3 Commits

Author	SHA1	Message	Date
Sergei	05f872d067	fix: voice session improvements - FAB stop, echo prevention, chat TTS ... - FAB button now correctly stops session during speaking/processing states - Echo prevention: STT stopped during TTS playback, results ignored during speaking - Chat TTS only speaks when voice session is active (no auto-speak for text chat) - Session stop now aborts in-flight API requests and prevents race conditions - STT restarts after TTS with 800ms delay for audio focus release - Pending interrupt transcript processed after TTS completion - ChatContext added for message persistence across tab navigation - VoiceFAB redesigned with state-based animations - console.error replaced with console.warn across voice pipeline - no-speech STT errors silenced (normal silence behavior)	2026-01-27 22:59:55 -08:00
Sergei	356205d8c0	Remove LiveKit SDK and related code ... - Remove @livekit/react-native-expo-plugin from app.json - Remove @config-plugins/react-native-webrtc plugin - Delete utils/audioSession.ts (depended on LiveKit AudioSession) - Update VoiceCallContext.tsx comments - Update callManager.ts comments - Update _layout.tsx TODO comment - Remove LiveKit documentation files - Add interruptIfSpeaking to VoiceContext for TTS interrupt 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-27 16:28:23 -08:00
Sergei	e3192ead12	Voice call improvements: single call limit, hide debug tab, remove speaker toggle ... Changes: - Add CallManager singleton to ensure only 1 call per device at a time - Hide Debug tab from production (href: null) - Remove speaker/earpiece toggle button (always use speaker) - Agent uses voice_ask API (fast ~1 sec latency) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2026-01-19 23:55:27 -08:00