Initial commit: audio-chat with fixes

- Created AGENTS.md with architecture documentation
- Fixed race conditions and async patterns
- Added conversation history to LLM prompts
- Fixed TTS audio shape handling
- Added buffer limits and graceful shutdown
- Fixed client.py with file sending support
- Removed duplicate requirements
- Added .gitignore

requirements.txt

@@ -0,0 +1,26 @@
+# WebSocket server
+fastapi==0.115.0
+uvicorn[standard]==0.30.6
+websockets==13.1
+
+# Speech-to-Text
+faster-whisper==1.0.3
+soundfile==0.12.1
+
+# LLM
+transformers==4.44.0
+torch==2.4.1
+accelerate==1.0.0
+bitsandbytes==0.44.0
+
+# TTS
+torchaudio>=2.4.0
+
+# Audio processing
+numpy==2.1.1
+scipy==1.14.1
+
+# Utilities
+python-dotenv==1.0.1
+pydantic==2.9.2
+pydantic-settings==2.5.2