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>

backend/app/models/__init__.py

@@ -6,5 +6,6 @@ from app.models.context_file import ContextFile
 from app.models.skill import Skill
 from app.models.document import Document
 from app.models.memory_entry import MemoryEntry
+from app.models.notification import Notification
 
-__all__ = ["User", "Session", "Chat", "Message", "ContextFile", "Skill", "Document", "MemoryEntry"]
+__all__ = ["User", "Session", "Chat", "Message", "ContextFile", "Skill", "Document", "MemoryEntry", "Notification"]