Close out the D&D combat turn extraction roadmap

docs/internal/llm.md

@@ -104,9 +104,13 @@ The small framework registry contains only generic test schemas; production
 schemas remain package-owned.
 
 The spell and combat extractors' package-owned prompts declare their structured
-JSON inputs and private response schemas. The spell extractor's prompt declares a required
-`application/json` `spell_catalog` input and an optional `application/json`
-`npcs` input. The extractor generates the catalog input from its prepared
+JSON inputs and private response schemas. The combat private schema owns the
+transport envelope—required fields, JSON types, nullability, and unknown-field
+rejection—while its deterministic validators own semantic constraints such as
+enum membership, non-empty values and collections, and positive numbers. The
+spell extractor's prompt declares a required `application/json` `spell_catalog`
+input and an optional `application/json` `npcs` input. The extractor generates
+the catalog input from its prepared
 effective catalog as `{"spell_names":[...]}` using sorted canonical names only.
 The shared D&D prompt assets include a generic NPC grounding fragment directly
 after the campaign reference message for both extractors. When an NPC registry