Document extraction reference support

docs/config.md

@@ -27,6 +27,9 @@ llm_profiles:
 pipelines:
   dnd-session:
     input: seriatim
+    references:
+      roster: ./dnd-spells-roster.txt
+      glossary: ./dnd-spells-glossary.txt
     chunk:
       module: generic
       options:
@@ -148,6 +151,36 @@ directory. Bound files must be UTF-8 text and are passed only to lane
 extractors that declare the slot. Reference content is not written to
 diagnostics, logs, errors, or manifests.
 
+Pipeline-level `references` are defaults. They apply only to selected lanes
+whose extractor declares the slot:
+
+```yaml
+pipelines:
+  dnd-session:
+    input: seriatim
+    references:
+      roster: ./campaign/party-roster.txt
+      glossary: ./campaign/glossary.txt
+    artifacts:
+      spells:
+        extract: dnd/spells
+```
+
+Lane-level `references` override or add bindings for one lane:
+
+```yaml
+pipelines:
+  dnd-session:
+    input: seriatim
+    references:
+      glossary: ./campaign/glossary.txt
+    artifacts:
+      spells:
+        extract: dnd/spells
+        references:
+          roster: ./campaign/session-roster.txt
+```
+
 ## Module Bindings
 
 Every module binding may use shorthand:
@@ -196,6 +229,14 @@ The `generic` chunker accepts:
 The `dnd/scenes` chunker requires transcript source capabilities, calls the
 configured structured LLM provider, and does not accept module options.
 
+The `dnd/spells` extractor declares optional text reference slots:
+
+- `roster`
+- `glossary`
+
+The extractor uses these references only as supporting disambiguation material;
+spell casts still must be present in the source transcript.
+
 ## Diagnostics
 
 `diagnostics` fields: