- Remove speaker button empty space (2-button centered layout)
- Remove "Asteria voice" text from voice call screen
- Fix chat input visibility with keyboard
- Add keyboard show listener for auto-scroll
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Remove allowBluetoothA2DP from audioCategoryOptions. This option is
incompatible with playAndRecord category on some iOS versions.
The allowBluetooth (HFP profile) is sufficient for voice calls.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
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>
- Changed audioStreamType from 'voiceCall' to 'music' on Android
- voiceCall stream defaults to earpiece
- music stream defaults to speaker
- Added Debug tab to test voice calls with detailed logs
- Added speaker/earpiece toggle button with proper stream switching
- Full Android AudioSession support for LiveKit voice calls
audioSession.ts:
- configureAudioForVoiceCall: uses music/media for speaker output
- setAudioOutput: switches between music (speaker) and voiceCall (earpiece)
- reconfigureAudioForPlayback: ensures speaker output on Android
debug.tsx:
- Added platform info display
- Added speaker toggle with logging
- Improved UI with control rows
As requested - same parameters, same response format.
Changed in both:
- chat.tsx (text chat)
- agent.py (voice agent)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes:
- Use anandk credentials (same as julia-agent)
- Add normalizeQuestion() function to transform questions
into format WellNuo API understands
- "how is my dad" → "how is dad doing"
- Remove user's SecureStore credentials
- Use cached token with auto-refresh on 401
This makes text chat return real Ferdinand sensor data
just like voice calls do.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change clientId from '001' to 'MA_001'
- Change deployment_id to '21' (Ferdinand)
- Send raw question without context wrapping
- Same params as julia-agent/julia-ai/src/agent.py
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Monitor page content for "session expired" patterns
- Send message to React Native when detected
- Auto-refresh token and reload WebView
- Add logging to refreshToken for debugging
- Enable Chat tab (replace Debug) - text chat with Julia AI
- Add voice call button in chat header and input area
- Add speaker/earpiece toggle in voice-call screen
- setAudioOutput() function for switching audio output
WellNuo API only returns real sensor data for exact phrase
"how is dad doing". This function maps various user questions
(how is Ferdinand, how's dad, is he okay, etc.) to that phrase.
- Added keyword detection for status, subject, sleep, activity
- All variations now return Ferdinand's real data
This enables WellNuo voice_ask API to return real sensor data
about Ferdinand (deployment_id=21) instead of generic responses.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- chat() must be synchronous, returning LLMStream directly
- LLMStream.__init__() takes 4 params: llm, chat_ctx, tools, conn_options
- _run() emits chunks via self._event_ch.send_nowait()
- Added model and provider properties required by LLM base class
Tested: STT (Deepgram Nova-2), TTS (Deepgram Aura Asteria), VAD (Silero)
all working. WellNuo voice_ask API integration confirmed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
NOT TESTED ON REAL DEVICE - simulator only verification
Components:
- LiveKit Cloud agent deployment (julia-agent/julia-ai/)
- React Native LiveKit client (hooks/useLiveKitRoom.ts)
- Voice call screen with audio session management
- WellNuo voice_ask API integration in Python agent
Tech stack:
- LiveKit Cloud for agent hosting
- @livekit/react-native SDK
- Deepgram STT/TTS (via LiveKit Cloud)
- Silero VAD for voice activity detection
Known issues:
- Microphone permissions may need manual testing on real device
- LiveKit audio playback not verified on physical hardware
- Agent greeting audio not confirmed working end-to-end
Next steps:
- Test on physical iOS device
- Verify microphone capture works
- Confirm TTS audio playback
- Test full conversation loop
- Add App Store build credentials and build-ios.sh script
- Document Julia AI voice agent architecture
- Add detailed instructions for editing agent behavior
- Document token server deployment
Chat screen now supports both:
- Text messaging (keyboard input)
- High-quality Ultravox voice calls (WebRTC)
Features:
- Voice call button in input bar (phone icon)
- Green status bar when call is active
- Transcripts from voice calls appear in chat history
- Voice badge on messages from voice conversation
- Mute button during calls
- Auto-end call when leaving screen
Background audio configured for iOS (audio, voip modes)
Replaced "Dashboard" text with app logo image in header:
- Import Image component from react-native
- Replace Text with Image (icon.png) in both header states
- Add logo style: 36x36px with horizontal margins
- Remove unused headerTitle and headerTitleWithBack styles
- Refresh button now uses marginLeft: 'auto' for proper spacing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed in-app account deletion implementation.
Reason: WellNuo uses B2B model where:
- Accounts created by company staff after contract signing
- Account deletion is part of service contract termination
- Handled through customer support, not self-service
Updated APPLE_REVIEW_RESPONSE.md with B2B exception explanation
for Apple Guidelines 5.1.1(v) and 3.1.1.
Apple App Store Review - Submission ID: 0992528e-4ce9-4167-9a1b-07f4334a8055
Fix#2: Login Screen Cleanup (Guideline 2.1)
- Removed non-functional "Create Account" button
- Removed "Forgot Password" button (not needed)
- Added actual logo image instead of text
- Streamlined login screen to focus on core functionality
Fix#3: Account Deletion Feature (Guideline 5.1.1(v))
- Added "Delete Account" button to Profile screen
- Implemented confirmation dialog with clear warning
- API integration: deleteAccount() method in api.ts
- Automatically logs out and clears data after deletion
- Redirects to login screen after successful deletion
Updated APPLE_REVIEW_RESPONSE.md with full documentation.
Apple Review Issue: Guideline 4.0 - Design
- Added back button in Chat screen header for iOS navigation
- Button navigates to Dashboard screen
- Includes proper touch target sizing (hitSlop) for accessibility
Technical changes:
- Added useRouter hook from expo-router
- Implemented TouchableOpacity with arrow-back icon
- Styled with consistent padding and app color scheme
Also added:
- APPLE_REVIEW_RESPONSE.md to track all review fixes
Submission ID: 0992528e-4ce9-4167-9a1b-07f4334a8055
- Add refreshToken() method to automatically refresh expired tokens
- Add isTokenExpiringSoon() to check if token expires within 1 hour
- Store password in SecureStore for auto-refresh capability
- Add periodic token check every 30 minutes in WebView
- Intercept WebView navigation to login pages and refresh instead
- Re-inject fresh token into WebView localStorage after refresh
- Add metro.config.js to fix Metro bundler path resolution
This prevents the app from showing web login page when session expires.
- Fetch activity + dashboard context in parallel
- Context embedded in question for better AI responses
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Terms of Service / Privacy Policy now open in browser
- Auto-select first beneficiary on chat load
- Allow typing while waiting for AI response
- Optimize AI response speed (removed pre-fetch)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- app.json: Added appleTeamId for correct team
- eas.json: Added submit.production.ios.appleTeamId
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Removed voice input features
- Simplified profile page (only legal links and logout)
- Chat with AI context working
- Auto-select first beneficiary
- Dashboard WebView intact
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
