Speed optimizations:
- Add session.prewarm() in InsightsViewModel and ReportsViewModel init
for 40% faster first-token latency
- Cap maximumResponseTokens on all 8 AI respond() calls (100-600 per use case)
- Add prompt brevity constraints ("1-2 sentences", "2 sentences")
- Reduce report batch concurrency from 4 to 2 to prevent device contention
- Pre-fetch health data once and share across all 3 insight periods
Richer insight data in MoodDataSummarizer:
- Tag-mood correlations: overall frequency + good day vs bad day tag breakdown
- Weather-mood correlations: avg mood by condition and temperature range
- Absence pattern detection: logging gap count with pre/post-gap mood averages
- Entry source breakdown: % of entries from App, Widget, Watch, Siri, etc.
- Update insight prompt to leverage tags, weather, and gap data when available
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three new Foundation Models features to deepen user engagement with mental wellness:
1. AI Reflection Companion — personalized feedback after completing guided reflections,
referencing the user's actual words with personality-pack-adapted tone
2. Mood Pattern Tags — auto-extracts theme tags (work, family, stress, etc.) from notes
and reflections, displayed as colored pills on entries
3. Weekly Emotional Digest — BGTask-scheduled Sunday digest with headline, summary,
highlight, and intention; shown as card in Insights tab with notification
All features: on-device (zero cost), premium-gated, iOS 26+ with graceful degradation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
