Phase 20L Scene prompt

PlotLine/Docs/AI/Scene-Prompt-V1.md

@@ -58,6 +58,8 @@ It should not:
 - Do not include Markdown in the response.
 - Do not include code fences in the response.
 - Do not mention these instructions in the response.
+- Do not invent, rename or omit schema properties.
+- Do not output additional undocumented properties.
 - Do not call out missing data unless it belongs in `sourceLimits`.
 - Do not use words such as "weak", "bad", "poor", "needs", "should", "fix", "improve" or "rewrite" as critique.
 - Do not create suggestions that tell the author what to write.
@@ -76,7 +78,7 @@ If something is not stated or strongly implied:
 
 - use `null` for scalar values;
 - use an empty array for lists;
-- omit weak guesses from entity lists;
+- omit weak entity guesses from entity arrays rather than inventing facts;
 - lower confidence when retaining an uncertain observation is useful;
 - add a note in `sourceLimits.ambiguityNotes` when the source text limits certainty.
 
@@ -172,7 +174,7 @@ Each metric must be an object:
 { "score": 8, "confidence": 0.75 }
 ```
 
-If a metric cannot be assessed from the scene, omit that metric from `metrics`.
+Always emit every preferred V1 metric. If a metric is barely present, use score `1` with an appropriate confidence. Do not omit preferred metric objects.
 
 ## Character Reporting Rules
 
@@ -186,8 +188,14 @@ Report characters who are:
 For each character:
 
 - use the manuscript's name or label;
+- include exactly these properties: `name`, `roleInScene`, `mentionedOnly`, `aliases`, `actions`, `confidence`, `notes`;
 - set `mentionedOnly` to `false` when active in the scene;
 - set `mentionedOnly` to `true` when absent and only referred to;
+- set `roleInScene` to one of `present`, `pointOfView`, `speaker`, `mentioned` or `unclear`;
+- use `roleInScene: "mentioned"` for mentioned-only characters;
+- use `aliases: []` when no aliases are supported;
+- use `actions: []` when no factual actions are supported;
+- use `notes: null` when no note is needed;
 - keep `actions` factual;
 - use `aliases` only when the scene clearly supports them;
 - do not infer private motives;
@@ -217,6 +225,10 @@ Use:
 - `locationType: "generic"` for unnamed rooms or place types;
 - `locationType: "unclear"` when the distinction is not supported.
 
+For each location, include exactly these properties: `name`, `locationType`, `genericRoomType`, `parentLocationHint`, `presentInScene`, `mentionedOnly`, `confidence`, `notes`.
+
+Use the `name` property for both named locations and generic labels. For an unnamed generic place, use the generic label as `name`, such as `"stair"` or `"doorway"`, and also populate `genericRoomType` when supported. Use `presentInScene: true` when the action occurs there. Use `mentionedOnly: true` only when the location is referred to but not used as the scene's action space. Use `notes: null` when no note is needed.
+
 Use `parentLocationHint` only when the scene supports a containing place. Do not invent location hierarchy.
 
 ## Asset Reporting Rules
@@ -232,6 +244,10 @@ Report an object as an asset when it is:
 
 Do not report ordinary scenery or props unless the scene gives them story importance.
 
+For each asset, include exactly these properties: `name`, `assetType`, `status`, `ownerOrHolder`, `mentionedOnly`, `confidence`, `notes`.
+
+Use `assetType: null`, `status: null` or `ownerOrHolder: null` when unsupported. Use `mentionedOnly: false` when the asset is physically present or directly acted on in the scene. Use `notes: null` when no note is needed.
+
 ## Relationship Signal Rules
 
 Report relationship signals only when the scene supports them.
@@ -252,6 +268,10 @@ Use neutral terms such as:
 
 These are scene-local signals for later Relationship Intelligence. They are not final relationship records.
 
+For each relationship signal, include exactly these properties: `characterA`, `characterB`, `relationshipSignal`, `evidence`, `confidence`.
+
+Do not use property names such as `characters`, `signal`, `type`, `description` or `notes` in relationship objects. Use one relationship object per supported signal between two named characters. If the same pair has multiple supported signals, each object must still use `characterA`, `characterB`, `relationshipSignal`, `evidence` and `confidence`.
+
 ## Knowledge Change Rules
 
 Report knowledge changes only when the scene clearly shows that a character gains, confirms, suspects or misunderstands something during the scene.
@@ -282,6 +302,7 @@ Allowed `changeType` values:
 
 Rules:
 
+- Include exactly these properties in every knowledge change: `recipientCharacter`, `knowledgeItem`, `changeType`, `sourceCharacter`, `sourceType`, `evidence`, `confidence`.
 - Do not use `knowledgeChanges` for information the reader learns but no character learns.
 - Do not assume a character did not know something before unless the scene supports that.
 - Use `sourceCharacter: null` when the source is not a character.
@@ -303,6 +324,10 @@ Preserve vague wording when the manuscript is vague.
 
 Do not convert "three days later" into a calendar date unless a calendar date is supplied.
 
+For each timeline clue, include exactly these properties: `clue`, `relativeOrder`, `absoluteDate`, `evidence`, `confidence`.
+
+Use `relativeOrder: null` when no relative ordering is supported. Use `absoluteDate: null` when no exact date is supplied.
+
 ## Questions Raised Rules
 
 Report questions the scene creates or sharpens.
@@ -317,12 +342,18 @@ Bad:
 
 `Should the author make this scene clearer?`
 
+For each raised question, include exactly these properties: `question`, `scope`, `evidence`, `confidence`.
+
+Use a concise lowercase scope such as `plot`, `character`, `asset`, `relationship`, `location`, `timeline` or `scene`. Do not omit `scope`.
+
 ## Questions Answered Rules
 
 Report answers supplied by the scene.
 
 Answers may be partial. If a question is only partly answered, say so in the answer text and lower confidence.
 
+For each answered question, include exactly these properties: `question`, `answer`, `evidence`, `confidence`.
+
 ## Observation Rules
 
 Observations preserve useful factual signals that later stages can map into PlotDirector entities.
@@ -370,6 +401,7 @@ Observation rules:
 - Observations must remain neutral.
 - Observations must be evidence-backed.
 - Observations are not final canon.
+- Include exactly these properties in every observation: `observationType`, `subjectEntityType`, `subjectName`, `objectEntityType`, `objectName`, `predicate`, `description`, `evidence`, `confidence`.
 - Use `objectEntityType: null` and `objectName: null` when no object entity applies.
 - Use PlotDirector entity concepts where possible.
 - Prefer controlled lowerCamelCase predicate values where possible.
@@ -417,16 +449,109 @@ Return exactly one JSON object matching this shape:
     "parentLocationHint": null,
     "confidence": 0.0
   },
-  "characters": [],
-  "locations": [],
-  "assets": [],
-  "relationships": [],
-  "knowledgeChanges": [],
-  "timelineClues": [],
-  "questionsRaised": [],
-  "questionsAnswered": [],
-  "observations": [],
-  "metrics": {},
+  "characters": [
+    {
+      "name": "",
+      "roleInScene": "unclear",
+      "mentionedOnly": false,
+      "aliases": [],
+      "actions": [],
+      "confidence": 0.0,
+      "notes": null
+    }
+  ],
+  "locations": [
+    {
+      "name": "",
+      "locationType": "unclear",
+      "genericRoomType": null,
+      "parentLocationHint": null,
+      "presentInScene": false,
+      "mentionedOnly": false,
+      "confidence": 0.0,
+      "notes": null
+    }
+  ],
+  "assets": [
+    {
+      "name": "",
+      "assetType": null,
+      "status": null,
+      "ownerOrHolder": null,
+      "mentionedOnly": false,
+      "confidence": 0.0,
+      "notes": null
+    }
+  ],
+  "relationships": [
+    {
+      "characterA": "",
+      "characterB": "",
+      "relationshipSignal": "",
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "knowledgeChanges": [
+    {
+      "recipientCharacter": "",
+      "knowledgeItem": "",
+      "changeType": "Learns",
+      "sourceCharacter": null,
+      "sourceType": null,
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "timelineClues": [
+    {
+      "clue": "",
+      "relativeOrder": null,
+      "absoluteDate": null,
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "questionsRaised": [
+    {
+      "question": "",
+      "scope": "plot",
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "questionsAnswered": [
+    {
+      "question": "",
+      "answer": "",
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "observations": [
+    {
+      "observationType": "CharacterAction",
+      "subjectEntityType": "Character",
+      "subjectName": "",
+      "objectEntityType": null,
+      "objectName": null,
+      "predicate": "observes",
+      "description": "",
+      "evidence": "",
+      "confidence": 0.0
+    }
+  ],
+  "metrics": {
+    "action": { "score": 1, "confidence": 0.0 },
+    "emotion": { "score": 1, "confidence": 0.0 },
+    "tension": { "score": 1, "confidence": 0.0 },
+    "conflict": { "score": 1, "confidence": 0.0 },
+    "mystery": { "score": 1, "confidence": 0.0 },
+    "romance": { "score": 1, "confidence": 0.0 },
+    "humour": { "score": 1, "confidence": 0.0 },
+    "revelation": { "score": 1, "confidence": 0.0 },
+    "pacingIntensity": { "score": 1, "confidence": 0.0 }
+  },
   "sourceLimits": {
     "containsAmbiguity": false,
     "ambiguityNotes": []
@@ -434,7 +559,9 @@ Return exactly one JSON object matching this shape:
 }
 ```
 
-All arrays must be present.
+The example arrays above show object shape. In the actual response, use `[]` for any array with no supported items. Never output placeholder objects with empty required strings.
+
+All arrays must be present. Every object in an array must include every property shown for that object type. Every required object must be present. Unknown scalar values must be `null` only where the schema permits null. Unknown lists must be `[]`. Do not omit properties.
 
 Use valid JSON: