- Import lookupPossibleOpenings and buildMoveSequenceFromSteps
- Build move sequence from steps array up to currentIndex
- Lookup up to 5 possible openings per position
- Update prompt to include all possible openings
- Update UI to show single opening name or count of possibilities
- Consistent with play page opening detection
- Import ChatSession from @google/generative-ai
- Add chatSession state to maintain conversation history
- Initialize chat session with personality and language context
- Replace stateless generateContent() with chatSession.sendMessage()
- Add FEN before/after to move analysis prompts
- Chat history is preserved when navigating between moves
- LLM can now provide context-aware commentary across the game
- Fix TypeScript errors in analysis page with non-null assertions
- Fix Chessboard component API usage to use options prop
- Fix Analyze Game button placement to be always visible
- Create chessFormatDetector utility for automatic format detection
- Update StartScreen with textarea supporting both FEN and PGN input
- Add real-time format detection with visual feedback indicators
- Update translations for all 4 languages (EN, DE, FR, IT)
- Add markdown rendering for Tutor chat messages
- Add comprehensive tests for format detection (20 tests)
- Update game initialization to handle both FEN and PGN formats
This completes the fix/stale-analysis-data branch with:
- Fixed stale evaluation data in hint/best move requests
- Clarified AI's dual role (opponent + tutor) to prevent hint rejection
- Stored complete evaluation history (P0, P1, P2) for all moves
- Improved end-game analysis with better mistake detection
- Fixed duplicate analysis runs with useRef flag
- Added markdown rendering for formatted analysis output
- Added unified FEN/PGN import with auto-detection
This commit fixes a bug where the AI tutor and end-game analysis would use stale data from previous evaluations.
The `Tutor` component now receives the live `game` instance and has a new function, `evaluateCurrentPosition`, which is called on-demand when a user requests a hint or the best move. This ensures the LLM receives up-to-date information.
The end-game analysis was also corrected to use the proper evaluation data when constructing the move history, preventing incorrect analysis of mistakes and blunders.
The test suite was improved by restoring deleted tests, adding a new test to verify the fix, and making existing tests more robust.
Stefan