3 Commits

Author SHA1 Message Date
b0790d719c Generalize from health-specific to universal personal assistant
The app manages multiple life areas (health, finance, personal, work),
not just health. Updated all health-specific language throughout:

Backend:
- Default system prompt: general personal assistant (not health-only)
- AI tool descriptions: generic (not health records/medications)
- Memory categories: health, finance, personal, work, document_summary, other
  (replaces condition, medication, allergy, vital)
- PDF template: "Prepared for" (not "Patient"), "Key Information" (not "Health Profile")
- Renamed generate_health_pdf -> generate_pdf_report, health_report.html -> report.html
- Renamed run_daily_health_review -> run_daily_review
- Context assembly: "User Profile" (not "Health Profile")
- OpenAPI: generic descriptions

Frontend:
- Dashboard subtitle: "Your personal AI assistant"
- Memory categories: Health, Finance, Personal, Work
- Document types: Report, Contract, Receipt, Certificate (not lab_result, etc.)
- Updated en + ru translations throughout

Documentation:
- README: general personal assistant description
- Removed health-only feature descriptions

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 15:15:39 +03:00
04e3ae8319 Fix Phase 5 review issues: mark_all_read, datetime, WS payload, logging
Review fixes:
- mark_all_read now filters status IN (sent, delivered), preventing
  pending notifications from being incorrectly marked as read
- schedule_notification tool: force UTC on naive datetimes, reject
  past dates (send immediately instead)
- WebSocket notification payload now includes all fields matching
  NotificationResponse (user_id, channel, status, scheduled_at, etc.)
- Centralized _serialize_notification helper in notification_sender
- notification_sender: per-notification error handling with rollback
- health_review: moved import json to module top level

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 14:14:08 +03:00
ada7e82961 Phase 5: Notifications — WebSocket, APScheduler, AI tool, health review
Backend:
- Notification model + Alembic migration
- Notification service: CRUD, mark read, unread count, pending scheduled
- WebSocket manager singleton for real-time push
- WebSocket endpoint /ws/notifications with JWT auth via query param
- APScheduler integration: periodic notification sender (every 60s),
  daily proactive health review job (8 AM)
- AI tool: schedule_notification (immediate or scheduled)
- Health review worker: analyzes user memory via Claude, creates
  ai_generated notifications with WebSocket push

Frontend:
- Notification API client + Zustand store
- WebSocket hook with auto-reconnect (exponential backoff)
- Notification bell in header with unread count badge + dropdown
- Notifications page with type badges, mark read, mark all read
- WebSocket initialized in AppLayout for app-wide real-time updates
- Enabled notifications nav in sidebar
- English + Russian translations

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-19 13:57:25 +03:00