Refactor the D&D spells module to apply deterministic fields where appropriate

docs/integrations/dnd-spell-artifacts.md

@@ -14,8 +14,10 @@ This document is the durable raw output contract for the implemented
 - Media type: `application/json`
 
 The extractor requires source chunks and transcript source capability. It
-returns the structured LLM response as raw JSON. The default `appendorder`
-merger passes a single chunk output through and concatenates multiple
+returns canonical spell-cast JSON derived from the structured LLM response. The
+extractor assigns source IDs deterministically and keeps source-unit ranges as
+model-authored evidence locations. The default `appendorder` merger passes a
+single chunk output through and concatenates multiple
 `spell_casts` arrays in chunk order. The default `noop` normalizer passes the
 merge output through unchanged.
 
@@ -76,7 +78,8 @@ Each spell cast contains:
 - `spell`: spell name;
 - `effect`: concise spell effect in the scene;
 - `narrative_description`: short description of the spell cast in context;
-- `source_refs`: transcript source references supplied by the model.
+- `source_refs`: transcript source references with extractor-assigned source
+  IDs and model-supplied unit ranges.
 
 `caster` is the in-world caster, not the transcript speaker.
 
@@ -88,8 +91,10 @@ Each source reference uses the generic source-reference shape:
 - `start_unit_id`
 - `end_unit_id`
 
-The extractor prompt and schema use integer `start_unit_id` and `end_unit_id`
-values matching source-unit IDs.
+The LLM-facing prompt schema asks only for integer `start_unit_id` and
+`end_unit_id` values matching source-unit IDs. `source_id` is assigned by the
+extractor from the source document ID before validation and output, and is
+required in this durable output contract.
 
 ## References