Add validator chain provenance

docs/integrations/json-output.md

@@ -82,6 +82,14 @@ sanitizing the lane ID:
       "normalizer": "noop"
     }
   ],
+  "validator_chains": [
+    {
+      "stage": "extract",
+      "lane_id": "spells",
+      "module_key": "dnd/spells",
+      "validators": []
+    }
+  ],
   "validation_status": "approved",
   "started_at": "2026-01-01T00:00:00Z",
   "completed_at": "2026-01-01T00:00:01Z"
@@ -103,6 +111,11 @@ references.
 `validation_status` is `approved` when no raw outputs were rejected and
 `rejected` when one or more raw outputs were rejected.
 
+`validator_chains` records the resolved validator chain for each validation
+point. Entries include stage, lane ID when applicable, module key, and validators
+with key and execution class. Empty chains are recorded with an empty
+`validators` array.
+
 `normalized_outputs` summarizes each normalized lane output without embedding
 payload bytes. Entries include lane ID, normalizer module key, source ID, media
 type, and response schema provenance where available.