Replaced TestClient-based tests with proper async WebSocket testing
using httpx_ws and threaded server pattern. TestClient has event loop
issues with WebSocket connections that were causing all tests to fail.
Changes:
- Rewrote all WebSocket tests to use aconnect_ws from httpx_ws
- Added chat_appserver fixture using threaded Uvicorn server
- Tests now use separate event loop in server thread
- All 6 tests now pass without asyncio/event loop errors
- Matches existing pattern from test_transcripts_rtc_ws.py
Tests validate:
- WebSocket connection and echo behavior
- Error handling for non-existent transcripts
- Multiple sequential messages
- Graceful disconnection
- WebVTT context generation
- Unknown message type handling
Closes fn-1.8 (End-to-end testing)
Task 3: LLM Streaming Integration
- Import Settings, ChatMessage, MessageRole from llama-index
- Configure LLM with temperature 0.7 on connection
- Build system message with WebVTT transcript context (max 15k chars)
- Initialize conversation history with system message
- Handle 'message' type from client to trigger LLM streaming
- Stream LLM response using Settings.llm.astream_chat()
- Send tokens incrementally via 'token' messages
- Send 'done' message when streaming completes
- Maintain conversation history across multiple messages
- Add error handling with 'error' message type
- Add message protocol validation test
Implements Tasks 3 & 4 from TASKS.md
- Import topics_to_webvtt_named and recordings controller
- Add _get_is_multitrack helper function
- Generate WebVTT context on WebSocket connection
- Add get_context message type to retrieve WebVTT
- Maintain backward compatibility with echo for other messages
- Add test fixture and test for WebVTT context generation
Implements task fn-1.2: WebVTT context generation for transcript chat
