feat: VoiceCoach v2.1 - GPU local, Ollama LLM, settings panel, token server separation

- pipeline.py: switched LLM from OpenClaw/Claude to local Ollama, added settings loading, sentence aggregator, async SpeechBrain, tuned VAD
- main.py: simplified (no more token server thread, just pipeline)
- token_server.py: NEW - standalone token + settings API server
- docker-compose.yml: all services on GPU machine, added token-server service, CUDA speaches, Ollama LLM
- web-client/index.html: added settings panel with sliders
- web-client/app.js: settings management, localStorage persistence, push to server
- web-client/style.css: settings panel styles
- web-client/nginx.conf: proxy to token-server instead of pipecat-agent
- patch_livekit.py: updated with proper indentation-safe patching

pipecat-agent/main.py

@@ -1,18 +1,15 @@
 """
-VoiceCoach pipeline entry point -- v2.
-Runs token server + pipeline with unique identity per session.
+VoiceCoach pipeline entry point.
+Token server runs as a separate container — this file only runs the pipeline.
+Pipeline exits on session end; Docker restarts the container for a fresh state.
 """
 import asyncio
 import logging
 import os
-import threading
 import uuid
-from pathlib import Path
+from datetime import timedelta
 
 import structlog
-import uvicorn
-from fastapi import FastAPI
-from pydantic import BaseModel
 from livekit import api as livekit_api
 
 from pipeline import run_voice_coach_pipeline
@@ -23,68 +20,23 @@ logger = structlog.get_logger()
 LIVEKIT_API_KEY = os.environ["LIVEKIT_API_KEY"]
 LIVEKIT_API_SECRET = os.environ["LIVEKIT_API_SECRET"]
 LIVEKIT_WS_URL = os.getenv("LIVEKIT_URL", "ws://livekit-server:7880")
-LIVEKIT_PUBLIC_URL = os.getenv("LIVEKIT_PUBLIC_URL", "wss://voice.hobbs.farm")
-OPENCLAW_TOKEN = os.getenv("OPENCLAW_TOKEN", "")
 
-# --- Token HTTP server ---
-
-token_app = FastAPI(title="VoiceCoach Token Service")
-
-
-class TokenRequest(BaseModel):
-    identity: str = "jeremy"
-
-
-class TokenResponse(BaseModel):
-    token: str
-    url: str
-
-
-@token_app.get("/health")
-async def health():
-    return {"status": "ok", "version": "2.0"}
-
-
-@token_app.post("/token")
-async def get_token(req: TokenRequest):
-    token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
-    token.with_grants(livekit_api.VideoGrants(
-        room_join=True, room="voicecoach",
-        can_publish=True, can_subscribe=True,
-    ))
-    token.identity = req.identity
-    return TokenResponse(token=token.to_jwt(), url=LIVEKIT_PUBLIC_URL)
-
-
-def run_token_server():
-    uvicorn.run(token_app, host="0.0.0.0", port=8080, log_level="info")
-
-
-# --- Main ---
 
 async def main():
-    server_thread = threading.Thread(target=run_token_server, daemon=True)
-    server_thread.start()
-    logger.info("Token server started on :8080")
+    agent_identity = f"voicecoach-agent-{uuid.uuid4().hex[:8]}"
+    token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
+    token.with_grants(livekit_api.VideoGrants(room_join=True, room="voicecoach"))
+    token.identity = agent_identity
+    token.ttl = timedelta(hours=24)
+    livekit_token = token.to_jwt()
 
-    while True:
-        agent_identity = f"voicecoach-agent-{uuid.uuid4().hex[:8]}"
-        token = livekit_api.AccessToken(LIVEKIT_API_KEY, LIVEKIT_API_SECRET)
-        token.with_grants(livekit_api.VideoGrants(room_join=True, room="voicecoach"))
-        token.identity = agent_identity
-        livekit_token = token.to_jwt()
-
-        logger.info("Starting VoiceCoach v2 pipeline", identity=agent_identity)
-        try:
-            await run_voice_coach_pipeline(
-                livekit_url=LIVEKIT_WS_URL,
-                livekit_token=livekit_token,
-                openclaw_token=OPENCLAW_TOKEN,
-            )
-        except Exception as e:
-            logger.error("Pipeline error, restarting in 35s", error=str(e))
-
-        await asyncio.sleep(35)
+    logger.info("Starting VoiceCoach pipeline", identity=agent_identity)
+    await run_voice_coach_pipeline(
+        livekit_url=LIVEKIT_WS_URL,
+        livekit_token=livekit_token,
+        openclaw_token="",
+    )
+    logger.info("Pipeline exited")
 
 
 if __name__ == "__main__":