ],
                "visual_inferences": [
                  "Industrial fluorescent tube lighting mounted on the shelter ceiling, emitting a consistently harsh spectrum."
                ],
                "creative_decisions": [
                  "Using the consistent cool, green-tinted lighting to visually unify the different areas of the shelter (the kennel and the bathing station), reinforcing an unglamorous mood."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 7,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C11O00",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_wash_grooming_area_day_bathing",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "83d6604855d996cc"
      },
      {
        "scene_index": 8,
        "heading": "S#8. 번화가·대형 마트 / 해질 무렵",
        "beat_title": "엇갈린 만남과 당혹감",
        "representative_moment": "직원의 말을 듣고 눈이 동그라진 수리영(C01)의 정면 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level close-up, sterile fluorescent lighting mixed with dusk-blue shadow",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a navy windbreaker, a young East Asian woman, facing the camera in an eye-level close-up. Her chin is slightly lifted, her widened eyes fixed on an implied figure off-camera, positioned just above the frame's center. Her shoulders and upper chest remain visible in the lower frame. Cold greenish-white fluorescent light flattens her facial features, while a faint dusk-blue ambient spill cools the shadows along her jawline. Behind her, [L11: soft background of supermarket display shelves, out-of-focus products blurring into vertical color bands under bright commercial lighting]. The shallow depth of field sharply isolates her confused expression against the sterile environment.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#8 action: 수리영 (헷갈림) 어? 여기서 만나기로 했는데.",
              "Shot 3: 진열대 앞 50대 한국인 여성을 향해 눈을 동그랗게 뜬 수리영의 정면 얼굴.",
              "Shot 3 camera direction: tightened so her widened eyes sit just above center while the 50대 한국인 여성 remains implied by her eyeline off-camera"
            ],
            "visual_inferences": [
              "fixed_element supermarket_interior_aisle: cold greenish-white fluorescent lighting reflecting on her face",
              "fixed_element dusk_evening_lighting: faint dusk-blue spill catching the shadows on her neck",
              "Out-of-focus shelves in the background to emphasize the sudden internal realization"
            ],
            "creative_decisions": [
              "Eye-level close framing with upper chest visible to anchor the subject and prevent a floating head",
              "Mixing harsh, flat top-lighting with cool ambient shadows to visually represent the uneasy, mundane atmosphere"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "342c709b876ffa1f",
              "owned_hash": "d2085ab95968fafc",
              "camera_direction_hash": "0ff085efb9ca4552",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "",
        "_shot_index": 3,
        "visible_entities": [
          "C01",
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 8,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision inheriting the frontal close-observation stage. An eye-level CU frames 수리영’s face almost straight on, tightened so her widened eyes sit just above center while the 50대 한국인 여성 remains implied by her eyeline off-camera near the display shelf. Fluorescent-lit products blur into vertical color bands behind her, emphasizing that only her confusion has snapped into focus.",
            "lighting_mood": "Cold supermarket fluorescents flatten her face while dusk-blue spill from the entrance faintly cools the shadows, making the ordinary aisle feel uneasy.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_sales_floor_dusk_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "supermarket_interior_aisle",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the large retail mart features rows of display shelves heavily stocked with various products. The space is brightly illuminated by slightly greenish-white overhead fluorescent ceiling fixtures, creating a cold, uniform commercial atmosphere.",
                "applies_to_shots": [
                  3,
                  5
                ],
                "source_facts": [
                  "Shot 3: Fluorescent-lit products blur into vertical color bands",
                  "Shot 3: Cold supermarket fluorescents flatten her face",
                  "Shot 5: Greenish-white fluorescent light mixes with faint sunset spill"
                ],
                "visual_inferences": [
                  "Standard dense product arrangement typical of a large Korean grocery store",
                  "Continuous rows of fluorescent tubes running along the ceiling"
                ],
                "creative_decisions": [
                  "Emphasizing the harsh, sterile greenish-white lighting to contrast against the natural dusk light, subtly heightening the character's growing unease"
                ],
                "confidence": "high"
              },
              {
                "element_id": "dusk_evening_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The overall environmental lighting reflects early evening twilight, characterized by a pervasive dusk-blue ambient glow. This natural dim blue light fully wraps the exterior surroundings and faintly spills through the main entrance into the building's interior, intermingling with artificial lights.",
                "applies_to_shots": [
                  3,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene heading: 해질 무렵 (around dusk)",
                  "Shot 3: dusk-blue spill from the entrance faintly cools the shadows",
                  "Shot 5: faint sunset spill from the aisle opening",
                  "Shot 6: Dusk-blue ambient light wraps her profile"
                ],
                "visual_inferences": [
                  "The darkening sky outside casts a cool twilight shadow that penetrates the threshold of the automatic glass doors"
                ],
                "creative_decisions": [
                  "Using the dusk-blue tone as a consistent unifying atmospheric element across both interior observation and exterior profile shots"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "031ee565382a0ce7"
      },
      {
        "scene_index": 8,
        "heading": "S#8. 번화가·대형 마트 / 해질 무렵",
        "beat_title": "의아한 소식",
        "representative_moment": "C01이 C06의 말을 듣고 의아해하며 고개를 기울이는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "An eye-level MCU emphasizing greenish-white fluorescent lighting mixed with dusk-blue sunset spill",
            "t2i_prompt": "Photorealistic cinematic still. An eye-level MCU head-and-shoulder composition. C01O02 in a navy windbreaker, a young Asian woman, occupies the left-center foreground at three-quarter angle from the right, head tilted questioning, eyes fixed on C06O08 across the narrow aisle space they both occupy. In the soft background off-axis to the right, C06O08 in a red mart uniform, a young Asian man, stands in three-quarter left profile, balancing worn cardboard boxes at chest height midstep, the box fronts angled slightly toward the camera, eyes fixed on C01O02. Focus on C01O02's uncertain expression, neck and upper chest in frame. [L11: frame-edge background showing vertical color bands of blurred products on shelves, the aisle opening visible behind them on the right side]. Cold greenish-white fluorescent light washes the side of C01O02's face, intermingling with a faint dusk-blue sunset spill from the opening, creating a tense and sickly atmosphere.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "source_facts": [
              "Shot 5: 남자 직원을 향해 고개를 살짝 기울인 수리영의 의아한 표정.",
              "남자 직원: 박스 들고와 진열하면서"
            ],
            "visual_inferences": [
              "fixed_element: supermarket_interior_aisle (shelves heavily stocked, greenish-white fluorescent)",
              "fixed_element: dusk_evening_lighting (dusk-blue ambient glow)",
              "Shared anchor: the narrow aisle space between them",
              "Midstep freeze to capture the male employee's movement while balancing boxes"
            ],
            "creative_decisions": [
              "Placing C06O08 in the soft background to comply with the close framing rule (only primary subject fully sharp) while maintaining the interaction",
              "Mixing the harsh greenish fluorescent light with the dusk-blue spill to visually heighten the uncertainty of the moment"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "b9f976fbcd3e5cf8",
              "owned_hash": "d2085ab95968fafc",
              "camera_direction_hash": "da315d878b2e40bc",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 8,
        "dependency_reason": "동일 씬 내 이전 샷(Shot 3)의 대형 마트 내부 조명(형광등+석양 빛 혼합) 및 공간적 분위기를 연속적으로 반영하기 위함",
        "_shot_index": 5,
        "visible_entities": [
          "C01",
          "C06",
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 8,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision from the aisle corner as the camera completes its pan. An eye-level MCU favors 수리영 from her front-left in a subtle over-the-shoulder/over-axis arrangement, her tilted head held in the left-center foreground while 남자 직원 stands off-axis to the right with boxes at chest height. The aisle opening stays visible behind them, giving the new information a direction of escape toward the outside.",
            "lighting_mood": "Greenish-white fluorescent light mixes with faint sunset spill from the aisle opening, increasing the sickly tension as her uncertainty sharpens.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C06",
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_sales_floor_dusk_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "supermarket_interior_aisle",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the large retail mart features rows of display shelves heavily stocked with various products. The space is brightly illuminated by slightly greenish-white overhead fluorescent ceiling fixtures, creating a cold, uniform commercial atmosphere.",
                "applies_to_shots": [
                  3,
                  5
                ],
                "source_facts": [
                  "Shot 3: Fluorescent-lit products blur into vertical color bands",
                  "Shot 3: Cold supermarket fluorescents flatten her face",
                  "Shot 5: Greenish-white fluorescent light mixes with faint sunset spill"
                ],
                "visual_inferences": [
                  "Standard dense product arrangement typical of a large Korean grocery store",
                  "Continuous rows of fluorescent tubes running along the ceiling"
                ],
                "creative_decisions": [
                  "Emphasizing the harsh, sterile greenish-white lighting to contrast against the natural dusk light, subtly heightening the character's growing unease"
                ],
                "confidence": "high"
              },
              {
                "element_id": "dusk_evening_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The overall environmental lighting reflects early evening twilight, characterized by a pervasive dusk-blue ambient glow. This natural dim blue light fully wraps the exterior surroundings and faintly spills through the main entrance into the building's interior, intermingling with artificial lights.",
                "applies_to_shots": [
                  3,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene heading: 해질 무렵 (around dusk)",
                  "Shot 3: dusk-blue spill from the entrance faintly cools the shadows",
                  "Shot 5: faint sunset spill from the aisle opening",
                  "Shot 6: Dusk-blue ambient light wraps her profile"
                ],
                "visual_inferences": [
                  "The darkening sky outside casts a cool twilight shadow that penetrates the threshold of the automatic glass doors"
                ],
                "creative_decisions": [
                  "Using the dusk-blue tone as a consistent unifying atmospheric element across both interior observation and exterior profile shots"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 8,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "138f0aaa63ba67b2"
      },
      {
        "scene_index": 8,
        "heading": "번화가·대형 마트 / 해질 무렵",
        "beat_title": "연결되지 않는 전화",
        "representative_moment": "어스름이 깔린 마트 밖 보도에서 C01이 P05를 귀에 댄 채 초조하게 먼 거리를 응시한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level medium shot profile, dusk-blue twilight with pink and cyan neon reflections",
            "t2i_prompt": "Photorealistic cinematic still. Eye-level medium shot. C01O02 in a navy windbreaker, a young East Asian woman, stands in right profile on the sidewalk, occupying the right third of the frame. P05, a small smartphone, is pressed against her ear, her eyes fixed on the distant street. In the middle background, the automatic glass door and storefront from the reference sit softly behind her. A pervasive dusk-blue ambient twilight wraps her side profile and the exterior surroundings. The glass panel behind her reflects blurred pink and cyan neon streaks from the street traffic, adding uneasy urban textures without dominating the frame.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#8 action: 수리영 마트 밖을 나오면서 연락을 취해보지만 받지않는다.",
              "shot description: 어스름이 깔린 마트 자동문 밖에서 휴대폰을 귀에 댄 수리영의 옆모습."
            ],
            "visual_inferences": [
              "fixed_element dusk_evening_lighting: The overall environmental lighting reflects early evening twilight, characterized by a pervasive dusk-blue ambient glow.",
              "Uneasy pink and cyan neon reflections cast on the glass doors from the busy street"
            ],
            "creative_decisions": [
              "Placed C01 on the right third of the frame to visually emphasize her waiting state and the empty space of her gaze",
              "Contrasted the cool dusk-blue ambient light on her profile with warm, blurred neon reflections in the background to build subtle tension"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "f780990dbbbd6b42",
              "owned_hash": "f09a73301b99308c",
              "camera_direction_hash": "41d24a6df5c411b9",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "door",
                  "violating_phrase": "the automatic glass door",
                  "reason": "The prompt refers to the door as a framed background element without asking to create or add a new one, using it as an existing reference object.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "storefront",
                  "violating_phrase": "storefront from the reference",
                  "reason": "The prompt explicitly references the existing storefront from the reference rather than directing it to be newly generated.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "glass panel",
                  "violating_phrase": "The glass panel behind her reflects",
                  "reason": "The glass panel is treated as an existing background element with reference context, not as a newly added object.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "door",
                  "violating_phrase": "the automatic supermarket doors",
                  "reason": "The doors are mentioned as existing background elements sitting behind her, which is a reference use rather than a redraw instruction.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 8,
        "dependency_reason": "S8_Shot3의 조명 톤과 배경(마트 입구와 보도) 요소의 일관성 유지 (exact_background)",
        "_shot_index": 6,
        "visible_entities": [
          "C01",
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 8,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision after the cut outside. An eye-level MS profile frames 수리영 four feet away on the sidewalk side, her side silhouette occupying the right third as she presses a phone to her ear; the automatic supermarket doors sit softly behind her in the middle background. The phone remains small and realistic near her cheek, while reflected neon and dusk traffic flicker across the glass without taking over the frame.",
            "lighting_mood": "Dusk-blue ambient light wraps her profile while supermarket fluorescents and neon reflections add uneasy pink and cyan accents behind her.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "cb_exterior_entrance_dusk_phone",
            "reference_usage": "exact_background",
            "owned_objects": [
              "CCTV camera",
              "alcove",
              "ceiling light",
              "curb",
              "door",
              "door sensor",
              "floor mat",
              "glass panel",
              "sidewalk",
              "storefront",
              "street",
              "wall"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_evening_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The overall environmental lighting reflects early evening twilight, characterized by a pervasive dusk-blue ambient glow. This natural dim blue light fully wraps the exterior surroundings and faintly spills through the main entrance into the building's interior, intermingling with artificial lights.",
                "applies_to_shots": [
                  3,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene heading: 해질 무렵 (around dusk)",
                  "Shot 3: dusk-blue spill from the entrance faintly cools the shadows",
                  "Shot 5: faint sunset spill from the aisle opening",
                  "Shot 6: Dusk-blue ambient light wraps her profile"
                ],
                "visual_inferences": [
                  "The darkening sky outside casts a cool twilight shadow that penetrates the threshold of the automatic glass doors"
                ],
                "creative_decisions": [
                  "Using the dusk-blue tone as a consistent unifying atmospheric element across both interior observation and exterior profile shots"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 8,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "cb_exterior_entrance_dusk_phone",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "ba33c1881f482fc1"
      },
      {
        "scene_index": 9,
        "heading": "S#9. 해안가 / N",
        "beat_title": "급박한 귀가길",
        "representative_moment": "차가운 달빛을 등진 C01이 가파른 해안 언덕을 향해 자전거 페달을 거세게 밟고 올라가는 역광 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle tracking shot from the seaward shoulder, underexposed moon backlight creating rim-lit silhouettes",
            "t2i_prompt": "Photorealistic cinematic still. A low angle tracking shot looking up a steep, slightly damp asphalt road that rises diagonally across the lower frame. C01O02 in a dark windbreaker, a young East Asian woman, appears as a backlit figure in left profile, rim light tracing her shoulders, back, and the jacket's edge, preserving her body volume against the deep blue-black underexposure. She is seated on the saddle of the bicycle in mid-pedal, her torso pitched sharply forward, one knee bent in the powerful down stroke, hands gripping the handlebar. The bicycle's main frame and wheels are clearly visible. Her eyes are fixed up the hill. The bright, cold moon shines directly from behind her, partially veiled by dense blue-gray coastal haze that blooms around the frame edges, leaving the seaward horizon in deep shadow. Focus on the tense, strained posture of the rim-lit silhouette against the glaring moon.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#9 action: '해안도로를 자전거를 타고 바삐 집으로 달려가는 수리영.'",
              "shot description: 자전거 페달을 강하게 밟기 위해 상체를 앞으로 숙인 채 한쪽 무릎을 굽힌 수리영, 자전거의 검은 실루엣, 달빛을 등짐"
            ],
            "visual_inferences": [
              "mid-action freeze applied to the fast pedaling motion (mid-pedal, knee bent in down stroke)",
              "vehicle rendering rule applied: bicycle frame and wheels made visible to avoid floating figure",
              "silhouette rendering rule applied: rim lighting and body volume preserved instead of a flat black cutout"
            ],
            "creative_decisions": [
              "low angle from the seaward shoulder to emphasize the diagonal uphill struggle against the stark moonlight",
              "deep blue-black underexposure combined with blue-gray coastal haze to enhance the ominous occult horror mood"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "202f83e92083a50e",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "99e9552e6d3c462b",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 6,
        "dependency_reason": "S6_Shot2와 동일한 해안도로 로케이션의 공간 분위기와 연속성 유지 (해무, 달빛, 차가운 톤)",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "L08"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 9,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision from the seaward shoulder. A low angle WS tracks three to five meters behind and beside 수리영, exposing for the cold moon so she and the bicycle become a hard black silhouette climbing the steep road across the center-left of frame. Her torso is pitched forward at the strongest pedal stroke, one knee bent sharply, with the uphill asphalt cutting diagonally toward the moonlit haze.",
            "lighting_mood": "Underexposed moon backlight carves everything into blue-black silhouette, with coastal haze blooming around the edges like an omen.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L08"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 6,
                "shot_index": 2,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "287fe4aed51c0d5f"
      },
      {
        "scene_index": 10,
        "heading": "S#10. 옥탑방 / N",
        "beat_title": "침입의 시작",
        "representative_moment": "거친 남자의 손이 전단지를 문틈으로 꾹 밀어 넣고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level extreme close-up, weak practical light and moon spill with sharp crimson-brown rust accents",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up, focus on the rough hand of a middle-aged East Asian man, a dark trench coat sleeve visible at the wrist. The fingers tightly grip a creased paper flyer, forcing its thin edge into the narrow vertical seam of a heavy iron door. The flyer is angled like a blade entering the latch line, proportionate and framed by the metal surface. [L04: Scratched iron door surface filling the immediate background, dropping into blackened negative space at the outer frame edges]. A weak rooftop practical light and cool moon spill skim across the knuckles and the paper, leaving the surrounding door surface in dirty blue-black shadow with sharp crimson-brown rust accents.",
            "outfit_assignments": [],
            "source_facts": [
              "S10 action: '전단지를 뽑아서 손가락으로 문틈에 꾹 밀어 넣는다.'",
              "shot description: 굳게 닫힌 현관 철문 틈새에 끼워진 종이 전단지를 쥔 거친 남자의 손 클로즈업"
            ],
            "visual_inferences": [
              "ECU framing requires substituting the character ID with a common noun and demographic descriptor for the isolated body part (hand)",
              "Dark trench coat sleeve visible near the wrist to ground the character's outfit",
              "The scratched iron door acts as the immediate frame-edge surface"
            ],
            "creative_decisions": [
              "Dropped the outer edges of the frame into blackened negative space to deeply emphasize the hand, flyer, and door seam",
              "Used weak practical and moon spill skimming the knuckles to create texture without slicing the body part with light"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "bd3668c413b54a16",
              "owned_hash": "17c170cf5d0badbe",
              "camera_direction_hash": "216bdec6405cd591",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 4,
        "dependency_reason": "S4_Shot1에서 옥탑방 외부(L04)가 설정되었으나, 본 샷은 extreme close-up(skipped_close_framing)이므로 배경 참조 이미지를 생략하고 즉각적인 철문 표면만 묘사함",
        "_shot_index": 3,
        "visible_entities": [
          "C10",
          "P04",
          "P07",
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 10,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision at the iron door’s seam. An eye-level ECU dollies inches toward the narrow gap, with 거친 남자’s hand, the paper flyer, and the dark door seam compressed into the center while the rest of the iron door drops into blackened negative space. The flyer is angled like a thin blade entering the latch line, but it stays proportionate and framed by the scratched metal surface for scale.",
            "lighting_mood": "A weak rooftop practical and moon spill skim the hand and paper, leaving the iron door in dirty blue-black shadow with a sharp crimson-brown rust accent.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C10",
              "P04",
              "P07",
              "L04"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C05",
                "outlook_id": "O06"
              },
              {
                "character_id": "C10",
                "outlook_id": "O12"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_rooftop_night_intrusion_door_shadow",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 4,
                "shot_index": 1,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C10O12",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "1369eef017322468"
      },
      {
        "scene_index": 10,
        "heading": "S#10. 옥탑방 / N",
        "beat_title": "낯선 남자의 침입과 민숙의 비명",
        "representative_moment": "An East Asian man's lower face leaning in from the dark edge, mouth meeting the shoulder of an East Asian woman.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Handheld close-up with a slight Dutch angle, near-dark cold blue-black shadow",
            "t2i_prompt": "Photorealistic cinematic still. Handheld close-up with a slight Dutch angle. Focus on the contact point where a man's mouth meets a woman's shoulder skin. An East Asian woman in a rumpled shirt, shoulder twisting away in left profile, her pulled-taut cloth and bare neck forming the foreground plane in the center-right, eyes looking toward the void. An East Asian man in dark clothes, at three-quarter angle from the right, leaning in from the dark left edge, lower face and teeth visible, eyes fixed on the woman. A narrow strip of cold window spill reflects on the man's teeth and the woman's shoulder skin, while the rest of the skin is washed in heavy, cold blue-gray shadow. [L04: cramped dark enclosure, rough wallpaper texture barely visible in deep shadow].",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 7 lighting: 'Near-dark interior lighting uses a narrow strip of cold window spill to catch skin and teeth, with the rest swallowed by blue-gray shadow'",
              "DP direction: 'A handheld CU with a slight Dutch angle ... angled across her shoulder toward the man's mouth as it meets the skin'"
            ],
            "visual_inferences": [
              "fixed_element dark_rooftop_room_interior: heavy cold blue-black shadows",
              "Close framing skips full room details, focusing only on the immediate contact surfaces"
            ],
            "creative_decisions": [
              "Omitted C##O## composite IDs per id_policy.body_part_focus_rule due to extreme close-up on mouth/shoulder, using demographic descriptors instead to prevent floating face artifacts",
              "Used frame-edge surface description for the background per skipped_close_framing rules"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "d18c21f862789e7d",
              "owned_hash": "17c170cf5d0badbe",
              "camera_direction_hash": "67ea0d30f1be35f7",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 4,
        "dependency_reason": "S4_Shot1 background reference requested but intentionally omitted at composition time due to close framing rules.",
        "_shot_index": 7,
        "visible_entities": [
          "P04",
          "P07",
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 10,
            "shot_index": 7
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Observer perspective, direct vision inside the cramped room. A handheld CU with a slight Dutch angle pauses almost still at shoulder height beside 한국인 여자, angled across her shoulder toward 한국인 남자’s mouth as it meets the skin in the center-right of frame. The woman’s shoulder and neck form the foreground plane, while the man’s lower face enters from the dark left edge, making the contact point the only sharp, terrifying detail before the scream.",
            "lighting_mood": "Near-dark interior lighting uses a narrow strip of cold window spill to catch skin and teeth, with the rest swallowed by blue-gray shadow and a sickly, violent stillness.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P04",
              "P07",
              "L04"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C05",
                "outlook_id": "O06"
              },
              {
                "character_id": "C10",
                "outlook_id": "O12"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_rooftop_night_intrusion_door_shadow",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dark_rooftop_room_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The cramped interior of the room is engulfed in heavy, cold blue-black shadows. A weak, sickly strip of light spills from an unseen window, cutting through the intense darkness and faintly illuminating the soft, dingy texture of a dirty wall in the background.",
                "applies_to_shots": [
                  7,
                  8
                ],
                "source_facts": [
                  "Shot 7 lighting: 'Near-dark interior lighting uses a narrow strip of cold window spill to catch skin and teeth, with the rest swallowed by blue-gray shadow'",
                  "Shot 8 lighting: 'Cold blue-black room darkness is cut by a weak sickly spill from outside'",
                  "Shot 8 camera: 'soft, dirty wall blur'"
                ],
                "visual_inferences": [
                  "The weak light source mimics nighttime streetlamps or faint moonlight, emphasizing the neglected and isolated nature of the rooftop room."
                ],
                "creative_decisions": [
                  "Maintaining a consistent cold blue-black color palette across the interior shots to establish a claustrophobic, violent, and terrifying atmosphere."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 4,
                "shot_index": 1,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C10O12",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "0da72a75f8d8c2be"
      },
      {
        "scene_index": 10,
        "heading": "S#10. 옥탑방 / N",
        "beat_title": "고통에 찬 비명과 침입자의 공격",
        "representative_moment": "어둠 속에서 얼굴에 강렬한 고통이 서린 채 비명을 지르는 C05의 얼굴 클로즈업",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "head-and-shoulder composition for ECU, maintaining shoulder visibility, cold blue-black and crimson warmth",
            "t2i_prompt": "Photorealistic cinematic still. Head-and-shoulder composition of in a faded shirt, a middle-aged East Asian woman, facing the camera with her head thrown back and eyes closed in severe agony. Tight framing on her expression, her face occupying most of the frame while her shoulders remain visible at the bottom edge. Focus on her terrified, screaming expression and the sweat-dampened texture of her skin. A weak, sickly strip of cool blue-black light washes across the side of her neck, while a raw crimson warmth reflects on her clenched eyelids and stretched open mouth. The background is compressed into a soft, dark blur of a grimy wall in heavy shadows, completely excluding the attacker from the frame.",
            "outfit_assignments": [],
            "source_facts": [
              "S10 action: '민숙을 덮쳐 어깨를 물어뜯는 듯한 모습 ‘아악-’'",
              "Shot 8 DP instruction: extreme close-up (ECU) holding only her clenched eyelids, stretched mouth, and sweat-dark skin texture",
              "Shot 8 DP instruction: cold blue-black room darkness cut by a weak sickly spill, raw crimson warmth implied in skin"
            ],
            "visual_inferences": [
              "fixed_element dark_rooftop_room_interior: soft, dingy texture of a dirty wall in the background",
              "head thrown back emphasizing extreme pain tension",
              "attacker is kept entirely out of frame to isolate her terror"
            ],
            "creative_decisions": [
              "head-and-shoulder composition used to prevent the floating head artifact common in extreme close-ups, while still occupying most of the frame",
              "raw crimson lighting mapped to skin reflections to visually imply the violence without showing the actual physical bite"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "04c6a83183a28eee",
              "owned_hash": "17c170cf5d0badbe",
              "camera_direction_hash": "8f1fd5477665fd93",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 10,
        "dependency_reason": "S10_Shot7의 옥탑방 내부 조명과 분위기 연속성 유지",
        "_shot_index": 8,
        "visible_entities": [
          "P04",
          "P07",
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 10,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From inside the dark rooftop room at face height and slightly below the woman's eyeline, the pan dies into an extreme close-up (ECU), eye-level with a slight upward pressure, holding only her clenched eyelids, stretched mouth, and sweat-dark skin texture. This is direct observer vision, not the attacker's POV; the attacker is completely excluded, and her face occupies most of the frame against a soft, dirty wall blur.",
            "lighting_mood": "Cold blue-black room darkness is cut by a weak sickly spill from outside, with a raw crimson warmth implied in the skin and mouth.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P04",
              "P07",
              "L04"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C05",
                "outlook_id": "O06"
              },
              {
                "character_id": "C10",
                "outlook_id": "O12"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_rooftop_night_intrusion_door_shadow",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dark_rooftop_room_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The cramped interior of the room is engulfed in heavy, cold blue-black shadows. A weak, sickly strip of light spills from an unseen window, cutting through the intense darkness and faintly illuminating the soft, dingy texture of a dirty wall in the background.",
                "applies_to_shots": [
                  7,
                  8
                ],
                "source_facts": [
                  "Shot 7 lighting: 'Near-dark interior lighting uses a narrow strip of cold window spill to catch skin and teeth, with the rest swallowed by blue-gray shadow'",
                  "Shot 8 lighting: 'Cold blue-black room darkness is cut by a weak sickly spill from outside'",
                  "Shot 8 camera: 'soft, dirty wall blur'"
                ],
                "visual_inferences": [
                  "The weak light source mimics nighttime streetlamps or faint moonlight, emphasizing the neglected and isolated nature of the rooftop room."
                ],
                "creative_decisions": [
                  "Maintaining a consistent cold blue-black color palette across the interior shots to establish a claustrophobic, violent, and terrifying atmosphere."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 10,
                "shot_index": 7,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C10O12",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "a0583fa8d3fec88d"
      },
      {
        "scene_index": 11,
        "heading": "S#11. 옥탑 방 밖 / N",
        "beat_title": "옥상에 감도는 역겨운 냄새와 반쯤 열린 현관 철문 발견",
        "representative_moment": "옥상에 올라온 수리영(C01)이 반쯤 열려있는 현관 철문을 발견하고 긴장한 채 뚫어지게 주시하는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "medium close-up from a slight low angle, chest-height, muted coastal night blues with a sickly fluorescent highlight",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a navy windbreaker, a young East Asian woman, captured in a medium close-up from a slight low angle at chest height. Shoulders rigid in the lower half of the frame, she stands in three-quarter left profile, her eyes fixed intently past the lens line toward an unseen, off-camera iron door. Focus on her tense expression and the sharp lighting contrast. The environment is immersed in a muted gray-blue coastal night darkness. A faint, sickly fluorescent light spills from the off-camera doorway, casting a distinct, pale highlight across her cheek and jacket against the gloomy ambient shadows. [L04: A dark, out-of-focus slice of the hazy night sky and a blurred rooftop railing frame her shoulder in the soft background].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "Shot 4 description: Suriyoung's upper body standing firm on the rooftop floor, staring intently forward.",
              "Beat context: spots the half-open iron door and visually recognizes a serious problem at home."
            ],
            "visual_inferences": [
              "fixed_element eerie_doorway_lighting: cold gray-blue night darkness with an off-camera sickly fluorescent spill highlighting her features.",
              "Her posture is rigid, reflecting tension upon smelling the odor and seeing the open door."
            ],
            "creative_decisions": [
              "Used a slight low angle chest-height MCU to emphasize her rigid shoulders and intense gaze.",
              "Applied strong color contrast between the cool ambient blue and the harsh pale fluorescent highlight to heighten the eerie thriller mood.",
              "Blurred the immediate background railing to adhere to close framing constraints while grounding her in the rooftop setting."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "a0a3c662b2395e8b",
              "owned_hash": "98a58c7b3b700047",
              "camera_direction_hash": "48afc9eef4d16e7c",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "없음",
        "_shot_index": 4,
        "visible_entities": [
          "C01",
          "L04",
          "L05",
          "L06"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 11,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "On the rooftop floor about two meters in front of 수리영, the camera holds a medium close-up (MCU) at a slight low angle, derived from the chest-height frontal axis of the flow. 수리영 is centered but turned just off-axis, her shoulders rigid in the lower half while her gaze cuts past the lens line toward the half-open iron door behind camera.",
            "lighting_mood": "Muted coastal night blues flatten the rooftop while a faint fluorescent spill from the doorway gives her skin a sickly pallor.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L04",
              "L05",
              "L06"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_approach_night_open_door",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "eerie_doorway_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The surrounding environment is immersed in a cold, muted gray-blue coastal night darkness. A faint, sickly fluorescent light spills from an unseen, half-open doorway located just outside the frame, casting a distinct, harsh highlight against the gloomy ambient shadows.",
                "applies_to_shots": [
                  4,
                  6
                ],
                "source_facts": [
                  "Shot 4 lighting: Muted coastal night blues flatten the rooftop while a faint fluorescent spill from the doorway gives her skin a sickly pallor.",
                  "Shot 6 lighting: A cold gray-blue top wash and a thin, dirty doorway highlight catch in her pupils."
                ],
                "visual_inferences": [
                  "The off-camera fluorescent light serves as the primary practical highlight source, consistently illuminating subjects facing the unseen half-open door."
                ],
                "creative_decisions": [
                  "Maintaining a stark contrast between the cool night ambient wash and the unnerving, pale doorway spill to unify the visual tone across different focal lengths."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "3ac7b697e2edd115"
      },
      {
        "scene_index": 11,
        "heading": "S#11. 옥탑 방 밖 / N",
        "beat_title": "Ominous Discovery",
        "representative_moment": "Extreme close-up of C01's terrified eyes reflecting the unseen open door.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up on eyes, cold gray-blue ambient with pale fluorescent pupil reflections",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up on the widened eyes of a young East Asian woman. The bridge of her nose and furrowed brow form tight borders along the edges of the composition. She is facing the camera, her dark, dilated pupils fixed intently just beyond the lens toward an unseen half-open door. The surrounding skin is immersed in a cold, muted gray-blue night darkness. A faint, sickly pale fluorescent light from the off-camera doorway spills across the surface of her brow and cheekbone, casting a distinct, harsh highlight that catches sharply in her wet pupils. The extreme shallow depth of field blurs the immediate dark edges into a soft, gloomy gray-blue obscurity.",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 6 description: ECU of widened eyes, pupils dilated, staring toward the open iron door.",
              "DP instruction: eye-level ECU, widened eyes dominating frame, bridge of nose/brow forming borders."
            ],
            "visual_inferences": [
              "fixed_element eerie_doorway_lighting: cold gray-blue night darkness, sickly fluorescent spill from unseen door.",
              "Reflection of the unseen door in the pupils emphasizes the off-camera focal point."
            ],
            "creative_decisions": [
              "Applied id_policy.body_part_focus_rule: Replaced C01O02 with 'young East Asian woman' to prevent face/body hallucination in an ECU eye shot.",
              "Applied skipped_close_framing rule: Excluded any mention of the background room, focusing entirely on the eyes and immediate light reflections."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "9f0d86735903fb3b",
              "owned_hash": "98a58c7b3b700047",
              "camera_direction_hash": "8c20f6748800d152",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "",
        "_shot_index": 6,
        "visible_entities": [
          "C01",
          "L04",
          "L05",
          "L06"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 11,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Continuing along the same frontal axis, the dolly-in ends in an extreme close-up (ECU), eye-level, with both of 수리영's widened eyes dominating the frame while the bridge of her nose and brow form tight borders. The shot remains direct observer vision; her pupils are fixed beyond the camera toward the open iron door, and the rooftop background disappears into shallow darkness.",
            "lighting_mood": "A cold gray-blue top wash and a thin, dirty doorway highlight catch in her pupils, making the eyes feel wet and terrified.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L04",
              "L05",
              "L06"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_approach_night_open_door",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "eerie_doorway_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The surrounding environment is immersed in a cold, muted gray-blue coastal night darkness. A faint, sickly fluorescent light spills from an unseen, half-open doorway located just outside the frame, casting a distinct, harsh highlight against the gloomy ambient shadows.",
                "applies_to_shots": [
                  4,
                  6
                ],
                "source_facts": [
                  "Shot 4 lighting: Muted coastal night blues flatten the rooftop while a faint fluorescent spill from the doorway gives her skin a sickly pallor.",
                  "Shot 6 lighting: A cold gray-blue top wash and a thin, dirty doorway highlight catch in her pupils."
                ],
                "visual_inferences": [
                  "The off-camera fluorescent light serves as the primary practical highlight source, consistently illuminating subjects facing the unseen half-open door."
                ],
                "creative_decisions": [
                  "Maintaining a stark contrast between the cool night ambient wash and the unnerving, pale doorway spill to unify the visual tone across different focal lengths."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 11,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "6daeb39cb0240a6f"
      },
      {
        "scene_index": 12,
        "heading": "S#12. 옥탑방 안 / N",
        "beat_title": "핏자국의 발견",
        "representative_moment": "방문 틈새로 보이는 방바닥 위 선명한 핏자국",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "At knee height, close-up (CU) through a narrow door gap, Dutch angle, sickly interior spill with cold blue shadow",
            "t2i_prompt": "Photorealistic cinematic still. At knee height looking through a narrow open doorway, a Dutch angle compresses the view. The dirty wooden door edge and jamb slice the extreme foreground into dark, out-of-focus vertical bands. Focus on [L07: the surface of the muted flooring beyond the threshold], violently covered in fresh, vivid red bloodstains and smeared pools of blood. Darker, heavier streaks of blood form a disturbing trail across the floor, maintaining a wet, glistening appearance under the dim interior light. Sickly ambient spill and a cold blue shadow wash the ground surface, making the glossy crimson marks look unnaturally vivid against the pale floor, the trail implying a path deeper into the dark interior.",
            "outfit_assignments": [],
            "source_facts": [
              "Scene text: '여기저기 핏자국. 바닥에 흥건한 혈흔. 피묻은 발자국은 커튼으로 이어져 있다.'",
              "Shot description: 방문 틈새로 보이는 방바닥 위 선명하고 붉은 핏자국 클로즈업"
            ],
            "visual_inferences": [
              "fixed_element bloody_bedroom_floor: violently covered in fresh, vivid red bloodstains and smeared pools of blood",
              "door edge in extreme foreground creates dark vertical framing bands"
            ],
            "creative_decisions": [
              "knee-height Dutch angle looking through the narrow door gap to compress the view and heighten horror tension",
              "sickly ambient spill mixed with cold blue shadows to contrast sharply with the wet crimson blood"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "31cebd25a3a9dc86",
              "owned_hash": "50e0a1bb6b2bd65b",
              "camera_direction_hash": "7f93a242364de21c",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 5,
        "dependency_reason": "Same room interior location, but close-framing omits direct background reference, carrying over only the floor surface mood.",
        "_shot_index": 7,
        "visible_entities": [
          "P05",
          "P08",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 12,
            "shot_index": 7
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At knee height outside 수리영's bedroom doorway, the camera compresses into a close-up (CU), Dutch angle, using the narrow door gap as through-object framing. The red blood marks sit in the center-right of the floor beyond the threshold, while the dirty door edge and jamb slice the foreground into dark vertical bands; the implied dolly direction is carried by the trail leading deeper inside.",
            "lighting_mood": "Sickly interior spill and cold blue shadow make the fresh red blood look unnaturally vivid against the muted floor.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "P08",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_daughter_bedroom_night_blood_curtain_body_red_circle",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "bloody_bedroom_floor",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The surface of the room's floor is violently covered in fresh, vivid red bloodstains and smeared pools of blood. Darker, heavier streaks of blood form a disturbing trail across the muted flooring, maintaining a wet, glistening appearance under the dim interior light.",
                "applies_to_shots": [
                  7,
                  10
                ],
                "source_facts": [
                  "Scene text: '여기저기 핏자국. 바닥에 흥건한 혈흔. 피묻은 발자국은 커튼으로 이어져 있다.'",
                  "Shot 7: 'The red blood marks sit in the center-right of the floor beyond the threshold'",
                  "Shot 10: 'smeared floor remain blurred at the frame edges', 'crimson floor reflections flickering'"
                ],
                "visual_inferences": [
                  "The floor is made of a standard, muted material (like linoleum or wood) typical of a Korean rooftop room, providing a stark contrast to the red blood.",
                  "The blood is fresh and wet, creating glossy reflections that catch the ambient room light."
                ],
                "creative_decisions": [
                  "Using the vibrant crimson color and smeared texture of the blood to anchor the spatial continuity and horror atmosphere across different camera angles in the room."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 5,
                "shot_index": 14,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "55fc74ea9140edde"
      },
      {
        "scene_index": 12,
        "heading": "S#12. 옥탑방 안 / N",
        "beat_title": "엄마의 참혹한 죽음 확인",
        "representative_moment": "수리영(C01)이 자신의 방 커튼 뒤에서 죽은 엄마를 발견하고 경악에 차 얼굴이 굳어지는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Dutch angle, handheld close-up with cold green-yellow tint and crimson accents",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a navy windbreaker, a young East Asian woman, facing the camera, recoiling mid-breath. Dutch angle, tight framing on her face, upper body in frame. Focus on her wide, shocked eyes fixed on the foreground, mouth slightly open. Cold window haze and weak yellow-green room spill reflect on her face. The out-of-focus shoulder of in a dark shirt, a middle-aged East Asian woman, appears at the lower foreground edge. [L07: A parted curtain hangs unevenly behind her. A blurred surface of the floor is visible at the lower frame edge, violently covered in fresh, wet crimson bloodstains with flickering red reflections].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "Scene text: '호흡을 가다듬고 커튼을 젖히자 앉은 채로 고개를 떨군 채 죽어있는 엄마- 민숙!!!!'",
              "Shot 10 description: 두 눈을 크게 뜬 채 입을 벌린 수리영의 경악한 얼굴 클로즈업.",
              "DP Note: eyes blown wide and mouth open, while the parted curtain and smeared floor remain blurred at the frame edges"
            ],
            "visual_inferences": [
              "fixed_element bloody_bedroom_floor: fresh, wet crimson bloodstains on the floor reflecting the room light",
              "Min-sook's body (C05) is implied in the extreme foreground as Suri-young faces the camera in shock",
              "The reaction moment is frozen exactly as she recoils from the gruesome sight"
            ],
            "creative_decisions": [
              "Dutch angle to emphasize psychological instability and sudden horror",
              "Soft-focus inclusion of C05O06 in the foreground to anchor the sightline without breaking the close-framing on C01's expression",
              "Yellow-green room spill contrasting with crimson floor reflections for a sickly, horrifying mood"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "4217f72667c108f8",
              "owned_hash": "9f4861cca11ac4b0",
              "camera_direction_hash": "ccc1472e5f0edd23",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 12,
        "dependency_reason": "같은 공간(수리영의 방) 내부의 연속된 상황이므로 조명, 바닥의 핏자국(fixed_element), 배경의 연속성 유지가 필요",
        "_shot_index": 10,
        "visible_entities": [
          "C01",
          "P05",
          "P08",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 12,
            "shot_index": 10
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Inside 수리영's bedroom near the curtained window, the handheld camera pushes into a close-up (CU), Dutch angle, frontal enough to trap her shock but trembling with her breath. 수리영's face fills the center, eyes blown wide and mouth open, while the parted curtain and smeared floor remain blurred at the frame edges as evidence of what she has just uncovered.",
            "lighting_mood": "The handheld close-up is lit by cold window haze and weak yellow-green room spill, with crimson floor reflections flickering at the bottom edge.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "P08",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_night_aftermath_tv_cups",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "bloody_bedroom_floor",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The surface of the room's floor is violently covered in fresh, vivid red bloodstains and smeared pools of blood. Darker, heavier streaks of blood form a disturbing trail across the muted flooring, maintaining a wet, glistening appearance under the dim interior light.",
                "applies_to_shots": [
                  7,
                  10
                ],
                "source_facts": [
                  "Scene text: '여기저기 핏자국. 바닥에 흥건한 혈흔. 피묻은 발자국은 커튼으로 이어져 있다.'",
                  "Shot 7: 'The red blood marks sit in the center-right of the floor beyond the threshold'",
                  "Shot 10: 'smeared floor remain blurred at the frame edges', 'crimson floor reflections flickering'"
                ],
                "visual_inferences": [
                  "The floor is made of a standard, muted material (like linoleum or wood) typical of a Korean rooftop room, providing a stark contrast to the red blood.",
                  "The blood is fresh and wet, creating glossy reflections that catch the ambient room light."
                ],
                "creative_decisions": [
                  "Using the vibrant crimson color and smeared texture of the blood to anchor the spatial continuity and horror atmosphere across different camera angles in the room."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 12,
                "shot_index": 7,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "63d718ac2eace0ff"
      },
      {
        "scene_index": 12,
        "heading": "S#12. 옥탑방 안 / N",
        "beat_title": "벽에 생겨나는 기이한 붉은 원형 표식",
        "representative_moment": "침대 위 흰 벽에 피처럼 붉은 원형 표식이 선명하게 드러나 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level wide shot, flat cold interior light, centered composition",
            "t2i_prompt": "Photorealistic cinematic still. Eye-level wide shot perfectly centered on the blank white wall from the reference. Focus on the fresh, vivid red circular symbol from the reference, sitting in the middle of the frame like wet paint, facing the camera squarely. The bed from the reference forms a low horizontal base across the lower frame, still and slightly rumpled. Flat cold interior light drains the wall to bone-white while the red circle appears saturated and occult, as if projected into reality. The dim, symmetrical bedroom wall corners remain motionless. No characters visible.",
            "outfit_assignments": [],
            "source_facts": [
              "S12 action: '침대 위 벽에 붉은 원이 생겨난다 (마치 누군가 붓으로 벽에 원으로 그리는 것처럼).'",
              "shot description: 침대 위 텅 빈 흰색 벽지 한가운데 붉은 물감으로 그려진 듯한 커다란 원형 표식의 정지 구도.",
              "DP note: no characters visible, omniscient POV, wide shot perfectly centered on the blank white wall."
            ],
            "visual_inferences": [
              "flat cold interior light contrasting with saturated red to emphasize the occult atmosphere",
              "symmetrical framing to highlight the unnatural manifestation of the symbol"
            ],
            "creative_decisions": [
              "anchored 'wall', 'bed', and 'red circular symbol' to the reference image as per background_ref_attached rules",
              "omitted character IDs entirely to fulfill the 'no characters visible' framing instruction",
              "used 'as if projected into reality' to align with the DP's projection perception mode"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "f26daec5da79e957",
              "owned_hash": "50e0a1bb6b2bd65b",
              "camera_direction_hash": "0c2ec342c0f79d05",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "wall",
                  "violating_phrase": "perfectly centered on the blank white wall from the reference",
                  "reason": "The wall is explicitly singled out as the main framed subject, which implies using the existing wall as a compositional anchor rather than introducing a new wall.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "bed",
                  "violating_phrase": "The bed from the reference forms a low horizontal base across the lower frame",
                  "reason": "The bed is explicitly referenced as already present in the source background and used as an anchor element only.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "circle",
                  "violating_phrase": "Focus on the fresh, vivid red circular symbol from the reference, sitting in the middle of the frame like wet paint",
                  "reason": "The circle is described as an existing reference element, so this is an anchor reference rather than a request to create a new circle.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 12,
        "dependency_reason": "Same rooftop room interior, preserving exact background structure (wall, bed, curtain) from S12 Shot 7.",
        "_shot_index": 20,
        "visible_entities": [
          "P05",
          "P08",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 12,
            "shot_index": 20
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Opposite the bed at eye height, the camera locks into a wide shot (WS), eye-level, perfectly centered on the blank white wall above the bed. The red circular symbol sits in the middle of the frame like wet paint, large but not overwhelming, with the bed forming a low horizontal base and no characters visible.",
            "lighting_mood": "Flat cold interior light drains the wall to bone-white while the red circle appears saturated and occult, as if projected into reality.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "P08",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C05",
                "outlook_id": "O06"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_daughter_bedroom_night_blood_curtain_body_red_circle",
            "reference_usage": "exact_background",
            "owned_objects": [
              "backpack",
              "bed",
              "circle",
              "curtain",
              "doll",
              "door",
              "floor",
              "photo",
              "pillow",
              "sheet",
              "wall",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 12,
                "shot_index": 7,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C05O06",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_daughter_bedroom_night_blood_curtain_body_red_circle",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "72e275431cdd6e56"
      },
      {
        "scene_index": 13,
        "heading": "S#13. 옥탑방 외곽 / N",
        "beat_title": "수리영을 붙잡은 혜수",
        "representative_moment": "C02 firmly grips the shoulders of the panicked C01 on the exterior path.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "eye-level medium wide shot, locked two-shot, cold night fog with pulsing red and blue police strobes",
            "t2i_prompt": "Photorealistic cinematic still. An eye-level medium wide two-shot. C01O02 in a navy windbreaker, a young East Asian woman, stands slightly nearer to the camera with her back to camera, her posture slumped as she looks blankly down at the void. Directly behind her in the middle ground, C02O03 in a grey leather jacket, a middle-aged East Asian woman, stands at three-quarter angle from the right, her eyes fixed entirely on C01O02. C02O03's hands firmly grip C01O02's shoulders, locking them together in the center frame. The two figures stand together on the exterior path from the reference. The surrounding environment is enveloped in cold night fog and swept by pulsing red and blue police strobe lights. Cool blue ambient light washes the damp road and stair from the reference, while bright crimson reflections pool on the women's wet jackets. Focus on the tense posture and the firm grip anchoring the two figures in the foggy night.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "S#13 action: '차에서 내린 혜수... 초점을 잃고 멍하니 서있는 수리영의 모습을 발견하고 달려간다. 영아? 왜! 무슨 일이야?'",
              "shot description: On the exterior path between the stairway and police car, the camera holds a medium wide shot (MWS), eye-level, in a locked two-shot.",
              "혜수's two hands gripping 수리영's shoulders become the center anchor"
            ],
            "visual_inferences": [
              "fixed_element police_strobe_lighting: The dark exterior environment is enveloped in cold night fog and continuously swept by pulsing red and blue police strobe lights.",
              "C01's posture is slumped and defeated, reflecting her state of shock, while C02's stance is firm and supportive.",
              "Both characters are physically grounded on the same path, strongly anchoring the medium wide composition."
            ],
            "creative_decisions": [
              "Explicitly anchored the shared exterior path and the background 'road and stair' to the exact background reference image, respecting the close framing limits.",
              "Applied alternating red and blue strobe lighting as surface reflections (e.g., 'crimson reflections pool on the women's wet jackets') to convey urgency without breaking Rule B."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "2bf160eeff49cc29",
              "owned_hash": "da184dd47ed9e9fa",
              "camera_direction_hash": "7d71cb484b0cd941",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "stair",
                  "violating_phrase": "the damp road and stair from the reference",
                  "reason": "The phrase references the stair as an existing element from the reference rather than asking to create a new one.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "road",
                  "violating_phrase": "the damp road",
                  "reason": "Road appears as part of the setting without any instruction to add or generate it, so it functions as an existing scene anchor.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 11,
        "dependency_reason": "previous_shot_refs points to S11_Shot6 for location/exact_background continuity rules as defined in the prompt card",
        "_shot_index": 4,
        "visible_entities": [
          "C01",
          "C02",
          "L05",
          "L06"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 13,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "On the exterior path between the stairway and police car, the camera holds a medium wide shot (MWS), eye-level, in a locked two-shot after the preceding movement. 혜수's two hands gripping 수리영's shoulders become the center anchor, with 수리영 slightly nearer to camera and 혜수 squared behind her in the middle ground, the siren-lit rooftop receding around them.",
            "lighting_mood": "Blue-red police strobes rake across cold rooftop fog, freezing the women in alternating panic and procedural glare.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C02",
              "L05",
              "L06"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_approach_night_siren_arrival",
            "reference_usage": "exact_background",
            "owned_objects": [
              "CCTV camera",
              "boundary wall",
              "building",
              "door",
              "drain channel",
              "emergency vehicle",
              "gate",
              "landing",
              "plume",
              "railing",
              "road",
              "security light",
              "stain",
              "stair",
              "utility pole",
              "window",
              "yard"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "police_strobe_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The dark exterior environment is enveloped in cold night fog and continuously swept by pulsing red and blue police strobe lights. These harsh, alternating colored glares cut through the mist, illuminating the surroundings with a striking and urgent atmosphere.",
                "applies_to_shots": [
                  4,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene text mentions sirens sounding and a police car arriving ('동시에 사이렌이 울리고~. 차에서 내린 혜수').",
                  "Shot 4 describes 'Blue-red police strobes rake across cold rooftop fog'.",
                  "Shot 5 describes 'pulsing red-blue siren light'.",
                  "Shot 6 mentions 'A cold blue base with intermittent crimson siren flicker'."
                ],
                "visual_inferences": [
                  "The physical police vehicle is off-screen or out of focus, but its strong flashing lights universally dictate the visual tone of the surrounding area."
                ],
                "creative_decisions": [
                  "Consistently applying the alternating blue and red strobe effects across all shots to visually anchor the urgency and shock of the moment."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 11,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_approach_night_siren_arrival",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "ae9366b7728dc0bd"
      },
      {
        "scene_index": 13,
        "heading": "S#13. 옥탑방 외곽 / N",
        "beat_title": "끔찍한 진실을 전하는 수리영의 반응",
        "representative_moment": "경찰 사이렌의 붉고 푸른 불빛 아래, 수리영(C01)이 눈물을 흘리며 혜수(C02)를 올려다보는 긴장감 넘치는 클로즈업 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle close-up, over-the-shoulder framing, cold night fog with red-blue strobe bokeh",
            "t2i_prompt": "Photorealistic cinematic still. Low angle looking up, head-and-shoulder composition. C01O02 in a navy windbreaker, a young East Asian woman, occupies the lower center at three-quarter angle from the left, her tearful face lifted, chin trembling, eyes fixed on C02O03. C02O03 in a gray leather jacket, a middle-aged East Asian woman, is positioned with back to camera in an over-the-shoulder perspective. Only C02O03's chin and lower jaw are partially visible, skimming the upper frame edge, looking down, her hands resting on C01O02's shoulders. They share the immediate space of the dark exterior landing. Cold night fog envelops them. Pulsing red and blue police strobe lights wash the side of C01O02's face, catching in her tears, and glow against the underside of C02O03's jaw. [L05: A wet concrete stair railing is faintly visible at the edge], while the remaining depth smears into soft blue-red bokeh. Focus on C01O02's tearful expression.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "S#13 action: '초점을 잃고 멍하니 서있는 수리영의 모습을 발견하고 달려간다... 엄마가 죽어있어.'",
              "shot description: reaction beat of Suri-young tearfully looking up at Hye-su."
            ],
            "visual_inferences": [
              "fixed_element police_strobe_lighting applies the continuous pulsing red and blue lights to the characters' skin and tears.",
              "Over-the-shoulder (OTS) low angle from below places Hye-su's jaw at the top frame edge and Suri-young's face in the lower center.",
              "Direct physical contact (hands on shoulders) anchors the two characters in the exact same spatial depth."
            ],
            "creative_decisions": [
              "Used a soft blue-red bokeh in the background to emphasize the emergency atmosphere without relying on background references (compliant with skipped_close_framing).",
              "Focused the strobe light reflection on C01's tears and the underside of C02's jaw to maximize the dramatic, horrific impact of the dialogue."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "9289550d95ff816d",
              "owned_hash": "da184dd47ed9e9fa",
              "camera_direction_hash": "603a29736687bcab",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 13,
        "dependency_reason": "Continuity with prior S13_Shot4 for the cold night fog and alternating red-blue police strobe lighting environment.",
        "_shot_index": 5,
        "visible_entities": [
          "C01",
          "C02",
          "L05",
          "L06"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 13,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Low and close in front of 수리영, the camera finishes its inward move as a close-up (CU), low angle, looking up so 혜수's chin and lower face skim the upper edge like a looming frame. 수리영's tearful face occupies the lower center, her eyes lifted toward 혜수 while the police lights smear behind them in soft blue-red bokeh.",
            "lighting_mood": "Cold night haze is punctured by pulsing red-blue siren light that catches in 수리영's tears and under 혜수's jaw.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C02",
              "L05",
              "L06"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_approach_night_siren_arrival",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "police_strobe_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The dark exterior environment is enveloped in cold night fog and continuously swept by pulsing red and blue police strobe lights. These harsh, alternating colored glares cut through the mist, illuminating the surroundings with a striking and urgent atmosphere.",
                "applies_to_shots": [
                  4,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene text mentions sirens sounding and a police car arriving ('동시에 사이렌이 울리고~. 차에서 내린 혜수').",
                  "Shot 4 describes 'Blue-red police strobes rake across cold rooftop fog'.",
                  "Shot 5 describes 'pulsing red-blue siren light'.",
                  "Shot 6 mentions 'A cold blue base with intermittent crimson siren flicker'."
                ],
                "visual_inferences": [
                  "The physical police vehicle is off-screen or out of focus, but its strong flashing lights universally dictate the visual tone of the surrounding area."
                ],
                "creative_decisions": [
                  "Consistently applying the alternating blue and red strobe effects across all shots to visually anchor the urgency and shock of the moment."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 13,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "f34f36eae14cf9a9"
      },
      {
        "scene_index": 13,
        "heading": "S#13. 옥탑방 외곽 / N",
        "beat_title": "엄마의 죽음을 전해 듣고 충격받은 혜수",
        "representative_moment": "수리영의 말을 듣고 충격에 빠진 혜수(C02)가 미간을 찌푸린 채 두 눈이 커진다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level frontal head-and-shoulder composition, shallow depth of field, cold blue ambient with crimson strobe highlights",
            "t2i_prompt": "Photorealistic cinematic still. C02O03 in a gray leather jacket, a middle-aged Asian woman, facing the camera with her jaw tightening still and eyes fixed intensely off-camera. Her widened eyes and furrowed brow are positioned dead center in a clean, frontal head-and-shoulder composition. A cold blue ambient base washes the left side of her face and neck, while an intermittent crimson police strobe light reflects warmly on her right jawline and jacket collar. The background is [L06: an out-of-focus dark foggy night, a faintly blurred wet railing forming a thin silhouette line behind her, soft negative space], maintaining extremely shallow focus to emphasize her profound shock.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "Scene text mentions Hye-su's shocked reaction: '혜수 (놀라) 뭐?!'",
              "Shot description: 미간을 찌푸린 채 두 눈이 커진 혜수의 충격받은 표정.",
              "DP directive: eye-level, clean and frontal... widened eyes and furrowed brow sit dead center."
            ],
            "visual_inferences": [
              "fixed_element police_strobe_lighting: red and blue alternating siren lights interact with her facial features and clothing.",
              "The dark rooftop environment is heavily obscured by fog and shallow depth of field, focusing purely on her emotional punctuation."
            ],
            "creative_decisions": [
              "Used a 'head-and-shoulder composition' to firmly center her face without filling the entire frame, avoiding the floating-head artifact while adhering to the close-framing scale.",
              "Replaced the background reference with a generic frame-edge description ([L06: out-of-focus dark foggy night...]) to comply with the 'skipped_close_framing' background binding.",
              "Applied lighting as surface reflections ('washes the left side', 'reflects warmly on her right jawline') to prevent the strobe lights from physically 'cutting' the character's geometry."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "2ef6b207568c7622",
              "owned_hash": "da184dd47ed9e9fa",
              "camera_direction_hash": "a2946dae0d2b8b29",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 13,
        "dependency_reason": "같은 공간(빌라 외부 계단 주변)에서의 연속적인 시간대이므로, 사이렌 불빛과 안개 낀 차가운 밤의 시각적 요소가 그대로 이어져야 함",
        "_shot_index": 6,
        "visible_entities": [
          "C02",
          "L05",
          "L06"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 13,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "The reverse cut lands less than a meter from 혜수 in a close-up (CU), eye-level, clean and frontal as an emotional punctuation. Her widened eyes and furrowed brow sit dead center while the dark rooftop behind her falls into shallow focus, leaving only the shock of 수리영's words in the frame.",
            "lighting_mood": "A cold blue base with intermittent crimson siren flicker sharpens the fear in her eyes and brow.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "L05",
              "L06"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_approach_night_siren_arrival",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "police_strobe_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The dark exterior environment is enveloped in cold night fog and continuously swept by pulsing red and blue police strobe lights. These harsh, alternating colored glares cut through the mist, illuminating the surroundings with a striking and urgent atmosphere.",
                "applies_to_shots": [
                  4,
                  5,
                  6
                ],
                "source_facts": [
                  "Scene text mentions sirens sounding and a police car arriving ('동시에 사이렌이 울리고~. 차에서 내린 혜수').",
                  "Shot 4 describes 'Blue-red police strobes rake across cold rooftop fog'.",
                  "Shot 5 describes 'pulsing red-blue siren light'.",
                  "Shot 6 mentions 'A cold blue base with intermittent crimson siren flicker'."
                ],
                "visual_inferences": [
                  "The physical police vehicle is off-screen or out of focus, but its strong flashing lights universally dictate the visual tone of the surrounding area."
                ],
                "creative_decisions": [
                  "Consistently applying the alternating blue and red strobe effects across all shots to visually anchor the urgency and shock of the moment."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 13,
                "shot_index": 5,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "86c25f1147aaed4f"
      },
      {
        "scene_index": 14,
        "heading": "S#14. 옥탑방 안 / N",
        "beat_title": "사라진 시신과 핏자국, 비정상적으로 깨끗한 방",
        "representative_moment": "혜수(C02)가 김형사(C04)의 어깨 너머로 기괴할 정도로 깨끗해진 옥탑방 거실을 마주하며 혼란에 빠져 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium shot, eye-level, over-the-shoulder composition, sickly fluorescent green-gray lighting mixed with cold blue TV flicker.",
            "t2i_prompt": "Photorealistic cinematic still. From an eye-level medium shot over the shoulder of C04O05 in a beige jacket, a middle-aged Asian man, whose soft shoulder occupies the left foreground, leaning into the doorway. In the middle ground, C02O03 in a gray leather jacket, a young Asian woman, stands facing the camera across the shared living room space. She pauses mid-search, her wide eyes looking directly past the camera toward the empty space. A casual backpack with a small plush doll rests motionless on the floor from the reference near the wall behind her. Sickly fluorescent green-gray interior light washes across her face, mixing with a dim glow from the TV from the reference in the background. The unnervingly spotless surface of the dining table from the reference emphasizes the impossible cleanliness of the shared room. Focus on her stunned expression and the eerie emptiness of the apartment interior.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "source_facts": [
              "지나칠 정도로 깨끗하게 정돈된 방안. 핏자국도 보이지 않고",
              "식탁 역시 깨끗한",
              "김형사의 어깨 너머로 텅 빈 거실을 바라보는 혜수의 정면",
              "혜수 faces the empty living room from the middle ground, centered against an unnervingly clean interior"
            ],
            "visual_inferences": [
              "fixed_element spotless_apartment_interior: eerily spotless under cold, sickly interior lighting",
              "fixed_element backpack_with_doll: rests quietly on the floor near the wall",
              "TV's cold blue flicker as a practical light source"
            ],
            "creative_decisions": [
              "Over-the-shoulder framing to anchor both characters in the same space while emphasizing the empty volume behind C02",
              "Sickly fluorescent green-gray lighting to heighten the unnatural cleanliness and eerie tension"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "3d0390eb4ce5fd01",
              "owned_hash": "cd9e08476100c331",
              "camera_direction_hash": "cc7a00f0b946560d",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "door",
                  "violating_phrase": "leaning into the doorway",
                  "reason": "The prompt uses the door as a frame element in the shot without explicit reference-only wording, which implies the existing door is being depicted anew.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "TV",
                  "violating_phrase": "the TV from the reference in the background",
                  "reason": "This is an explicit reference to an existing TV already in the scene, so it is not a redraw instruction.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "dining table",
                  "violating_phrase": "the dining table from the reference",
                  "reason": "This explicitly refers to the existing dining table from the reference, which is an anchor reference rather than a request to create it.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 5,
        "dependency_reason": "S5_Shot14의 옥탑방 구조, TV, 테이블 등 배경 요소를 그대로 유지하며 핏자국과 시신만 사라진 상태를 표현 (exact_background).",
        "_shot_index": 2,
        "visible_entities": [
          "C02",
          "C04",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 14,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From inside the rooftop room entry area, the camera holds a medium shot (MS), eye-level, over-the-shoulder behind 김형사 as his soft shoulder frames the left foreground. 혜수 faces the empty living room from the middle ground, centered against an unnervingly clean interior, while the negative space behind her makes the vanished evidence feel louder than any body.",
            "lighting_mood": "Sickly fluorescent green-gray interior light mixes with the TV's cold blue flicker, emphasizing the impossible cleanliness of the room.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "C04",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_living_kitchen_night_cleaned_no_cups",
            "reference_usage": "exact_background",
            "owned_objects": [
              "AC",
              "TV",
              "bathroom door",
              "bedroom door",
              "chair",
              "cooktop",
              "curtain",
              "dining table",
              "door",
              "floor cushion",
              "framed photo",
              "kitchen counter",
              "media console",
              "refrigerator",
              "shelf",
              "shoe cabinet",
              "shoe step",
              "sink",
              "sliding window",
              "sofa",
              "storage door"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "spotless_apartment_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the rooftop apartment, encompassing the living area and bedroom, is impossibly clean and meticulously organized. There are absolutely no traces of blood, no bodies, and no strange marks on any surfaces. The floors, walls, and furniture are eerily spotless under the cold, sickly interior lighting, presenting an unnerving contrast to the expected crime scene.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "지나칠 정도로 깨끗하게 정돈된 방안. 핏자국도 보이지 않고",
                  "식탁 역시 깨끗한",
                  "unnervingly clean interior",
                  "spotless room"
                ],
                "visual_inferences": [
                  "The cleanliness is uniformly maintained across all visible areas (living room, bedroom, dining area) to emphasize the sudden and impossible disappearance of the gruesome scene."
                ],
                "creative_decisions": [
                  "The cold, sickly lighting is used to enhance the eerie feeling of the completely sanitized and empty space."
                ],
                "confidence": "high"
              },
              {
                "element_id": "backpack_with_doll",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A casual backpack with a small plush doll dangling from it rests quietly on the floor near the wall in the apartment. It remains completely stationary throughout the search, serving as a silent, slightly displaced artifact of the room's normal state before the anomalous events.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "수리영 방안에 놓여진 백팩, 인형. 약간씩 위치가 달라진.",
                  "등장 요소: P09(인형 달린 백팩) in shots 2, 6, 8"
                ],
                "visual_inferences": [
                  "Placed on the floor near a wall so it can be visible in the background across different framing angles without obstructing the moving characters."
                ],
                "creative_decisions": [
                  "The backpack is used as an eerie anchor to mundane reality in the otherwise impossibly cleaned room."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 5,
                "shot_index": 14,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_living_kitchen_night_cleaned_no_cups",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "d342d8f5b2507454",
        "status": "contract_violation"
      },
      {
        "scene_index": 14,
        "heading": "S#14. 옥탑방 안 / N",
        "beat_title": "사라진 시신과 흔적, 수리영의 극심한 혼란",
        "representative_moment": "C01 stares in shock at the impossibly clean room, her face pale as she realizes the corpse and blood have vanished.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level head-and-shoulder composition with shallow depth of field, holding the subject in center-right, cold dawn-gray interior light.",
            "t2i_prompt": "Photorealistic cinematic still. Head-and-shoulder composition with shallow depth of field, face occupying the center-right. C01O02 in a navy windbreaker, a young East Asian woman, at three-quarter angle from the left, head jerked back, eyes wide open and fixed on the empty curtain corner out of frame. The camera focuses on her tense upper body and pale features, emphasizing her extreme shock. Cold dawn-gray interior light reflects on her cheek and jacket, faint sickly ambient spill washing the side of her neck with no warm relief. Behind her, the background dissolves into soft blur, revealing [L07: a neatly made bed edge and a clean curtain fabric edge facing the camera, eerily spotless]. In the deep out-of-focus background, a casual backpack with a small plush doll rests on the floor.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "핏기가 가신 창백한 얼굴로 두 눈을 크게 뜬 수리영의 클로즈업.",
              "지나칠 정도로 깨끗하게 정돈된 방안. 핏자국도 보이지 않고",
              "수리영 방안에 놓여진 백팩, 인형. 약간씩 위치가 달라진."
            ],
            "visual_inferences": [
              "fixed_element spotless_apartment_interior: soft blurred background evidence of the clean room",
              "fixed_element backpack_with_doll: blurred prop in the rear to anchor the unchanged reality against the anomalous disappearance"
            ],
            "creative_decisions": [
              "Head-and-shoulder composition used instead of a full face-filling close-up to prevent floating head artifact, while still capturing her extreme shock",
              "Cold dawn-gray light draining her skin tone to heighten the eerie, sickly atmosphere of the sanitized space"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "6efd89a35205a5eb",
              "owned_hash": "a7f71fcf41c4d0e3",
              "camera_direction_hash": "f35e94b6b36fe3e1",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 5,
        "dependency_reason": "S5_Shot9 established the room's layout before the anomaly; background layout carries through softly via fixed_elements, though heavily blurred in this close framing.",
        "_shot_index": 6,
        "visible_entities": [
          "C01",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 14,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Near the foot of the bed at eye level, the camera completes the stage dolly-in into a tight CU with shallow DOF, holding 수리영’s drained face in the center-right of frame while the spotless room dissolves into blur behind her. This is a direct observer view, not her hallucination: the empty curtain corner and clean bed remain only as soft background evidence around her widened eyes.",
            "lighting_mood": "Cold dawn-gray interior light drains her skin tone, with a faint sickly room spill and no warm relief.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_daughter_bedroom_night_cleaned_rearranged",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "spotless_apartment_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the rooftop apartment, encompassing the living area and bedroom, is impossibly clean and meticulously organized. There are absolutely no traces of blood, no bodies, and no strange marks on any surfaces. The floors, walls, and furniture are eerily spotless under the cold, sickly interior lighting, presenting an unnerving contrast to the expected crime scene.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "지나칠 정도로 깨끗하게 정돈된 방안. 핏자국도 보이지 않고",
                  "식탁 역시 깨끗한",
                  "unnervingly clean interior",
                  "spotless room"
                ],
                "visual_inferences": [
                  "The cleanliness is uniformly maintained across all visible areas (living room, bedroom, dining area) to emphasize the sudden and impossible disappearance of the gruesome scene."
                ],
                "creative_decisions": [
                  "The cold, sickly lighting is used to enhance the eerie feeling of the completely sanitized and empty space."
                ],
                "confidence": "high"
              },
              {
                "element_id": "backpack_with_doll",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A casual backpack with a small plush doll dangling from it rests quietly on the floor near the wall in the apartment. It remains completely stationary throughout the search, serving as a silent, slightly displaced artifact of the room's normal state before the anomalous events.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "수리영 방안에 놓여진 백팩, 인형. 약간씩 위치가 달라진.",
                  "등장 요소: P09(인형 달린 백팩) in shots 2, 6, 8"
                ],
                "visual_inferences": [
                  "Placed on the floor near a wall so it can be visible in the background across different framing angles without obstructing the moving characters."
                ],
                "creative_decisions": [
                  "The backpack is used as an eerie anchor to mundane reality in the otherwise impossibly cleaned room."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 5,
                "shot_index": 9,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "cafde308c8ccb61e"
      },
      {
        "scene_index": 14,
        "heading": "S#14. 옥탑방 안 / N",
        "beat_title": "사라진 시신과 깨끗해진 방, 그리고 짜증을 내는 김형사",
        "representative_moment": "C04 places his hands on his waist and looks down with annoyance at C01, who stands hunched in disbelief inside the eerily spotless apartment.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low-angle over-the-shoulder medium shot, harsh sickly fluorescent lighting",
            "t2i_prompt": "Photorealistic cinematic still. Low-angle over-the-shoulder composition from hip height, the two figures sharing the spotless living area. C01O02 in a navy windbreaker, a young East Asian woman, occupies the left foreground with her back to the camera, shoulders hunched low and head bowed, her upper body framing the lower-left edge. Across the space, C04O05 in a beige field jacket, a middle-aged East Asian man, stands in the center-right midground, facing the camera at a three-quarter angle from the right. His hands rest on his waist as he looms over her, his eyes fixed down on her. Focus on the tense spatial dynamic between the towering detective and the shrinking figure in the foreground. Harsh, sickly fluorescent ceiling light washes over his shoulders and upper chest, casting cold shadows across his annoyed face. In the dim background behind him, a casual backpack with a small plush doll rests quietly on the floor. The impeccably clean dining table and the closed entry door from the reference recede into the chillingly empty room, emphasizing the unnatural absence of the crime scene.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "source_facts": [
              "S#14 action: 김형사(짜증) 이봐요. 학생? 장난전화 하면 안 되는 거 몰라?",
              "Shot 8 description: 허리춤에 양손을 얹은 채 수리영을 내려다보는 김형사의 불만스러운 표정.",
              "DP instructions: over_shoulder, low angle frames 김형사 upper-center as he looms over her, hands-on-waist silhouette",
              "DP instructions: dining table clean, no teacups present, fluorescent ceiling light on"
            ],
            "visual_inferences": [
              "fixed_element spotless_apartment_interior: the room is unnervingly clean, creating a cold contrast",
              "fixed_element backpack_with_doll: remains stationary on the floor near the wall as a subtle anchor to reality",
              "low camera placement emphasizes Kim's accusatory dominance and Su-ri-young's helplessness"
            ],
            "creative_decisions": [
              "Sickly fluorescent lighting casts harsh, clinical shadows to enhance the uncomfortable, interrogative mood of the scene.",
              "Foreground/background separation anchored explicitly by 'sharing the spotless living area' to maintain coherent spatial relations."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "7a9dcf91b42ce2e4",
              "owned_hash": "cd9e08476100c331",
              "camera_direction_hash": "765934081edb6589",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "dining table",
                  "violating_phrase": "The impeccably clean dining table",
                  "reason": "The prompt names the dining table as a framed scene element without only using it as a reference anchor, which implies re-placing that owned object in the render.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "door",
                  "violating_phrase": "the closed entry door from the reference",
                  "reason": "This is an explicit reference to the existing door from the background reference, so it is being used as an anchor rather than newly created.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 14,
        "dependency_reason": "exact_background reference from S14_Shot6 to maintain the perfectly cleaned state of the apartment's interior and background objects.",
        "_shot_index": 8,
        "visible_entities": [
          "C01",
          "C04",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 14,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From low beside 수리영 in the living area, a static MWS low angle frames 김형사 upper-center as he looms over her, his hands-on-waist silhouette cutting into the fluorescent haze. 수리영’s shoulder and bowed head sit low in the left foreground as an OTS pressure point, while the clean dining area recedes behind them.",
            "lighting_mood": "Sickly police-procedural fluorescent light mixes with cold apartment shadows, making 김형사 feel accusatory and 수리영 smaller.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C04",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_living_kitchen_night_cleaned_no_cups",
            "reference_usage": "exact_background",
            "owned_objects": [
              "AC",
              "TV",
              "bathroom door",
              "bedroom door",
              "chair",
              "cooktop",
              "curtain",
              "dining table",
              "door",
              "floor cushion",
              "framed photo",
              "kitchen counter",
              "media console",
              "refrigerator",
              "shelf",
              "shoe cabinet",
              "shoe step",
              "sink",
              "sliding window",
              "sofa",
              "storage door"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "spotless_apartment_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the rooftop apartment, encompassing the living area and bedroom, is impossibly clean and meticulously organized. There are absolutely no traces of blood, no bodies, and no strange marks on any surfaces. The floors, walls, and furniture are eerily spotless under the cold, sickly interior lighting, presenting an unnerving contrast to the expected crime scene.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "지나칠 정도로 깨끗하게 정돈된 방안. 핏자국도 보이지 않고",
                  "식탁 역시 깨끗한",
                  "unnervingly clean interior",
                  "spotless room"
                ],
                "visual_inferences": [
                  "The cleanliness is uniformly maintained across all visible areas (living room, bedroom, dining area) to emphasize the sudden and impossible disappearance of the gruesome scene."
                ],
                "creative_decisions": [
                  "The cold, sickly lighting is used to enhance the eerie feeling of the completely sanitized and empty space."
                ],
                "confidence": "high"
              },
              {
                "element_id": "backpack_with_doll",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A casual backpack with a small plush doll dangling from it rests quietly on the floor near the wall in the apartment. It remains completely stationary throughout the search, serving as a silent, slightly displaced artifact of the room's normal state before the anomalous events.",
                "applies_to_shots": [
                  2,
                  6,
                  8
                ],
                "source_facts": [
                  "수리영 방안에 놓여진 백팩, 인형. 약간씩 위치가 달라진.",
                  "등장 요소: P09(인형 달린 백팩) in shots 2, 6, 8"
                ],
                "visual_inferences": [
                  "Placed on the floor near a wall so it can be visible in the background across different framing angles without obstructing the moving characters."
                ],
                "creative_decisions": [
                  "The backpack is used as an eerie anchor to mundane reality in the otherwise impossibly cleaned room."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 14,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_living_kitchen_night_cleaned_no_cups",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "45ff7d12b893bef9",
        "status": "contract_violation"
      },
      {
        "scene_index": 15,
        "heading": "S#15. 해안가. 버스정류장 부근 / N",
        "beat_title": "헛것을 봤다 자위하며 엄마를 확인하러 급히 일어나는 수리영",
        "representative_moment": "C01이 건네받지 않은 캔 음료를 무시한 채 벤치에서 다급히 몸을 일으켜 안개 낀 도로를 향한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "chest height observer POV, muted blue-gray coastal night haze",
            "t2i_prompt": "Photorealistic cinematic still. At chest height, looking across a shared damp bus stop bench, an unopened can is held out by the partial arm of a middle-aged East Asian woman at the left edge of the frame. On the right side of the same bench, C01O02 in a navy windbreaker, a young East Asian woman, is captured mid-rise from the seat, body leaning forward and legs braced to stand, at three-quarter angle from the right, eyes fixed on the foggy road ahead. Focus on C01O02's tense rising posture, leaving the unaccepted can hanging in the space between them. The surrounding environment is heavily blanketed in cold sea mist, establishing a muted blue-gray coastal night haze that flattens the scene. Weak roadside streetlight glints off the damp bench surface and the metallic can. A faded bus stop sign stands in the background, its face angled partly toward the camera against the empty, fog-softened road.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "혜수, 사온 음료수를 수리영에게 건네며",
              "수리영 (훅 일어나며) 집에 가봐야 겠어.",
              "바다를 바라보며 멍한 채로 앉아있는 수리영"
            ],
            "visual_inferences": [
              "fixed_element coastal_night_atmosphere: heavy sea mist, desaturated blue-gray night mood",
              "fixed_element damp_bus_stop_bench: standard roadside bench catching weak specular light",
              "Hyesoo is depicted only as a partial arm holding the can to keep focus on Sooyoung's movement"
            ],
            "creative_decisions": [
              "Chest-height composition anchors both the offered can and Sooyoung's rising action within the same frame",
              "The unopened can is left hanging in the foreground to visually represent the ignored gesture",
              "Motion direction preserved by leaning posture and braced legs to emphasize the sudden urge to leave"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "90938b9367734f19",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "a89375ffbf9ffefd",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "",
        "_shot_index": 3,
        "visible_entities": [
          "C01",
          "L14"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 15,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At chest height from the front-left corner of the bus-stop bench, a held MS eye-level composition lets 수리영’s sudden rise become the only violent motion in frame. The offered can and 혜수’s partial arm remain at the left edge, while 수리영 lifts from the bench on the right third and turns toward the foggy road.",
            "lighting_mood": "Muted blue-gray coastal night haze flattens the scene, with weak streetlight glinting off the damp bench and can.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L14"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "coastal_night_atmosphere",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A cold, blue-gray coastal night environment heavily blanketed in sea mist. The area is dimly lit by sparse, weak roadside streetlights, creating a desaturated, moody, and damp overall atmosphere.",
                "applies_to_shots": [
                  3,
                  6
                ],
                "source_facts": [
                  "Muted blue-gray coastal night haze flattens the scene",
                  "weak streetlight glinting",
                  "Cold sea mist and sparse roadside light create a predatory, desaturated image"
                ],
                "visual_inferences": [
                  "The heavy mist diffuses the artificial street lighting, significantly reducing background visibility and color saturation."
                ],
                "creative_decisions": [
                  "Maintain a consistent cool color palette (blue-gray) and foggy diffusion across both framings to anchor the spatial continuity of the coastal road."
                ],
                "confidence": "high"
              },
              {
                "element_id": "damp_bus_stop_bench",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A standard roadside bus stop bench situated near the misty road. Its damp surface faintly catches and reflects the weak specular light from the nearby streetlamp.",
                "applies_to_shots": [
                  3,
                  6
                ],
                "source_facts": [
                  "weak streetlight glinting off the damp bench",
                  "front-left corner of the bus-stop bench",
                  "stays near the bus stop in the midground"
                ],
                "visual_inferences": [
                  "The bench remains a stationary physical anchor point in the environment, marking the exact location where the interaction began."
                ],
                "creative_decisions": [
                  "Ensure the bench has a noticeable sheen from the coastal moisture to enhance the tactile, cold feeling of the night setting."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "665c40ed46b479e5"
      },
      {
        "scene_index": 15,
        "heading": "S#15. 해안가. 버스정류장 부근 / N",
        "beat_title": "수리영의 급작스런 이탈과 몰래 지켜보는 시선",
        "representative_moment": "정체불명의 시선이 수풀 뒤에 숨어, C02를 뒤로 한 채 해안도로를 달려가는 C01의 뒷모습을 지켜본다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low-angle voyeur POV from behind dark coastal bushes, through-object framing with leaves, cold blue-gray desaturated color palette",
            "t2i_prompt": "Photorealistic cinematic still. From a low hidden position at ground level, dark wet leaf silhouettes partially occlude the lower and side edges of the frame. Through this leafy opening, C02O03 in a gray leather jacket, a middle-aged Asian woman, stands in the midground with back to camera near a damp bus stop bench, one arm raised calling out, eyes fixed on the distant figure. Further down the shared misty coastal road, C01O02 in a navy windbreaker, a young Asian woman, is caught mid-stride running away, with back to camera, one leg lifted toward the road, her jacket flap streaming in the direction opposite to her motion, eyes on the distant fog. [L14: A cold, blue-gray coastal night blanketed in heavy sea mist, dimly lit by sparse, weak roadside streetlights, creating a desaturated, damp, and predatory atmosphere.] The low camera angle places the wet road surface in the lower frame, extending the figures' upper bodies toward the upper edge. Focus on the distant figure of C01O02 retreating into the thick mist.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "수리영, 응. 나 갈게 (달려간다)",
              "혜수 (등 뒤에 대고 소리친다)",
              "두 사람을 지켜보는 듯한 카메라 시선.",
              "shot description: From a low hidden position inside the coastal bushes, a handheld WS low angle uses through-object framing as leaves partially occlude the lower and side edges of the image."
            ],
            "visual_inferences": [
              "fixed_element coastal_night_atmosphere: Cold sea mist and sparse roadside light create a predatory, desaturated image",
              "fixed_element damp_bus_stop_bench: damp surface faintly catches and reflects the weak specular light",
              "Motion frozen mid-stride with one leg up and jacket trailing backward",
              "Low camera position anchors the wet ground in the lower frame, maintaining geometric consistency"
            ],
            "creative_decisions": [
              "Position the dark, wet leaf silhouettes tightly against the frame edges to emphasize the voyeuristic surveillance tension",
              "Anchor both characters explicitly on the 'shared misty coastal road' to maintain the fg/bg depth relationship without breaking spatial continuity"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "4abd5167ab870ae2",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "e5d19daff9af5dfb",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 15,
        "dependency_reason": "앞 샷(Shot 3)의 해안가 정류장 공간, 푸른빛의 짙은 해무와 젖은 벤치 배경을 exact_background로 유지하되, 이 샷만의 새로운 인물 동작과 앵글(POV)을 적용",
        "_shot_index": 6,
        "visible_entities": [
          "C01",
          "C02",
          "L14"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 15,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From a low hidden position inside the coastal bushes, a handheld WS low angle uses through-object framing as leaves partially occlude the lower and side edges of the image. This is an unidentified voyeur’s direct first-person surveillance view: 혜수 stays near the bus stop in the midground while 수리영 is caught farther away mid-stride, back to camera, one leg lifted toward the road.",
            "lighting_mood": "Cold sea mist and sparse roadside light create a predatory, desaturated image with dark leaf silhouettes in the foreground.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C02",
              "L14"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "coastal_night_atmosphere",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A cold, blue-gray coastal night environment heavily blanketed in sea mist. The area is dimly lit by sparse, weak roadside streetlights, creating a desaturated, moody, and damp overall atmosphere.",
                "applies_to_shots": [
                  3,
                  6
                ],
                "source_facts": [
                  "Muted blue-gray coastal night haze flattens the scene",
                  "weak streetlight glinting",
                  "Cold sea mist and sparse roadside light create a predatory, desaturated image"
                ],
                "visual_inferences": [
                  "The heavy mist diffuses the artificial street lighting, significantly reducing background visibility and color saturation."
                ],
                "creative_decisions": [
                  "Maintain a consistent cool color palette (blue-gray) and foggy diffusion across both framings to anchor the spatial continuity of the coastal road."
                ],
                "confidence": "high"
              },
              {
                "element_id": "damp_bus_stop_bench",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A standard roadside bus stop bench situated near the misty road. Its damp surface faintly catches and reflects the weak specular light from the nearby streetlamp.",
                "applies_to_shots": [
                  3,
                  6
                ],
                "source_facts": [
                  "weak streetlight glinting off the damp bench",
                  "front-left corner of the bus-stop bench",
                  "stays near the bus stop in the midground"
                ],
                "visual_inferences": [
                  "The bench remains a stationary physical anchor point in the environment, marking the exact location where the interaction began."
                ],
                "creative_decisions": [
                  "Ensure the bench has a noticeable sheen from the coastal moisture to enhance the tactile, cold feeling of the night setting."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 15,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "cdaa3cfd8efebe9a"
      },
      {
        "scene_index": 16,
        "heading": "S#16. 경찰서 사무실 / N",
        "beat_title": "불길한 예감과 위치 추적 요청",
        "representative_moment": "C02 thrusts her smartphone screen forward towards C04 to track a number, her tense fingers gripping the device prominently in the foreground.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "A tight CU slight Dutch angle focusing on the phone screen in the foreground, with sickly green-blue reflections and a cold monitor glow from the soft background",
            "t2i_prompt": "Photorealistic cinematic still. A tight Dutch angle framing on a glowing smartphone held by a young East Asian woman's hand in a gray leather sleeve entering from the left. Focus on the smartphone screen facing the camera, the device thrust forward and crossing the air between them above the shared desk. In the soft, out-of-focus background, a middle-aged East Asian man in a beige jacket sits hunched at three-quarter angle from the left, his blurry silhouette looking toward the phone. [L15: A blurred computer monitor and the cluttered desk edge form the immediate background]. Sickly green-blue fluorescent light reflects on the phone glass and the woman's gripping fingers, while the monitor casts a cold bureaucratic glow behind the phone.",
            "outfit_assignments": [],
            "source_facts": [
              "S#16 action: 혜수(Hye-su) asks 김형사(Kim) to track the saved number, showing him the phone screen.",
              "Shot description: A tight CU slight Dutch angle frames the phone screen. Hye-su's sleeve and gripping fingers enter from the left.",
              "Shot description: Kim is a soft, skeptical presence beyond the screen."
            ],
            "visual_inferences": [
              "body_part_focus_rule applied: The framing is strictly focused on the hand and phone, so common nouns and demographic descriptors are used to prevent unintended facial compositing artifacts.",
              "fg_bg_shared_anchor_rule applied: Added 'crossing the air between them above the shared desk' to logically ground the foreground and background interactions in the same space.",
              "face_identifiability_rule applied: Since Detective Kim is rendered as a soft, out-of-focus silhouette in the background, a common noun is used instead of his composite ID."
            ],
            "creative_decisions": [
              "Translated the 'sickly green-blue fluorescent light' and 'cold bureaucratic glow' into reflections on the phone's glass and the gripping fingers, grounding the lighting physically onto surfaces.",
              "Utilized L15 to describe only the immediate frame-edge surfaces (blurred monitor and desk edge) as mandated by the skipped_close_framing rule, completely omitting reference to the wider room geometry."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "2c4f63c9d5650a62",
              "owned_hash": "6aa2365bedec5d16",
              "camera_direction_hash": "e1ff54441110edbe",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "The shot primarily relies on its immediate foreground action and shared anchors rather than dependencies on a previous scene's specific layout, especially given the skipped_close_framing background mode.",
        "_shot_index": 4,
        "visible_entities": [
          "C02",
          "C04",
          "P05",
          "L15"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 16,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At desk height directly in front of 김형사’s monitor, a tight CU slight Dutch angle frames 혜수’s phone screen as a through-device insert, the display occupying just under two-fifths of the frame with the monitor plane blurred behind it. 혜수’s sleeve and gripping fingers enter from the left, while 김형사 is only a soft, skeptical presence beyond the screen.",
            "lighting_mood": "Sickly fluorescent office light reflects green-blue off the phone glass, with the monitor adding a cold bureaucratic glow.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "C04",
              "P05",
              "L15"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_office_night_duty_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "police_office_night_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of a police station office at night, heavily illuminated by harsh, sickly green-blue fluorescent lights. A standard office desk equipped with a softly glowing computer monitor serves as the central workspace, creating a cold, bureaucratic, and airless atmosphere.",
                "applies_to_shots": [
                  4,
                  6
                ],
                "source_facts": [
                  "Sickly fluorescent office light reflects green-blue",
                  "monitor adding a cold bureaucratic glow",
                  "Harsh fluorescent green-blue light makes the police office feel airless",
                  "desk line traps the space between them"
                ],
                "visual_inferences": [
                  "The desk is a typical police station night-duty setup with a monitor acting as a physical barrier between the detective and the civilian"
                ],
                "creative_decisions": [
                  "Consistent green-blue color grading across both shots to emphasize the tense and unhealthy night-shift environment"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "fbd21d09aa38eaf4"
      },
      {
        "scene_index": 16,
        "heading": "S#16. 경찰서 사무실 / N",
        "beat_title": "혜수의 불길한 직감과 위치 추적 지시",
        "representative_moment": "C02 leans heavily on the desk, staring intensely at C04, who sits across from her.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium wide low angle at low standing height, focusing on the tense interaction across the desk.",
            "t2i_prompt": "Photorealistic cinematic still. Medium wide low angle from low standing height. C04O05 in a beige jacket, a middle-aged East Asian man, occupies the right foreground in an over-the-shoulder view, his back to the camera, slumping slightly. Across the shared desk from the reference, C02O03 in a gray leather jacket, a young East Asian woman, leans heavily forward at a three-quarter left angle, both hands planted hard on the surface of the desk from the reference. Her eyes are fixed intensely on C04O05. The softly glowing monitor from the reference sits on the desk between them, acting as a partial barrier. The background features a file cabinet from the reference. Harsh green-blue illumination from the fluorescent light from the reference washes over the room, casting cold shadows that highlight the tension in C02O03's jaw.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "source_facts": [
              "S#16 action: 혜수 showing a phone number and asking 김형사 to track the location, expressing a bad premonition.",
              "S#16 setting: Police office at night, 김형사 is alone on night duty.",
              "shot description: Across the desk from 혜수 at low standing height, a static MWS low angle holds her leaning into the frame, both hands planted hard on the desk edge. 김형사 sits partly right of frame as an OTS counterweight."
            ],
            "visual_inferences": [
              "fixed_element police_office_night_environment: The interior of a police station office at night, heavily illuminated by harsh, sickly green-blue fluorescent lights.",
              "The desk from the reference acts as a shared anchor separating the two characters in the foreground and midground.",
              "C02's posture is tense and commanding, leaning aggressively over the desk.",
              "C04 slumps in his chair, indicating a reluctant attitude."
            ],
            "creative_decisions": [
              "Medium wide low angle to emphasize C02's imposing pressure over the seated C04 in the foreground.",
              "Cold green-blue color temperature to enhance the airless, bureaucratic tension of the night shift."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "b47a2b16b74da792",
              "owned_hash": "6aa2365bedec5d16",
              "camera_direction_hash": "c150bd7ec7c581df",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "desk",
                  "violating_phrase": "the desk from the reference",
                  "reason": "The prompt explicitly references the desk as already existing in the reference, which is an anchor reference rather than a request to create a new desk.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "monitor",
                  "violating_phrase": "The softly glowing monitor from the reference sits on the desk between them",
                  "reason": "The monitor is explicitly described as coming from the reference and placed using existing context, so it is treated as an anchor reference.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "file cabinet",
                  "violating_phrase": "The background features a file cabinet from the reference",
                  "reason": "The file cabinet is directly referenced as part of the existing background, not newly generated.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "from the fluorescent light from the reference",
                  "reason": "The fluorescent light is explicitly attributed to the reference background, so this is an anchor reference.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 16,
        "dependency_reason": "Same space and time, maintaining exact background consistency with S16_Shot4.",
        "_shot_index": 6,
        "visible_entities": [
          "C02",
          "C04",
          "P05",
          "L15"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 16,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Across the desk from 혜수 at low standing height, a static MWS low angle holds her leaning into the frame, both hands planted hard on the desk edge in the foreground. 김형사 sits partly right of frame as an OTS counterweight, while the desk line traps the space between them like an interrogation barrier.",
            "lighting_mood": "Harsh fluorescent green-blue light makes the police office feel airless, sharpening the tension in 혜수’s hands and jaw.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "C04",
              "P05",
              "L15"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_office_night_duty_normal",
            "reference_usage": "exact_background",
            "owned_objects": [
              "PC",
              "blind",
              "box",
              "chair",
              "coat rack",
              "copier",
              "corridor",
              "desk",
              "door",
              "evidence board",
              "file cabinet",
              "fluorescent light",
              "map board",
              "monitor",
              "partition",
              "phone",
              "printer",
              "table",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "police_office_night_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of a police station office at night, heavily illuminated by harsh, sickly green-blue fluorescent lights. A standard office desk equipped with a softly glowing computer monitor serves as the central workspace, creating a cold, bureaucratic, and airless atmosphere.",
                "applies_to_shots": [
                  4,
                  6
                ],
                "source_facts": [
                  "Sickly fluorescent office light reflects green-blue",
                  "monitor adding a cold bureaucratic glow",
                  "Harsh fluorescent green-blue light makes the police office feel airless",
                  "desk line traps the space between them"
                ],
                "visual_inferences": [
                  "The desk is a typical police station night-duty setup with a monitor acting as a physical barrier between the detective and the civilian"
                ],
                "creative_decisions": [
                  "Consistent green-blue color grading across both shots to emphasize the tense and unhealthy night-shift environment"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 16,
                "shot_index": 4,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_office_night_duty_normal",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "600beb02c175690c"
      },
      {
        "scene_index": 17,
        "heading": "S#17. 옥탑방 / 동틀무렵",
        "beat_title": "푸른 새벽 안개 속 옥탑방의 정적",
        "representative_moment": "어스름한 푸른 새벽 안개 속에서, 빈 골목 너머 멀리 홀로 불이 켜진 옥탑방 창문이 고요하게 빛나고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level static extreme wide shot from a neighboring rooftop, creating a sparse dawn-gray composition.",
            "t2i_prompt": "Photorealistic cinematic still. Eye-level wide composition from a neighboring rooftop. A dark, damp textured concrete parapet from the reference runs across the lower foreground. Beyond a shadowed, empty narrow alley, a distant small rooftop structure from the reference stands enveloped in a thick, cold blue-gray dawn haze. Focus on the faint, warm yellow glow emitting from the single rectangular window from the reference, sitting slightly above center. The glowing window contrasts sharply with the sparse, dim blue environment, creating a quiet occult unease in the implied stillness. No characters are present.",
            "outfit_assignments": [],
            "source_facts": [
              "Scene text: 새벽녘 (dawn)",
              "Shot description: From a neighboring rooftop at eye level, a static EWS establishes the rooftop room window as a small warm rectangle suspended in a sparse dawn-gray composition across the alley.",
              "Shot description: Dim pre-sunrise blue haze surrounds the faint yellow window glow, creating a quiet occult unease."
            ],
            "visual_inferences": [
              "fixed_element dawn_rooftop_atmosphere: cold, dim blue fog, textured concrete parapet wall, single rectangular window with warm yellow glow",
              "The scene description focuses on the empty parapet and the distant window; no human characters are rendered in this specific establishing frame."
            ],
            "creative_decisions": [
              "Used 'from the reference' anchoring for the parapet, rooftop structure, and window to strictly bind to the exact background image and avoid generating new background entities.",
              "Emphasized the strong color contrast between the cold blue-gray haze and the warm yellow light to heighten the eerie, occult mood."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "68e1c8dbcd4ff274",
              "owned_hash": "c2336a1fc231169c",
              "camera_direction_hash": "ec4197214fc553fa",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "parapet",
                  "violating_phrase": "A dark, damp textured concrete parapet from the reference runs across the lower foreground.",
                  "reason": "The parapet is explicitly referenced as an existing element from the reference/background, so it is being used as an anchor rather than newly created.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "window",
                  "violating_phrase": "the single rectangular window from the reference, sitting slightly above center",
                  "reason": "The window is explicitly described as coming from the reference, which indicates anchor usage instead of redraw.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 4,
        "dependency_reason": "동일한 옥탑방 배경(S4_Shot1)을 기반으로 하되, 인물이 보이지 않는 푸른 새벽 시간대의 정적과 대비되는 창문 불빛을 강조",
        "_shot_index": 1,
        "visible_entities": [
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 17,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From a neighboring rooftop at eye level, a static EWS establishes the rooftop room window as a small warm rectangle suspended in a sparse dawn-gray composition across the alley. The lit window sits slightly above center, with empty parapet lines and haze taking most of the frame in a long take implied stillness.",
            "lighting_mood": "Dim pre-sunrise blue haze surrounds the faint yellow window glow, creating a quiet occult unease.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "L04"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C12",
                "outlook_id": "O00"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_rooftop_dawn_window_lit_cat",
            "reference_usage": "exact_background",
            "owned_objects": [
              "cat",
              "door",
              "laundry line",
              "parapet",
              "post",
              "roof drain",
              "roof terrace",
              "stairwell headhouse",
              "wall light",
              "water tank",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dawn_rooftop_atmosphere",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A pre-sunrise dawn setting enveloped in a cold, dim blue fog. A textured concrete parapet wall runs across the space. In the distance, a small rooftop structure features a single rectangular window that emits a faint, warm yellow glow, contrasting sharply with the cold surrounding haze.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "source_facts": [
                  "Scene text: 새벽녘 (dawn)",
                  "Shot 1: Dim pre-sunrise blue haze surrounds the faint yellow window glow, empty parapet lines",
                  "Shot 3: cold dawn rim light, dawn fog as soft peripheral detail, wall texture, window reflection burns as a tiny sick yellow point"
                ],
                "visual_inferences": [
                  "The parapet wall is made of rough, aged concrete typical for older urban villa rooftops in Korea",
                  "The yellow light from the window is the only warm light source in the predominantly cold blue environment"
                ],
                "creative_decisions": [
                  "Maintain the stark color contrast between the ambient cold blue dawn fog and the warm yellow window light as the primary visual anchor across different framing scales"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 4,
                "shot_index": 1,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C12O00",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_rooftop_dawn_window_lit_cat",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "bfa46be608101e05"
      },
      {
        "scene_index": 17,
        "heading": "S#17. 옥탑방 / 동틀무렵",
        "beat_title": "불 켜진 옥탑방과 검은 고양이",
        "representative_moment": "검은 고양이의 눈동자에 옥탑방의 불빛이 반사되는 극단적 클로즈업 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up worm's eye reflection shot, focusing on the cat's eye, cold blue dawn vs warm yellow catchlight",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up worm's eye framing on the glossy eye of a black cat in right profile, crouched low. Focus on the dark eye where a tiny, sick warm yellow catchlight from a distant lit window reflects sharply. A cold dawn rim light catches the wet-looking black fur along the frame edges. [L04: rough, damp concrete parapet edge occupying the lower frame just below the cat's face, backed by soft out-of-focus dim blue-gray dawn fog].",
            "outfit_assignments": [],
            "source_facts": [
              "Scene text: 새벽녘 (dawn), 검은 고양이가 불이 켜져 있는 옥탑 방을 슬쩍 보더니 담을 넘는다",
              "Shot 3 description: Very low on the wall, dolly-in resolves into an ECU worm's eye reflection shot aligned with one eye of the black cat. A tiny catchlight of the lit rooftop window trembles inside it."
            ],
            "visual_inferences": [
              "fixed_element dawn_rooftop_atmosphere: cold dim blue fog and warm yellow window glow are maintained through the reflection and rim lighting",
              "The cat's head is oriented in right profile to capture the reflection of the window",
              "Rough concrete texture under the face aligns correctly with the low worm's eye angle"
            ],
            "creative_decisions": [
              "Applied body_part_focus_rule by replacing the cat entity ID (C12) with the common noun 'a black cat' to ensure proper eye and fur generation without risking anomalous full-body composites",
              "Used a tight frame that pushes the background fog into soft focus, leaving the concrete edge and the eye's reflection as the sharp focal points",
              "Emphasized the sick warm yellow catchlight contrasting with the cold dawn rim light for a mysterious, eerie horror tone"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "e5ad3adaec728daa",
              "owned_hash": "c2336a1fc231169c",
              "camera_direction_hash": "be5ea07316c2ea43",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 17,
        "dependency_reason": "같은 옥상 공간과 새벽녘 안개, 옥탑방 불빛(dawn_rooftop_atmosphere)의 시각적 연속성 유지",
        "_shot_index": 3,
        "visible_entities": [
          "C12",
          "L04"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 17,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Very low on the wall, the dolly-in resolves into an ECU worm's eye reflection shot aligned with one eye of 검은 고양이. The glossy eye occupies most of the human-scale close-up allowance while a tiny catchlight of the lit rooftop window trembles inside it, leaving fur, wall texture, and dawn fog as soft peripheral detail.",
            "lighting_mood": "A cold dawn rim light outlines the cat’s black fur while the window reflection burns as a tiny sick yellow point in the eye.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C12",
              "L04"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C12",
                "outlook_id": "O00"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_rooftop_dawn_window_lit_cat",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dawn_rooftop_atmosphere",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A pre-sunrise dawn setting enveloped in a cold, dim blue fog. A textured concrete parapet wall runs across the space. In the distance, a small rooftop structure features a single rectangular window that emits a faint, warm yellow glow, contrasting sharply with the cold surrounding haze.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "source_facts": [
                  "Scene text: 새벽녘 (dawn)",
                  "Shot 1: Dim pre-sunrise blue haze surrounds the faint yellow window glow, empty parapet lines",
                  "Shot 3: cold dawn rim light, dawn fog as soft peripheral detail, wall texture, window reflection burns as a tiny sick yellow point"
                ],
                "visual_inferences": [
                  "The parapet wall is made of rough, aged concrete typical for older urban villa rooftops in Korea",
                  "The yellow light from the window is the only warm light source in the predominantly cold blue environment"
                ],
                "creative_decisions": [
                  "Maintain the stark color contrast between the ambient cold blue dawn fog and the warm yellow window light as the primary visual anchor across different framing scales"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 17,
                "shot_index": 1,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C12O00",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "afd71c934e4b8288"
      },
      {
        "scene_index": 18,
        "heading": "S#18. 안방 안 / D",
        "beat_title": "고양이 울음소리에 번쩍 깨어난 수리영",
        "representative_moment": "침대에서 깜빡 졸다 고양이 소리에 두 눈을 번쩍 뜨며 고개를 치켜든 수리영(C01)의 놀란 얼굴.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Close-up low angle, tight framing with shallow depth of field, pale sickly green-gray tint",
            "t2i_prompt": "Photorealistic cinematic still. Low angle looking up at the figure, tight framing on her expression, her shoulders visible at the lower edge. C01O02 in a dark navy windbreaker, a young Asian woman, positioned at three-quarter angle from the right, head raised abruptly from the bed, neck tense. Focus on her wide, shocked eyes fixed on the unseen doorway beyond the frame. Thin cold gray daylight reflects on the side of her pale face, while a pervasive sickly green-gray ambient tone washes over the shadows. [L07: an out-of-focus dark headboard and heavily rumpled bedding occupying the lower and rear frame edges behind her].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "Shot 2: 두 눈을 번쩍 뜬 채 고개를 치켜든 수리영의 놀란 얼굴 클로즈업.",
              "DP direction: Low at the bedside from the foot side of the bed, CU low angle on 수리영 snapping awake and lifting her head.",
              "Lighting mood: Thin daylight seeps in cold and gray, leaving her face pallid with a faint undercurrent of sleepless exhaustion."
            ],
            "visual_inferences": [
              "fixed_element environment_state: cold_gray_interior_lighting (sickly green-gray tint)",
              "Applying close framing composition by omitting the background room and only describing the frame-edge headboard and bedding.",
              "Mid-action tension is shown through her raised head and tense neck, freezing the jolting motion."
            ],
            "creative_decisions": [
              "Shallow depth of field blurring the headboard and bedding to strictly isolate her startled expression and prevent distraction.",
              "Low angle placement to emphasize her sudden vulnerability and the abruptness of the awakening."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "8bd820c735c50345",
              "owned_hash": "eb0ef19840d12bce",
              "camera_direction_hash": "f0799f30d183ac45",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 14,
        "dependency_reason": "동일한 옥탑방 배경 및 시간대 변화(새벽->아침)에 따른 조명 연속성 (단, 본 샷은 클로즈업이므로 뒷배경은 생략됨)",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "P05",
          "P09",
          "P10",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 18,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Low at the bedside from the foot side of the bed, the camera finishes an abrupt dolly-in into a CU low angle on 수리영 snapping awake and lifting her head. Her face lands center frame with the headboard and bedding falling out of focus behind her, turning the cat’s cry into a physical jolt rather than a visible source.",
            "lighting_mood": "Thin daylight seeps in cold and gray, leaving her face pallid with a faint undercurrent of sleepless exhaustion.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "P09",
              "P10",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_master_bedroom_dawn_waiting_empty_home",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_gray_interior_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A pervasive cold and gray lighting condition that fills the interior spaces. The light casts a pale, sickly, and slightly green-gray tone over the surroundings, creating an eerie, unnatural, and chilling atmosphere across the different rooms.",
                "applies_to_shots": [
                  2,
                  12,
                  15
                ],
                "source_facts": [
                  "Shot 2: 'Thin daylight seeps in cold and gray'",
                  "Shot 12: 'Cold fluorescent bathroom light turns the glass green-gray'",
                  "Shot 15: 'Cold gray daylight mixes with a sickly interior cast'"
                ],
                "visual_inferences": [
                  "A unified desaturated color palette with cold tones to visually connect the different rooms (bedroom, bathroom, dining area) throughout the sequence."
                ],
                "creative_decisions": [
                  "Applying a sickly green-gray tint to the overall ambient light to foreshadow and emphasize the character's psychological instability and the supernatural hallucinations."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 14,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "2792d0d7842d41bd"
      },
      {
        "scene_index": 18,
        "heading": "S#18. 안방 안 / D",
        "beat_title": "거울에 떠오른 붉은 원 환영",
        "representative_moment": "욕실 거울 표면에 선명하게 떠오른 붉은 원형 표식의 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up Dutch angle locking onto the mirror surface, sickly green-gray fluorescent lighting with a striking crimson accent.",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up Dutch angle on a slightly wet, streaked mirror surface at face height. Focus on a bright, sharp-edged crimson circular mark appearing directly on the glass in the central third of the frame. [L07: close framing of a bathroom mirror reflecting pale, damp tiles ghosted behind the glass, with a slice of a wet white ceramic sink edge visible at the lower boundary]. Cold fluorescent lighting casts a pervasive sickly green-gray tone across the reflected background, while the unreal red sign provides a sharp, chilling contrast against the desaturated ambient light.",
            "outfit_assignments": [],
            "source_facts": [
              "S18 action: '거울에 비친 욕실 벽에 갑자기 또 발생하는 붉은 원'",
              "shot description: crimson circular mark appears in the central third of frame, character reflection reduced out of frame"
            ],
            "visual_inferences": [
              "fixed_element cold_gray_interior_lighting: pervasive cold and gray lighting condition, sickly green-gray tone",
              "Dutch angle emphasizes the sudden, unnatural psychological hallucination",
              "Character is fully out of frame to isolate the supernatural mark and sink edge"
            ],
            "creative_decisions": [
              "Used [L07] block to build the immediate frame-edge surfaces (sink edge and tile reflection) per the skipped_close_framing rule",
              "Contrasted the bright crimson red against the muted green-gray tile reflection to highlight the supernatural accent"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "7f037f28941eda45",
              "owned_hash": "a65185601a83e11d",
              "camera_direction_hash": "a6c42418a86b5ee0",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 18,
        "dependency_reason": "같은 씬 S18_Shot2의 조명 상태(cold_gray_interior_lighting)를 공유하되, 클로즈업 프레이밍 규칙에 따라 즉각적인 거울/타일 표면 묘사로 대체",
        "_shot_index": 12,
        "visible_entities": [
          "P05",
          "P09",
          "P10",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 18,
            "shot_index": 12
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At face height, nearly perpendicular to the bathroom mirror, a static CU Dutch angle locks onto the glass surface as a crimson circular mark appears in the central third of frame. This is a hallucination seen via reflection: 수리영’s reflection is reduced out of frame, leaving the sink edge below and tiled wall ghosted behind the impossible red sign.",
            "lighting_mood": "Cold fluorescent bathroom light turns the glass green-gray while the red circle cuts through as a sick, supernatural accent.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "P09",
              "P10",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_bathroom_dawn_mirror_red_circle_hallucination",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_gray_interior_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A pervasive cold and gray lighting condition that fills the interior spaces. The light casts a pale, sickly, and slightly green-gray tone over the surroundings, creating an eerie, unnatural, and chilling atmosphere across the different rooms.",
                "applies_to_shots": [
                  2,
                  12,
                  15
                ],
                "source_facts": [
                  "Shot 2: 'Thin daylight seeps in cold and gray'",
                  "Shot 12: 'Cold fluorescent bathroom light turns the glass green-gray'",
                  "Shot 15: 'Cold gray daylight mixes with a sickly interior cast'"
                ],
                "visual_inferences": [
                  "A unified desaturated color palette with cold tones to visually connect the different rooms (bedroom, bathroom, dining area) throughout the sequence."
                ],
                "creative_decisions": [
                  "Applying a sickly green-gray tint to the overall ambient light to foreshadow and emphasize the character's psychological instability and the supernatural hallucinations."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 18,
                "shot_index": 2,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "a72aaf112faad1bd"
      },
      {
        "scene_index": 18,
        "heading": "S#18. 거실 / D",
        "beat_title": "기괴하게 녹아내리는 액자 속 엄마의 얼굴",
        "representative_moment": "거실 식탁 위 액자 속 40대 여성의 얼굴이 붉고 기괴하게 뭉개지며 녹아내리는 환영을 보는 수리영의 시점 정지 컷.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Subjective POV high-angle close-up, sickly green-gray ambient daylight with sharp crimson-brown accents",
            "t2i_prompt": "Photorealistic cinematic still. High angle close-up, subjective POV looking down at a dining table. Focus on an upright framed photograph near the right-center of the frame. Inside the photo, a portrait of a middle-aged East Asian woman facing the camera is distorted by a hallucinated surface event: her face is grotesquely liquefied, melting into thick, unnatural crimson-brown streaks running down the glossy paper. In the left foreground, a half-full drinking glass with faint condensation is heavily blurred out of focus. The composition is anchored strictly by the immediate [L07: bare wooden table surface bathed in pale, sickly green-gray light] at the lower frame edge, avoiding any wider room context. A chilling, cold gray daylight mixes with the sickly interior cast, isolating the sharp, disturbing red distortion.",
            "outfit_assignments": [],
            "source_facts": [
              "S#18 action: '식탁에 놓인 엄마와 수리영의 사진을 보는데... 환하게 웃는 엄마 얼굴이 뭉개져 흘러내린다'",
              "shot description: Subjective POV from Suyeong at dining-table height, frozen insert holding on the upright framed photograph",
              "shot description: drinking glass blurred at the left foreground, mother's portrait liquefying"
            ],
            "visual_inferences": [
              "fixed_element cold_gray_interior_lighting: pervasive cold, sickly green-gray tone applied to the ambient light",
              "POV constraint: Suyeong is the observer, so she is entirely excluded from the physical frame",
              "reproduction surface rule applied: the face inside the photograph is described as 'a middle-aged East Asian woman' without using C## ID",
              "skipped_close_framing applied: background elements are omitted, framing is anchored solely by the table surface [L07]"
            ],
            "creative_decisions": [
              "Heavy shallow depth of field to blur the foreground drinking glass, forcing extreme focus on the melting photograph surface",
              "Using thick crimson-brown streaks for the hallucination effect to visually pop against the desaturated, sickly green-gray environment"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "9105e595ec79a186",
              "owned_hash": "f46489d405a4bd51",
              "camera_direction_hash": "1bf4c911c03fd123",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 18,
        "dependency_reason": "동일 씬 내 이전 샷(Shot 12)의 sickly green-gray lighting 분위기(fixed_element)를 그대로 유지",
        "_shot_index": 15,
        "visible_entities": [
          "P05",
          "P09",
          "P10",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 18,
            "shot_index": 15
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Subjective POV from 수리영 at dining-table height: a CU, high angle, frozen insert holds on the upright framed photograph near the right-center of the table, with the drinking glass blurred at the left foreground and the frame kept to roughly the central third. The camera inherits the lateral table move but stops dead as the mother's portrait appears to liquefy behind the glass, turning a family snapshot into a hallucinated surface event.",
            "lighting_mood": "Cold gray daylight mixes with a sickly interior cast, while the melted facial streaks carry a sharp, unnatural crimson-brown accent.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "P09",
              "P10",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_dawn_photo_hallucination",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_gray_interior_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A pervasive cold and gray lighting condition that fills the interior spaces. The light casts a pale, sickly, and slightly green-gray tone over the surroundings, creating an eerie, unnatural, and chilling atmosphere across the different rooms.",
                "applies_to_shots": [
                  2,
                  12,
                  15
                ],
                "source_facts": [
                  "Shot 2: 'Thin daylight seeps in cold and gray'",
                  "Shot 12: 'Cold fluorescent bathroom light turns the glass green-gray'",
                  "Shot 15: 'Cold gray daylight mixes with a sickly interior cast'"
                ],
                "visual_inferences": [
                  "A unified desaturated color palette with cold tones to visually connect the different rooms (bedroom, bathroom, dining area) throughout the sequence."
                ],
                "creative_decisions": [
                  "Applying a sickly green-gray tint to the overall ambient light to foreshadow and emphasize the character's psychological instability and the supernatural hallucinations."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 18,
                "shot_index": 12,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "5fd3aef3cab4cd2f"
      },
      {
        "scene_index": 19,
        "heading": "S#19. 마트 / D",
        "beat_title": "사라진 엄마의 마지막 단서 확인",
        "representative_moment": "수리영(C01)이 마트 통로를 막아선 채, 종이 박스를 든 남자 직원(C06)을 응시한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level medium wide two-shot, flat pale blue-gray fluorescent lighting, deep background emptiness",
            "t2i_prompt": "Photorealistic cinematic still. A medium wide two-shot from chest height. C01O02 in a navy windbreaker, a young East Asian woman, stands at three-quarter angle from the right, blocking the aisle path, eyes fixed on the man. Across from her in the same shared aisle space, C06O08 in a red supermarket uniform, a middle-aged East Asian man, stands at three-quarter angle from the left, paper boxes clutched high against his chest, eyes fixed on the woman. They are framed together between the tall shelves from the reference. Focus on the rigid paper boxes wedged between them, acting as a physical barrier in the tension. Flat early-morning fluorescent light from the reference washes their faces and the clean aisle floor in pale blue-gray, draining warmth from the setting. Both figures are visible from the waist up, their heads positioned in the upper frame.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "source_facts": [
              "S#19 action: 수리영이 마트 여기저기를 돌아다니며 어제 만났던 남자 직원을 찾는다 / 남자직원과 대화",
              "shot description: 종이 박스를 든 남자 직원 앞을 막아선 채 눈을 맞춘 수리영의 정지 상태"
            ],
            "visual_inferences": [
              "medium wide two-shot from chest height to capture the physical blockage in the aisle",
              "C06 holding boxes creates a natural barrier between the two figures",
              "early morning setting implies cold, quiet, and sparse atmosphere"
            ],
            "creative_decisions": [
              "squared two-shot framing with figures in opposite three-quarter profiles to emphasize confrontation without overt aggression",
              "pale blue-gray color grading to align with the overarching eerie, tense tone of the thriller genre"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "d3b1fca888bece7c",
              "owned_hash": "b0062c44273bd902",
              "camera_direction_hash": "9198f41bcf8f4be0",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "shelf",
                  "violating_phrase": "framed together between the tall shelves",
                  "reason": "The shelves are referenced as framing elements without explicit reference to the existing background, which risks reintroducing them as scene objects.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "Flat early-morning fluorescent light from the reference",
                  "reason": "This explicitly refers to the existing light source from the reference background rather than adding a new one.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 8,
        "dependency_reason": "마트 내부(S8_Shot5)와 동일한 공간, 통로 앵글 및 배경(exact_background) 일관성 유지",
        "_shot_index": 3,
        "visible_entities": [
          "C01",
          "C06",
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 19,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At chest height inside the quiet supermarket aisle, the camera ends its parallel track in a MWS, eye-level, squared two-shot framed between tall shelves, holding 수리영 left-middle and 남자 직원 right-middle with the paper boxes wedged between them. The confrontation reads as a still blockage in the aisle: boxed goods form rigid vertical lines behind him while 수리영 cuts across his path without changing the established approach axis.",
            "lighting_mood": "Flat early-morning supermarket fluorescents wash the aisle in pale blue-gray, draining warmth from the everyday setting.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C06",
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "cb_sales_floor_day_quiet",
            "reference_usage": "exact_background",
            "owned_objects": [
              "CCTV camera",
              "cash register",
              "checkout counter",
              "display island",
              "drink case",
              "emergency exit door",
              "endcap display",
              "fluorescent light",
              "notice board",
              "refrigerated case",
              "service shelf",
              "shelf",
              "shopping basket",
              "sliding door",
              "staff door",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 8,
                "shot_index": 5,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "cb_sales_floor_day_quiet",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "0ce6ec40bc35d8d5",
        "status": "contract_violation"
      },
      {
        "scene_index": 19,
        "heading": "마트 / D",
        "beat_title": "CCTV 단서 발견",
        "representative_moment": "마트 외벽 처마 아래 장착된 둥근 CCTV 카메라의 렌즈.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Close-up, low angle looking up, cold overcast daylight with muted blue-gray tones",
            "t2i_prompt": "Photorealistic cinematic still. Close-up, low angle looking up. Focus on a round CCTV dome camera mounted under an eave, occupying the upper-right of the frame. The lens housing is slightly dirty, angled downward, and catches a small cold highlight. [L12: A weather-stained concrete exterior wall cuts diagonally behind the camera, showing subtle vertical water streaks and a coarse finish. The dull metal underside of the eave presses down from the top frame edge.] Illuminated by cold overcast coastal daylight casting a muted blue-gray tone over the concrete. No people are visible.",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 7: 'weather-stained concrete', 'supermarket corner', 'Overcast coastal daylight keeps the wall muted blue-gray'",
              "Shot description: CU, low angle, isolating the round CCTV under the eave near the upper-right of frame.",
              "DP instruction: No people are visible; the lens housing sits like a mute eye."
            ],
            "visual_inferences": [
              "fixed_element environment_state: The concrete has a slightly coarse finish with subtle vertical water stains indicating long-term exposure to coastal weather.",
              "The low angle places the eave at the very top of the frame, acting as a visual ceiling."
            ],
            "creative_decisions": [
              "Tight low-angle composition isolating the CCTV in the upper-right to make it look like an observing, ominous eye.",
              "Muted blue-gray palette to match the bleak coastal overcast mood and maintain continuity."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "2514487b3b7e0a8c",
              "owned_hash": "59d4c51343060376",
              "camera_direction_hash": "10e0e3d0b31ad8b6",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 8,
        "dependency_reason": "앞선 씬 8에서 설정된 마트 외벽(weather-stained concrete, blue-gray tone)의 환경 상태를 연속성 있게 유지",
        "_shot_index": 7,
        "visible_entities": [
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 19,
            "shot_index": 7
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Outside at the supermarket corner, the tilt reaches its highest point and tightens into a CU, low angle, isolating the round CCTV under the eave near the upper-right of frame while the corner wall cuts diagonally behind it. No people are visible; the lens housing sits like a mute eye against weather-stained concrete, held as the decisive clue before the camera can drop back toward 수리영.",
            "lighting_mood": "Overcast coastal daylight keeps the wall muted blue-gray, with the CCTV dome catching a small cold highlight like an accusing eye.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_exterior_entrance_day_cctv_wall",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "supermarket_exterior_wall",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A weather-stained concrete exterior wall of a commercial building. The surface is textured with age, showing subtle streaks and wear typical of an older structure. It is illuminated by cold, overcast daylight, casting a muted blue-gray tone over the concrete.",
                "applies_to_shots": [
                  7,
                  8
                ],
                "source_facts": [
                  "Shot 7: 'weather-stained concrete', 'supermarket corner', 'Overcast coastal daylight keeps the wall muted blue-gray'",
                  "Shot 8: 'Beside the supermarket wall', 'The wall line slides shallowly behind her', 'wall-reflected gray light'"
                ],
                "visual_inferences": [
                  "The concrete has a slightly coarse finish with subtle vertical water stains indicating long-term exposure to coastal weather."
                ],
                "creative_decisions": [
                  "Maintaining a consistent bleak blue-gray color palette on the wall to anchor the spatial continuity between the CCTV reveal and the character's reaction shot."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 8,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "8324985efe2528ec"
      },
      {
        "scene_index": 19,
        "heading": "마트 / D",
        "beat_title": "CCTV 위치 확인 후 혜수에게 연락하여 조사 준비",
        "representative_moment": "휴대폰을 귀에 바짝 댄 채 입을 벌린 수리영의 긴장된 옆얼굴.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "tight CU, Dutch angle, head-and-shoulder composition",
            "t2i_prompt": "Photorealistic cinematic still. A tight CU, Dutch angle, head-and-shoulder composition. C01O02 in a navy windbreaker, a young East Asian woman, in right profile, occupying the right half of the frame. The P05 phone is pressed close against her ear in the lower-right quadrant, its screen turned inward against her face. Her mouth is slightly open, catching a strained breath, eyes looking distant. Focus on the P05 phone and her tense expression, neck and shoulder edge visible below. [L12: A weather-stained concrete exterior wall of a commercial building with subtle vertical water stains, casting a muted blue-gray tone] serves as a shallow background plane behind her. Cold overcast daylight and wall-reflected gray light wash her profile sharply, with a faint sickly green cast from storefront fluorescents reflecting on her cheek and the navy windbreaker.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "Shot 8: 휴대폰을 귀에 바짝 댄 채 입을 벌린 수리영의 긴장된 옆얼굴.",
              "camera_direction: tight CU, Dutch angle, profile shot of her tense side face occupying the right half while the phone presses against her ear in the lower-right quadrant.",
              "lighting_mood: Cold daylight and wall-reflected gray light carve her profile sharply, with a faint sickly green cast from the storefront fluorescents leaking outside."
            ],
            "visual_inferences": [
              "fixed_element supermarket_exterior_wall: A weather-stained concrete exterior wall showing subtle streaks and wear, illuminated by cold overcast daylight.",
              "The green fluorescent light reflects on her skin and clothing instead of 'cutting' across her face, adhering to the surface illumination rule."
            ],
            "creative_decisions": [
              "Using a head-and-shoulder composition to fulfill the 'close framing' without triggering face-only detachment.",
              "Explicitly defining the prop orientation of the phone (screen turned inward) to prevent conflicting dual-facing geometry.",
              "Describing the background strictly through the [L12] frame-edge surface block as required by 'skipped_close_framing'."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "30d34456a3b44d3f",
              "owned_hash": "59d4c51343060376",
              "camera_direction_hash": "63c9f90195e4f103",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 8,
        "dependency_reason": "S19의 이전 샷들 및 S8 마트 외부 씬과 외벽의 질감, 조명 톤 등 공간적 연속성 유지.",
        "_shot_index": 8,
        "visible_entities": [
          "C01",
          "P05",
          "L11",
          "L12"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 19,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Beside the supermarket wall at 수리영's shoulder height, the lateral track resolves into a tight CU, Dutch angle, profile shot of her tense side face occupying the right half while the phone presses against her ear in the lower-right quadrant. The wall line slides shallowly behind her, but the only emphasized change from the CCTV reveal is camera distance, pulled close enough to hold her open mouth and strained breath.",
            "lighting_mood": "Cold daylight and wall-reflected gray light carve her profile sharply, with a faint sickly green cast from the storefront fluorescents leaking outside.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "L11",
              "L12"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C06",
                "outlook_id": "O08"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_exterior_entrance_day_cctv_wall",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "supermarket_exterior_wall",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A weather-stained concrete exterior wall of a commercial building. The surface is textured with age, showing subtle streaks and wear typical of an older structure. It is illuminated by cold, overcast daylight, casting a muted blue-gray tone over the concrete.",
                "applies_to_shots": [
                  7,
                  8
                ],
                "source_facts": [
                  "Shot 7: 'weather-stained concrete', 'supermarket corner', 'Overcast coastal daylight keeps the wall muted blue-gray'",
                  "Shot 8: 'Beside the supermarket wall', 'The wall line slides shallowly behind her', 'wall-reflected gray light'"
                ],
                "visual_inferences": [
                  "The concrete has a slightly coarse finish with subtle vertical water stains indicating long-term exposure to coastal weather."
                ],
                "creative_decisions": [
                  "Maintaining a consistent bleak blue-gray color palette on the wall to anchor the spatial continuity between the CCTV reveal and the character's reaction shot."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 8,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C06O08",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "dab9f21ef60c031b"
      },
      {
        "scene_index": 20,
        "heading": "S#20. 마트 총무과 / 실내",
        "beat_title": "모니터 앞의 초조함",
        "representative_moment": "어두운 CCTV 화면을 돌려보며 C01의 불안감이 깊어지는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "MCU, eye-level, over-the-shoulder composition from the desk corner, sickly fluorescent and cold monitor glow",
            "t2i_prompt": "Photorealistic cinematic still. MCU head-and-shoulder composition. C01O02 in a navy windbreaker, a young East Asian woman, facing the camera in the center background. Her anxious face sits directly above her tightly clasped hands, her eyes fixed on the monitor below. In the out-of-focus foreground, the blurred backs and shoulders of two figures—an East Asian woman and a middle-aged East Asian man—are hunched over the shared desk, their backs to the camera. The dark top bezel of a computer monitor and the shared desk corner form a boxed-in foreground frame, the screen facing away from the camera. The monitor continuously emits a harsh, cold bluish glow that washes over the young woman's face and hands. [L13: Heavy blue-gray office shadows press in on the tight space, with the dim surface of worn beige-gray wall cabinets visible just behind her]. Sickly fluorescent light pools on the desk surface. Focus on the anxious face and tightly clasped hands of the young East Asian woman, trapped behind the cold digital glow.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "scene text: 그 부분만 유독 어두워 식별이 불가능하다. 수리영 불안이 깊어지고.",
              "Shot 2 description: The monitor edge and desk corner forming a boxed-in foreground frame... monitor glow"
            ],
            "visual_inferences": [
              "fixed_element cctv_monitor: A computer monitor resting on a desk... emits a cold, bluish glow.",
              "fixed_element dim_office_environment: blue-gray shadows... sickly fluorescent light pooling directly on the desk.",
              "Hyesu and the security employee are seen strictly from behind (OTS) with blurred backs to emphasize Suriyoung's reaction."
            ],
            "creative_decisions": [
              "Using shallow depth of field (blurred foreground figures) to intensely isolate Suriyoung's anxiety.",
              "Contrasting the sickly fluorescent desk light with the cold monitor glow to heighten psychological tension.",
              "Omitting C02 and C14 composite IDs since they are completely facing away (back-to-camera with no visible face rule)."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "64c9a922af4e5027",
              "owned_hash": "8a3bc4b2c5784cad",
              "camera_direction_hash": "703b5825d7e91a67",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "L13"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 20,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From the front corner of the desk at eye level, the camera steadies after its track into an MCU, eye-level, over-the-shoulder composition across the blurred backs of 혜수 and the security employee toward 수리영 centered in the background. Her anxious face sits above her tightly clasped hands near the lower center, with the monitor edge and desk corner forming a boxed-in foreground frame.",
            "lighting_mood": "Sickly fluorescent light pools on the desk while the room falls into blue-gray office shadow, making 수리영's hands and face feel trapped behind the monitor glow.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L13"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C14",
                "outlook_id": "O14"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_security_office_day_cctv_review",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cctv_monitor",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A computer monitor resting on a desk, featuring a thin dark bezel. The screen displays extremely dark, blackened digital footage heavily obscured by murky gray-green pixel noise, refresh lines, and compression artifacts. The screen continuously emits a cold, bluish glow.",
                "applies_to_shots": [
                  2,
                  3
                ],
                "source_facts": [
                  "scene text: 그 부분만 유독 어두워 식별이 불가능하다.",
                  "Shot 2: the monitor edge and desk corner forming a boxed-in foreground frame... monitor glow",
                  "Shot 3: monitor at just above desk height... blackened footage surrounded by a thin bezel... distorted by pixel noise, refresh lines, and compression darkness... gray-green digital noise."
                ],
                "visual_inferences": [
                  "The monitor is a standard modern flat-screen display used in typical security setups.",
                  "The footage remains statically unidentifiable, showing no clear movement due to the heavy digital noise."
                ],
                "creative_decisions": [
                  "Emphasizing the gray-green noise and the physical thin bezel to strongly anchor the prop as the source of the mystery and frustration in the scene."
                ],
                "confidence": "high"
              },
              {
                "element_id": "dim_office_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The office interior is submerged in heavy, blue-gray shadows, creating a dim and murky atmosphere. The darkness is only broken by a sickly fluorescent light pooling directly on the desk surface and the harsh, cold bluish light cast outward from the computer monitor.",
                "applies_to_shots": [
                  2,
                  3
                ],
                "source_facts": [
                  "Shot 2: Sickly fluorescent light pools on the desk while the room falls into blue-gray office shadow",
                  "Shot 3: The monitor casts cold bluish light into the surrounding dim office"
                ],
                "visual_inferences": [
                  "The ambient ceiling lights are mostly turned off or broken, resulting in localized pools of light rather than even illumination."
                ],
                "creative_decisions": [
                  "Using a stark contrast between the sickly fluorescent pooling and the cold blue monitor glow to heighten the sense of anxiety and claustrophobia."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C14O14",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "5b5e6400d3ade7c0"
      },
      {
        "scene_index": 20,
        "heading": "S#20. 마트 총무과 / 실내",
        "beat_title": "식별 불가한 화면과 깊어지는 불안",
        "representative_moment": "어두운 그림자만 보이는 CCTV 화면이 띄워진 모니터 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Close-up on the monitor, slight low angle just above desk height, strong contrast between screen glow and desk shadows",
            "t2i_prompt": "Photorealistic cinematic still. Focus on a computer monitor centered in the frame, viewed from a slight low angle just above the desk. The monitor, framed by a thin dark bezel, sits on [L13: a flat desk surface submerged in heavy blue-gray shadow]. The screen displays an extremely dark CCTV playback: a vague black silhouette of a figure positioned off-center against a murky background. The digital footage is heavily distorted by gray-green pixel noise, horizontal refresh lines, and dark compression artifacts. A harsh, cold bluish light radiates from the screen, illuminating a few tangled cables at the monitor's base.",
            "outfit_assignments": [],
            "source_facts": [
              "scene text: 그 부분만 유독 어두워 식별이 불가능하다.",
              "shot description: 검은 그림자만 어렴풋이 보이는 어두운 CCTV 영상이 띄워진 모니터 화면 클로즈업.",
              "DP instruction: Directly in front of the monitor at just above desk height... blackened footage surrounded by a thin bezel and desk shadows... vague black shadow in the recorded image sits off-center like a stain... gray-green digital noise."
            ],
            "visual_inferences": [
              "fixed_element cctv_monitor: thin dark bezel, heavy pixel noise, cold bluish glow",
              "fixed_element dim_office_environment: heavy blue-gray shadows on the desk surface",
              "Tangled cables at the monitor base added to ground the prop naturally on the desk surface."
            ],
            "creative_decisions": [
              "Keeping the monitor perfectly centered and filling most of the frame to emphasize the frustrating lack of visual information.",
              "Using the cold bluish light of the screen against the dark, murky surroundings to create a tense, claustrophobic mood."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "f40850bb8d03d3ba",
              "owned_hash": "0dc9315dd6506f73",
              "camera_direction_hash": "0cc77d90b6a252ea",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 20,
        "dependency_reason": "이전 샷에서 확립된 모니터 소품(cctv_monitor)의 질감과 보안 사무실 데스크 조명(dim_office_environment)의 일관성 유지",
        "_shot_index": 3,
        "visible_entities": [
          "L13"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 20,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Directly in front of the monitor at just above desk height, the dolly-in ends in a CU, slight low angle, through-device frame of the CCTV playback, with the screen surface kept central and the blackened footage surrounded by a thin bezel and desk shadows. The vague black shadow in the recorded image sits off-center like a stain, distorted by pixel noise, refresh lines, and compression darkness rather than by the room itself.",
            "lighting_mood": "The monitor casts cold bluish light into the surrounding dim office, while the CCTV image collapses into murky blacks and gray-green digital noise.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "L13"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C14",
                "outlook_id": "O14"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_security_office_day_dark_cctv_monitor",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cctv_monitor",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A computer monitor resting on a desk, featuring a thin dark bezel. The screen displays extremely dark, blackened digital footage heavily obscured by murky gray-green pixel noise, refresh lines, and compression artifacts. The screen continuously emits a cold, bluish glow.",
                "applies_to_shots": [
                  2,
                  3
                ],
                "source_facts": [
                  "scene text: 그 부분만 유독 어두워 식별이 불가능하다.",
                  "Shot 2: the monitor edge and desk corner forming a boxed-in foreground frame... monitor glow",
                  "Shot 3: monitor at just above desk height... blackened footage surrounded by a thin bezel... distorted by pixel noise, refresh lines, and compression darkness... gray-green digital noise."
                ],
                "visual_inferences": [
                  "The monitor is a standard modern flat-screen display used in typical security setups.",
                  "The footage remains statically unidentifiable, showing no clear movement due to the heavy digital noise."
                ],
                "creative_decisions": [
                  "Emphasizing the gray-green noise and the physical thin bezel to strongly anchor the prop as the source of the mystery and frustration in the scene."
                ],
                "confidence": "high"
              },
              {
                "element_id": "dim_office_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The office interior is submerged in heavy, blue-gray shadows, creating a dim and murky atmosphere. The darkness is only broken by a sickly fluorescent light pooling directly on the desk surface and the harsh, cold bluish light cast outward from the computer monitor.",
                "applies_to_shots": [
                  2,
                  3
                ],
                "source_facts": [
                  "Shot 2: Sickly fluorescent light pools on the desk while the room falls into blue-gray office shadow",
                  "Shot 3: The monitor casts cold bluish light into the surrounding dim office"
                ],
                "visual_inferences": [
                  "The ambient ceiling lights are mostly turned off or broken, resulting in localized pools of light rather than even illumination."
                ],
                "creative_decisions": [
                  "Using a stark contrast between the sickly fluorescent pooling and the cold blue monitor glow to heighten the sense of anxiety and claustrophobia."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 20,
                "shot_index": 2,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C14O14",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "a6f86a6bac15826d"
      },
      {
        "scene_index": 21,
        "heading": "S#21. 경찰서 안 / D",
        "beat_title": "끔찍한 사건 사진과 직면",
        "representative_moment": "책상 위에 어지럽게 널린 훼손된 시신의 인화 사진을 클로즈업으로 비춘다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Tabletop height, high angle CU, shallow-DOF insert",
            "t2i_prompt": "Photorealistic cinematic still. High angle tabletop perspective. Focus on a glossy printed crime-scene photograph, prominently featuring a horrific gaping wound with dark red torn flesh. The print surface is angled slightly upward toward the camera, overlapping haphazardly with other scattered printed photographs at varied angles. [L15: A scratched office laminate desk surface is visible at the narrow frame edges, along with a small out-of-focus silver paper clip]. Harsh cold blue-gray fluorescent light flattens the glossy paper, allowing the deep crimson tones of the wound to contrast sharply as the only saturated color.",
            "outfit_assignments": [],
            "source_facts": [
              "혜수 책상위에는 살인사건 확대 사진들이 어지럽게 널려있다.",
              "목, 어깨, 얼굴등 살점이 떨어져 보는 것만으로도 끔찍하다.",
              "shot description: A close-up of a printed crime-scene photograph on a desk, showing horrific torn flesh wounds.",
              "DP notes: CU, high angle, shallow-DOF insert of a printed crime-scene photograph"
            ],
            "visual_inferences": [
              "fixed_element scattered_crime_photos: chaotic pile of overlapping glossy prints",
              "fixed_element cold_police_office_environment: cold blue-gray tone and institutional stillness",
              "shallow depth of field to isolate the central photograph while blurring the desk edge"
            ],
            "creative_decisions": [
              "Used close framing with [L15: ...] block to describe only the immediate frame-edge desk surface, omitting the wider room.",
              "Emphasized the stark contrast between the desaturated cold blue-gray fluorescent lighting and the vivid dark red of the wound to heighten the grim atmosphere."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "b8164aab46d8da85",
              "owned_hash": "aa34738df1198728",
              "camera_direction_hash": "516d6445544dd91d",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 16,
        "dependency_reason": "경찰서 사무실 책상 위 사진이라는 배경/소품의 연속성 유지 (S16 Shot 6의 공간적 흐름 공유)",
        "_shot_index": 6,
        "visible_entities": [
          "P11",
          "L15"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 21,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At tabletop height beside 혜수's desk, the camera continues its forward pressure into a CU, high angle, shallow-DOF insert of a printed crime-scene photograph, with the torn wound area held near center and the desk reduced to narrow edges around it. The photograph is not hallucinated but feels invasive: neighboring prints overlap at the margins, making the evidence pile look like something spreading across the desk surface.",
            "lighting_mood": "Harsh police-office fluorescents flatten the glossy photo in cold blue-gray, with the wound’s dark red tones cutting through as the only saturated color.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P11",
              "L15"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_office_day_evidence_photos_gps_popup",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "scattered_crime_photos",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A chaotic pile of glossy, printed crime-scene photographs scattered and overlapping across a flat office desk. The visible images prominently feature horrific, dark red wounds of torn flesh, serving as a gruesome focal point in the workspace.",
                "applies_to_shots": [
                  6,
                  7
                ],
                "source_facts": [
                  "혜수 책상위에는 살인사건 확대 사진들이 어지럽게 널려있다.",
                  "목, 어깨, 얼굴등 살점이 떨어져 보는 것만으로도 끔찍하다."
                ],
                "visual_inferences": [
                  "The photos have a glossy finish that catches the ambient office light.",
                  "They are piled haphazardly, indicating a busy and ongoing investigation."
                ],
                "creative_decisions": [
                  "Positioning the overlapping photographs prominently on the desk to visually connect the insert shot with the character's reaction shot."
                ],
                "confidence": "high"
              },
              {
                "element_id": "cold_police_office_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A sterile police office workspace anchored by a standard, flat bureaucratic desk surface. The surrounding environment is characterized by a cold, desaturated blue-gray tone and institutional stillness, providing a grim backdrop for the evidence and equipment on the desk.",
                "applies_to_shots": [
                  6,
                  7,
                  8
                ],
                "source_facts": [
                  "S#21. 경찰서 안 / D",
                  "사무실에 홀로 앉아있는 수리영"
                ],
                "visual_inferences": [
                  "The desk features a dull, standard institutional surface.",
                  "The overall lighting remains cold and harsh, emphasizing a bleak atmosphere."
                ],
                "creative_decisions": [
                  "Using the edge of the desk and the cold ambient tone as a framing and atmospheric anchor across the close-up shots."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 16,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "e8830f856ec7536c"
      },
      {
        "scene_index": 21,
        "heading": "S#21. 경찰서 안 / D",
        "beat_title": "경악하는 수리영",
        "representative_moment": "수리영(C01)이 책상에 널린 끔찍한 사진들을 보고 큰 충격을 받아 눈을 크게 뜬 채 상체를 숙이고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "close framing with a diagonal tilt, sharp focus on the character's wide eyes, blurred foreground elements",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a navy windbreaker, a young East Asian woman, leaning forward across a flat desk edge, her head and shoulders occupying the upper frame in a tilted diagonal composition. She is positioned at a three-quarter angle from the left, her eyes wide with horror, staring intensely downward at a chaotic pile of glossy, blurred printed photographs overlapping in the lower foreground. Cold fluorescent light reflects on the wetness in her eyes and washes across her pale cheek. [L15: sterile, desaturated blue-gray institutional space, heavily out of focus behind her]. Focus on her horrified eyes and tense expression, the desk edge and scattered papers remaining soft in the lower frame.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "넘겨보며 놀라는 수리영, 환각상태에서 본 엄마의 시신모습과 너무도 흡사한 - 목, 어깨, 얼굴등 살점이 떨어져 보는 것만으로도 끔찍하다.",
              "Shot 7: 사진을 향해 상체를 숙인 채 눈동자가 커진 수리영의 경악한 얼굴.",
              "Suri-young: three_quarter_left, leaning over photographs, eyes→printed photographs"
            ],
            "visual_inferences": [
              "fixed_element scattered_crime_photos: rendered as blurred glossy prints overlapping in the lower foreground",
              "fixed_element cold_police_office_environment: rendered as heavily out-of-focus desaturated backdrop",
              "tilted diagonal framing to visually represent psychological shock"
            ],
            "creative_decisions": [
              "Using close framing and a diagonal tilt to isolate her shocked expression, ensuring the gruesome photos remain a blurred foreground anchor rather than a sharp distraction.",
              "Applying cold fluorescent light reflections on her wet eyes to emphasize the grim institutional atmosphere and her emotional state."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "42b1ae25a57cc95f",
              "owned_hash": "aa34738df1198728",
              "camera_direction_hash": "26b6b6d9dade6188",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "",
        "_shot_index": 7,
        "visible_entities": [
          "C01",
          "P11",
          "L15"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 21,
            "shot_index": 7
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Just across the desk from 수리영 at seated eye level, the upward tilt stops in a CU, Dutch angle, front-side composition with her widened eyes in the upper third and the blurred photographs low in the foreground. She leans into the frame from behind the desk edge, recognizing the echo of her vision while the office behind her falls soft and empty.",
            "lighting_mood": "Cold fluorescent light catches the wetness in her eyes while the background remains desaturated blue-gray, pushing the shock into a claustrophobic police-office stillness.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P11",
              "L15"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_office_day_evidence_photos_gps_popup",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "scattered_crime_photos",
                "element_type": "persistent_prop",
                "character_name": "",
                "description": "A chaotic pile of glossy, printed crime-scene photographs scattered and overlapping across a flat office desk. The visible images prominently feature horrific, dark red wounds of torn flesh, serving as a gruesome focal point in the workspace.",
                "applies_to_shots": [
                  6,
                  7
                ],
                "source_facts": [
                  "혜수 책상위에는 살인사건 확대 사진들이 어지럽게 널려있다.",
                  "목, 어깨, 얼굴등 살점이 떨어져 보는 것만으로도 끔찍하다."
                ],
                "visual_inferences": [
                  "The photos have a glossy finish that catches the ambient office light.",
                  "They are piled haphazardly, indicating a busy and ongoing investigation."
                ],
                "creative_decisions": [
                  "Positioning the overlapping photographs prominently on the desk to visually connect the insert shot with the character's reaction shot."
                ],
                "confidence": "high"
              },
              {
                "element_id": "cold_police_office_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A sterile police office workspace anchored by a standard, flat bureaucratic desk surface. The surrounding environment is characterized by a cold, desaturated blue-gray tone and institutional stillness, providing a grim backdrop for the evidence and equipment on the desk.",
                "applies_to_shots": [
                  6,
                  7,
                  8
                ],
                "source_facts": [
                  "S#21. 경찰서 안 / D",
                  "사무실에 홀로 앉아있는 수리영"
                ],
                "visual_inferences": [
                  "The desk features a dull, standard institutional surface.",
                  "The overall lighting remains cold and harsh, emphasizing a bleak atmosphere."
                ],
                "creative_decisions": [
                  "Using the edge of the desk and the cold ambient tone as a framing and atmospheric anchor across the close-up shots."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 21,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "bdef60a5660bdfe3"
      },
      {
        "scene_index": 21,
        "heading": "S#21. 경찰서 안 / D",
        "beat_title": "바다를 가리키는 절망적인 위치 좌표",
        "representative_moment": "모니터 화면 중앙에 뜬 차가운 해상 지도와 붉은색 GPS 좌표를 클로즈업으로 비추는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Centered eye-level framing on the monitor, cold cyan map light contrasting with sharp crimson text against a dark background.",
            "t2i_prompt": "Photorealistic cinematic still. A computer monitor occupies the center of the frame, its dark bezel and a thin sliver of a flat bureaucratic desk surface visible at the bottom edge. On the screen, a cold cyan digital sea map is displayed, featuring sharp crimson GPS coordinate numbers positioned slightly below the center. Faint reflections of ambient light catch on the slightly glossy monitor glass. Focus on the glowing crimson text on the digital map. The frame edges beyond the monitor fall into [L15: a cold, desaturated blue-gray darkness].",
            "outfit_assignments": [],
            "source_facts": [
              "S#21 action: '김형사 모니터에서 뭔가 뜬다... 엄마 폰 위치추적 결과다. 해상 지도위에 좌표. 37.484400 N / 126. 072486 E'",
              "shot description: computer monitor showing sea map and red GPS coordinates, desk surface visible at the bottom"
            ],
            "visual_inferences": [
              "fixed_element cold_police_office_environment: cold, desaturated blue-gray tone, flat bureaucratic desk surface",
              "faint reflections on the glossy monitor glass from the surrounding environment"
            ],
            "creative_decisions": [
              "Centered composition with the monitor bezel and a sliver of desk to provide physical scale without revealing the wider room.",
              "Strong color contrast between the cold cyan map and the sharp crimson coordinates to emphasize the alarming revelation."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "9022352afe5e8e90",
              "owned_hash": "aa34738df1198728",
              "camera_direction_hash": "98dc3757e06b7a77",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 21,
        "dependency_reason": "경찰서 사무실 공간의 질감과 데스크탑 모니터의 조명, 톤 연속성 유지",
        "_shot_index": 8,
        "visible_entities": [
          "P11",
          "L15"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 21,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At monitor height on the side of the desk, the camera completes its track into a squared CU, eye-level, through-device composition where the display sits cleanly in the center with its bezel and a sliver of desk still visible for scale. The sea map and red GPS coordinate text are readable, the crimson numbers positioned slightly below center like a wound opening in an otherwise bureaucratic interface.",
            "lighting_mood": "The monitor’s cold cyan map light dominates the frame, punctured by sharp crimson coordinate text against the muted police-office darkness.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P11",
              "L15"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_office_day_evidence_photos_gps_popup",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_police_office_environment",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A sterile police office workspace anchored by a standard, flat bureaucratic desk surface. The surrounding environment is characterized by a cold, desaturated blue-gray tone and institutional stillness, providing a grim backdrop for the evidence and equipment on the desk.",
                "applies_to_shots": [
                  6,
                  7,
                  8
                ],
                "source_facts": [
                  "S#21. 경찰서 안 / D",
                  "사무실에 홀로 앉아있는 수리영"
                ],
                "visual_inferences": [
                  "The desk features a dull, standard institutional surface.",
                  "The overall lighting remains cold and harsh, emphasizing a bleak atmosphere."
                ],
                "creative_decisions": [
                  "Using the edge of the desk and the cold ambient tone as a framing and atmospheric anchor across the close-up shots."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 21,
                "shot_index": 6,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "d6d152fa203a8030"
      },
      {
        "scene_index": 22,
        "heading": "S#22. 경찰서 밖 / D",
        "beat_title": "다급한 자전거 출발",
        "representative_moment": "C01이 자전거 핸들을 꽉 쥔 채 다급하게 도로를 향해 상체를 숙이고 출발하는 측면 정지 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "chest-height medium shot tracking side-profile, cold daylight, blue coastal cast",
            "t2i_prompt": "Photorealistic cinematic still. At chest height, tracking with the subject in a medium shot. C01O02 in a navy windbreaker, a young Asian woman, in left profile, leaning heavily forward over the bicycle from the reference. Torso and arms occupy the frame, with bent shoulders driving diagonally forward in a mid-ride pose, her hair flowing back in the direction opposite to motion. Her clenched hands grip the handlebars tightly in the lower foreground. Her eyes are fixed on the open road from the reference stretching forward on the left. Behind her, the muted gray station building from the reference and wet-looking concrete curb from the reference recede into the background. Cold daylight washes the scene with a blue coastal cast, highlighting the gritty texture of the damp asphalt.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#22 action: '주차된 자전거를 타고 이내 달리는 수리영'",
              "shot description: side-profile action frame of 수리영 leaning over the handlebars, riding urgently toward the road"
            ],
            "visual_inferences": [
              "C01 is frozen in mid-ride with hair flowing opposite to motion to capture the dynamic forward momentum",
              "tight framing on upper torso and handlebars based on chest height DP instruction, keeping legs out of the primary frame"
            ],
            "creative_decisions": [
              "Anchored background elements like 'bicycle', 'station building', 'road', and 'curb' with 'from the reference' to satisfy exact_background constraints and avoid drawing duplicates",
              "Applied a blue coastal cast and damp textures to emphasize the cold, gritty urgency of the scene"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "a6b25f533e0c9b66",
              "owned_hash": "4d2f9e2d47e6da8f",
              "camera_direction_hash": "92c780fae517292b",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "bicycle",
                  "violating_phrase": "the bicycle from the reference",
                  "reason": "The prompt references the bicycle as an existing element from the reference, not as a newly created object.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "road",
                  "violating_phrase": "the open road from the reference",
                  "reason": "The road is explicitly identified as coming from the reference, so it is being used as an anchored background element.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "station building",
                  "violating_phrase": "the muted gray station building from the reference",
                  "reason": "The station building is explicitly referred to as already present in the reference background.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "curb",
                  "violating_phrase": "wet-looking concrete curb from the reference",
                  "reason": "The curb is explicitly anchored to the reference background rather than newly generated.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "L16"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 22,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Parallel to the bicycle on 수리영's side at chest height, the camera tracks with her in an MS, low angle, side-profile action frame, tightening toward the handlebar line and upper torso while the road opens ahead on the left. Her clenched hands occupy the lower foreground without overwhelming the frame, and her bent shoulders drive diagonally forward as she pushes off from the curb into traffic space.",
            "lighting_mood": "Cold daylight over the police-station curb gives the scene a blue coastal cast, with hard gray asphalt and damp concrete sharpening the urgency.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L16"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_station_entrance_day_bicycle_departure",
            "reference_usage": "exact_background",
            "owned_objects": [
              "CCTV pole",
              "bicycle",
              "bicycle rack",
              "bollard",
              "canopy",
              "car",
              "crosswalk",
              "curb",
              "parking lot",
              "parking marking",
              "plaza",
              "road",
              "road arrow",
              "service door",
              "sign panel",
              "sliding door",
              "station building",
              "tactile paving",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_station_entrance_day_bicycle_departure",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "457b47441f3f08b1"
      },
      {
        "scene_index": 23,
        "heading": "S#23. 어느 PC방 / 실내",
        "beat_title": "PC방에서 바다 좌표 추적",
        "representative_moment": "어두운 PC방 안, 모니터의 푸른 불빛에 의지해 디지털 지도 좌표를 노려보는 C01의 집중한 얼굴.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium close-up (MCU), eye-level through-object framing, cold blue monitor illumination contrasting with muted shadows",
            "t2i_prompt": "Photorealistic cinematic still. Medium close-up, eye-level through-object framing. A dark monitor bezel sits as a blurred vertical sliver in the right foreground. C01O02 in a navy windbreaker, a young East Asian woman, occupies the left-center frame, head and shoulders clearly visible. She is hunched forward at a three-quarter angle from the right, her eyes fixed on the digital display just out of frame. Cold blue monitor light washes across her tense features and the front of her jacket. The background consists of [L17: soft out-of-focus scuffed plastic PC cubicle partitions sunk in deep muted gray-black shadow, with a faint sickly fluorescent glow catching the upper frame edge]. Focus on her concentrated expression illuminated by the cool screen reflection.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#23 action: '모니터 화면에 앉아있는 수리영, 좌표를 찍고 위치를 확인하고'",
              "shot description: digital map monitor on, blue-white map displayed",
              "observer at eye-level, through-object framing"
            ],
            "visual_inferences": [
              "C01 is hunched toward the monitor in three-quarter right profile, focusing intently on the screen",
              "Cold blue monitor light illuminating her face",
              "PC room partitions are dim and scuffed in the background"
            ],
            "creative_decisions": [
              "Changed 'carves' to 'washes across' for the lighting on her face to avoid the forbidden body-part physical cut violation",
              "Placed a blurred dark monitor bezel in the foreground right to anchor the through-object depth while keeping the framing close on her face",
              "Used soft out-of-focus background for the L17 description to comply with the skipped background reference constraint for close framing"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "53b74dc128b7b3f8",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "46c8495429a88c12",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "N/A",
        "_shot_index": 1,
        "visible_entities": [
          "C01",
          "P09",
          "P12",
          "L17"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 23,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From the flow's front-left monitor edge, use a medium close-up (MCU), eye-level, through-object framing: the monitor bezel sits as a dark sliver in the right foreground while 수리영's map-lit face holds left-center within arm's length. The camera is an observer, not her POV, settling at the end of a quiet dolly-in and holding just long enough for her concentration to read against the indistinct rows of the PC room.",
            "lighting_mood": "Cold blue monitor light carves her face while the PC방 remains sunk in muted gray-black shadow with sickly fluorescent residue overhead.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P09",
              "P12",
              "L17"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "eb107dfa8557e28f"
      },
      {
        "scene_index": 24,
        "heading": "S#24. 해안가 / 소나기",
        "beat_title": "폭우 속의 질주",
        "representative_moment": "쏟아지는 빗속에서 자전거 핸들을 꽉 쥐고 비바람을 맞으며 앞으로 나아가는 C01의 고정된 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Front-left tracking medium shot, eye-level, shallow DOF, compressing forward motion",
            "t2i_prompt": "Photorealistic cinematic still. Front-left tracking medium shot, eye-level, shallow depth of field. C01O02 in a wet navy windbreaker, a young East Asian woman, occupies the center-left frame at a three-quarter left angle, positioned leaning forcefully forward over the bicycle in mid-pedal. Her wet hair and jacket flap whipped backward in the direction opposite to motion. Both clenched hands locked around the wet handlebar tightly near the lower third of the frame, the bicycle's front tube visible just below the hands. Eyes fixed on the wet road ahead. Focus on her clenched hands and determined expression against the heavy rain. [L08: A rain-slick asphalt coastal road with blurred wet guardrails in the lateral background. Heavy wind-driven rain falling hard across the frame. Storm-dark blues and slate grays dominate the ambient light, accented by brief cold highlights reflected on the rainwater and her soaked skin, creating a harsh, desperate mood.]",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#24 action: 자전거를 타고 빗속을 달리는 수리영. 천둥 번개와 함께 잔뜩 낀 먹구름이 세찬 비를 뿌린다.",
              "shot description: 쏟아지는 빗방울 속에서 자전거 핸들을 꽉 쥔 수리영의 젖은 상체, 젖은 머리카락과 옷자락이 등 뒤로 세차게 휘날리며",
              "camera direction: Maintain the flow's front-left tracking position with a medium shot (MS), eye-level, shallow DOF... wet upper body center-left, clenched hands near lower third",
              "lighting mood: Storm-dark blues and slate grays are cut by brief cold highlights on rainwater"
            ],
            "visual_inferences": [
              "mid-action freeze applied to preserve forward motion with hair and jacket whipped backward",
              "bicycle front tube included below the handlebar to visually anchor the large prop and prevent floating hands effect"
            ],
            "creative_decisions": [
              "shallow depth of field used to blur the lateral background guardrails, emphasizing raw speed and isolation",
              "cold highlights placed specifically on wet skin and asphalt to heighten the harsh coastal storm atmosphere without physically cutting the subject"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "a158a28ae5d952f6",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "831b1c1357d6a81b",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 9,
        "dependency_reason": "동일한 해안가 도로 배경 참조 및 분위기 연계",
        "_shot_index": 2,
        "visible_entities": [
          "C01",
          "L08"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 24,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Maintain the flow's front-left tracking position with a medium shot (MS), eye-level, shallow DOF frame held unusually steady inside the motion: 수리영's wet upper body occupies center-left, both clenched hands visible near the lower third on the handlebar. The camera runs just ahead of the bicycle, compressing rain, wind-whipped hair, and forward lean into a single forceful instant while the slick coastal road streaks behind her.",
            "lighting_mood": "Storm-dark blues and slate grays are cut by brief cold highlights on rainwater, making her skin and soaked clothes look harsh and desperate.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "L08"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 9,
                "shot_index": 2,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "8e3add8d9656925b"
      },
      {
        "scene_index": 25,
        "heading": "S#25. 옥탑방 안 / 해질 무렵",
        "beat_title": "거실 장판에 찍힌 낯선 발자국",
        "representative_moment": "바닥 장판에 선명하게 찍힌 진흙 묻은 낯선 발자국.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up from worm's eye angle at floor level, fading cold gray dusk light with faint greenish cast",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up from a worm's eye angle, positioned almost at floor level. Focus on fresh, wet, dark muddy footprints stamping diagonally across the foreground of [L07: a sickly pale beige vinyl floor, with small, soft-blurred shapes of overturned dining chairs and an open window in the deep background]. Fading cold gray dusk light leaks across the surface in bands, mixing with dull heavy shadows and a faint greenish cast, making the mud appear nearly black against the pale floor.",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 2: 거실 장판 바닥 곳곳에 선명하게 찍힌 진흙 묻은 낯선 발자국들의 클로즈업.",
              "거실에 난 창은 열려있고, 식탁 의자들을 쓰러져있다."
            ],
            "visual_inferences": [
              "fixed_element cold_dusk_lighting",
              "fixed_element ransacked_living_room"
            ],
            "creative_decisions": [
              "Used a worm's eye angle ECU to make the muddy footprints the absolute primary subject while maintaining the observer's POV.",
              "Blurred the background to keep focus on the floor texture while maintaining continuity of the ransacked state (chairs and window).",
              "Excluded the character entirely as requested to focus solely on the unsettling evidence left on the floor."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "be4772483bff9143",
              "owned_hash": "80f679b464a34fb0",
              "camera_direction_hash": "f4dafde5c706768e",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 12,
        "dependency_reason": "previous_shot_refs indicates S12_Shot20 as a location reference, establishing the continuity of the interior space.",
        "_shot_index": 2,
        "visible_entities": [
          "P08",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 25,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Drop below the flow default into an extreme close-up (ECU), worm's eye angle, almost at floor level from the entrance threshold, looking inward across the 장판. Muddy unfamiliar footprints run diagonally from the lower left toward the dim living room, sharp in the foreground while overturned furniture and the open window remain small, blurred scale references in the distance.",
            "lighting_mood": "Fading dusk light leaks across the floor in cold gray bands, turning the mud nearly black against the sickly beige vinyl.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P08",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_dusk_ransacked_windy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior space is illuminated by fading, cold gray dusk light, mixed with heavy dull shadows and a faint greenish cast, creating a gloomy and suspenseful atmosphere.",
                "applies_to_shots": [
                  2,
                  5,
                  9
                ],
                "source_facts": [
                  "Shot 2: Fading dusk light leaks across the floor in cold gray bands",
                  "Shot 5: Dim sunset gray mixes with a faint interior green cast",
                  "Shot 9: Cold dusk light from the open window and dull interior shadow"
                ],
                "visual_inferences": [
                  "The time of day creates a consistent cold, low-light environment across both the living room and the inner bedroom."
                ],
                "creative_decisions": [
                  "Unified the overall color palette with cold grays and faint greens to emphasize the eerie occult theme of the scene."
                ],
                "confidence": "high"
              },
              {
                "element_id": "ransacked_living_room",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A chaotic living room area featuring a pale beige vinyl floor stamped with dark, muddy footprints. In the background, pieces of furniture are overturned and scattered, and a window is left wide open, letting in the outside air.",
                "applies_to_shots": [
                  2,
                  9
                ],
                "source_facts": [
                  "Shot 2: Muddy unfamiliar footprints... sickly beige vinyl... overturned furniture and the open window remain small",
                  "Shot 9: Cold dusk light from the open window... dollies out along the entrance path"
                ],
                "visual_inferences": [
                  "The muddy footprints and overturned furniture established in Shot 2 remain in the background and on the floor of Shot 9 as the character walks through the same living room entrance path."
                ],
                "creative_decisions": [
                  "Kept the open window and muddy footprints visually present in the living room framing to ensure visual continuity of the recent break-in across both angles."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 12,
                "shot_index": 20,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "6c4288d3e13a4f1b"
      },
      {
        "scene_index": 25,
        "heading": "S#25. 옥탑방 안 / 해질 무렵",
        "beat_title": "방 안의 불길한 표식과 과거의 사진",
        "representative_moment": "벽의 붉은 원 한가운데 피 묻은 사진 P08이 꽂혀 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level straight-on composition, cold dusk lighting with a faint green cast",
            "t2i_prompt": "Photorealistic cinematic still. Eye-level observer perspective looking straight at the back wall from the reference, illuminated by fading cold gray dusk light with a faint interior green cast. Centered on the wallpaper from the reference is a large, freshly painted red circle from the reference with uneven crimson edges. Pinned at its exact middle is P08, the blood-stained photograph from the reference, facing the camera. The open doorway from the reference at the side margin and the rumpled bed from the reference at the lower margin define the cramped space, steeped in heavy dull shadows. Focus on the crimson mark and the photograph, standing out aggressively in the gloomy room.",
            "outfit_assignments": [],
            "source_facts": [
              "Shot 5: 벽지 한가운데 붉은색으로 칠해진 커다란 원형 표식과 그 정중앙에 꽂힌 사진 한 장.",
              "The red circle sits centered on the back wall with the blood-stained photograph pinned at its exact middle"
            ],
            "visual_inferences": [
              "fixed_element cold_dusk_lighting: fading, cold gray dusk light, mixed with heavy dull shadows and a faint greenish cast",
              "The shot is an observer's POV of the wall, so no characters are in the frame"
            ],
            "creative_decisions": [
              "Anchored the wall, circle, photograph, doorway, and bed using 'from the reference' to satisfy exact_background and owned_objects constraints",
              "Emphasized the crimson color against the green cast to highlight the central graphic threat"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "083ea98fe64a5e29",
              "owned_hash": "36aeda8df398abde",
              "camera_direction_hash": "d6ec4c2026a8b3b1",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "wallpaper",
                  "violating_phrase": "Center on the wallpaper from the reference",
                  "reason": "The wallpaper is treated as a frame element to be newly described and centered upon, which goes beyond a simple anchor-only reference.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "circle",
                  "violating_phrase": "a large, freshly painted red circle from the reference",
                  "reason": "The prompt explicitly asks for a newly painted circle on the wall, which indicates drawing the owned object again.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "photo",
                  "violating_phrase": "Pinned at its exact middle is P08, the blood-stained photograph from the reference",
                  "reason": "The photograph is explicitly called out as a visible object to be placed and emphasized, which is a redraw request despite the reference wording.",
                  "verdict": "redraw_violation"
                },
                {
                  "owned_object": "door",
                  "violating_phrase": "The open doorway from the reference at the side margin",
                  "reason": "This is an explicit reference to the existing doorway from the background, used as an anchor rather than asking to create a new door.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "bed",
                  "violating_phrase": "the rumpled bed from the reference at the lower margin",
                  "reason": "The bed is explicitly referenced as already present in the background and used as a margin anchor, not newly generated.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "wall",
                  "violating_phrase": "the back wall from the reference",
                  "reason": "The wall is referenced as an existing background element and serves as the surface for other details, so this is an anchor reference.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 25,
        "dependency_reason": "같은 공간의 배경 묘사 일관성 유지 (이전 샷의 옥탑방 배경 참조)",
        "_shot_index": 5,
        "visible_entities": [
          "P08",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 25,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From just inside 수리영's room, keep the flow's straight-on push and resolve into a wide shot (WS), eye-level, graphic reveal of the marked wallpaper. The red circle sits centered on the back wall with the blood-stained photograph pinned at its exact middle, while the bed edge and open doorway stay at the frame margins so the symbol reads like an occult target without losing the cramped room's realism.",
            "lighting_mood": "Dim sunset gray mixes with a faint interior green cast, making the crimson circle the only aggressive color in the room.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P08",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "bg_daughter_bedroom_dusk_red_circle_bloody_photo",
            "reference_usage": "exact_background",
            "owned_objects": [
              "backpack",
              "bed",
              "blanket",
              "ceiling light",
              "circle",
              "curtain",
              "doll",
              "door",
              "floor",
              "photo",
              "wall",
              "wallpaper",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior space is illuminated by fading, cold gray dusk light, mixed with heavy dull shadows and a faint greenish cast, creating a gloomy and suspenseful atmosphere.",
                "applies_to_shots": [
                  2,
                  5,
                  9
                ],
                "source_facts": [
                  "Shot 2: Fading dusk light leaks across the floor in cold gray bands",
                  "Shot 5: Dim sunset gray mixes with a faint interior green cast",
                  "Shot 9: Cold dusk light from the open window and dull interior shadow"
                ],
                "visual_inferences": [
                  "The time of day creates a consistent cold, low-light environment across both the living room and the inner bedroom."
                ],
                "creative_decisions": [
                  "Unified the overall color palette with cold grays and faint greens to emphasize the eerie occult theme of the scene."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 25,
                "shot_index": 2,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "bg_daughter_bedroom_dusk_red_circle_bloody_photo",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "20546db5d6786df3",
        "status": "contract_violation"
      },
      {
        "scene_index": 25,
        "heading": "S#25. 옥탑방 안 / 해질 무렵",
        "beat_title": "혼미함 속의 결연한 외출",
        "representative_moment": "C01이 P08(피 묻은 사진)을 꽉 쥔 채 P09(백팩)를 메고 밖을 향해 정면으로 걸어 나온다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium close-up (MCU), low observer at chest height, cold gray dusk light with a faint green cast",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a navy windbreaker, a young East Asian woman, facing the camera. Low observer at chest height, torso and arms in the lower frame, head and shoulders occupying the center-upper frame. She is frozen mid-stride, advancing directly toward the lens, her expression rigid, eyes fixed on the camera. The dark straps of her backpack, P09, cut sharp vertical lines over both shoulders. Her hand tightly grips a blood-stained photograph, P08, near the lower right of her torso, its dark red marks standing out against the shadow. [L07: soft, out-of-focus dark corridor edge, wrapped in fading cold gray dusk light, heavy dull shadows, and a faint greenish cast]. Focus on the figure advancing into the center.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#25 action: '마치 이끌리듯 백팩을 메고 밖으로 나간다. 사진을 손에 꼭 쥔 채.'",
              "shot description: MCU, low angle from chest height, backpack straps cut dark lines, photo clenched near lower right torso",
              "shot staging: facing_camera, eyes->camera"
            ],
            "visual_inferences": [
              "fixed_element cold_dusk_lighting: faded gray light mixed with dull shadows and faint green cast",
              "Due to skipped_close_framing, background details like the ransacked living room are excluded, replaced with out-of-focus immediate frame edges"
            ],
            "creative_decisions": [
              "Positioned the camera at chest height to emphasize her resolute forward motion while keeping both the backpack straps and the clutched photo in the frame",
              "Used a cool, dull lighting scheme with sharp crimson accents on the photo to echo the eerie occult theme"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "7a82799f9e061f9f",
              "owned_hash": "80f679b464a34fb0",
              "camera_direction_hash": "94232b33af724f11",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 25,
        "dependency_reason": "Shares the continuous cold dusk lighting established in S25 Shot 5, while omitting specific room layout details due to close framing.",
        "_shot_index": 9,
        "visible_entities": [
          "C01",
          "P08",
          "P09",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 25,
            "shot_index": 9
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Hold the flow's frontal retreat as a medium close-up (MCU), low angle from chest height, with 수리영 advancing into the center while the camera dollies out along the entrance path. Her backpack straps cut dark lines over both shoulders, and the clenched photograph stays visible near the lower right of her torso, making the frontal stare feel like a decision rather than a neutral portrait.",
            "lighting_mood": "Cold dusk light from the open window and dull interior shadow flatten the room, while the photo's dark red stains echo the occult mark she has just left behind.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P08",
              "P09",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_dusk_ransacked_windy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "cold_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior space is illuminated by fading, cold gray dusk light, mixed with heavy dull shadows and a faint greenish cast, creating a gloomy and suspenseful atmosphere.",
                "applies_to_shots": [
                  2,
                  5,
                  9
                ],
                "source_facts": [
                  "Shot 2: Fading dusk light leaks across the floor in cold gray bands",
                  "Shot 5: Dim sunset gray mixes with a faint interior green cast",
                  "Shot 9: Cold dusk light from the open window and dull interior shadow"
                ],
                "visual_inferences": [
                  "The time of day creates a consistent cold, low-light environment across both the living room and the inner bedroom."
                ],
                "creative_decisions": [
                  "Unified the overall color palette with cold grays and faint greens to emphasize the eerie occult theme of the scene."
                ],
                "confidence": "high"
              },
              {
                "element_id": "ransacked_living_room",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A chaotic living room area featuring a pale beige vinyl floor stamped with dark, muddy footprints. In the background, pieces of furniture are overturned and scattered, and a window is left wide open, letting in the outside air.",
                "applies_to_shots": [
                  2,
                  9
                ],
                "source_facts": [
                  "Shot 2: Muddy unfamiliar footprints... sickly beige vinyl... overturned furniture and the open window remain small",
                  "Shot 9: Cold dusk light from the open window... dollies out along the entrance path"
                ],
                "visual_inferences": [
                  "The muddy footprints and overturned furniture established in Shot 2 remain in the background and on the floor of Shot 9 as the character walks through the same living room entrance path."
                ],
                "creative_decisions": [
                  "Kept the open window and muddy footprints visually present in the living room framing to ensure visual continuity of the recent break-in across both angles."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 25,
                "shot_index": 5,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "5eef56dd826fa350"
      },
      {
        "scene_index": 26,
        "heading": "S#26. 포구 / 해질 무렵",
        "beat_title": "안개 속에서 다가오는 어선",
        "representative_moment": "안개 낀 빈 포구의 젖은 선착장 너머로, 짙은 잿빛 안개를 뚫고 검은 실루엣의 작은 어선 뱃머리가 다가오는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle near ground level, muted cold blue-gray coastal fog",
            "t2i_prompt": "Photorealistic cinematic still. Viewed from near ground level at the edge of the pier. Wet dock planks, darkened by moisture, occupy the lower foreground. In the center frame, the sharp bow of an old small fishing boat cuts through the dark rippled harbor water, moving forward. The boat appears as a half-revealed, nearly black silhouette against a thick, pervasive gray fog bank that swallows most of the hull. The harbor is bathed in cold, muted blue-gray ambient lighting, softening distant shapes and desaturating the environment. Focus on the sharp bow of the boat piercing the dense, pale fog.",
            "outfit_assignments": [],
            "source_facts": [
              "S#26 action: '안개를 뚫고 배 한척이 다가오는 게 보인다.'",
              "shot description: 'old fishing boat's bow appears center-frame as a half-revealed black silhouette cutting the water, with wet dock boards in the lower foreground and most of the hull swallowed by the gray fog bank.'"
            ],
            "visual_inferences": [
              "fixed_element dense_harbor_fog: thick gray fog, cold blue-gray ambient light, damp atmosphere",
              "Low observer viewpoint emphasizes the wet texture of the foreground dock planks and positions the boat as an imposing presence"
            ],
            "creative_decisions": [
              "Center-frame composition for the boat's bow to act as a focal point emerging from the void",
              "Strong contrast between the black silhouette of the boat and the pale gray fog bank",
              "Absence of human figures in this frame to highlight the isolation and ominous mood of the harbor"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "0d7aa562dd9a3d30",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "bdd4ae438ee3f2e8",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "none",
        "_shot_index": 3,
        "visible_entities": [
          "P05",
          "P13",
          "L18",
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 26,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At the pier edge, use a wide shot (WS), low angle with a slightly long lens, aimed straight into the fog as established by the flow. The old fishing boat's bow appears center-frame as a half-revealed black silhouette cutting the water, with wet dock boards in the lower foreground and most of the hull swallowed by the gray fog bank.",
            "lighting_mood": "A cold coastal haze desaturates the harbor into blue-gray layers, leaving the boat as a nearly black omen against pale fog.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "P13",
              "L18",
              "L19"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "not_applicable",
            "bg_id": null,
            "reference_usage": "none",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "no chain_bg is bound to this shot — describe the location freely without referencing a background image",
              "do not use 'from the reference' / 'the existing room' / 'preserving the room' style phrasing — there is no reference image to refer to"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dense_harbor_fog",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A thick, pervasive gray fog blankets the coastal harbor and the sea, severely limiting background visibility. The ambient lighting is a muted, cold blue-gray, creating a damp atmosphere that softens distant shapes and desaturates the overall environment.",
                "applies_to_shots": [
                  3,
                  6,
                  9
                ],
                "source_facts": [
                  "Scene text states the rain stopped and thick fog rolled in (비는 그치고 안개가 자욱하다)",
                  "Shot 3 explicitly mentions 'gray fog bank' and 'blue-gray layers'",
                  "Shot 6 references 'Flat blue-gray fog light softens the background'",
                  "Shot 9 notes 'foggy water' and 'Muted coastal blue-gray light'"
                ],
                "visual_inferences": [
                  "The fog acts as a natural light diffuser, removing harsh shadows and rendering the illumination flat and gloomy",
                  "Environmental surfaces such as the dock boards appear damp or wet due to the recent rain and heavy fog"
                ],
                "creative_decisions": [
                  "Using the thick fog to visually isolate the setting from the rest of the world, emphasizing the bleak, lonely mood of the isolated harbor"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "2d39136d819f90c9"
      },
      {
        "scene_index": 26,
        "heading": "S#26. 포구 / 해질 무렵",
        "beat_title": "안개를 뚫고 온 배의 주인 인우를 만나다",
        "representative_moment": "밧줄을 쥐고 있는 C03가 무심한 눈빛으로 뒤를 돌아보며 배경의 C01을 응시한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Head-and-shoulder composition with shallow depth of field, keeping foreground sharp while blurring the background, flat blue-gray fog lighting",
            "t2i_prompt": "Photorealistic cinematic still. Head-and-shoulder composition, C03O04 in a green waterproof jacket, a young East Asian man, occupies the right foreground at a three-quarter angle from the right. He holds a thick, wet mooring rope low in his hand, with a slice of the damp, chipped wooden boat gunwale visible at the lower frame edge. His eyes are fixed backward across the foggy space. In the soft, out-of-focus background, C01O02 in a navy windbreaker, a young East Asian woman, is paused mid-stride at a three-quarter angle from the left, her eyes fixed on the man, occupying the same damp pier. [L18: The dense gray fog blankets the harbor and limits visibility.] Flat blue-gray ambient light washes over the man's cheek and the wooden boat, creating faint damp highlights on his skin. Focus on the heavy mooring rope and the thick fog crossing the air between the two figures.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "source_facts": [
              "Scene text: In-woo is securing the mooring rope (인우(24세. 남)는 닷줄을 고정시키고 있다)",
              "Shot description: tighten the flow into a close-up, indifferent glance lands across frame toward Su-ri-young"
            ],
            "visual_inferences": [
              "fixed_element dense_harbor_fog: thick gray fog blankets the coastal harbor, blue-gray layers",
              "The boat's gunwale has chipped paint and damp textures from the recent rain"
            ],
            "creative_decisions": [
              "Shallow depth of field to keep the focus sharply on In-woo while turning Su-ri-young into a soft background figure, emphasizing the psychological distance",
              "Using the boat gunwale at the lower edge to physically ground In-woo without needing to show the full vessel"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "407b7606e770eb13",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "146e8f1f047d2725",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "No direct visual dependency on a prior scene needed for this specific moment.",
        "_shot_index": 6,
        "visible_entities": [
          "C01",
          "C03",
          "P05",
          "P13",
          "L18",
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 26,
            "shot_index": 6
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From close beside the boat, tighten the flow into a close-up (CU), eye-level, slight over-the-shoulder geometry from just forward of 인우's shoulder back toward his face. The rope remains implied along the lower edge while 인우's indifferent glance lands across frame toward 수리영, who is held smaller in the pier background along his eyeline.",
            "lighting_mood": "Flat blue-gray fog light softens the background while damp highlights on rope and skin keep the close-up gritty and restrained.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C03",
              "P05",
              "P13",
              "L18",
              "L19"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dense_harbor_fog",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A thick, pervasive gray fog blankets the coastal harbor and the sea, severely limiting background visibility. The ambient lighting is a muted, cold blue-gray, creating a damp atmosphere that softens distant shapes and desaturates the overall environment.",
                "applies_to_shots": [
                  3,
                  6,
                  9
                ],
                "source_facts": [
                  "Scene text states the rain stopped and thick fog rolled in (비는 그치고 안개가 자욱하다)",
                  "Shot 3 explicitly mentions 'gray fog bank' and 'blue-gray layers'",
                  "Shot 6 references 'Flat blue-gray fog light softens the background'",
                  "Shot 9 notes 'foggy water' and 'Muted coastal blue-gray light'"
                ],
                "visual_inferences": [
                  "The fog acts as a natural light diffuser, removing harsh shadows and rendering the illumination flat and gloomy",
                  "Environmental surfaces such as the dock boards appear damp or wet due to the recent rain and heavy fog"
                ],
                "creative_decisions": [
                  "Using the thick fog to visually isolate the setting from the rest of the world, emphasizing the bleak, lonely mood of the isolated harbor"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 26,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "5a9866959b85a446"
      },
      {
        "scene_index": 26,
        "heading": "S#26. 포구 / 해질 무렵",
        "beat_title": "결심의 음성메시지",
        "representative_moment": "수리영(C01)이 배에 오르기 직전, 바다를 바라보며 핸드폰에 음성메시지를 남긴다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "near-static medium close-up, slight high angle, profile framing, muted coastal blue-gray light",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a dark navy windbreaker, a young East Asian woman, occupies the left third of the frame in clean right profile, top of her head and shoulders in the upper-left frame, chest-up visible from a slight high angle. She holds P05, a mobile phone, near her mouth, its screen turned away from the camera. Her eyes look distant toward the right edge of the frame. [L18: A wet, dark pier railing edge crosses the lower foreground, while a thick gray fog severely limits visibility behind her, rendering the sea and the partial silhouette of a moored fishing boat as a soft, out-of-focus blur]. Muted coastal blue-gray ambient light wraps her profile in damp softness, with a faint cold highlight catching on the phone edge and her lips.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "S#26 action: '수리영, 떠나기전, 바다를 바라보며 음성메시지를 남긴다.'",
              "shot description: observer at slight high angle, profile framing, left third, phone at mouth."
            ],
            "visual_inferences": [
              "fixed_element: dense_harbor_fog severely limits visibility, rendering the sea and boat as a soft blur.",
              "Muted blue-gray lighting with faint cold highlights on the lips and phone edge to emphasize the damp coastal atmosphere."
            ],
            "creative_decisions": [
              "Applied shallow depth of field for the close framing, keeping the background boat and sea out of focus to emphasize her profile and the phone interaction.",
              "Placed the subject in the left third looking right to create leading room for her distant gaze toward the sea."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "3a396c8e69d5436d",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "650b1d399555aeb5",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 26,
        "dependency_reason": "Same continuous location and atmosphere as the earlier shots in Scene 26, with the dense fog persisting.",
        "_shot_index": 9,
        "visible_entities": [
          "C01",
          "P05",
          "P13",
          "L18",
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 26,
            "shot_index": 9
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Settle the flow's seaward-side track into a near-static medium close-up (MCU), slight high angle, profile framing across 수리영's cheek line toward the foggy water. 수리영 occupies the left third in clean side profile with the phone at her mouth, while the waiting boat and gray sea sit beyond her gaze rather than showing her boarding yet.",
            "lighting_mood": "Muted coastal blue-gray light wraps her profile in damp softness, with the phone and lips catching the faintest cold highlight.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P05",
              "P13",
              "L18",
              "L19"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": null,
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dense_harbor_fog",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A thick, pervasive gray fog blankets the coastal harbor and the sea, severely limiting background visibility. The ambient lighting is a muted, cold blue-gray, creating a damp atmosphere that softens distant shapes and desaturates the overall environment.",
                "applies_to_shots": [
                  3,
                  6,
                  9
                ],
                "source_facts": [
                  "Scene text states the rain stopped and thick fog rolled in (비는 그치고 안개가 자욱하다)",
                  "Shot 3 explicitly mentions 'gray fog bank' and 'blue-gray layers'",
                  "Shot 6 references 'Flat blue-gray fog light softens the background'",
                  "Shot 9 notes 'foggy water' and 'Muted coastal blue-gray light'"
                ],
                "visual_inferences": [
                  "The fog acts as a natural light diffuser, removing harsh shadows and rendering the illumination flat and gloomy",
                  "Environmental surfaces such as the dock boards appear damp or wet due to the recent rain and heavy fog"
                ],
                "creative_decisions": [
                  "Using the thick fog to visually isolate the setting from the rest of the world, emphasizing the bleak, lonely mood of the isolated harbor"
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 26,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "6ffc5ee05fbc125d"
      },
      {
        "scene_index": 27,
        "heading": "S#27. 옥탑방 안 / 해질 무렵",
        "beat_title": "수리영의 메시지를 확인하며 불안해하는 혜수",
        "representative_moment": "C02 stands amidst the shadowed room, a phone pressed to her ear with an anxious expression.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium close-up (MCU), eye-level intimate observer framing, tight on the face and phone, sickly green-gray and dusk lighting.",
            "t2i_prompt": "Photorealistic cinematic still. C02O03 in a gray leather jacket, a young East Asian woman, positioned at a three-quarter angle from the left, a P05 mobile phone pressed tightly to her ear. She looks down, a serious and anxious expression on her face. Medium close-up, eye-level observer framing, tight on her face and the phone with her upper chest and shoulders visible in the frame. Her face and the phone dominate the center composition. Focus on her tense expression. Sickly green-gray ambient light mixes with dying, cold dusk light, washing evenly across her cheek and the leather jacket, flattening her features. [L07: Soft, out-of-focus frame-edge background showing heavily shadowed, broken layers of scattered debris and displaced household items catching the faint dusk light].",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "S#27 action: 수리영의 녹음메시지를 확인하는 혜수",
              "shot description: 엉망이 된 옥탑방 거실 한가운데 서서 핸드폰을 귀에 댄 혜수의 심각한 얼굴."
            ],
            "visual_inferences": [
              "fixed_element: ransacked_rooftop_interior (messy, scattered objects, green-gray gloom, dusk light) translated into the soft frame-edge background to comply with close framing rules.",
              "Hye-su's posture is tense, looking down at a three-quarter angle to emphasize her internal anxiety."
            ],
            "creative_decisions": [
              "Utilized a tight medium close-up (MCU) to isolate Hye-su's anxiety while rendering the ransacked room purely as out-of-focus frame-edge textures.",
              "Applied the sickly green-gray and cold dusk lighting to wash evenly over her face, avoiding harsh cuts of light to keep the facial structure intact."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "36da85b85645a75b",
              "owned_hash": "80f679b464a34fb0",
              "camera_direction_hash": "32d2be677a626134",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 12,
        "dependency_reason": "Shares the rooftop room location with scene 12, maintaining the continuous ransacked state and sickly green-gray dusk lighting, though isolated via close framing.",
        "_shot_index": 1,
        "visible_entities": [
          "C02",
          "P05",
          "L04",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 27,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Begin the scene flow with a medium close-up (MCU), eye-level, intimate observer framing about two meters in front of 혜수, tightened so her face and phone dominate center frame. The ransacked rooftop room stays visible behind her in broken layers, but the composition holds on her anxious listening before the camera will later slide away toward the entrance.",
            "lighting_mood": "Sickly interior green-gray mixes with dying dusk, flattening 혜수's face while the room behind her feels emptied and cold.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C02",
              "P05",
              "L04",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_dusk_ransacked_windy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "ransacked_rooftop_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of an old rooftop room is left in a messy, ransacked state with scattered objects and debris lying around in broken layers. The entire space is heavily shadowed and enveloped in a cold, sickly green-gray gloom, dimly illuminated by the fading light of dusk.",
                "applies_to_shots": [
                  1,
                  4
                ],
                "source_facts": [
                  "Shot 1: The ransacked rooftop room stays visible behind her in broken layers",
                  "Shot 1: Sickly interior green-gray mixes with dying dusk",
                  "Shot 4: gray-green interior gloom",
                  "Shot 4: cold dusk light leaks through"
                ],
                "visual_inferences": [
                  "The chaotic placement of objects from being ransacked remains untouched across the scene.",
                  "The ambient light level is consistently dim, relying entirely on the minimal dusk light leaking from outside."
                ],
                "creative_decisions": [
                  "Maintain a consistent green-gray color grading to emphasize the bleak, empty, and anxious atmosphere of the scene, visually tying the isolated frames together."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 12,
                "shot_index": 20,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "4ca22c07a7ffe698"
      },
      {
        "scene_index": 27,
        "heading": "S#27. 옥탑방 안 / 해질 무렵",
        "beat_title": "불안감을 증폭시키는 황량한 문소리",
        "representative_moment": "바람에 덜컹이며 살짝 열린 낡은 철문 사이로 서늘한 빛이 새어 들어오는 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle close-up, cold dusk lighting contrast",
            "t2i_prompt": "Photorealistic cinematic still. Low angle close-up on an old metal door. The heavy door is pushed slightly open, creating a narrow vertical gap positioned just off-center. Focus on the worn metal edge of the door and the thin opening. A sharp blade of cold, pale gray exterior dusk light slices through the gap, spilling across the immediate lower frame. The surrounding edge surfaces, [L07: a dusty concrete threshold and a bare, scuffed lower wall], are swallowed in a heavy, sickly green-gray gloom, casting deep shadows.",
            "outfit_assignments": [],
            "source_facts": [
              "S#27 action: '덜커덩 덜커덩. 바람에 현관문 소리. 황량하다.'",
              "shot description: old metal entrance door, slightly open, rattling in strong wind.",
              "DP directive: close-up (CU), low angle, static through-gap composition on the old metal door."
            ],
            "visual_inferences": [
              "fixed_element: cold, sickly green-gray gloom from the interior.",
              "Low camera angle places the worn concrete threshold at the bottom of the frame.",
              "The rattle of the door is conveyed through the slightly ajar, tense positioning of the heavy metal edge."
            ],
            "creative_decisions": [
              "Focusing tightly on the gap and the threshold limits spatial information, intensifying the claustrophobic and anxious mood.",
              "Strong contrast between the thin blade of pale exterior light and the heavy green-gray interior shadow to make the door feel like a visual threat."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "2058f7cc405ca21e",
              "owned_hash": "80f679b464a34fb0",
              "camera_direction_hash": "70cf50605a58524f",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 12,
        "dependency_reason": "동일한 옥탑방 공간(배경 참조)을 사용하지만, 이 샷은 close framing 룰에 따라 배경 참조 이미지를 무시하고 문틈과 즉각적인 프레임 가장자리 표면만 새로 묘사하여 연속성을 유지함.",
        "_shot_index": 4,
        "visible_entities": [
          "P05",
          "L04",
          "L07"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 27,
            "shot_index": 4
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "End the flow near the entrance with a close-up (CU), low angle, static through-gap composition on the old metal door about one meter away. The narrow opening sits just off-center, showing a sliver of exterior gray light while the door edge shudders in the wind, making the sound source feel like a presence pressing into the room.",
            "lighting_mood": "A thin blade of cold dusk light leaks through the metal door gap into otherwise gray-green interior gloom, turning the rattle into a visual threat.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "P05",
              "L04",
              "L07"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O03"
              },
              {
                "character_id": "C04",
                "outlook_id": "O05"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "bg_living_kitchen_dusk_ransacked_windy",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "ransacked_rooftop_interior",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of an old rooftop room is left in a messy, ransacked state with scattered objects and debris lying around in broken layers. The entire space is heavily shadowed and enveloped in a cold, sickly green-gray gloom, dimly illuminated by the fading light of dusk.",
                "applies_to_shots": [
                  1,
                  4
                ],
                "source_facts": [
                  "Shot 1: The ransacked rooftop room stays visible behind her in broken layers",
                  "Shot 1: Sickly interior green-gray mixes with dying dusk",
                  "Shot 4: gray-green interior gloom",
                  "Shot 4: cold dusk light leaks through"
                ],
                "visual_inferences": [
                  "The chaotic placement of objects from being ransacked remains untouched across the scene.",
                  "The ambient light level is consistently dim, relying entirely on the minimal dusk light leaking from outside."
                ],
                "creative_decisions": [
                  "Maintain a consistent green-gray color grading to emphasize the bleak, empty, and anxious atmosphere of the scene, visually tying the isolated frames together."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 12,
                "shot_index": 20,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O03",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C04O05",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "5a0e8e35e186f887"
      },
      {
        "scene_index": 28,
        "heading": "바다 + 갑판 / 해질 무렵",
        "beat_title": "사진 속 '금월'을 확인시키는 수리영",
        "representative_moment": "C01의 손가락 끝에 들려 있는 낡은 흑백 사진의 귀퉁이와 '금월'이라는 글씨에 카메라가 집중한다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "high angle extreme close-up hovering above the deck with shallow depth of field, cold dusk-blue lighting",
            "t2i_prompt": "Photorealistic cinematic still. An old, worn black-and-white photograph dominates the frame, pinched at its lower edge by the thumb and fingertip of a young East Asian woman in a navy windbreaker. The small photograph faces upward, revealing curled, salt-stained edges and visible paper fibers. A faint crimson-brown stain and tiny dark scribbled text mark the upper right corner of the paper. [L19: Wet, scratched wooden deck planks darkened by sea spray form the immediate surface directly beneath the hand]. A folded paper map rests partially visible and heavily blurred at the periphery. Cold dusk-blue ambient light skims the damp wooden planks and the textured paper, isolating the photograph with a shallow depth of field.",
            "outfit_assignments": [],
            "source_facts": [
              "S#28 action: '(다시 내밀며) 자세히 좀 봐요. 여기 작게 ‘금월’이라는 글씨 보이죠.'",
              "shot description: extreme close-up of the old black-and-white photograph held by Suri-young's fingertip, showing the word 'Geumwol'."
            ],
            "visual_inferences": [
              "fixed_element dusk_ambient_lighting: Cold dusk-blue ambient light skims the damp deck.",
              "Due to id_policy.body_part_focus_rule, Suri-young's fingertip is described using a common noun and demographic descriptor (young East Asian woman) instead of C01O02.",
              "The background is skipped due to close framing, replaced by immediate frame-edge surface description (deck planks) using [L19]."
            ],
            "creative_decisions": [
              "High angle tight composition hovering inches above the deck to emphasize the small detail of the photo.",
              "Shallow depth of field isolates the photo's texture, salt stains, and the faint crimson-brown stain from the damp deck background.",
              "A folded map is placed in the blurred periphery to provide situational context without distracting from the primary focus."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "c8b76a5a8233d1a3",
              "owned_hash": "36194228037de9ee",
              "camera_direction_hash": "f1e85ae5f15a8a38",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 25,
        "dependency_reason": "25씬에서 수리영이 발견한 낡은 흑백 사진(P08)이 이 씬에서 중요한 단서로 다시 등장하며 클로즈업됨.",
        "_shot_index": 3,
        "visible_entities": [
          "C01",
          "P08",
          "P12",
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 28,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Direct observer view derived from the low close-observation flow: an extreme close-up (ECU), high angle macro frame hovers inches above the wet deck, angled down onto the old black-and-white photograph. The tiny handwritten 'Geumwol' in the corner sits near the upper right of frame, while 수리영's fingertip anchors the lower edge at natural scale; the worn paper fibers, salt stains, and curled photo corner are emphasized with shallow DOF.",
            "lighting_mood": "Cold dusk-blue ambient light skims the damp deck, with a faint crimson-brown stain in the photograph corner giving the clue an occult charge.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P08",
              "P12",
              "L19"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_deck_exterior_dusk_normal",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_ambient_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The exterior of the small boat is enveloped in a cold, dusk-blue ambient light. This fading evening illumination creates a dim, moody atmosphere across the deck and exterior surfaces. The low light casts a desaturated, chilly tone over the surroundings, indicating the late hour on the water.",
                "applies_to_shots": [
                  3,
                  8
                ],
                "source_facts": [
                  "scene heading: 해질 무렵 (around dusk)",
                  "Shot 3 lighting: Cold dusk-blue ambient light skims the damp deck",
                  "Shot 8 lighting: Dying coastal dusk"
                ],
                "visual_inferences": [
                  "The overall ambient lighting remains consistently dim and bluish-gray across the boat's exterior during the short time frame of the scene."
                ],
                "creative_decisions": [
                  "Focusing on the cold dusk lighting as an environmental anchor to maintain visual consistency across drastically different shot scales."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "c591e093acca7d72"
      },
      {
        "scene_index": 28,
        "heading": "바다 + 갑판 / 해질 무렵",
        "beat_title": "조타실을 막아서는 수리영",
        "representative_moment": "C01이 좁은 조타실 입구에서 두 팔을 벌려 C03의 앞을 가로막고 서 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Eye-level medium shot from just outside the wheelhouse, cold dusk-blue ambient and sickly green-gray interior spill",
            "t2i_prompt": "Photorealistic cinematic still. Eye-level observer view. Focus on the tense space between the two figures framed by the doorway. C01O02 in a navy windbreaker, a young East Asian woman, with back to camera, standing full-body in the center, boots to shoulders visible, arms braced wide across the shared wheelhouse doorway, eyes fixed on C03O04. She appears as a backlit figure, rim light tracing her shoulders and outstretched arms, body volume preserved against the dim ambient fill. C03O04 in a green waterproof jacket, a middle-aged East Asian man, at three-quarter angle from the left, standing in the rear background, halted at the helm console from the reference, seen through the gap between her arm and the doorframe, eyes fixed on C01O02. Cold dusk-blue ambient light falling on the damp deck from the reference, while sickly green-gray interior spill washes the threshold.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "source_facts": [
              "scene heading: 해질 무렵 (around dusk)",
              "Shot 8 description: 좁은 조타실 입구에서 두 팔을 벌린 채 인우의 앞을 막아선 수리영의 전신 구도.",
              "action: 인우, 발작적으로 일어나 조타실로 달려가 뱃머리를 돌리려 한다. 이를 눈치 챈 수리영, 조타실로 따라들어가 막으면서"
            ],
            "visual_inferences": [
              "fixed_element dusk_ambient_lighting: cold dusk-blue ambient light skims the damp deck",
              "Soori-young stands blocking the entrance, creating a silhouette against the dim interior spill",
              "In-woo is halted near the steering controls in the background"
            ],
            "creative_decisions": [
              "Framing Soori-young centrally with her back to the camera to emphasize her blocking stance as a human barricade.",
              "Using rim lighting to ensure the silhouette maintains depth and volume, preventing a flat cutout effect.",
              "Using the shared wheelhouse doorway as the spatial anchor between foreground and background characters."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "42a54bb542d1b68c",
              "owned_hash": "36194228037de9ee",
              "camera_direction_hash": "d04156ebb659e32b",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "wheelhouse",
                  "violating_phrase": "the tense space between the two figures framed by the doorway",
                  "reason": "The prompt uses the wheelhouse doorway as a frame element without telling the model to create a new wheelhouse; it is referenced as existing background context.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "helm console",
                  "violating_phrase": "halted at the helm console from the reference",
                  "reason": "The phrase explicitly anchors the helm console to the reference/background rather than instructing a new console to be drawn.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "deck",
                  "violating_phrase": "the damp deck from the reference",
                  "reason": "The deck is explicitly referred to as coming from the reference, so it is an anchor mention, not a redraw instruction.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "sliding door",
                  "violating_phrase": "across the shared wheelhouse doorway",
                  "reason": "The doorway is used as an existing spatial anchor and is not being introduced as a new object to create.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 28,
        "dependency_reason": "previous_shot_refs specifies Scene 28 Shot 3 for exact_background, anchoring the boat deck and cold dusk-blue ambient lighting.",
        "_shot_index": 8,
        "visible_entities": [
          "C01",
          "C03",
          "P08",
          "P12",
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 28,
            "shot_index": 8
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Direct observer view from just outside the wheelhouse entrance: a wide shot (WS), eye-level, static doorway frame holds 수리영 full-body in the center with both arms spread across the narrow opening. The camera stays far enough back to keep her boots, shoulders, and outstretched hands visible, while 인우 remains partially trapped beyond her in the dim wheelhouse, seen through the gap between her arm and the doorframe.",
            "lighting_mood": "Dying coastal dusk silhouettes 수리영 against sickly green-gray wheelhouse spill, turning her blocking posture into a tense human barricade.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "C03",
              "P08",
              "P12",
              "L19"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "cb_deck_exterior_dusk_normal",
            "reference_usage": "exact_background",
            "owned_objects": [
              "boat",
              "cleat",
              "deck",
              "deck hatch",
              "fishing rod rack",
              "fog",
              "helm console",
              "net bin",
              "rail",
              "rope coil",
              "sea",
              "sliding door",
              "wheelhouse",
              "winch",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "dusk_ambient_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The exterior of the small boat is enveloped in a cold, dusk-blue ambient light. This fading evening illumination creates a dim, moody atmosphere across the deck and exterior surfaces. The low light casts a desaturated, chilly tone over the surroundings, indicating the late hour on the water.",
                "applies_to_shots": [
                  3,
                  8
                ],
                "source_facts": [
                  "scene heading: 해질 무렵 (around dusk)",
                  "Shot 3 lighting: Cold dusk-blue ambient light skims the damp deck",
                  "Shot 8 lighting: Dying coastal dusk"
                ],
                "visual_inferences": [
                  "The overall ambient lighting remains consistently dim and bluish-gray across the boat's exterior during the short time frame of the scene."
                ],
                "creative_decisions": [
                  "Focusing on the cold dusk lighting as an environmental anchor to maintain visual consistency across drastically different shot scales."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 28,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "cb_deck_exterior_dusk_normal",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "f753e800d0ac299a"
      },
      {
        "scene_index": 29,
        "heading": "S#29. 조타실 / 해질 무렵",
        "beat_title": "엄마의 생존 가능성을 외치며 절박하게 매달리는 수리영",
        "representative_moment": "수리영(C01)이 눈가가 붉어진 채 입을 벌리고 화면 밖의 인우를 향해 절박하게 소리치는 헤드-앤-숄더 클로즈업.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Tight low-angle head-and-shoulder close-up, sickly fluorescent and blue-gray dual-tone lighting, shallow depth of field",
            "t2i_prompt": "Photorealistic cinematic still. C01O02 in a dark navy windbreaker, a young East Asian woman, framed in a tight head-and-shoulder composition. She occupies the left-center of the frame, positioned at a three-quarter angle from the right, leaning forward in a desperate plea. Focus on her strained expression: reddened eyes fixed intensely off-camera, mouth open mid-shout, and tense jaw muscles. A low-angle observer view pushes in from slightly below her eyeline. Sickly greenish-yellow fluorescent light washes across the right side of her face and neck, while a cold, bruised blue-gray dusk spill reflects on her opposite cheek and shoulder. [L20: Soft, out-of-focus background melting into a murky blue-gray haze, featuring a thin blurred vertical window frame edge, a dim indistinct steering console angled away behind her shoulder, and faint crimson circular smears hidden in the deep shadows].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "Shot 3 action: 눈가를 붉힌 채 입을 크게 벌린 수리영의 절박하고 일그러진 얼굴 클로즈업.",
              "DP instructions: Direct observer view at 수리영's eyeline: a tight close-up (CU), low angle... She is framed slightly left of center in three-quarter view."
            ],
            "visual_inferences": [
              "fixed_element wheelhouse_dusk_lighting: harsh greenish-yellow and bruised blue-gray spill lighting her face.",
              "fixed_element red_circular_wall_markings: rendered as faint, completely blurred crimson smears in the L20 background block due to close framing.",
              "The steering console and window frame are pushed into out-of-focus background elements to emphasize her facial tension."
            ],
            "creative_decisions": [
              "Used a 'head-and-shoulder composition' rather than a 'face filling the frame' to comply with T2I face framing rules and avoid floating-head artifacts.",
              "Described the background entirely within an L20 block using blur adjectives, strictly following the skipped_close_framing binding policy (no reference to prior rooms or owned objects)."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "02c9cbd47dc4989e",
              "owned_hash": "3dcdffa44980a305",
              "camera_direction_hash": "e478caefc8d825a4",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "No cross-scene dependency required for this shot; internal continuity handled via fixed_elements.",
        "_shot_index": 3,
        "visible_entities": [
          "C01",
          "P08",
          "L20"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 29,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Direct observer view at 수리영's eyeline: a tight close-up (CU), low angle, pushes in from slightly below her face so her reddened eyes, open mouth, and strained jaw muscles occupy most of the frame without flattening into a frontal portrait. She is framed slightly left of center in three-quarter view, with the cramped wheelhouse melting into blue-gray blur behind her as she pleads about her mother.",
            "lighting_mood": "Sickly fluorescent interior light mixes with cold dusk spill, reddening her eyes while leaving the background in a bruised blue-gray haze.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P08",
              "L20"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_wheelhouse_interior_dusk_red_circle_marks",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "wheelhouse_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The cramped interior of the wheelhouse is illuminated by a constant, unsettling dual-tone light. A sickly, harsh greenish-yellow fluorescent light from the cabin fixtures mixes heavily with the cold, bruised blue-gray spill of dusk coming from outside, creating a murky and oppressive atmosphere.",
                "applies_to_shots": [
                  3,
                  5,
                  7
                ],
                "source_facts": [
                  "Shot 3: Sickly fluorescent interior light mixes with cold dusk spill, reddening her eyes while leaving the background in a bruised blue-gray haze.",
                  "Shot 5: harsh greenish cabin light with cold blue dusk leaking",
                  "Shot 7: Muted blue-gray cabin darkness... sickly fluorescent spill"
                ],
                "visual_inferences": [
                  "The ambient light sources remain constant throughout the short dialogue exchange, casting consistent color temperatures across different angles."
                ],
                "creative_decisions": [
                  "Defined the specific color palette (greenish-yellow vs blue-gray) as an environment state to ensure the claustrophobic and tense mood is maintained across all tight and macro shots."
                ],
                "confidence": "high"
              },
              {
                "element_id": "red_circular_wall_markings",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The dark, muted interior walls of the wheelhouse are densely covered with numerous crude, red circular markings arranged in rows. The crimson paint has a slightly wet or glossy texture that contrasts sharply against the grim, dimly lit background of the cabin.",
                "applies_to_shots": [
                  3,
                  7
                ],
                "source_facts": [
                  "Scene text: 조타실안 수많은 원... 붉은 원!",
                  "Shot 7: dark wheelhouse wall fills the center and right with rows of red circular markings.",
                  "Shot 7: sharp crimson of the circles... wall texture feel wet and real."
                ],
                "visual_inferences": [
                  "Although explicitly revealed as a focal point in Shot 7, these markings are physically painted on the walls and would exist in the background environment of Shot 3, even if obscured or heavily blurred by the shallow depth of field."
                ],
                "creative_decisions": [
                  "Excluded from Shot 5 as it is an extreme macro shot pointing downward at a photograph where walls would not be visible. Included in Shot 3 and 7 to ground the spatial continuity of the cabin."
                ],
                "confidence": "medium"
              }
            ],
            "previous_shot_refs": [],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "9da983ebfbcfeaab"
      },
      {
        "scene_index": 29,
        "heading": "S#29. 조타실 / 해질 무렵",
        "beat_title": "사진 속 아이의 정체",
        "representative_moment": "An extreme close-up of a dirt-marked index finger pressing down on the face of a young girl in a faded black-and-white photograph.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme close-up, high angle macro shot, harsh greenish-yellow and cold blue-gray lighting",
            "t2i_prompt": "Photorealistic cinematic still. Extreme close-up, high angle macro shot. Focus on an East Asian woman's dirt-marked index finger pressing firmly down on a creased, faded black-and-white photograph. The mud-stained finger pad partly obscures the printed face of a young East Asian girl, which sits just right of center on the paper. The photograph is held flat, filling almost the entire view. At the edge, a sliver of [L20: scratched, out-of-focus dark counter surface] remains visible just beneath the photo border to provide scale. The macro frame is washed in a harsh greenish-yellow fluorescent glow mixed with a cold blue-gray dusk spill. The light catches on the textured photo grain, casting deep shadows that make the dirt on the tense fingertip appear almost black. The rest of the character's body is completely absent from the frame.",
            "outfit_assignments": [],
            "source_facts": [
              "S#29 action: '이 사진속의 얘가 우리 엄마예요.'",
              "shot description: 낡은 사진 속 어린 소녀의 얼굴을 꾹 누른 수리영의 흙 묻은 검지손가락 클로즈업.",
              "DP instruction: extreme close-up (ECU), high angle macro shot looks down at the photograph... only the photo border and a sliver of shadowed wheelhouse surface remain for scale."
            ],
            "visual_inferences": [
              "fixed_element wheelhouse_dusk_lighting: harsh greenish-yellow fluorescent mixed with cold blue-gray dusk",
              "Body part focus rule applied: C01O02 is replaced by 'an East Asian woman's dirt-marked index finger'",
              "Reproduction surface rule applied: The girl in the photo is described as 'a young East Asian girl'"
            ],
            "creative_decisions": [
              "Framed from a high angle looking down at the surface, placing the out-of-focus counter at the bottom edge to anchor the composition.",
              "Described the lighting directly interacting with the photo's texture to emphasize the gritty, realistic occult horror tone."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "4c2531ad4bf89848",
              "owned_hash": "3dcdffa44980a305",
              "camera_direction_hash": "c68e2742a0a4a8e4",
              "validator": "scene_detail_owned_objects.v1.close_skip",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 29,
        "dependency_reason": "Maintains the continuous ambient lighting environment (wheelhouse_dusk_lighting) established in Shot 3.",
        "_shot_index": 5,
        "visible_entities": [
          "C01",
          "P08",
          "L20"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 29,
            "shot_index": 5
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "close",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Direct observer view continuing the downward evidence move: an extreme close-up (ECU), high angle macro shot looks down at the photograph held between the two people, compressing the frame to 수리영's dirt-marked index finger pressing the young girl's face. The girl's face sits just right of center under the fingertip, while the surrounding hands are mostly excluded and only the photo border and a sliver of shadowed wheelhouse surface remain for scale.",
            "lighting_mood": "The macro frame is lit by harsh greenish cabin light with cold blue dusk leaking across the photo grain, making the fingertip's dirt look almost black.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C01",
              "P08",
              "L20"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "skipped_close_framing",
            "bg_id": "cb_wheelhouse_interior_dusk_red_circle_marks",
            "reference_usage": "skipped_close_framing",
            "owned_objects": [],
            "camera_reference": null,
            "close_framing_skips_background_ref": true,
            "constraints": [
              "this shot uses close framing — the background reference is intentionally omitted at composition time",
              "do not mention the existing room, the chain_bg reference image, or any item from the owned_objects list",
              "do not use any of: 'the existing X', 'from the reference', 'use the X from the reference', 'preserving the same room perspective', 'maintaining the reference's framing', 'do not generate a new X' — these phrases are invalid when the reference is absent",
              "do not use any of: 'matching the reference camera', 'deviation from reference', 'same … angle as the reference', 'match the reference framing' — Rule A close-framing invalidation: close framing has no reference camera to match or deviate from",
              "compose the close subject from its immediate surroundings only — use [L##: ...] block for frame-edge surface description"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "wheelhouse_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The cramped interior of the wheelhouse is illuminated by a constant, unsettling dual-tone light. A sickly, harsh greenish-yellow fluorescent light from the cabin fixtures mixes heavily with the cold, bruised blue-gray spill of dusk coming from outside, creating a murky and oppressive atmosphere.",
                "applies_to_shots": [
                  3,
                  5,
                  7
                ],
                "source_facts": [
                  "Shot 3: Sickly fluorescent interior light mixes with cold dusk spill, reddening her eyes while leaving the background in a bruised blue-gray haze.",
                  "Shot 5: harsh greenish cabin light with cold blue dusk leaking",
                  "Shot 7: Muted blue-gray cabin darkness... sickly fluorescent spill"
                ],
                "visual_inferences": [
                  "The ambient light sources remain constant throughout the short dialogue exchange, casting consistent color temperatures across different angles."
                ],
                "creative_decisions": [
                  "Defined the specific color palette (greenish-yellow vs blue-gray) as an environment state to ensure the claustrophobic and tense mood is maintained across all tight and macro shots."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 29,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              }
            ],
            "forbidden_refs": [
              {
                "kind": "background",
                "reason": "close framing skips chain_bg reference"
              }
            ],
            "readiness_policy": "skipped_by_policy",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": true,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "55e471af9d34f555"
      },
      {
        "scene_index": 29,
        "heading": "S#29. 조타실 / 해질 무렵",
        "beat_title": "조타실 벽의 붉은 원 발견",
        "representative_moment": "Over C03's shoulder, dense red circular markings cover the dark wheelhouse wall.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "over-the-shoulder medium shot, sickly fluorescent and blue-gray dusk mix",
            "t2i_prompt": "Photorealistic cinematic still. Over-the-shoulder perspective. C03O04, a middle-aged Asian man in a green waterproof jacket, positioned on the left foreground edge with his back to the camera and rigid shoulders hunched, blocking part of the frame. The focus is entirely on the dark, muted interior wall of the wheelhouse from the reference, filling the center and right. The wall panel is densely covered with numerous crude, red circular markings arranged in rows. A sickly, harsh greenish-yellow fluorescent light mixes heavily with the cold, bruised blue-gray spill of dusk coming from outside, puncturing the dark space with the sharp crimson of the circles. The wet, glossy texture of the red paint reflects the dim ambient light, contrasting against the grim background.",
            "outfit_assignments": [
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "source_facts": [
              "Shot 7: 인우의 어깨 너머 조타실 어두운 벽면에 빼곡하게 칠해진 붉은색 원형 표식들의 정지 구도.",
              "Over-the-shoulder perspective behind 인우: a medium shot (MS)",
              "dark wheelhouse wall fills the center and right with rows of red circular markings",
              "red circular markings: many uneven crimson circles, dense and ominous",
              "Muted blue-gray cabin darkness is punctured by the sharp crimson of the circles, with just enough sickly fluorescent spill to make the wall texture feel wet and real."
            ],
            "visual_inferences": [
              "fixed_element wheelhouse_dusk_lighting: sickly greenish-yellow fluorescent light mixed with cold blue-gray dusk spill",
              "fixed_element red_circular_wall_markings: dark interior walls densely covered with crude, red circular markings, wet or glossy texture",
              "wall panel is an owned object anchored to the reference"
            ],
            "creative_decisions": [
              "Placed C03 strictly as an over-the-shoulder foreground element to maintain scale and focus entirely on the terrifying revelation of the red circles.",
              "Used descriptive lighting terms (sickly greenish-yellow, bruised blue-gray) to enhance the oppressive and occult horror mood."
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "a4e5448e4bde335f",
              "owned_hash": "3dcdffa44980a305",
              "camera_direction_hash": "05a44b010237961c",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "wall panel",
                  "violating_phrase": "the dark, muted interior wall of the wheelhouse from the reference",
                  "reason": "The prompt explicitly references the existing wall panel from the reference, so it is not asking to redraw it.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "A sickly, harsh greenish-yellow fluorescent light",
                  "reason": "The lighting is described as part of the existing scene illumination rather than a newly added object, so this is an anchor-like reference.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 29,
        "dependency_reason": "Shot 5 established the exact_background of the wheelhouse interior; this shot reveals the red circles on the same walls.",
        "_shot_index": 7,
        "visible_entities": [
          "C03",
          "P08",
          "L20"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 29,
            "shot_index": 7
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Over-the-shoulder perspective behind 인우: a medium shot (MS), eye-level, static frame places his shoulder and a narrow slice of his cheek along the left foreground edge while the dark wheelhouse wall fills the center and right with rows of red circular markings. The composition holds completely still after the reveal, minimizing 인우 as a scale reference so the crimson circles become the occult focal point without cutting away from the established axis.",
            "lighting_mood": "Muted blue-gray cabin darkness is punctured by the sharp crimson of the circles, with just enough sickly fluorescent spill to make the wall texture feel wet and real.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "C03",
              "P08",
              "L20"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O04"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "cb_wheelhouse_interior_dusk_red_circle_marks",
            "reference_usage": "exact_background",
            "owned_objects": [
              "bench",
              "chair",
              "console",
              "dashboard",
              "display",
              "door",
              "fluorescent light",
              "radio microphone",
              "steering wheel",
              "storage locker",
              "switch panel",
              "throttle lever",
              "wall panel",
              "window",
              "windshield"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "wheelhouse_dusk_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The cramped interior of the wheelhouse is illuminated by a constant, unsettling dual-tone light. A sickly, harsh greenish-yellow fluorescent light from the cabin fixtures mixes heavily with the cold, bruised blue-gray spill of dusk coming from outside, creating a murky and oppressive atmosphere.",
                "applies_to_shots": [
                  3,
                  5,
                  7
                ],
                "source_facts": [
                  "Shot 3: Sickly fluorescent interior light mixes with cold dusk spill, reddening her eyes while leaving the background in a bruised blue-gray haze.",
                  "Shot 5: harsh greenish cabin light with cold blue dusk leaking",
                  "Shot 7: Muted blue-gray cabin darkness... sickly fluorescent spill"
                ],
                "visual_inferences": [
                  "The ambient light sources remain constant throughout the short dialogue exchange, casting consistent color temperatures across different angles."
                ],
                "creative_decisions": [
                  "Defined the specific color palette (greenish-yellow vs blue-gray) as an environment state to ensure the claustrophobic and tense mood is maintained across all tight and macro shots."
                ],
                "confidence": "high"
              },
              {
                "element_id": "red_circular_wall_markings",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The dark, muted interior walls of the wheelhouse are densely covered with numerous crude, red circular markings arranged in rows. The crimson paint has a slightly wet or glossy texture that contrasts sharply against the grim, dimly lit background of the cabin.",
                "applies_to_shots": [
                  3,
                  7
                ],
                "source_facts": [
                  "Scene text: 조타실안 수많은 원... 붉은 원!",
                  "Shot 7: dark wheelhouse wall fills the center and right with rows of red circular markings.",
                  "Shot 7: sharp crimson of the circles... wall texture feel wet and real."
                ],
                "visual_inferences": [
                  "Although explicitly revealed as a focal point in Shot 7, these markings are physically painted on the walls and would exist in the background environment of Shot 3, even if obscured or heavily blurred by the shallow depth of field."
                ],
                "creative_decisions": [
                  "Excluded from Shot 5 as it is an extreme macro shot pointing downward at a photograph where walls would not be visible. Included in Shot 3 and 7 to ground the spatial continuity of the cabin."
                ],
                "confidence": "medium"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 29,
                "shot_index": 5,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C01O02",
                "policy": "required"
              },
              {
                "kind": "character_outlook",
                "id": "C03O04",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "cb_wheelhouse_interior_dusk_red_circle_marks",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "8b16f34e1bf512de"
      },
      {
        "scene_index": 30,
        "heading": "S#30. 바다 / 해질 무렵",
        "beat_title": "안개 속으로 사라지는 어선",
        "representative_moment": "인우의 소형 어선이 거대한 안개벽을 향해 나아가는 원경.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Extreme wide establishing shot, offshore eye-level tracking behind the boat, fading gold dusk into cold gray-blue haze.",
            "t2i_prompt": "Photorealistic cinematic still. Extreme wide establishing shot, eye-level to the horizon from far offshore. A small fishing boat, featuring the wheelhouse and deck from the reference, sits centered in the lower middle of the frame, its stern facing the camera and a faint engine wake trailing behind. Its bow aims directly into the towering, opaque gray fog wall from the reference that swallows the entire horizon line. The dark blue-gray sea from the reference stretches outward, its rippled surface reflecting a muted golden dusk glow that rapidly drains into a cold gray-blue atmospheric haze. Focus on the stark scale difference between the tiny vessel and the immense fog boundary.",
            "outfit_assignments": [],
            "source_facts": [
              "S#30 action: '세상과 경계를 지우는 것 같은 짙은 안개 띠. 서서히 안개 안으로 들어가는 인우의 배.'",
              "shot description: A small fishing boat moving toward a towering gray fog wall at dusk, from an extreme wide offshore perspective."
            ],
            "visual_inferences": [
              "The boat remains small and centered to emphasize isolation",
              "The muted golden reflection on the dark blue-gray sea contrasts with the overwhelming gray-blue haze"
            ],
            "creative_decisions": [
              "Extreme wide establishing shot to showcase the scale difference between the boat and the fog wall",
              "Lighting emphasizes the transition from fading sunset warmth to cold, ominous occult horror tones"
            ],
            "confidence": "high",
            "owned_validation": {
              "schema_version": 1,
              "t2i_prompt_hash": "bc53b891641ea967",
              "owned_hash": "8b48a58b29003f6d",
              "camera_direction_hash": "970ffee42e28799f",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "wheelhouse",
                  "violating_phrase": "featuring the wheelhouse and deck from the reference",
                  "reason": "The prompt explicitly mentions the wheelhouse as a featured frame element; although it references the source, it still invokes the owned object in the scene description rather than merely using it as a positional anchor.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "deck",
                  "violating_phrase": "featuring the wheelhouse and deck from the reference",
                  "reason": "The deck is explicitly called out as part of the boat’s visible features from the reference, which is a reference-based mention rather than a request to add a new deck.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "sea",
                  "violating_phrase": "The dark blue-gray sea from the reference stretches outward",
                  "reason": "The sea is referenced as an existing background element from the reference and used to describe the shot composition, not introduced as a new object.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fog",
                  "violating_phrase": "the towering, opaque gray fog wall from the reference",
                  "reason": "The fog wall is clearly marked as coming from the reference background, so this is a reference to an existing element rather than a redraw instruction.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 28,
        "dependency_reason": "Same location (sea/fog boundary) established in S28_Shot3, requiring exact background consistency for the fog and sea atmosphere.",
        "_shot_index": 2,
        "visible_entities": [
          "L19"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 30,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Direct observer view from far offshore: an extreme wide / establishing shot (EWS), eye-level to the horizon from about three meters above the water, tracks behind the small fishing boat on its stern-to-bow axis. The boat remains small and centered in the lower middle of frame, its bow aimed into a towering gray fog wall that spans the entire horizon line, while the sea surface and sunset reflection stretch outward to dwarf it.",
            "lighting_mood": "Fading gold dusk is rapidly drained into cold gray-blue haze, making the fog wall feel like a physical boundary between worlds.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction specifies a vertical height/position (low / hip-height / overhead / ground level / quay level / floor level / from above) and the scene description includes frame-edge surfaces",
                "consistency_check_summary": "elements described inside the frame must be at vertical/depth positions consistent with the camera's height — low cameras place feet/lower-body in the lower frame, overhead cameras place head/shoulders in upper frame, hip-height cameras place torso in frame with head/feet implied beyond edges",
                "core_principles": [
                  "low cameras at ground/quay/floor level place feet and lower legs in the lower frame; chest-height frame-edge surfaces behind the subject are geometrically forbidden",
                  "overhead high angles from above place the top of head and shoulders in the upper-center frame; floor surfaces visible below feet at the lower frame edge are forbidden",
                  "hip-height side cameras place torso and arms in frame; head and feet are implied beyond frame edges, not both fully visible together",
                  "full body shots require either eye-level or high-angle framing where head and feet both fit; low cameras + full silhouette in one frame is forbidden"
                ],
                "forbidden_combinations": [
                  "low camera at ground/quay/floor level + frame-edge surface described at chest/waist height behind the subject",
                  "overhead high angle + feet visible at the lower frame edge with floor visible below them",
                  "hip-height side camera + full silhouette including head and feet visible in same frame",
                  "low angle looking up + ceiling and floor both fully visible in same frame"
                ],
                "recommended_phrasings": [
                  "low observer at ground level, shoes and lower legs occupying the lower frame, upper body extending toward the upper edge",
                  "overhead high angle from above, the top of head and shoulders fill the upper-center frame, the floor visible around them",
                  "at hip height beside the subject, torso and arms in frame, head and lower legs implied beyond frame edges",
                  "low angle looking up at the figure, ceiling lamps in the upper frame, the wall behind extending downward"
                ],
                "self_check_steps": [
                  "identify the camera position phrasing (height + angle)",
                  "list elements described inside the frame (foreground prop, body parts, background surfaces)",
                  "verify each element's vertical/depth placement is geometrically consistent with that camera position",
                  "if mismatch found, adjust frame-edge description to match camera position"
                ],
                "rationale_summary": "T2I 모델은 카메라 위치와 frame 안 요소 vertical 좌표 모순 시 절충 합성 — 인물이 가구에 박히거나 신체 일부가 잘리거나 prop 이 떠 있는 부자연스러운 결과"
              },
              "fg_bg_shared_anchor_rule": {
                "applies_when": "two characters share an interaction (dialogue / handing object / facing / co-watching) AND are described as foreground/background separated AND a shared surface or spatial anchor exists between them (bench / table / door / room)",
                "shared_anchor_required": "describe the shared surface or spatial anchor explicitly so both figures occupy the same physical space",
                "forbidden_phrasings": [
                  "fg/bg separation without naming the shared surface/space",
                  "isolated foreground hand reaching with another figure 'in the rear background' (no shared anchor named)",
                  "one figure 'in the foreground' and another 'in the back' without naming the room/surface they share"
                ],
                "recommended_keywords": [
                  "shared bench / shared table / shared surface",
                  "the same X they both occupy (X = bench, sofa, table, doorway, room)",
                  "across the X from each other",
                  "<prop> crosses the air between them (interaction prop visually links the two)",
                  "the <surface> sharing a single line of sight from the camera"
                ],
                "self_check_steps": [
                  "do the two characters share a single interaction (dialogue, handing, facing, co-watching)?",
                  "is one foreground and the other background-separated?",
                  "is the shared surface/space anchor explicitly named?",
                  "if not, add one of the recommended keywords"
                ],
                "rationale_summary": "fg/bg 분리만 묘사하면 모델이 두 인물을 다른 공간에 배치하거나 인터랙션이 끊긴 어색한 합성 — 공유 anchor 명시가 같은 물리적 공간 강제"
              },
              "primary_framing_rule": {
                "applies_when": "framing_scale ∈ {close, medium, insert} from `_derive_framing_scale()` (render_strategy.framing_scale, production enum). wide-class shots are mapped to medium and use `wide_medium_rules`. The LLM may *additionally* infer wide from prose keywords (`wide shot` / `전경` / `establishing` / `aerial`) for stricter checking — these are LLM-side reasoning hints, not the production framing_scale enum (RO-4 binding — card-only classification).",
                "framing_scale_keywords": {
                  "_comment": "LLM-facing reasoning hints — not the production framing_scale enum. card framing_scale is close/medium/insert from _derive_framing_scale(); wide is LLM hint only (RO-4 / RO-5 binding). Canary close-framing shot scope filter uses production _CLOSE_FRAMING_RE (9-entry alignment) — separate from this 11-entry LLM list.",
                  "close": [
                    "close-up",
                    "CU",
                    "MCU",
                    "ECU",
                    "XCU",
                    "extreme close-up",
                    "클로즈업",
                    "손가락이",
                    "손이",
                    "눈이",
                    "얼굴이"
                  ],
                  "wide": [
                    "wide shot",
                    "establishing",
                    "aerial",
                    "전경",
                    "전신"
                  ],
                  "medium_default": "medium / mid / two-shot — anything not matching close/wide keywords"
                },
                "close_framing_rules": {
                  "primary_subject_only_fully_visible": "the named primary subject (hand / face / object) is the only fully visible entity in the frame",
                  "other_entities_appearance_options": [
                    "partial visibility — shoulder slice / arm slice / sleeve / fingertips entering the frame edge",
                    "soft background — out-of-focus silhouette via shallow depth of field",
                    "absent — not rendered at all even if listed in visible_entities"
                  ],
                  "forbidden_combinations": [
                    "same character's full body and body-part close-up in the same frame (view mixing)",
                    "two characters both rendered as sharp close-up faces in the same frame"
                  ],
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "wide_medium_rules": {
                  "primary_and_secondary_both_visible": "primary subject + secondary entities all renderable",
                  "body_part_close_up_forbidden": "body-part close-up of any character is forbidden in wide/medium framing — close-up belongs in a separate shot",
                  "fg_bg_separation_requires_shared_anchor": "if two characters are rendered fg/bg separated, also apply fg_bg_shared_anchor_rule",
                  "body_part_focus_cross_ref": "see id_policy.body_part_focus_rule (G4.3 sub-field — body-part Focus 시 C##O## 금지)"
                },
                "self_check_steps": [
                  "identify framing_scale from camera_direction",
                  "if close: verify only primary subject is fully visible; other entities are partial / soft bg / absent",
                  "verify same character's full body + body-part close-up are not combined",
                  "if close: verify two faces are not both rendered sharp"
                ],
                "rationale_summary": "한 shot 안 framing scale 가 일관되어야 모델이 단일 카메라 셔터로 해석. close/wide/medium 혼합은 multi-camera 합성으로 인식되어 인물 분열 / 부위 분리 / 시점 혼합 합성"
              },
              "rationale_summary": "Rule F/G/J 의 spatial consistency 룰 통합 — camera 위치 vs frame edge 모순, fg/bg 분리 시 공유 anchor 누락, framing scale 혼합. 3 sub-rule 모두 single t2i_prompt = single camera shutter 원칙의 spatial 측면."
            },
            "constraints": [
              "one prompt captures one still moment",
              "do not combine full-body framing and body-part close-up in one frame",
              "camera position and frame-edge elements must be geometrically consistent — see render_strategy.spatial_consistency.camera_frame_rule",
              "two characters in fg/bg separation must share a named surface/space anchor — see render_strategy.spatial_consistency.fg_bg_shared_anchor_rule",
              "framing_scale binds entity rendering — close = primary subject only fully visible, wide/medium = no body-part close-up — see render_strategy.spatial_consistency.primary_framing_rule"
            ]
          },
          "id_policy": {
            "allowed_base_entity_ids": [
              "L19"
            ],
            "allowed_outlook_pairs": [],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "body-part close-up",
              "photo/poster/screen/mirror/reflection/projection depiction",
              "unregistered extra"
            ],
            "demographic_fallback_required": true,
            "face_identifiability_rule": {
              "use_entity_id_when": [
                "face identifiable: front, profile, three-quarter, or eyes closed",
                "OTS framing with any visible face"
              ],
              "common_noun_required_when": [
                "back to camera with no visible face",
                "silhouette or blurred outline only",
                "OTS with only back of head/shoulder, face entirely hidden"
              ],
              "id_use_summary": "C##/C##O## allowed only when face is identifiable AND framing is not dominated by an isolated body part",
              "rationale_summary": "C## 사용 시 얼굴 ref 가 자동 결합 — 얼굴이 안 보이는 인물에 C## 부착하면 ref 와 본문 묘사가 충돌"
            },
            "body_part_focus_rule": {
              "trigger_phrases": [
                "focus on",
                "close on",
                "tight on",
                "detail on"
              ],
              "applies_to": "any body part (face or non-face) when the framing is dominated by that part",
              "id_use": "forbidden — use a common noun + demographic descriptor instead",
              "common_noun_examples_generic": [
                "a trembling hand",
                "an exposed forearm",
                "the furrowed brow of a figure in shadow",
                "the clenched jaw of a figure in profile"
              ]
            },
            "close_framing_face_phrasing": {
              "forbidden_phrases": [
                "face filling the entire frame",
                "face filling nearly the entire frame",
                "her face fills the frame",
                "shoulders only entering the frame",
                "head snapped sideways",
                "his face fills the frame"
              ],
              "recommended_phrasings": [
                "tight framing on her face, upper body in frame",
                "close on his expression, shoulder visible at the edge",
                "head-and-shoulder composition, face occupying the center-right",
                "face in profile at the left, neck and upper chest visible"
              ],
              "rationale_summary": "T2I 모델은 얼굴이 프레임 전체를 가득 채우는 묘사를 받으면 몸과 분리된 얼굴만 공중에 떠 있는 합성을 낸다 — 어깨/상반신 일부를 프레임 안에 유지"
            },
            "reproduction_surface_rule": {
              "applies_to_surfaces": [
                "photograph",
                "poster",
                "painting",
                "portrait",
                "monitor",
                "TV",
                "mirror",
                "window reflection",
                "projection"
              ],
              "id_use": "forbidden — common noun + demographic descriptor only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면 속 얼굴이 사진 밖 실물 크기로 합성됨"
            },
            "demographic_descriptor_policy": {
              "required_on_first_appearance": true,
              "applies_to_id_forms": [
                "C##",
                "C##O##"
              ],
              "token_count_range": [
                1,
                2
              ],
              "components": {
                "ethnicity": [
                  "Asian",
                  "East Asian",
                  "South Asian",
                  "Southeast Asian",
                  "Black",
                  "Middle Eastern",
                  "Hispanic",
                  "Latina",
                  "Latino",
                  "Caucasian"
                ],
                "gender": [
                  "man",
                  "woman",
                  "figure"
                ],
                "age_band": [
                  "in his/her 20s",
                  "in his/her 30s",
                  "in his/her 40s",
                  "young",
                  "middle-aged",
                  "elderly"
                ],
                "role_hint_from_outfit": [
                  "in worker uniform",
                  "in fisher workwear",
                  "in detective coat",
                  "in business suit"
                ]
              },
              "format_template_a": "C##O## in <옷 1-3 단어>, <demographic descriptor>",
              "format_template_b": "C##O##, <demographic descriptor>, <자세 표현>",
              "source_priority": [
                "visual_world_rules.region",
                "visual_world_rules.era",
                "shot context outfit hint"
              ],
              "scenario_dependency_ban": "no work-specific proper nouns (character names, place names) — common nouns only",
              "regional_consistency": "한 작품 내 region 표기는 일관 — 선택된 세분 ethnicity (East Asian / Southeast Asian / South Asian / Caucasian / Black / Hispanic / Latina|o / Middle Eastern) 를 작품 단위 고정"
            },
            "constraints": [
              "visible real people with outfit binding use C##O## composite IDs",
              "do not use C##O## for a reproduced face inside a photograph, poster, painting, portrait, monitor, TV, mirror, window reflection, or projection — use a common noun + demographic descriptor instead",
              "do not use C##O## for isolated body-part focus (face or non-face) — when the framing is dominated by a single body part triggered by 'focus on / close on / tight on / detail on' phrasing, use a common noun (hand / eye / brow / jaw / etc.)",
              "for close-up of a face, do not use 'face filling the entire frame' / 'face filling nearly the entire frame' / 'her face fills the frame' / 'shoulders only entering the frame' / 'head snapped sideways' — keep upper body or shoulder edge visible in the frame ('tight framing on her face, upper body in frame')",
              "when introducing a C##O## (or C##) for the first time in this t2i_prompt, append a 1-2 token demographic descriptor (ethnicity + age band, or ethnicity + role hint) consistent with visual_world_rules.region — never use scenario-specific proper nouns",
              "use the format `C##O## in <옷 1-3 단어>, <demographic descriptor>` or `C##O##, <demographic descriptor>, <자세 표현>` — main characters with face refs may include this descriptor too (image inject takes precedence)"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "cb_deck_exterior_dusk_fog_wall",
            "reference_usage": "exact_background",
            "owned_objects": [
              "cleat",
              "deck",
              "fishing rod rack",
              "fog",
              "hatch",
              "helm console",
              "net bin",
              "rail",
              "rope coil",
              "sea",
              "sliding door",
              "wheelhouse",
              "winch",
              "window"
            ],
            "camera_reference": null,
            "close_framing_skips_background_ref": false,
            "constraints": [
              "owned_objects lists all environment objects already drawn in the background reference — do not create new ones",
              "when focusing on an owned object, anchor it explicitly: 'the door from the reference'"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [],
            "previous_shot_refs": [
              {
                "scene_index": 28,
                "shot_index": 3,
                "ref_usage": "",
                "kind": "location"
              }
            ],
            "forward_zoom_targets": [],
            "cross_shot_id_substitution_rule": {
              "applies_when": "fixed_elements[i].character_name maps to a C## allowed in id_policy.allowed_base_entity_ids OR a C##O## in id_policy.allowed_outlook_pairs",
              "substitution": "replace the common-noun person reference inside fixed_elements[i].description (e.g. 'An Asian man' / 'a woman' / 'a figure') with the matched C## or C##O##",
              "double_description_forbidden": "do not describe the same character with both a C##/C##O## and a separate common-noun person reference in the same t2i_prompt — produces phantom extra figures",
              "preserve_pose_unchanged": "fixed_elements[i].description 의 자세/위치/상태 keyword 는 그대로 유지 — 인물 참조 토큰만 교체",
              "no_repeat_after_pose": "이미 t2i_prompt 안에서 같은 인물의 자세를 묘사했다면, 같은 fixed_element description 을 별도 문장으로 반복하지 마라",
              "rationale_summary": "fixed_element description 이 보통명사로 작성되었고 같은 인물의 C## 묘사가 t2i_prompt 에 따로 있으면 모델이 두 인물로 인식해 인원 수가 부풀려진다"
            },
            "ref_usage_constraints": {
              "zoom_in_detail": {
                "scope_summary": "same moment, same space, same primary subject; camera moved/zoomed onto a sub-region only",
                "forbidden_additions": [
                  "new persons not in the prior shot",
                  "new props not in the prior shot",
                  "new background elements not in the prior shot",
                  "new poses, gestures, or expressions not in the prior shot",
                  "different moments of action"
                ],
                "required_phrasings": [
                  "describe only the focused sub-region in concrete terms",
                  "explicitly state the same environment (lighting, background) is preserved",
                  "use continuity tokens such as 'the same figure', 'the same room', 'the same surface'"
                ],
                "body_part_cross_ref": "id_policy.body_part_focus_rule applies — when the focused sub-region is a body part, use a common noun + demographic descriptor (no C##/C##O##)",
                "rationale_summary": "zoom_in_detail = 앞 샷의 특정 영역을 확대한 '같은 사진'. 새 정보 추가 금지 — 현재 프레임이 보여주는 부분만 정확히 묘사"
              },
              "exact_background": {
                "scope_summary": "same room, possibly different moment or angle; background carries through, persons/actions are described fresh for this shot",
                "permitted_additions": [
                  "new persons, poses, expressions, actions for this shot's moment",
                  "different camera angle within the same room"
                ],
                "background_consistency_rule": "background elements established in the prior shot must remain consistent (no contradictory walls, doors, furniture)",
                "ignore_keep_handled_elsewhere": "ignore/keep directives are auto-applied via reference image processing — do not echo them inside t2i_prompt",
                "rationale_summary": "같은 공간, 새 순간 — 인물·동작은 이 샷의 instantaneous moment 로 묘사하되 배경은 prior shot 과 일관"
              },
              "atmosphere_reference": {
                "scope_summary": "different room/floor/angle entirely — only mood/tone is shared with the prior shot",
                "forbidden_imports": [
                  "furniture layout from the prior shot",
                  "wall positions from the prior shot",
                  "specific architectural features from the prior shot"
                ],
                "required_handling": "describe the new space's background directly in this shot; carry through only color tone or lighting mood (e.g. 'cool gray ambient' / 'dim warm pool')",
                "rationale_summary": "atmosphere_reference = 분위기 reference 만, 레이아웃 reference 아님. 가구·벽 배치를 끌어오면 모델이 두 공간을 한 공간으로 합성"
              }
            },
            "view_consistency": {
              "framing_scope_options": [
                "third_person",
                "close_up"
              ],
              "single_camera_rule": "one t2i_prompt = one camera position. do not combine a third-person full-body description and a close-up of the same character's body part.",
              "third_person_handling": "describe persons with full or partial body in frame; their hands/arms remain attached to their bodies (no isolated hand close-up alongside the full body)",
              "close_up_handling": "isolated body part (hand, wrist, fingers, brow) — do not include the same character's full body in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "the phrasing 'Focus on ...' specifies the area of focus while the camera position remains the same; it is NOT a view switch",
              "id_policy_cross_ref_for_body_part_focus": "id_policy.body_part_focus_rule applies — body-part Focus 시 C##O## 금지 (얼굴 ref 합성 차단)",
              "prop_orientation_rule": "props the character holds must face one direction only — toward camera OR toward character, not both. forbidden contradiction example: 'photo angled partly toward the camera' + 'eyes fixed on the photograph' (양방향 모순)",
              "mixing_forbidden": true,
              "rationale_summary": "single t2i_prompt = single camera shutter at 1/1000s. 시점 혼합은 모델이 두 카메라 합성으로 해석해 인물이 두 번 등장 또는 부위 분리"
            },
            "constraints": [
              "fixed_elements are continuity inputs derived from prior shots — treat them as binding context, not as source facts to be invented",
              "when fixed_elements[i].character_name maps to a C## in id_policy.allowed_base_entity_ids or a C##O## in id_policy.allowed_outlook_pairs, replace the common-noun person reference inside fixed_elements[i].description with that C##/C##O## and do not also write a separate common-noun reference for the same character in the same t2i_prompt",
              "previous_shot_refs with ref_usage='zoom_in_detail' must preserve the same moment, the same space, and the same lighting as the prior shot — no new persons, props, background elements, poses, or moments",
              "previous_shot_refs with ref_usage='exact_background' may freely describe this shot's persons, poses, and moment, but must keep background elements consistent with the prior shot's established room",
              "previous_shot_refs with ref_usage='atmosphere_reference' must describe a new space directly — do not import furniture layout or wall positions from the prior shot, only mood/tone",
              "one t2i_prompt = one camera position — do not combine a third-person full-body description and a close-up of the same character's body part; 'Focus on' specifies the area of focus, not a view switch (id_policy.body_part_focus_rule applies for any body-part Focus)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "background",
                "id": "cb_deck_exterior_dusk_fog_wall",
                "policy": "required"
              }
            ],
            "forbidden_refs": [],
            "readiness_policy": "block_if_missing",
            "constraints": [
              "do not imply or describe a reference image that is not listed in required_refs (no phantom references)",
              "if a required character_outlook ref is missing, scene image generation must block before the image stage"
            ]
          },
          "_card_metadata": {
            "lift_status": {
              "rule_a_lifted": true,
              "rule_c_lifted": true,
              "rule_e_lifted": false,
              "rule_h_lifted": true,
              "id_policy_composite_lifted": true,
              "id_policy_close_framing_face_lifted": true,
              "id_policy_reproduction_surface_lifted": true,
              "continuity_cross_shot_id_substitution_lifted": true,
              "continuity_ref_usage_constraints_lifted": true,
              "continuity_view_consistency_lifted": true,
              "continuity_constraints_extended": true,
              "spatial_camera_frame_lifted": true,
              "spatial_fg_bg_shared_anchor_lifted": true,
              "spatial_primary_framing_lifted": true,
              "spatial_constraints_extended": true
            },
            "rule_source": {
              "camera_rule": "A",
              "owned_rule": "C",
              "close_skip_rule": "E",
              "demographic_rule": "H",
              "composite_id_rule": "C## 사용 규칙 — 참조 이미지 연동 (v17:32-64)",
              "close_framing_face_rule": "극단 클로즈업 표현 (v17:66-85)",
              "reproduction_surface_rule": "사진·포스터·화면·거울 속 인물 규칙 (v17:133-146)",
              "cross_shot_id_substitution_rule": "v20/scene_detail/system.md#continuity-section",
              "ref_usage_rule": "v20/scene_detail/system.md#continuity-section",
              "view_consistency_rule": "v20/scene_detail/system.md#continuity-section",
              "camera_frame_rule": "v20/scene_detail/system.md#spatial-consistency",
              "fg_bg_shared_anchor_rule": "v20/scene_detail/system.md#spatial-consistency",
              "primary_framing_rule": "v20/scene_detail/system.md#spatial-consistency"
            }
          }
        },
        "render_prompt_card_hash": "d183beff419a3d10"
      }
    ]
  },
  "step_id": "scene_detail",
  "run_id": "451307ae-302d-40a7-a27f-d1647a41da0e",
  "resolved_model": "gemini-pro",
  "updated_at": "2026-05-05T08:14:59.867197+00:00",
  "project_config_snapshot": {}
}