- chat() must be synchronous, returning LLMStream directly
- LLMStream.__init__() takes 4 params: llm, chat_ctx, tools, conn_options
- _run() emits chunks via self._event_ch.send_nowait()
- Added model and provider properties required by LLM base class
Tested: STT (Deepgram Nova-2), TTS (Deepgram Aura Asteria), VAD (Silero)
all working. WellNuo voice_ask API integration confirmed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
dcdd06739d