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>
Users without Apple Intelligence can now export their mood data as a
visual PDF with charts and statistics instead of seeing a disabled
Generate button. The existing ExportService.exportPDF is reused for
the non-AI path, gated behind the same privacy confirmation dialog.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Walks users through 3-4 guided questions based on mood category:
positive (great/good) gets gratitude-oriented questions, neutral
(average) gets exploratory questions, and negative (bad/horrible)
gets empathetic questions. Stored as JSON in MoodEntryModel,
integrated into PDF reports, AI summaries, and CSV export.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a Reports tab to the Insights view with date range selection, two report
types (Quick Summary / Detailed), Foundation Models AI generation with batched
concurrent processing, and clinical PDF export via WKWebView HTML rendering.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
