Phase 1 - Database Schema & Basic API:
- Add ChatConversation and ChatMessage tables with proper relationships
- Create conversation CRUD API endpoints with authentication
- Update chat API to support persistent conversations
- Implement auto-generated conversation titles and language separation
- Add conversation soft delete and user-specific access control
Phase 2 - Enhanced Memory System:
- Implement intelligent context selection beyond simple chronological order
- Add relevance scoring for older messages based on keyword overlap and biblical references
- Create automatic message summarization for very long conversations
- Optimize token usage with smart context management (1500 token budget)
- Add biblical awareness with Romanian/English book name detection
- Implement time-based relevance decay for better context prioritization
Frontend Improvements:
- Add chat history button to floating chat header
- Create basic history panel UI with placeholder content
- Maintain backward compatibility for anonymous users
Database Changes:
- Enhanced schema with conversation relationships and message roles
- Proper indexing for performance and user-specific queries
- Migration completed successfully with prisma db push
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added next-intl for internationalization with Romanian as default locale
- Restructured app directory with [locale] routing (/ro, /en)
- Created comprehensive translation files for both languages
- Fixed Next.js 15 async params compatibility in layout components
- Updated all components to use proper i18n hooks and translations
- Configured middleware for locale routing and fallbacks
- Fixed FloatingChat component translation array handling
- Restored complete home page with internationalized content
- Fixed Material-UI Slide component prop error (mountOnExit → unmountOnExit)
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add pgvector support with bible_passages table for vector search
- Create Python ingestion script for Azure OpenAI embed-3 embeddings
- Implement hybrid search combining vector similarity and full-text search
- Update AI chat to use vector search with Azure OpenAI gpt-4o
- Add floating chat component with Material UI design
- Import complete Romanian Bible (FIDELA) with 30K+ verses
- Add vector search library for semantic Bible search
- Create multi-language implementation plan for future expansion
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implemented comprehensive Romanian Biblical Guide web app:
- Next.js 15 with App Router and TypeScript
- Material UI 7.3.2 for modern, responsive design
- PostgreSQL database with Prisma ORM
- Complete Bible reader with book/chapter navigation
- AI-powered biblical chat with Romanian responses
- Prayer wall for community prayer requests
- Advanced Bible search with filters and highlighting
- Sample Bible data imported from API.Bible
- All API endpoints created and working
- Professional Material UI components throughout
- Responsive layout with navigation and theme
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
