A "Hermes agent" assistant model talks to a Hermes Agent gateway's
OpenAI-compatible API server (streamed /v1/chat/completions), with Hermes URL
and key settings under Assistant. Hermes keeps the conversation: each
assistant session maps to one X-Hermes-Session-Id and only the latest user
message is sent. Faceclaw's own tools are not offered to it, and its reasoning
stream is not shown on the glasses. See notes/hermes-assistant.md.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- "Whisper server (self-hosted)" transcription provider for OpenAI-compatible
Whisper servers (vLLM, speaches, LocalAI) over plain HTTP batch requests,
with URL, model, language and key settings (Voice). Pause-ended spans are
one request each, finalized in audio order, with provisional text while a
span is open. See notes/whisper-server.md.
- Transcribe (and other continuous capture) works on iOS with a cloud or
Whisper-server provider; push-to-talk shares a running capture.
- Transcribe saves each session's audio as transcribe-<time>.wav in Downloads
(setting "Save Transcribe audio", on by default), written as it is captured
so a crash leaves a playable file; a saved transcript uses the same stamp.
- Calculator stops continuous listening when its window closes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Phase 3 of the voice-assistant design: assistant.backend=external routes
utterances over a dial-out websocket to faceclaw-agent-bridge (an OpenClaw
plugin on the user's machine). The phone serves its ToolRegistry as MCP on
the same socket, with proactive gating and rate limiting enforced locally.
New Assistant settings section with backend/bridge settings.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XCdkQyB3RUVPTuEmhxVEdp