on_audio was resetting the timer on every chunk including silence,
so the timeout never fired. Now passes the raw chunk and checks RMS;
only resets if energy is above 0.02 (speech, not ambient silence).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
STT (Silero VAD + Whisper via sherpa-onnx), Chatterbox TTS HTTP server,
query completeness classifier (Ollama), multi-voice demo scripts, and
planning docs. Kept as reference; clean rewrite planned in separate repos.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
