4 Commits

Author	SHA1	Message	Date
Andrei	8a342fa85b	Fix Web Speech API desktop voice recognition ... - Set continuous=true to keep listening through pauses - Only process final results, ignore interim transcripts - Add usesFallback check to route Web Speech API transcripts through classification - Desktop now captures complete phrases before classification - Add detailed logging for debugging recognition flow 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-02 07:25:16 +00:00
Andrei	a44faf6ef4	Fix voice input for iOS Safari and prevent infinite loop ... - Remove temperature parameter from GPT-5-mini activity extraction (not supported) - Add classification state to useVoiceInput hook to avoid duplicate API calls - Prevent infinite loop in VoiceFloatingButton by tracking lastClassifiedTranscript - Use classification from backend directly instead of making second request - iOS Safari now successfully transcribes with Azure Whisper and classifies with GPT-5-mini 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-02 07:15:44 +00:00
Andrei	b00e75f679	Fix hydration error in VoiceFloatingButton - remove nested buttons	2025-10-01 20:27:21 +00:00
Andrei	63a333bba3	Add voice input UI components for hands-free tracking ... Implemented complete voice input user interface: **Voice Recording Hook (useVoiceInput):** - Browser Web Speech API integration - Real-time speech recognition - Continuous and interim results - 10-second auto-timeout - Error handling for permissions, network, audio issues - Graceful fallback for unsupported browsers **Voice Input Button Component:** - Modal dialog with microphone button - Animated pulsing microphone when recording - Real-time transcript display - Automatic intent classification on completion - Structured data visualization - Example commands for user guidance - Success/error feedback with MUI Alerts - Confidence level indicators **Floating Action Button:** - Always-visible FAB in bottom-right corner - Quick access from any page - Auto-navigation to appropriate tracking page - Snackbar feedback messages - Mobile-optimized positioning (thumb zone) **Integration with Tracking Pages:** - Voice button in feeding page header - Auto-fills form fields from voice commands - Seamless voice-to-form workflow - Example: "Fed baby 120ml" → fills bottle type & amount **Features:** - ✅ Browser speech recognition (Chrome, Edge, Safari) - ✅ Real-time transcription display - ✅ Automatic intent classification - ✅ Auto-fill tracking forms - ✅ Visual feedback (animations, colors) - ✅ Error handling & user guidance - ✅ Mobile-optimized design - ✅ Accessibility support **User Flow:** 1. Click microphone button (floating or in-page) 2. Speak command: "Fed baby 120 ml" 3. See real-time transcript 4. Auto-classification shows intent & data 5. Click "Use Command" 6. Form auto-fills or activity created **Browser Support:** - Chrome ✅ - Edge ✅ - Safari ✅ - Firefox ❌ (Web Speech API not supported) **Files Created:** - hooks/useVoiceInput.ts - Speech recognition hook - components/voice/VoiceInputButton.tsx - Modal input component - components/voice/VoiceFloatingButton.tsx - FAB for quick access - app/layout.tsx - Added floating button globally - app/track/feeding/page.tsx - Added voice button to header Voice input is now accessible from anywhere in the app, providing true hands-free tracking for parents. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-10-01 20:24:43 +00:00