{ "type": "object", "properties": { "shots": { "type": "array", "items": { "type": "object", "properties": { "scene_index": {"type": "integer"}, "shot_index": {"type": "integer"}, "framing_scale": { "type": "string", "enum": ["close", "medium", "wide", "insert"], "description": "Primary framing scale of this shot. close = primary subject fills most of the frame. medium = upper body or mid-distance subject with some surrounding context. wide = full body or environment/layout visible. insert = isolated detail without surrounding context. Judge by camera distance and primary subject visibility, not vocabulary." }, "perspective": {"type": "string", "description": "Camera POV: subjective_pov, over_shoulder, observer, omniscient, object_pov, voyeur"}, "pov_character": {"type": "string", "description": "For subjective POV: the character whose eyes we see through (must NOT appear in image). Empty string if not subjective."}, "perception_mode": {"type": "string", "description": "How the scene is perceived: direct (normal vision), hallucination, dream, memory, reflection, through_device (CCTV/phone/binoculars), projection. Affects visual treatment."}, "camera_direction": {"type": "string", "description": "Creative camera placement, framing, physical layout, and composition including POV (2-3 sentences, English)"}, "lighting_mood": {"type": "string", "description": "Lighting technique and color mood (1 sentence, English)"}, "character_angles": { "type": "array", "description": "Camera-relative angle and body pose for each visible character (exclude POV character)", "items": { "type": "object", "properties": { "character": {"type": "string", "description": "Character name (as registered)"}, "angle": {"type": "string", "description": "Camera-relative direction: facing_camera, back_to_camera, profile_left, profile_right, three_quarter_left, three_quarter_right, over_shoulder, looking_away"}, "body_pose": {"type": "string", "description": "Specific body posture in English (2-5 words). Must NOT use 'standing' alone — use action-grounded or state-grounded poses such as 'one foot on pedal', 'leaning against doorframe', 'crouching behind desk', 'slumping into chair', 'mid-stride paused'. See system prompt 'body_pose 다양화' for full guidance."}, "gaze_target": {"type": "string", "description": "Where the character's eyes are looking: another character's name, an object name, 'camera', 'down', 'up', 'distant', 'closed', 'unconscious', 'dead', 'severely_injured'"} }, "required": ["character", "angle", "body_pose", "gaze_target"], "additionalProperties": false } }, "key_bg_elements": { "type": "array", "items": { "type": "object", "properties": { "element": {"type": "string", "description": "Background element name"}, "state": {"type": "string", "description": "State in this shot (open/closed, clean/dirty, on/off, etc.)"}, "orientation": {"type": "string", "description": "Natural-language description tied to directionality_class. For content_surface: which face/side is visible to camera and what is on it. For reflective_surface: what is being reflected and how. For transparent_surface: surface state and what is seen through it. For directional_3d: which side faces camera. For non_directional: empty allowed. content_surface and reflective_surface MUST have a non-empty orientation."}, "camera_use": {"type": "string", "description": "How this element is used in the shot (foreground frame, focal point, light source, etc.)"}, "directionality_class": { "type": "string", "enum": ["content_surface", "reflective_surface", "transparent_surface", "directional_3d", "non_directional"], "description": "Semantic classification of this element. content_surface = thin object that carries content on one face; which face is visible changes the meaning. reflective_surface = object whose surface reflects content; what is reflected determines meaning. transparent_surface = object the camera sees through; surface state and what lies beyond determine meaning. directional_3d = 3D object with multiple faces where the camera-facing side matters. non_directional = texture/surface/ambient element with no directional meaning. Judge by meaning, not by surface vocabulary or specific examples (non-exhaustive examples, do not classify by this list)." } }, "required": ["element", "state", "orientation", "camera_use", "directionality_class"], "additionalProperties": false } }, "frame_spatial_contract": { "oneOf": [ {"type": "null"}, { "type": "object", "properties": { "reason": { "type": "string", "enum": ["movement_direction", "points_to_anchor", "looks_to_anchor", "shared_space_relation", "required_background_position", "primary_subject_isolation"], "description": "Single primary trigger — see system prompt 'Frame Spatial Contract' section." }, "constraints": { "type": "array", "minItems": 1, "maxItems": 3, "items": { "type": "object", "properties": { "target_kind": {"type": "string", "enum": ["character", "prop", "background"]}, "target_id": {"type": "string", "description": "character → C##, prop → P##, background → empty string"}, "label": {"type": "string", "minLength": 1, "description": "Human-readable label"}, "screen_zone": {"type": "string", "enum": [ "upper_left", "upper_center", "upper_right", "middle_left", "middle_center", "middle_right", "lower_left", "lower_center", "lower_right"]}, "depth_plane": {"type": "string", "enum": ["foreground", "midground", "background"]}, "gesture_action": {"type": "string", "enum": [ "none", "points_to", "reaches_for", "looks_toward", "moves_toward"]}, "gesture_target_label": {"type": "string", "description": "non-empty when gesture_action != 'none', empty string when gesture_action == 'none'"} }, "required": ["target_kind", "target_id", "label", "screen_zone", "depth_plane", "gesture_action", "gesture_target_label"], "additionalProperties": false } } }, "required": ["reason", "constraints"], "additionalProperties": false } ], "description": "Opt-in frame-space contract. null when not needed. See system prompt 'Frame Spatial Contract' section for emit gating." }, "subject_reference_policy": { "type": "array", "description": "Per-subject identity reference policy (exceptions-first). Default 'id_and_outlook_required' if subject omitted. Empty array allowed.", "items": { "type": "object", "properties": { "subject_id": { "type": "string", "pattern": "^C\\d{2,3}(?:O\\d{2,3})?$", "description": "Base C## recommended. C##O## form is accepted and normalized to base (outlook context not available in shot_staging input)." }, "policy_type": { "type": "string", "enum": ["identity_reference"], "description": "v1 single value. Other values forbidden (envelope future hook only)." }, "policy": { "type": "string", "enum": [ "id_and_outlook_required", "base_id_required", "generic_descriptor_allowed" ] }, "reason": { "type": "string", "minLength": 1 } }, "required": ["subject_id", "policy_type", "policy", "reason"], "additionalProperties": false } } }, "required": ["scene_index", "shot_index", "framing_scale", "perspective", "pov_character", "perception_mode", "camera_direction", "lighting_mood", "character_angles", "key_bg_elements", "frame_spatial_contract", "subject_reference_policy"], "additionalProperties": false } } }, "required": ["shots"], "additionalProperties": false }