Switch OpenClaw bridge from HTTP to WebSocket protocol

Add EMA smoothing to face tracking to reduce jitter

Fix missing Any import in main.py

Add Reachy Mini animated GIF to main page hero section

Add Reachy Mini dance GIF to README

Add local face tracking (YOLO) and vision processing (SmolVLM2)

Refactor to native OpenAI Realtime with OpenClaw identity

Fix speech cutoff and echo: track speaking state, wait for responses

Fix TTS: cancel OpenAI auto-response, route through OpenClaw

Add acknowledgment for long-running queries to prevent timeout

Fix modalities error: must use ['text', 'audio'] not ['audio']

Fix dual-response issue: disable OpenAI auto-response

Trigger CI: test HF sync

Use x-openclaw-session-key header for proper session routing

Fix cross-channel conversation awareness with shared user ID

Fix conversation awareness across channels (WhatsApp, web, robot)

Update README with face tracking feature documentation

Add GitHub Action to auto-sync to Hugging Face Space

Add face tracking for robot to look at person speaking

Add prominent simulator support documentation

Add YAML frontmatter to SKILL.md for directory compatibility

Update SKILL.md for OpenClaw skills directory submission

Add more discoverable tags for OpenClaw and AI assistant searches

Add polished landing page

Initial release of ClawBody