- Replace HealthService.analyzeCorrelations() with computeHealthAverages()
- Remove hardcoded threshold-based correlation analysis (8k steps, 7hrs sleep, etc.)
- Pass raw averages (steps, exercise, sleep, HRV, HR, mindfulness, calories) to AI
- Let Apple Intelligence find nuanced multi-variable patterns naturally
- Update MoodDataSummarizer to format raw health data for AI prompts
- Simplifies code by ~200 lines while improving insight quality
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Premium Features:
- Journal notes and photo attachments for mood entries
- Data export (CSV and PDF reports)
- Privacy lock with Face ID/Touch ID
- Apple Health integration for mood correlation
- 4 new personality packs (Motivational Coach, Zen Master, Best Friend, Data Analyst)
Settings Tab Reorganization:
- Combined Customize and Settings into single tab with segmented control
- Added upgrade banner with trial countdown above segment
- "Why Upgrade?" sheet showing all premium benefits
- Subscribe button opens improved StoreKit 2 subscription view
UI Improvements:
- Enhanced subscription store with feature highlights
- Entry detail view for viewing/editing notes and photos
- Removed duplicate subscription banners from tab content
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Change mood scale from 0-4 to 1-5 for human-readable averages
(Horrible=1, Bad=2, Average=3, Good=4, Great=5)
- Fix streak calculation to check consecutive calendar days,
not just consecutive entries in array
- Update prompt to show /5 scale instead of /4
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace static insights with on-device AI generation via FoundationModels framework
- Add @Generable AIInsight model for structured LLM output
- Create FoundationModelsInsightService with session-per-request for concurrent generation
- Add MoodDataSummarizer to prepare mood data for AI analysis
- Implement loading states with skeleton UI and pull-to-refresh
- Add AI availability badge and error handling
- Support default (supportive) and rude (sarcastic) personality modes
- Optimize prompts to fit within 4096 token context limit
- Bump iOS deployment target to 26.0 for Foundation Models support
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
