end_prompt was being sent to antaf as user message, causing LLM
to output its thinking process. Disabled end_prompt and added
more thinking patterns to filter.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Antaf returns markdown with hyperlinks and formatting that TTS
reads out as raw text. Now cleaned before sending to TTS.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- modules/antaf/ — Antaf LLM provider, voice passthrough, bridge scripts
- modules/tts/ — sherpa-onnx local TTS provider
- modules/docs/ — integration plan
These are standalone files, NOT patched into xiaozhi-server framework.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
hailin