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

web-client/nginx.conf

@@ -4,7 +4,7 @@ server {
     index index.html;
 
     location /api/ {
-        proxy_pass http://pipecat-agent:8080/;
+        proxy_pass http://token-server:8080/;
         proxy_http_version 1.1;
         proxy_set_header Host $host;
     }