M4: voice pipeline (software-only telephony)

- AudioSocket server (asyncio TCP, Asterisk wire protocol) bridging calls
  into the same M2 agent used by chat
- Call session engine: greeting → energy-VAD utterance collection → STT →
  agent turn → TTS playback with barge-in (120ms of caller speech stops
  playback); inactivity + max-duration guards; unintelligible audio reaches
  the agent as '[nerazumljivo]' so the two-attempt rule stays in the prompt
- STTProvider (faster-whisper, lang hint 'sr', GPU/CPU via env) and
  TTSProvider (Azure Neural raw-8k PCM / ElevenLabs Flash) + test fakes
- Recording (mixed caller+agent WAV), transcripts, per-turn latency trace,
  metering via record_agent_call (§12)
- Internal dialplan API: /internal/calls/register (ring targets computed from
  working hours + ring settings §5.2), /answered (human outcome, no minutes),
  /hangup (abandoned → missed-call SMS §5.5); shared-token auth
- Asterisk config generator (pjsip.conf + extensions.conf from DB): worker
  endpoints, per-tenant test-caller endpoint, register→Dial→AudioSocket
  dialplan with h-extension reporting — validated against a real Asterisk 20
  container (modules, dialplan, endpoints all load)
- docker-compose 'voice' profile (voice server + Asterisk), Dockerfile.voice,
  docs/VOICE_TESTING.md softphone runbook
- 16 new tests incl. full fake-call e2e and a real-TCP AudioSocket wire test

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docker-compose.yml

@@ -33,6 +33,37 @@ services:
       sh -c "alembic upgrade head &&
              uvicorn gogo.main:app --host 0.0.0.0 --port 8000"
 
+  # Voice pipeline (M4): AudioSocket server with STT/TTS/LLM.
+  # Heavy (faster-whisper); start with: docker compose --profile voice up
+  voice:
+    build:
+      context: .
+      dockerfile: Dockerfile.voice
+    profiles: ["voice"]
+    depends_on:
+      db:
+        condition: service_healthy
+    environment:
+      GOGO_DATABASE_URL: postgresql+psycopg://gogo:gogo@db:5432/gogo
+      GOGO_RECORDINGS_DIR: /data/recordings
+    env_file:
+      - path: .env
+        required: false
+    ports:
+      - "127.0.0.1:9092:9092"
+    volumes:
+      - recordings:/data/recordings
+
+  # Asterisk (M4): softphones register here; agent calls bridge to `voice`.
+  # Config is generated: python -m gogo.telephony.asterisk --out ./asterisk/conf
+  asterisk:
+    image: andrius/asterisk:alpine-20.5.2
+    profiles: ["voice"]
+    network_mode: host  # SIP/RTP is painful behind NAT; host networking for MVP
+    volumes:
+      - ./asterisk/conf/pjsip.conf:/etc/asterisk/pjsip.conf:ro
+      - ./asterisk/conf/extensions.conf:/etc/asterisk/extensions.conf:ro
+
 volumes:
   pgdata:
   recordings: