Bugfix in the built-in prompt references definition

docs/config.md

@@ -252,15 +252,17 @@ The `generic` chunker accepts:
   `max_units`.
 
 The `dnd/scenes` chunker requires transcript source capabilities, calls the
-configured structured LLM runtime, and does not accept module options.
+configured structured LLM runtime, and does not accept module options. It
+declares optional `roster` and `glossary` references for scene disambiguation.
 
-The `dnd/spells` extractor declares optional text reference slots:
+The `dnd/spells` extractor declares optional reference slots:
 
 - `roster`
 - `glossary`
 
-The extractor uses these references only as supporting disambiguation material;
-spell casts still must be present in the source transcript.
+Both modules accept UTF-8 plain text, Markdown, YAML, or JSON reference files.
+The extractor uses references only as supporting disambiguation material; spell
+casts still must be present in the source transcript.
 
 ## Diagnostics
 

docs/internal/modules.md

@@ -157,10 +157,10 @@ metadata under `artifact_lanes[].metadata.extractor`. Durable artifact payload
 details belong in the
 [D&D spell artifact contract](../integrations/dnd-spell-artifacts.md).
 
-The extractor declares optional `roster` and `glossary` reference slots
-accepting UTF-8 text without narrowing accepted media types. Its prompt frames
-references as supporting disambiguation material only; spell-cast artifacts must
-still be grounded in the source transcript.
+The `dnd/scenes` chunker and `dnd/spells` extractor declare optional `roster`
+and `glossary` reference slots accepting UTF-8 plain text, Markdown, YAML, or
+JSON. Their prompts frame references as supporting disambiguation material only;
+spell-cast artifacts must still be grounded in the source transcript.
 
 ## D&D Spell Validators
 

docs/troubleshooting.md

@@ -119,8 +119,8 @@ Symptoms include:
 Fix:
 
 - Confirm the selected chunker, extractor, or normalizer declares the slot. The
-  implemented `dnd/spells` extractor declares optional `roster` and `glossary`
-  slots.
+  implemented `dnd/scenes` chunker and `dnd/spells` extractor declare optional
+  `roster` and `glossary` slots.
 - Use a specific selector when more than one selected target declares the same
   slot. Examples include `chunk.context=./context.txt`,
   `spells.extract.context=./extract-context.txt`, and
@@ -136,7 +136,8 @@ Fix:
 - Ensure the file is readable UTF-8 text and within any byte limit declared by
   the declaring module.
 - If the declaring module narrows accepted media types, use a file extension that
-  infers an accepted type such as `text/markdown` or `application/json`.
+  infers an accepted type such as `text/markdown`, `application/yaml`, or
+  `application/json`.
   Unknown extensions infer `application/octet-stream`.
 - If diagnostics are retained, inspect `resolved-pipeline.json`,
   `resolved-references.json`, and `error.log`.