{
  "status": "completed",
  "completed_count": 6,
  "applicable_count": 6,
  "failed_count": 0,
  "schema_version": 13,
  "config_hash": "c249b401e1e7118a",
  "data": {
    "scenes": [
      {
        "scene_index": 1,
        "heading": "#1. 정비소 안 – 저녁",
        "beat_title": "정비에 집중하는 민수",
        "representative_moment": "형광등 불빛 아래에서 민수가 거꾸로 세워진 자전거 체인을 정비하고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "medium shot, waist-height low three-quarter view angled slightly upward, modest low-key contrast",
            "t2i_prompt": "Photorealistic cinematic still. From a waist-height observer position beside the workbench, with a low three-quarter view angled slightly upward. C01O01 in a navy worker uniform, an Asian middle-aged man with short natural dark hair, stands at three-quarter angle from the left, occupying the right half of the frame. He is leaning forward into the repair, looking down, his oil-marked fingertips touching the inverted P01 near the center. The inverted bicycle frame and front wheel are visible above the surface. The open toolbox rests on the oil-grimed workbench in the lower-left foreground, forming the bottom edge beneath his hands. The scene is illuminated by the single overhead fluorescent light, casting a restrained, slightly desaturated glow with modest low-key contrast across [L01: the dim narrow repair shop interior].",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              }
            ],
            "source_facts": [
              "민수(40대), 남색 작업복 차림. 자전거 체인을 손보는 중이다. 손끝에 기름이 묻어 있다.",
              "좁은 정비소. 형광등 하나가 천장에 매달려 있다. 기름때 묻은 작업대 위에 공구 상자가 열려 있고, 그 옆에 낡은 자전거 한 대가 거꾸로 세워져 있다."
            ],
            "visual_inferences": [
              "fixed_element repair_shop_interior_lighting: The overall environment is illuminated by a single overhead fluorescent light, which casts a restrained, slightly desaturated glow.",
              "A waist-height camera logically places the workbench in the lower foreground beneath the subject's working hands."
            ],
            "creative_decisions": [
              "Adopted a low three-quarter view angled upward to emphasize the subject's focus on the suspended bicycle chain.",
              "Placed the open toolbox and workbench strictly in the lower-left to anchor the spatial depth without obstructing the medium framing of the hands and torso."
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [],
            "reference_phrase_kinds": [
              "character",
              "background"
            ],
            "owned_object_usage": [
              {
                "owned_token": "bicycle",
                "usage_kind": "anchor",
                "source_phrase": "The inverted bicycle frame and front wheel are visible"
              },
              {
                "owned_token": "door",
                "usage_kind": "absent",
                "source_phrase": ""
              },
              {
                "owned_token": "fluorescent light",
                "usage_kind": "anchor",
                "source_phrase": "the single overhead fluorescent light"
              },
              {
                "owned_token": "toolbox",
                "usage_kind": "anchor",
                "source_phrase": "The open toolbox rests on the oil-grimed workbench"
              },
              {
                "owned_token": "workbench",
                "usage_kind": "anchor",
                "source_phrase": "beside the workbench"
              }
            ],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "8605d442b68d8606",
              "owned_hash": "0d4417d43dc11d80",
              "camera_direction_hash": "08c9e012a327937c",
              "owned_usage_hash": "91ec6dc17d18506e",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "bicycle",
                  "violating_phrase": "The inverted bicycle frame and front wheel are visible",
                  "reason": "The prompt refers to the inverted bicycle frame as a spatial reference for composition, which matches the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "the single overhead fluorescent light",
                  "reason": "The fluorescent light is used as a light source to establish the atmosphere of the scene, matching the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "toolbox",
                  "violating_phrase": "The open toolbox rests on the oil-grimed workbench",
                  "reason": "The prompt specifies the placement of the toolbox in the foreground to anchor the scene composition, which matches the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "workbench",
                  "violating_phrase": "beside the workbench",
                  "reason": "The workbench is referenced as a camera and spatial anchor in the scene, consistent with the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "첫 번째 씬이므로 앞선 시각 연관 씬 없음",
        "_shot_index": 1,
        "visible_entities": [
          "L01",
          "C01",
          "P01"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 1,
            "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 waist height beside the workbench, hold a low three-quarter view angled slightly upward, with 민수 occupying the right half while his oil-marked fingertips meet the inverted bicycle chain near center. Keep the open toolbox and workbench in the lower left, allowing the chain, hands, and 민수's navy-clad upper body to remain legible in one restrained composition; his attention stays fixed downward on the repair.",
            "lighting_mood": "The single hanging fluorescent light gives the evening workshop restrained, slightly desaturated illumination with modest low-key contrast.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": null,
            "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": [
              "L01",
              "C01",
              "P01"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": false,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "L01B02",
            "reference_usage": "exact_background",
            "owned_objects": [
              "bicycle",
              "door",
              "fluorescent light",
              "toolbox",
              "workbench"
            ],
            "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",
              "if focusing on an owned object, declare its reference-kind via the reference_phrase_kinds sidecar (producer contract)"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "repair_shop_interior_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of a narrow repair shop in a modern Korean city during the evening. The overall environment is illuminated by a single overhead fluorescent light, which casts a restrained, slightly desaturated glow. This establishes a consistent low-key contrast and a dim atmosphere across the space.",
                "applies_to_shots": [
                  1,
                  2
                ],
                "element_scope": "full",
                "source_facts": [
                  "좁은 정비소. 형광등 하나가 천장에 매달려 있다.",
                  "The single hanging fluorescent light gives the evening workshop restrained, slightly desaturated illumination",
                  "Established fluorescent illumination from inside the workshop catches 연희's wet shoulder"
                ],
                "visual_inferences": [
                  "The fluorescent light creates a cool, slightly dim ambiance that uniformly affects the background elements and subjects within the narrow space."
                ],
                "creative_decisions": [
                  "Applying a consistent low-key contrast and desaturated color palette to unify the distinct subject framings in both 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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "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": "background",
                "id": "L01B02",
                "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"
            ]
          },
          "render_contracts": [],
          "_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": "99efedff9d517de7"
      },
      {
        "scene_index": 1,
        "heading": "#1. 정비소 안 – 저녁",
        "beat_title": "민수가 자전거 수리에만 집중하여 외부 상황을 전혀 모르는 상태 → 연희가 다급하게 뛰어 들어와 골목에 사람이 쓰러져 있다는 위급 상황을 인지한 상태",
        "representative_moment": "연희(C02)가 젖은 우비를 입고 손전등을 든 채 열린 정비소 문 안쪽으로 막 발을 디딘 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "chest height observer POV, medium framing",
            "t2i_prompt": "Photorealistic cinematic still. C02O02 in a wet yellow raincoat, an Asian woman in her 20s with natural dark hair, is captured mid-stride in the middle-center midground, moving toward the garage interior, with the open door situated in the middle-right background of [L01: a narrow, dim repair shop interior]. Viewed from a chest-height observer perspective just inside the space, the figure occupies the center frame from the waist up. She appears at a three-quarter angle from the right, her leading foot crossing the threshold and her wet shoulder turned obliquely toward the lens. Her expression is tense, eyes fixed past the camera toward the workbench off-screen. Her hand grips P03, a portable flashlight, its front end visible beside her hip without aiming at the camera. An overhead fluorescent light casts a restrained, slightly desaturated glow, creating a low-key contrast atmosphere that catches the sheen of moisture on her raincoat shoulder.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "연희(20대), 노란 우비를 입고 손전등을 든 채로 문을 밀고 들어선다.",
              "어깨가 젖어 있다."
            ],
            "visual_inferences": [
              "fixed_element: interior of a narrow repair shop illuminated by a single overhead fluorescent light",
              "low-key contrast and dim atmosphere carried from prior shot"
            ],
            "creative_decisions": [
              "chest-height medium framing to capture her abrupt entry from the waist up",
              "restrained desaturated glow specifically highlighting the wet texture of her yellow raincoat against the dim background"
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [
              "fsc_001",
              "fsc_002"
            ],
            "reference_phrase_kinds": [
              "character",
              "background"
            ],
            "owned_object_usage": [
              {
                "owned_token": "bicycle",
                "usage_kind": "absent",
                "source_phrase": ""
              },
              {
                "owned_token": "door",
                "usage_kind": "anchor",
                "source_phrase": "with the open door situated in the middle-right background"
              },
              {
                "owned_token": "fluorescent light",
                "usage_kind": "anchor",
                "source_phrase": "An overhead fluorescent light casts a restrained, slightly desaturated glow"
              },
              {
                "owned_token": "toolbox",
                "usage_kind": "absent",
                "source_phrase": ""
              },
              {
                "owned_token": "workbench",
                "usage_kind": "anchor",
                "source_phrase": "toward the workbench off-screen"
              }
            ],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "421ac2d5ab5f0758",
              "owned_hash": "0d4417d43dc11d80",
              "camera_direction_hash": "8749aee0ce5fbaaa",
              "owned_usage_hash": "2436d30ed10028da",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "door",
                  "violating_phrase": "with the open door situated in the middle-right background",
                  "reason": "The door is mentioned only as a spatial reference for the character's movement, which matches the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "An overhead fluorescent light casts a restrained, slightly desaturated glow",
                  "reason": "The fluorescent light is mentioned as a light source to describe the illumination, which matches the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "workbench",
                  "violating_phrase": "toward the workbench off-screen",
                  "reason": "The workbench is described as off-screen and serves only as a target direction for the character's gaze, matching the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 1,
        "dependency_reason": "exact_background 모드로 이전 샷의 정비소 내부 환경(조명, 분위기) 연속성 유지",
        "_shot_index": 2,
        "visible_entities": [
          "L01",
          "C02",
          "P03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 1,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "At the end of the lateral track, settle just inside and to one side of the doorway at chest height, catching 연희 obliquely as her leading foot crosses the threshold and her yellow raincoat occupies the middle of the frame. Her wet shoulder turns toward the lens while her face and urgent gaze angle past the camera toward 민수 at the workbench; the open doorway remains behind her rather than becoming a frontal portrait backdrop.",
            "lighting_mood": "Established fluorescent illumination from inside the workshop catches 연희's wet shoulder in restrained, slightly desaturated contrast.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": {
              "reason": "movement_direction",
              "constraints": [
                {
                  "constraint_id": "fsc_001",
                  "target_kind": "background",
                  "target_id": "",
                  "label": "open workshop doorway",
                  "screen_zone": "middle_right",
                  "depth_plane": "background",
                  "gesture_action": "none",
                  "gesture_target_label": ""
                },
                {
                  "constraint_id": "fsc_002",
                  "target_kind": "character",
                  "target_id": "C02",
                  "label": "연희",
                  "screen_zone": "middle_center",
                  "depth_plane": "midground",
                  "gesture_action": "moves_toward",
                  "gesture_target_label": "garage interior"
                }
              ]
            },
            "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": [
              "L01",
              "C02",
              "P03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": false,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "L01B01",
            "reference_usage": "exact_background",
            "owned_objects": [
              "bicycle",
              "door",
              "fluorescent light",
              "toolbox",
              "workbench"
            ],
            "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",
              "if focusing on an owned object, declare its reference-kind via the reference_phrase_kinds sidecar (producer contract)"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "repair_shop_interior_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of a narrow repair shop in a modern Korean city during the evening. The overall environment is illuminated by a single overhead fluorescent light, which casts a restrained, slightly desaturated glow. This establishes a consistent low-key contrast and a dim atmosphere across the space.",
                "applies_to_shots": [
                  1,
                  2
                ],
                "element_scope": "full",
                "source_facts": [
                  "좁은 정비소. 형광등 하나가 천장에 매달려 있다.",
                  "The single hanging fluorescent light gives the evening workshop restrained, slightly desaturated illumination",
                  "Established fluorescent illumination from inside the workshop catches 연희's wet shoulder"
                ],
                "visual_inferences": [
                  "The fluorescent light creates a cool, slightly dim ambiance that uniformly affects the background elements and subjects within the narrow space."
                ],
                "creative_decisions": [
                  "Applying a consistent low-key contrast and desaturated color palette to unify the distinct subject framings in both shots."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 1,
                "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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O02",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "L01B01",
                "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"
            ]
          },
          "render_contracts": [],
          "_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": "174642ed92af764c"
      },
      {
        "scene_index": 2,
        "heading": "#2. 갈래길 – 저녁",
        "beat_title": "사거리에 쓰러진 노인",
        "representative_moment": "가로등 불빛이 번지는 넓은 젖은 사거리 한가운데에 의식을 잃고 쓰러진 노인과 그 곁에 떨어진 지팡이.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "wide steeply oblique overhead view, restrained desaturated cool tones",
            "t2i_prompt": "Photorealistic cinematic still. Seen from a wide, steeply oblique overhead angle, C03O03 in a grey coat, an elderly Korean man with greying hair and natural facial wrinkles, lies unconscious in the middle-center midground, while a streetlight reflection on wet ground stretches across the lower-left background. The figure is lying curled still on his side in right profile, slack and limp in an inactive state, eyes closed, his face turned away from the camera. A fallen wooden cane rests nearby on the damp pavement, clearly separated with a visible gap, its length running at a distinct angle from the man's body. The wide junction displays four diverging roads stretching outward, lit by a nearby flickering streetlight seen from an oblique top-down perspective. The wet intersection road surface reflects the intermittent illumination, creating an elongated, spread-out streak of light separated from the figure, rendered in restrained, slightly desaturated color tones.",
            "outfit_assignments": [
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "길이 네 갈래로 갈라지는 사거리. 가로등 하나가 깜빡인다.",
              "젖은 바닥에 불빛이 길게 번져 있다.",
              "사거리 한가운데에 노인(70대)이 회색 외투 차림으로 눈을 감은 채 옆으로 누워 있다. 곁에 지팡이가 떨어져 있다."
            ],
            "visual_inferences": [
              "fixed_element old_man_side_lying_posture: overall physical posture remains in an unconscious, inactive state.",
              "fixed_element wet_intersection_surface: the damp pavement displays an elongated, spread-out light reflection rendered in a restrained, slightly desaturated color tone.",
              "The steep oblique overhead angle makes all four diverging roads geometrically readable."
            ],
            "creative_decisions": [
              "Placing the figure and the cane clearly separated to enhance readability from the wide high-angle view.",
              "Positioning the long streetlight reflection in the lower-left background to create a visual counterweight to the character in the midground."
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [
              "fsc_001",
              "fsc_002"
            ],
            "reference_phrase_kinds": [
              "character"
            ],
            "owned_object_usage": [],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "2b18cad399c13bda",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "05aedf8fac245e55",
              "owned_usage_hash": "4f53cda18c2baa0c",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": -1,
        "dependency_reason": "No prior visual scene established in the provided context for dependent background continuity.",
        "_shot_index": 1,
        "visible_entities": [
          "L02",
          "C03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 2,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "wide",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Pause the crane at its widest high, steeply oblique view so the four diverging roads remain readable around the intersection center. Place 노인's side-lying figure slightly off center and the fallen cane nearby but clearly separated, while the elongated streetlight reflection occupies a different portion of the wet ground; his closed face stays turned away from any lens address.",
            "lighting_mood": "The flickering streetlight creates intermittent illumination and a long reflected spread across the wet intersection, rendered in restrained, slightly desaturated tones.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": {
              "reason": "required_background_position",
              "constraints": [
                {
                  "constraint_id": "fsc_001",
                  "target_kind": "background",
                  "target_id": "",
                  "label": "streetlight reflection on wet ground",
                  "screen_zone": "lower_left",
                  "depth_plane": "background",
                  "gesture_action": "none",
                  "gesture_target_label": ""
                },
                {
                  "constraint_id": "fsc_002",
                  "target_kind": "character",
                  "target_id": "C03",
                  "label": "노인",
                  "screen_zone": "middle_center",
                  "depth_plane": "midground",
                  "gesture_action": "none",
                  "gesture_target_label": ""
                }
              ]
            },
            "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": [
              "L02",
              "C03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": true,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "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"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "old_man_side_lying_posture",
                "element_type": "character_state",
                "character_name": "노인",
                "description": "An elderly Korean man wearing a grey coat is lying still on his side on the ground. His eyes are closed, and his overall physical posture remains in an unconscious, inactive state.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "element_scope": "full",
                "source_facts": [
                  "노인(70대)이 회색 외투 차림으로 눈을 감은 채 옆으로 누워 있다.",
                  "Shot 1: lying curled on side, gaze=closed_eyes, state=unconscious",
                  "Shot 3: lying still on side, gaze=closed_eyes, state=unconscious"
                ],
                "visual_inferences": [
                  "His physical body maintains a consistent side-lying position on the wet pavement, defining his overall volume and shape regardless of the viewing angle."
                ],
                "creative_decisions": [
                  "Keeping the old man's inactive posture and grey coat consistent across both the extreme high angle and the low ground angle without detailing localized facial sub-regions that only appear in one shot."
                ],
                "confidence": "high"
              },
              {
                "element_id": "wet_intersection_surface",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A wet intersection road surface that reflects intermittent illumination from a nearby streetlight. The damp pavement displays an elongated, spread-out light reflection rendered in a restrained, slightly desaturated color tone.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "element_scope": "full",
                "source_facts": [
                  "젖은 바닥에 불빛이 길게 번져 있다.",
                  "Shot 1: a long reflected spread across the wet intersection, rendered in restrained, slightly desaturated tones.",
                  "Shot 3: the intersection retains the established intermittent streetlight illumination and restrained color."
                ],
                "visual_inferences": [
                  "The constant dampness of the asphalt creates a distinct, continuous reflective surface for the flickering street lighting."
                ],
                "creative_decisions": [
                  "Maintaining the moody, desaturated visual tone of the wet ground and the specific elongated shape of the light reflection to anchor the nighttime 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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [],
            "forbidden_refs": [],
            "readiness_policy": "not_applicable",
            "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"
            ]
          },
          "render_contracts": [],
          "_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": "9d6b573d18d0031e"
      },
      {
        "scene_index": 2,
        "heading": "#2. 갈래길 – 저녁",
        "beat_title": "손전등 불빛으로 확인하는 노인의 상태",
        "representative_moment": "연희가 손전등으로 쓰러진 노인의 얼굴을 비추는 순간.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Low angle from the ground looking upward on a three-quarter axis, highlighting the contrast between the concentrated flashlight beam and the moody, desaturated wet background.",
            "t2i_prompt": "Photorealistic cinematic still. C02O02 in a yellow raincoat, a Korean woman in her 20s with a natural dark neat hairstyle, positions herself in the upper-right midground at a three-quarter angle from the left, looking toward the elderly man's face. In the same frame, C03O03 in a grey coat, an elderly Korean man with grey hair and natural facial wrinkles, lies motionless in the lower-left foreground. Captured from a low observer position near the ground looking upward, the composition physically anchors both figures in [L02: a dark wet intersection]. C02O02 braces a P03 portable flashlight downward. The visible beam path extends diagonally to concentrate bright light on C03O03's face. C03O03 is lying still on his side in left profile, eyes closed, his overall physical posture remaining in an unconscious, inactive state. A cane rests on the pavement, its side partially visible beyond C03O03 without intersecting the flashlight beam. The damp intersection road surface around them displays an elongated, spread-out light reflection rendered in a restrained, slightly desaturated color tone, retaining the ambient illumination of a nearby streetlight.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "연희가 손전등을 켜서 노인의 얼굴 쪽을 조심스럽게 비춘다.",
              "노인(70대)이 회색 외투 차림으로 눈을 감은 채 옆으로 누워 있다. 곁에 지팡이가 떨어져 있다.",
              "Shot 3: 손전등을 든 연희가 빛을 아래로 향한 자세. 빛줄기가 바닥에 누운 노인의 얼굴을 비춘다."
            ],
            "visual_inferences": [
              "fixed_element old_man_side_lying_posture: C03 lying still on his side, unconscious.",
              "fixed_element wet_intersection_surface: damp pavement with elongated reflections.",
              "Low camera angle places the lying man in the foreground and the standing woman leaning down in the midground, fulfilling the spatial geometry."
            ],
            "creative_decisions": [
              "Emphasizing the diagonal beam from the P03 flashlight to create a strong visual line between C02 and C03's face.",
              "Keeping the ambient streetlight reflection desaturated and restrained so the flashlight remains the primary focal light source."
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [
              "fsc_001",
              "fsc_002"
            ],
            "reference_phrase_kinds": [
              "character"
            ],
            "owned_object_usage": [],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "4297c970902898e4",
              "owned_hash": "e3b0c44298fc1c14",
              "camera_direction_hash": "0c497bbedcd271fe",
              "owned_usage_hash": "4f53cda18c2baa0c",
              "validator": "scene_detail_owned_objects.v1",
              "violations": []
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 2,
        "dependency_reason": "S2_Shot1의 젖은 사거리 바닥 상태와 쓰러진 노인의 위치 및 자세(fixed_elements)를 유지하기 위함.",
        "_shot_index": 3,
        "visible_entities": [
          "L02",
          "C02",
          "C03",
          "P03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 2,
            "shot_index": 3
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From a low position beside 노인's head, look upward on a three-quarter axis so 연희 occupies the upper-right portion while 노인's illuminated face remains in the lower-left foreground. 연희 leans carefully into the flashlight's downward aim, her gaze fixed on 노인's face, and the visible beam path joins her hand to him without obscuring either expression.",
            "lighting_mood": "The switched-on flashlight concentrates light on 노인's face while the intersection retains the established intermittent streetlight illumination and restrained color.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": {
              "reason": "looks_to_anchor",
              "constraints": [
                {
                  "constraint_id": "fsc_001",
                  "target_kind": "character",
                  "target_id": "C02",
                  "label": "연희",
                  "screen_zone": "upper_right",
                  "depth_plane": "midground",
                  "gesture_action": "looks_toward",
                  "gesture_target_label": "노인의 얼굴"
                },
                {
                  "constraint_id": "fsc_002",
                  "target_kind": "character",
                  "target_id": "C03",
                  "label": "노인",
                  "screen_zone": "lower_left",
                  "depth_plane": "foreground",
                  "gesture_action": "none",
                  "gesture_target_label": ""
                }
              ]
            },
            "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": [
              "L02",
              "C02",
              "C03",
              "P03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              },
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": true,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "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"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "old_man_side_lying_posture",
                "element_type": "character_state",
                "character_name": "노인",
                "description": "An elderly Korean man wearing a grey coat is lying still on his side on the ground. His eyes are closed, and his overall physical posture remains in an unconscious, inactive state.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "element_scope": "full",
                "source_facts": [
                  "노인(70대)이 회색 외투 차림으로 눈을 감은 채 옆으로 누워 있다.",
                  "Shot 1: lying curled on side, gaze=closed_eyes, state=unconscious",
                  "Shot 3: lying still on side, gaze=closed_eyes, state=unconscious"
                ],
                "visual_inferences": [
                  "His physical body maintains a consistent side-lying position on the wet pavement, defining his overall volume and shape regardless of the viewing angle."
                ],
                "creative_decisions": [
                  "Keeping the old man's inactive posture and grey coat consistent across both the extreme high angle and the low ground angle without detailing localized facial sub-regions that only appear in one shot."
                ],
                "confidence": "high"
              },
              {
                "element_id": "wet_intersection_surface",
                "element_type": "environment_state",
                "character_name": "",
                "description": "A wet intersection road surface that reflects intermittent illumination from a nearby streetlight. The damp pavement displays an elongated, spread-out light reflection rendered in a restrained, slightly desaturated color tone.",
                "applies_to_shots": [
                  1,
                  3
                ],
                "element_scope": "full",
                "source_facts": [
                  "젖은 바닥에 불빛이 길게 번져 있다.",
                  "Shot 1: a long reflected spread across the wet intersection, rendered in restrained, slightly desaturated tones.",
                  "Shot 3: the intersection retains the established intermittent streetlight illumination and restrained color."
                ],
                "visual_inferences": [
                  "The constant dampness of the asphalt creates a distinct, continuous reflective surface for the flickering street lighting."
                ],
                "creative_decisions": [
                  "Maintaining the moody, desaturated visual tone of the wet ground and the specific elongated shape of the light reflection to anchor the nighttime atmosphere."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 2,
                "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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O02",
                "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"
            ]
          },
          "render_contracts": [],
          "_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": "eb8a02596c42ad1d"
      },
      {
        "scene_index": 3,
        "heading": "#3. 정비소 안 – 밤",
        "beat_title": "노인을 보살피는 민수",
        "representative_moment": "바닥에 밀어둔 작업대 앞, 민수(C01)가 담요 덮인 노인(C03) 곁에 쪼그려 앉아 상태를 살피고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Waist-height medium wide shot angled downward, cool and desaturated low-key lighting",
            "t2i_prompt": "Photorealistic cinematic still. [L01: The interior of the narrow bicycle workshop, illuminated by overhead fluorescent light casting a restrained, slightly desaturated cool glow with modest low-key contrast and deep shadows in the periphery.] Shot from a waist-height downward angle, the cleared floor occupies the lower frame. C03O03 in a grey coat, an elderly Korean man in his 70s with greying hair and natural wrinkles, in left profile, lying unconscious and limp on the floor along the lower-left, with eyes closed, his body covered by a blanket. C01O01 in a navy worker uniform, a middle-aged Korean man in his 40s with short dark hair, at three-quarter angle from the right, crouched close on the floor beside the blanket at the lower-right, his eyes fixed on the closed face of C03O03. A displaced workbench sits obliquely behind the two figures, anchoring the cleared space in front of it.",
            "outfit_assignments": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              },
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "source_facts": [
              "좁은 자전거 정비소 내부 (Narrow bicycle workshop interior)",
              "작업대를 한쪽으로 밀어 자리를 냈다 (Workbench moved aside to clear floor space)",
              "형광등 불빛 아래 (Under fluorescent light)",
              "노인이 담요를 덮고 눈을 감은 채 누워 있다 (Elderly man lying with eyes closed, covered by blanket)",
              "민수가 노인 곁에 쪼그려 앉아 있다 (Min-su crouched beside the elderly man)"
            ],
            "visual_inferences": [
              "fixed_element workshop_fluorescent_lighting: cool color temperature, heavily shadowed peripheral areas",
              "Waist-height downward angle places the cleared floor and figures naturally in the lower half of the frame",
              "C03 is unconscious and limp, in left profile, while C01 is in three-quarter right angle"
            ],
            "creative_decisions": [
              "Used wide framing to show both figures fully within the cleared floor space, adhering to the no body-part close-up rule.",
              "Positioned the displaced workbench directly behind the figures to visually explain the cleared floor in the foreground without changing the prior room layout."
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [],
            "reference_phrase_kinds": [
              "character",
              "background"
            ],
            "owned_object_usage": [
              {
                "owned_token": "blanket",
                "usage_kind": "anchor",
                "source_phrase": "covered by a blanket"
              },
              {
                "owned_token": "door",
                "usage_kind": "absent",
                "source_phrase": ""
              },
              {
                "owned_token": "fluorescent light",
                "usage_kind": "anchor",
                "source_phrase": "illuminated by overhead fluorescent light"
              },
              {
                "owned_token": "workbench",
                "usage_kind": "anchor",
                "source_phrase": "A displaced workbench sits obliquely behind the two figures"
              }
            ],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "52608d2d3770c524",
              "owned_hash": "55f55016e10bbff9",
              "camera_direction_hash": "cdfaf87b396cb139",
              "owned_usage_hash": "21cdcd821e5aba54",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "blanket",
                  "violating_phrase": "covered by a blanket",
                  "reason": "The blanket is depicted as covering the character, changing its physical state, which is permitted because it is explicitly required by the shot intent ('담요 덮인 노인').",
                  "verdict": "allowed_visual_state_change"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "illuminated by overhead fluorescent light",
                  "reason": "The fluorescent light is used as an environmental light source to guide the lighting, which is a valid anchor reference.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "workbench",
                  "violating_phrase": "A displaced workbench sits obliquely behind the two figures",
                  "reason": "The workbench is referenced solely to anchor the spatial layout and composition of the shot, consistent with the producer's declaration.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 1,
        "dependency_reason": "S1_Shot1 의 배경(정비소 내부)과 시각적 일관성 유지 (exact_background)",
        "_shot_index": 1,
        "visible_entities": [
          "L01",
          "C01",
          "C03"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 3,
            "shot_index": 1
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "wide",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "From waist height at medium distance, angle gently downward from 민수's three-quarter side, placing the blanket-covered 노인 along the lower-left floor and 민수 crouched close at lower right. The displaced workbench remains behind them with enough surrounding floor visible to explain the cleared space; 민수 bends toward 노인 and watches his closed face in tense silence.",
            "lighting_mood": "The workshop's fluorescent illumination provides restrained, slightly desaturated light over the cleared floor with modest low-key contrast.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": null,
            "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": [
              "L01",
              "C01",
              "C03"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C01",
                "outlook_id": "O01"
              },
              {
                "character_id": "C03",
                "outlook_id": "O03"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": false,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "L01B04",
            "reference_usage": "exact_background",
            "owned_objects": [
              "blanket",
              "door",
              "fluorescent light",
              "workbench"
            ],
            "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",
              "if focusing on an owned object, declare its reference-kind via the reference_phrase_kinds sidecar (producer contract)"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "workshop_fluorescent_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the narrow bicycle workshop is illuminated by overhead fluorescent lighting. The light is restrained and slightly desaturated, casting a cool, utilitarian glow with modest low-key contrast. Deep shadows fill the peripheral areas, emphasizing the stark difference between the illuminated interior and the pitch-black night outside.",
                "applies_to_shots": [
                  1,
                  2
                ],
                "element_scope": "full",
                "source_facts": [
                  "좁은 자전거 정비소 내부 (Narrow bicycle workshop interior)",
                  "형광등 불빛 아래 (Under fluorescent light)",
                  "The workshop's fluorescent illumination provides restrained, slightly desaturated light",
                  "Interior fluorescent illumination outlines 연희 against the explicitly dark night alley"
                ],
                "visual_inferences": [
                  "The fluorescent light has a cool color temperature, giving the indoor space a slightly pale, industrial look.",
                  "The corners of the room not directly under the light remain heavily shadowed."
                ],
                "creative_decisions": [
                  "Maintained a stark contrast between the steady, cool interior lighting and the dark exterior to heighten the sense of isolation and anxious waiting."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 1,
                "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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "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": "background",
                "id": "L01B04",
                "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"
            ]
          },
          "render_contracts": [],
          "_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": "75d8882f13c3095a"
      },
      {
        "scene_index": 3,
        "heading": "#3. 정비소 안 – 밤",
        "beat_title": "기다림과 위로",
        "representative_moment": "연희가 문가에 서서 손전등을 든 채 어두운 골목 밖을 내다보고 있다.",
        "t2i_variations": [
          {
            "variant_label": "var_1",
            "camera_effect": "Medium shot at chest height from the interior side, capturing the contrast between the cool fluorescent interior and the dark alley.",
            "t2i_prompt": "Photorealistic cinematic still. C02O02 in a yellow raincoat, an Asian woman in her 20s with natural dark hair, stands in the middle-left midground, inclining her upper body and looking toward the dark alley outside, while the open doorway and dark alley occupy the middle-right background. Captured at chest height from the interior side, the figure is seen in right profile, gazing off-screen. One hand grips a flashlight mid-toggle, its front end angled toward the doorway rather than the camera. Lit by the overhead fluorescent light that casts a cool, utilitarian glow with modest low-key contrast across the L01B04 space, the interior illumination strongly outlines her figure against the pitch-black night outside. Deep shadows fill the peripheral areas, and the workshop door frame borders the right edge, reinforcing her strong sightline toward the exterior.",
            "outfit_assignments": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              }
            ],
            "source_facts": [
              "연희는 문가에 서서 손전등을 껐다 켰다 하며 골목 쪽을 내다본다.",
              "The interior of the narrow bicycle workshop is illuminated by overhead fluorescent lighting."
            ],
            "visual_inferences": [
              "fixed_element workshop_fluorescent_lighting: cool, utilitarian glow with modest low-key contrast.",
              "C02 is in right profile, viewed from a chest-height camera inside the workshop.",
              "The action of switching the flashlight is frozen mid-toggle to capture a single instant."
            ],
            "creative_decisions": [
              "Medium framing anchors her in the middle-left while dedicating the middle-right to the dark alley, visualizing her anxious waiting.",
              "Backlighting her figure with the interior fluorescent light against the dark exterior emphasizes the threshold and depth."
            ],
            "confidence": "high",
            "applied_frame_spatial_constraint_ids": [
              "fsc_001",
              "fsc_002"
            ],
            "reference_phrase_kinds": [
              "character",
              "background"
            ],
            "owned_object_usage": [
              {
                "owned_token": "blanket",
                "usage_kind": "absent",
                "source_phrase": ""
              },
              {
                "owned_token": "door",
                "usage_kind": "anchor",
                "source_phrase": "the workshop door frame borders the right edge"
              },
              {
                "owned_token": "fluorescent light",
                "usage_kind": "anchor",
                "source_phrase": "Lit by the overhead fluorescent light"
              },
              {
                "owned_token": "workbench",
                "usage_kind": "absent",
                "source_phrase": ""
              }
            ],
            "owned_validation": {
              "schema_version": 2,
              "t2i_prompt_hash": "032c224bbee01eac",
              "owned_hash": "55f55016e10bbff9",
              "camera_direction_hash": "6115a23187b4484e",
              "owned_usage_hash": "745e9bdd0ef12a3d",
              "validator": "scene_detail_owned_objects.v1",
              "violations": [
                {
                  "owned_object": "door",
                  "violating_phrase": "the workshop door frame borders the right edge",
                  "reason": "The prompt references the door frame as a composition border and anchor without redrawing or altering the door, matching the producer's anchor declaration.",
                  "verdict": "anchor_reference"
                },
                {
                  "owned_object": "fluorescent light",
                  "violating_phrase": "Lit by the overhead fluorescent light",
                  "reason": "The prompt uses the fluorescent light as a light source to establish the scene's lighting, which is an anchor reference that matches the producer's declaration.",
                  "verdict": "anchor_reference"
                }
              ]
            }
          }
        ],
        "scene_type": "normal",
        "dependent_scene_index": 1,
        "dependency_reason": "Same location (L01B04) at night, continuing the lighting mood and spatial layout from previous interior shots.",
        "_shot_index": 2,
        "visible_entities": [
          "L01",
          "C02"
        ],
        "render_prompt_card": {
          "schema_version": 1,
          "shot_key": {
            "scene_index": 3,
            "shot_index": 2
          },
          "render_strategy": {
            "mode": "direct",
            "primary_subject": "",
            "framing_scale": "medium",
            "moment_lock": "single still moment from the selected shot only",
            "camera_direction": "Hold at chest height just inside the doorway, offset to 연희's interior side, with her profile in the middle-left and the open doorway continuing across the right side along her sightline. She inclines her head and upper body toward the dark alley while one hand holds the flashlight mid-toggle, keeping her attention outside rather than toward the camera.",
            "lighting_mood": "Interior fluorescent illumination outlines 연희 against the explicitly dark night alley, with the flashlight's intermittent switching adding brief localized variation.",
            "perception_mode": "direct",
            "spatial_consistency": {
              "camera_frame_rule": {
                "applies_when": "camera_direction expresses a vertical camera height or viewpoint position 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, wide, insert} from `shot_staging.framing_scale` enum (render_strategy.framing_scale, production SOT). LLM consumes the enum only; keyword classification is forbidden.",
                "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"
                  ],
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "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",
                  "subject_reference_policy_cross_ref": "see id_policy.subject_reference_policy (subject_reference_policy SOT — policy enum 에 따라 ID/outlook 사용)"
                },
                "self_check_steps": [
                  "read framing_scale enum from render_strategy.framing_scale (do NOT infer 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."
            },
            "frame_spatial_contract": {
              "reason": "looks_to_anchor",
              "constraints": [
                {
                  "constraint_id": "fsc_001",
                  "target_kind": "background",
                  "target_id": "",
                  "label": "open doorway and dark alley",
                  "screen_zone": "middle_right",
                  "depth_plane": "background",
                  "gesture_action": "none",
                  "gesture_target_label": ""
                },
                {
                  "constraint_id": "fsc_002",
                  "target_kind": "character",
                  "target_id": "C02",
                  "label": "연희",
                  "screen_zone": "middle_left",
                  "depth_plane": "midground",
                  "gesture_action": "looks_toward",
                  "gesture_target_label": "dark alley outside"
                }
              ]
            },
            "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": [
              "L01",
              "C02"
            ],
            "allowed_outlook_pairs": [
              {
                "character_id": "C02",
                "outlook_id": "O02"
              }
            ],
            "must_use_composite_character_ids": true,
            "common_noun_required_when": [
              "a reproduced face inside any declared reproduction surface",
              "unregistered extra"
            ],
            "id_use_required_when": [
              "a physical photo/poster/document/picture-frame/map/key prop appearing in the scene — use its P## ID and preserve canonical content from entity_canon"
            ],
            "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"
            },
            "reproduction_surface_rule": {
              "applies": false,
              "id_use": "forbidden — generic descriptor with demographic only",
              "rationale_summary": "C##O## 은 얼굴 reference 이미지를 원본 해상도로 inject 하므로 사진/화면/반사 표면 안 얼굴이 표면 밖 실물 크기로 합성됨. 이 rule 은 표면 안 얼굴 (face) 에만 적용 — 물리적 사진/액자/문서 prop 자체는 P## ID 보존 (Patch A)."
            },
            "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"
            },
            "subject_reference_policy": [],
            "constraints": [
              "ID format for visible subjects (C## bare, C##O## composite IDs, or common-noun descriptor) is determined per-subject by the id_policy per-subject policy array — see constraints[2] below",
              "do not use C##O## for a reproduced face inside any element flagged by id_policy.reproduction_surface_rule.applies (declared reproduction surface) — use a generic descriptor with demographic instead. NOTE: the physical photo/poster/document/picture-frame/map/key prop itself MUST use its P## ID — the generic-descriptor rule applies only to a face reproduction, not to the prop entity.",
              "per-subject identity reference policy is provided in id_policy.subject_reference_policy[] — apply each subject's policy when emitting references: (a) id_and_outlook_required ⇒ subject must use C##O## composite ID; (b) base_id_required ⇒ subject must use bare C## only (no outlook); (c) generic_descriptor_allowed ⇒ subject must NOT use C## or C##O##, render with a common/demographic descriptor only. omitted subjects default to id_and_outlook_required",
              "when an ID is required for a subject (policy = id_and_outlook_required or base_id_required) and a C##O## (or C##) is introduced 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. does not apply to generic_descriptor_allowed subjects (no ID emitted)",
              "when an ID is required (policy = id_and_outlook_required or base_id_required), 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). does not apply to generic_descriptor_allowed subjects — those use a common/demographic descriptor with no C##/C##O##"
            ]
          },
          "background_binding": {
            "mode": "background_ref_attached",
            "bg_id": "L01B04",
            "reference_usage": "exact_background",
            "owned_objects": [
              "blanket",
              "door",
              "fluorescent light",
              "workbench"
            ],
            "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",
              "if focusing on an owned object, declare its reference-kind via the reference_phrase_kinds sidecar (producer contract)"
            ]
          },
          "continuity_elements_used": {
            "fixed_elements": [
              {
                "element_id": "workshop_fluorescent_lighting",
                "element_type": "environment_state",
                "character_name": "",
                "description": "The interior of the narrow bicycle workshop is illuminated by overhead fluorescent lighting. The light is restrained and slightly desaturated, casting a cool, utilitarian glow with modest low-key contrast. Deep shadows fill the peripheral areas, emphasizing the stark difference between the illuminated interior and the pitch-black night outside.",
                "applies_to_shots": [
                  1,
                  2
                ],
                "element_scope": "full",
                "source_facts": [
                  "좁은 자전거 정비소 내부 (Narrow bicycle workshop interior)",
                  "형광등 불빛 아래 (Under fluorescent light)",
                  "The workshop's fluorescent illumination provides restrained, slightly desaturated light",
                  "Interior fluorescent illumination outlines 연희 against the explicitly dark night alley"
                ],
                "visual_inferences": [
                  "The fluorescent light has a cool color temperature, giving the indoor space a slightly pale, industrial look.",
                  "The corners of the room not directly under the light remain heavily shadowed."
                ],
                "creative_decisions": [
                  "Maintained a stark contrast between the steady, cool interior lighting and the dark exterior to heighten the sense of isolation and anxious waiting."
                ],
                "confidence": "high"
              }
            ],
            "previous_shot_refs": [
              {
                "scene_index": 1,
                "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'"
                ],
                "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy applies per-subject; policy enum (id_and_outlook_required / base_id_required / generic_descriptor_allowed) determines C##/C##O## use",
                "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. third-person full body and close-up of the same character must not be combined in a single prompt.",
              "third_person_handling": "describe persons with full or partial body in frame; single-camera consistency forbids combining a partial close-up and the same character's full body in one prompt",
              "close_up_handling": "an isolated framed area of a single subject must not coexist with that subject's full-body description in the same prompt",
              "focus_on_is_focus_area_not_view_switch": "any framing-intent wording designates the area shown by the single camera position; it does not switch the view",
              "subject_reference_policy_cross_ref": "id_policy.subject_reference_policy — subjects with policy = 'base_id_required' or 'generic_descriptor_allowed' must not use outlook reference (C##O## form); additionally, subjects with policy = 'generic_descriptor_allowed' must not use bare C## either — render with a common/demographic descriptor only",
              "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 — third-person full body and close-up of the same character must not be combined in a single shot. any framing-intent wording designates the area shown by the single camera position, not a view switch (id_policy.subject_reference_policy applies per-subject)",
              "props held by characters face one direction only — toward camera OR toward character, never both"
            ]
          },
          "asset_requirements": {
            "required_refs": [
              {
                "kind": "character_outlook",
                "id": "C02O02",
                "policy": "required"
              },
              {
                "kind": "background",
                "id": "L01B04",
                "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"
            ]
          },
          "render_contracts": [],
          "_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": "a21257f1e72e95c4"
      }
    ],
    "consumed_bg_catalog_hash": "401bfa83feca7d6b",
    "consumed_shot_binding_hash": "4bf36dd946769c30"
  },
  "step_id": "scene_detail",
  "run_id": "86c3511d-040c-4066-8606-6c58b7a6204a",
  "resolved_model": "gemini-pro",
  "updated_at": "2026-08-24T19:32:39.733453+00:00",
  "project_config_snapshot": {}
}