feat(engine): voice pipeline Phase 1 — composition engine and data model

Add the voice pipeline composition engine (D-138 Spike 2, Phase 1):

- voice/prompt_builder.rs: full prompt assembly from culture profile,
  tell state, and base text. Handles occasional injection gating,
  epistemic marker extraction, content-length-gated tell injection.
  16 unit tests.

- blueprint.rs: CultureProfile gains voice_persona, voice_examples,
  occasional_injections fields. NpcBlueprint gains tell_behaviors.
  OccasionalInjection struct with kind discriminator (oath/faith/
  hesitancy/etc), frequency, and tell-suppression gating.

- culture-krenn.ron: v2 voice injector from Spike 1 — persona block,
  3 examples, oath injection at 0.25 frequency.

- D-138 amended: Phi-3 dropped entirely, exact Gemma 2B provenance
  documented. Model file renamed to gemma2.gguf.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

server/src/voice/mod.rs

@@ -0,0 +1,15 @@
+//! Voice pipeline integration (D-138, Spike 2).
+//!
+//! Translates culture-neutral semantic base text into character-voiced output
+//! via an LLM re-voicing pipeline. The pipeline is a background runtime
+//! enhancement — the game is complete and functional without it.
+//!
+//! ## Components
+//!
+//! - `prompt_builder` — composition engine: NPC data + culture + tell state → prompt string
+//! - `cache` — MessagePack voice cache (store/retrieve, length-gated variants)
+//! - `queue` — crossbeam work queue with priority + backpressure
+//! - `worker` — inference worker pool (dynamic scaling, owns sr-voice HTTP clients)
+//! - `hardware` — hardware detection + dynamic sr-voice instance management
+
+pub mod prompt_builder;