Remove detect toggle button, keep model selector

Add detailed latency metrics overlay

Add head tracking with smoothed roll control, auto-start detection, and UI cleanup

Add YOLO26 model support with detection + pose estimation

Add remote robot discovery via Grand Central signaling server

Add local object detection with bounding box overlay

Add visual feedback on active button and turn-back toggle

Add button commands for all robot actions (look, gestures, turn)

Eagerly load Whisper model on page init instead of first mic tap

Add robot host switcher UI and fix TTS language detection

V2: Replace keyword parser with OpenAI-compatible LLM API

V1: Add voice interaction with STT/TTS and keyword commands

V0: Svelte + Vite app with WebRTC robot connection