Complete D&D NPC interaction integration

docs/internal/llm.md

@@ -98,7 +98,7 @@ D&D prompt content. `internal/framework/promptfs` provides the domain-neutral
 filesystem composition helper used to combine module-owned files with shared
 domain prompt fragments.
 
-The D&D scene chunker and spell, NPC, and combat-turn extractors each declare an
+The D&D scene chunker and spell, NPC, combat-turn, and NPC-interaction extractors each declare an
 ordered prompt asset manifest. The manifest lists the package-owned YAML and
 Markdown files, then the exact shared fragments rendered by that prompt; the
 same ordered list drives both filesystem mounting and the prompt fingerprint.
@@ -126,17 +126,18 @@ per-chunk transcript changes. Cache reuse requires the preceding message
 sequence and content to be exactly identical; semantic similarity is not
 sufficient. Cache boundaries belong at the ends of reusable stable tiers,
 subject to the provider's cache-boundary limit. The shared identity and
-campaign-reference messages form the first two extraction boundaries. Spell
-and combat prompts add a boundary at the shared NPC registry. Each extraction
+campaign-reference messages form the first two extraction boundaries. Spell,
+combat, and interaction prompts add a boundary at the shared NPC registry. Each extraction
 prompt places its final boundary on its lane-specific instructions, immediately
 before the transcript. The transcript does not carry cache control because no
 reusable content follows it.
 
-Accordingly, the common prefix of all three extraction prompts is system,
+Accordingly, the common prefix of all four extraction prompts is system,
 extraction evidence, identity, and campaign references. The NPC prompt then
 renders task, instructions, and transcript. Spell renders the NPC registry,
 catalog, task, instructions, and transcript. Combat renders the NPC registry,
-task, instructions, and transcript. The
+task, instructions, and transcript. NPC interaction renders the names-only NPC
+registry, task, instructions, and transcript. The
 scene chunker is not an extraction lane: it retains its separate system,
 transcript, campaign-reference, task, and instruction order and marks its
 transcript and campaign-reference messages ephemeral.
@@ -154,7 +155,7 @@ 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, NPC, and combat extractors' package-owned prompts declare their
+The spell, NPC, combat, and NPC-interaction extractors' package-owned prompts declare their
 structured JSON inputs and private response schemas. Each private response
 schema remains separate from its durable artifact codec schema; this work does
 not use shared schema fragments or schema generation. Those private schemas own
@@ -167,14 +168,14 @@ numbers. The spell extractor's prompt declares a required
 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 spell and combat prompts. When an NPC
+after the campaign reference message for spell, combat, and interaction prompts. When an NPC
 registry is bound, the
 domain registry boundary strictly decodes and identity-validates one durable
 artifact, re-encodes canonical JSON for provenance, and separately generates a
 names-only prompt projection. The unbound projection is exactly `{"npcs":[]}`.
 Prompt input and component-local checkpoint digests cover the projected bytes;
 manifests retain the optional full registry digest/count rather than names,
-overlay bytes, registry paths, or source metadata. Combat prompt,
+overlay bytes, registry paths, or source metadata. Combat and interaction prompt,
 response-schema, mapping, normalization, identity, and registry-projection
 fingerprints remain separate semantic inputs to checkpoint identity.