Ground spell extraction with the effective catalog

docs/internal/llm.md

@@ -103,6 +103,13 @@ return defensive copies, and expose a diagnostics map that omits schema bytes.
 The small framework registry contains only generic test schemas; production
 schemas remain package-owned.
 
+The spell extractor's package-owned prompt declares a required
+`application/json` `spell_catalog` input. The extractor generates that input
+from its prepared effective catalog as `{"spell_names":[...]}` using sorted
+canonical names only. Its input digest covers those generated bytes; manifests
+record catalog identity and digest rather than names, aliases, overlay bytes,
+or source metadata.
+
 ## Debug And Redaction Boundaries
 
 The pipeline may wrap the client with a debug recorder that captures prepared

docs/internal/modules.md

@@ -153,7 +153,12 @@ earliest cited unit, and returns `dnd.SpellList`.
 
 The extractor owns its private model-response DTO, embedded prompt, LLM response
 schema, strict option decoder, injected shared LLM client, and prompt/schema
-manifest metadata. The separate `internal/modules/dnd/codec/spells` package
+manifest metadata. During preparation it resolves the optional `spell_catalog`
+reference into an immutable effective catalog and adds a generated
+canonical-name-only JSON input to every structured completion request. Overlay
+failures therefore stop construction before source parsing or an LLM call;
+campaign references remain separate disambiguation inputs and never become
+source evidence. The separate `internal/modules/dnd/codec/spells` package
 owns the durable schema and stable JSON representation for artifact kind
 `dnd/spell-list`. The runner keeps the result typed through validators and later
 stages, using the codec only for checkpoint, debug, and output boundaries.