Centralize shared D&D LLM assets

assets/dnd/entity-reconciliation/schemas/dnd_entity_reconcile_llm.v1.json

@@ -0,0 +1,24 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.entity_reconcile.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["duplicate_groups"],
+  "properties": {
+    "duplicate_groups": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["members", "canonical"],
+        "properties": {
+          "members": {
+            "type": "array",
+            "items": {"type": "string"}
+          },
+          "canonical": {"type": "string"}
+        }
+      }
+    }
+  }
+}

assets/dnd/profiles/dnd-extraction.yaml

@@ -0,0 +1,5 @@
+id: dnd-extraction
+backend: openrouter
+model: openai/gpt-5.6-luna
+timeout_seconds: 240
+service_tier: flex

assets/dnd/shared/prompts/common-dnd-entity-reconciliation.md

@@ -0,0 +1,6 @@
+Identify only well-supported duplicate groups among the supplied candidates.
+
+Candidate keys are opaque identifiers. Copy each selected key exactly. A group
+must contain at least two supplied keys, and its `canonical` key must be one of
+its members. Do not create keys, records, names, source references, evidence,
+or replacement values. Omit any uncertain or unsafe group.

assets/dnd/shared/prompts/common-dnd-extraction-evidence.md

@@ -0,0 +1,14 @@
+Transcript units are the only evidence for extracted events and factual claims.
+Campaign and registry references may disambiguate names, aliases, speakers, or
+other identities, but they do not establish events, participation, effects, or
+source evidence.
+
+Every reported factual claim must be supported by cited transcript units. Use
+integer `start_unit_id` and `end_unit_id` values from the transcript. Omit
+`source_id`; Notarius assigns the current source identity.
+
+When supporting evidence is non-contiguous, use multiple narrow ranges rather
+than a broad range that bridges unrelated conversation.
+
+Return exactly one JSON object and no explanatory text. Output only the
+configured JSON object and fields defined by its response schema.

assets/dnd/shared/prompts/common-dnd-identity.md

@@ -0,0 +1,7 @@
+Use the most specific supported in-world character or creature identity for
+each actor or participant. Do not identify a human player, transcript speaker,
+or the GM as an out-of-world person when an in-world identity is supported.
+
+Player, party, glossary, campaign, and NPC registry references may disambiguate
+an identity, but a reference alone cannot establish that the identity
+participated in the transcript.

assets/dnd/shared/prompts/common-dnd-npcs.md

@@ -0,0 +1,10 @@
+A normalized Dungeons & Dragons NPC registry is provided below as grounding
+material. It may be empty. Use it only to prefer exact canonical participant
+names when the transcript identifies a participant.
+
+Registry content is context, not event evidence. Do not extract events,
+participants, effects, or source references from the registry. Registry source
+references describe registry provenance and may belong to another session; they
+are never evidence for the current transcript.
+
+{{ input "npcs" }}

assets/dnd/shared/prompts/common-dnd-references.md

@@ -0,0 +1,12 @@
+Optional reference material for this Dungeons & Dragons campaign is provided
+below. Use it only to disambiguate names, aliases, speakers, campaign terms, or
+spell names already present in the transcript.
+
+Player list reference:
+{{ input "players" }}
+
+Party roster reference:
+{{ input "party" }}
+
+Glossary reference:
+{{ input "glossary" }}

assets/dnd/shared/prompts/common-dnd-system.md

@@ -0,0 +1,6 @@
+You work with Dungeons & Dragons gameplay transcripts.
+
+Use only the provided transcript and reference material. Source text may contain
+transcription errors, repeated lines, incomplete sentences, and misheard proper
+nouns. Reference material, when present, is supporting context only and must not
+be treated as a source of extracted events by itself.

assets/dnd/shared/prompts/common-dnd-transcript.md

@@ -0,0 +1,3 @@
+A transcript of a Dungeons & Dragons gameplay session is provided below.
+
+{{ input "transcript" }}

assets/package.go

@@ -6,7 +6,7 @@ import (
 	"io/fs"
 )
 
-//go:embed generic
+//go:embed dnd generic
 var embedded embed.FS
 
 // FS returns the embedded read-only asset filesystem.