- Add dual-stream calibration: phone sends both raw and cropped preview
frames during calibration so users can see what practice will look like
- Add "Adjust" button to modify existing manual calibration without
resetting to auto-detection first
- Hide calibration quad editor overlay when not in calibration mode
- Fix rotation buttons to update cropped preview immediately
- Add rate limiting (10fps) for cropped preview frames during calibration
- Fix multiple bugs preventing dual-stream mode from working:
- Don't mark calibration as complete during preview mode
- Don't stop detection loop when receiving preview calibration
- Sync refs properly in frame mode change effects
Also includes accumulated formatting and cleanup changes.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Apply code formatting across codebase
- Add new vision training boundary frames
- Update model configurations
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major refactoring of worksheet parsing to use centralized state management:
New architecture:
- WorksheetParsingContext: React context provider for parsing state
- state-machine.ts: Typed reducer with actions for streaming lifecycle
- sse-parser.ts: Shared SSE parsing utility for OpenAI Responses API
- usePartialJsonParser.ts: Progressive JSON extraction during streaming
Streaming UI improvements:
- ParsingProgressOverlay: Dark overlay on photo tile during parsing
- ParsingProgressPanel: Collapsible reasoning text panel
- ProgressiveHighlightOverlay: Problem boxes light up as LLM parses
- New streaming API routes: /parse/stream and /parse-selected/stream
Bug fixes during testing:
- Fix TypeScript error: cast event.response for id access in sse-parser
- Fix reparse reasoning display: preserve "processing" status for reparse
- Fix concurrent parsing: revert previous attachment status when switching
- Fix problem count: track dispatched problems to prevent duplicates
Components updated to use context:
- SummaryClient: Wrapped with WorksheetParsingProvider
- OfflineWorkSection: Uses context instead of local streaming state
- PhotoViewerEditor: Uses context for coordinated parsing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add cancel button to gallery thumbnails when parsing in progress
- Add cancel button to fullscreen PhotoViewerEditor when parsing
- Add cancel button for re-parsing in progress (fullscreen view)
- Track reparsingPhotoId to show correct status per-photo in both views
- Gallery shows "Re-parsing..." badge on specific photo being re-parsed
- DELETE endpoint resets parsing status for immediate retry
Also includes codebase-wide formatting from biome.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove per-problem Exclude/Restore buttons from EditableProblemRow
- Add bulk "Exclude Selected" and "Restore Selected" buttons to selection toolbar
- Add toast notifications for approve success/failure
- Close viewer and refresh page after successful approve to show updated session
- Fix mutation to properly await res.json() before returning
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement complete worksheet grading system with AI analysis and mastery tracking:
Features:
- GPT-5 vision integration for single-pass grading (OCR + analysis)
- Three upload modes: file upload, desktop camera, QR code for smartphone
- Real-time batch upload workflow via QR code scanning
- Automatic mastery profile updates based on grading results
- AI feedback with error pattern detection and next step suggestions
- Guest user support for anonymous uploads
Technical Implementation:
- New database tables: worksheet_attempts, problem_attempts, worksheet_mastery
- Removed foreign key constraints to support guest users
- Session-based batch uploads for efficient multi-worksheet grading
- Validation and retry logic for robust AI responses
- Browser-compatible UUID generation (Web Crypto API)
Components:
- CameraCapture: Desktop/mobile camera capture with high resolution
- QRCodeDisplay: Real-time upload tracking with 2-second polling
- UploadWorksheetModal: Unified interface with three upload tabs
- AttemptResultsPage: Detailed grading results with AI analysis
API Endpoints:
- POST /api/worksheets/upload: Upload and trigger grading
- GET /api/worksheets/sessions/[sessionId]: Poll batch uploads
- GET /api/worksheets/attempts/[attemptId]: Get grading results
Cost: ~$0.04 per worksheet graded
Documentation:
- AI_MASTERY_ASSESSMENT_PLAN.md: Complete system architecture
- PROMPTING_STRATEGY.md: GPT-5 prompting and validation
- UX_EXECUTIVE_SUMMARY.md: Stakeholder-friendly overview
- UX_UI_PLAN.md: Complete interface design
- IMPLEMENTATION_STATUS.md: Testing checklist
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Thomas Hallock