Add D&D NPC extraction and validation

internal/modules/dnd/extract/npcs/assets/prompts/dnd.npcs.yaml

@@ -0,0 +1,36 @@
+id: dnd.npcs
+version: "v1"
+default_profile: gemini-2-flash
+inputs:
+  - name: transcript
+    required: true
+    content_type: application/json
+  - name: players
+    required: false
+    content_type: text/plain
+  - name: party
+    required: false
+    content_type: text/plain
+  - name: glossary
+    required: false
+    content_type: text/plain
+messages:
+  - role: system
+    content_file: ./sharedassets/common-dnd-system.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-transcript.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-references.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./task.md
+  - role: user
+    content_file: ./instructions.md
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_npcs_llm.v1.json
+  repair_attempts: 0

internal/modules/dnd/extract/npcs/assets/prompts/instructions.md

@@ -0,0 +1,25 @@
+Return exactly one JSON object and no explanatory text.
+
+For every NPC record, cite one or more transcript source-unit ranges that
+collectively support the canonical name, every alias, the description, and
+every relationship. Use integer start_unit_id and end_unit_id values from the
+transcript. Do not provide source_id; the extractor assigns it automatically.
+Use narrow ranges when evidence is not contiguous and do not bridge unrelated
+conversation with a broad range.
+
+A canonical name must be the most specific in-world identity supported by the
+transcript. Never use a human player, transcript speaker, or GM name when an
+associated in-world character or creature is identified. Player, party, and
+glossary references may disambiguate identities, but they are not transcript
+evidence and cannot establish that an NPC appeared, acted, or was discussed.
+Do not return a person or entity mentioned only in those references.
+
+Descriptions must be short session records, not biographies, statistics,
+alignment, motivations, or lore inferred from general D&D knowledge. Do not
+summarize every action or follow a participant through unrelated scenes.
+Relationships must be stated or directly demonstrated by cited transcript
+units, not inferred from game lore.
+
+Return aliases and relationships as arrays, including empty arrays when there
+are none. Return only NPC records supported by the transcript and preserve
+observed display spelling.

internal/modules/dnd/extract/npcs/assets/prompts/task.md

@@ -0,0 +1,16 @@
+Extract a concise Dungeons & Dragons non-player-character registry from the
+provided transcript.
+
+Include an in-world non-PC participant when the transcript establishes that it
+appears, acts, speaks, or is materially discussed and gives it a proper name,
+a stable alias or title, or an individually useful distinguishing description.
+
+Exclude human players, transcript speakers, the GM as an out-of-world person,
+player characters identified by the player or party references, incidental or
+hypothetical name drops, corrected transcription mistakes, characters mentioned
+only by reference material, indistinguishable crowds or groups, and temporary
+summoned creatures or spell effects without a persistent individual identity.
+
+Return canonical in-world names rather than player names or transcript speaker
+names. Keep each description concise and limited to facts established by the
+transcript. Include only explicitly supported aliases and relationships.

internal/modules/dnd/extract/npcs/assets/schemas/dnd_npcs_llm.v1.json

@@ -0,0 +1,77 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.npcs.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["npcs"],
+  "properties": {
+    "npcs": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": [
+          "name",
+          "aliases",
+          "description",
+          "relationships",
+          "source_refs"
+        ],
+        "properties": {
+          "name": {
+            "type": "string",
+            "minLength": 1
+          },
+          "aliases": {
+            "type": "array",
+            "items": {
+              "type": "string",
+              "minLength": 1
+            }
+          },
+          "description": {
+            "type": "string",
+            "minLength": 1
+          },
+          "relationships": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["target", "relationship"],
+              "properties": {
+                "target": {
+                  "type": "string",
+                  "minLength": 1
+                },
+                "relationship": {
+                  "type": "string",
+                  "minLength": 1
+                }
+              }
+            }
+          },
+          "source_refs": {
+            "type": "array",
+            "minItems": 1,
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["start_unit_id", "end_unit_id"],
+              "properties": {
+                "start_unit_id": {
+                  "type": "integer",
+                  "minimum": 1
+                },
+                "end_unit_id": {
+                  "type": "integer",
+                  "minimum": 1
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}