Migrate production modules to raw outputs

docs/integrations/dnd-spell-artifacts.md

@@ -15,9 +15,9 @@ This document is the durable raw output contract for the implemented
 
 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 wraps multiple chunk outputs in
-an ordered `outputs` array. The default `noop` normalizer passes the merge
-output through unchanged.
+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.
 
 ## Output Shape
 
@@ -45,18 +45,24 @@ For a single chunk, `outputs/spells.json` has this shape:
 
 `spell_casts` must be present. It may be empty when no spell casts are found.
 
-For multiple chunks with the default merger, the lane output has this shape:
+For multiple chunks with the default merger, the lane output keeps the same
+top-level shape and concatenates `spell_casts` in chunk order:
 
 ```json
 {
-  "outputs": [
+  "spell_casts": [
     {
-      "chunk_id": "chunk-000001",
-      "chunk_index": 0,
-      "media_type": "application/json",
-      "content": {
-        "spell_casts": []
-      }
+      "caster": "Aria",
+      "spell": "Cure Wounds",
+      "effect": "heals an injured ally",
+      "narrative_description": "Aria raises her holy symbol and casts Cure Wounds.",
+      "source_refs": [
+        {
+          "source_id": "session-alpha",
+          "start_unit_id": 1,
+          "end_unit_id": 1
+        }
+      ]
     }
   ]
 }