feat: spirit engine — seance WS, entity minting/Codex, Piper TTS voices, wire telemetry

- WS /ws/session: modes, summon, anomaly fragments, streaming direct contact,
  passive wire-ghost ambient loop, per-user rate limits, event transcript
- entities: anomaly-signature fingerprinting, LLM minting + procedural
  fallback, Codex matching with contact counts and sightings
- tts: 8 local Piper voices (EN/ES), per-entity voice profiles, numpy
  effects chain (pitch/rate/bitcrush/echo/static)
- llm: streaming client, submit_stream in bounded queue, SpiritService
  with offline fallbacks for every channel
- routes: public /api/codex, /api/codex/{id}, /api/stats; /audio static mount
- models: Entity, EntitySighting, Event, ContactSession(entity_id, language)

.env.example

@@ -2,3 +2,8 @@ DATABASE_URL=postgresql+asyncpg://quantumancy:quantumancy@localhost:5432/quantum
 OLLAMA_BASE_URL=http://10.30.20.107:11434
 SESSION_SECRET=change-me-to-a-random-64-char-string
 PORT=7777
+# LLM tiers on the Ollama box (fast = fragments/ambient, chat = direct contact/minting)
+OLLAMA_FAST_MODEL=granite4.1:3b
+OLLAMA_CHAT_MODEL=minicpm-v4.5:latest
+LLM_MAX_CONCURRENCY=2
+LLM_MAX_QUEUE_DEPTH=8