ba0b9a1fae
feat(dashboard): Enhanced chat, spec management, and Claude integration
...
Backend:
- spec.py: New AtomizerSpec REST API endpoints
- spec_manager.py: SpecManager service for unified config
- interview_engine.py: Study creation interview logic
- claude.py: Enhanced Claude API with context
- optimization.py: Extended optimization endpoints
- context_builder.py, session_manager.py: Improved services
Frontend:
- Chat components: Enhanced message rendering, tool call cards
- Hooks: useClaudeCode, useSpecWebSocket, improved useChat
- Pages: Updated Dashboard, Analysis, Insights, Setup, Home
- Components: ParallelCoordinatesPlot, ParetoPlot improvements
- App.tsx: Route updates for canvas/studio
Infrastructure:
- vite.config.ts: Build configuration updates
- start/stop-dashboard.bat: Script improvements
2026-01-20 13:10:47 -05:00
5bd142780f
feat(canvas): Add Phase 3+4 - Bidirectional sync, templates, and visual polish
...
Phase 3 - Bidirectional Sync:
- Add loadFromIntent and loadFromConfig to canvas store
- Create useIntentParser hook for parsing Claude messages
- Create ConfigImporter component (file upload, paste JSON, load study)
- Add import/clear buttons to CanvasView header
Phase 4 - Templates & Polish:
- Create template library with 5 presets:
- Mass Minimization (single-objective)
- Multi-Objective Pareto (NSGA-II)
- Turbo Mode (with MLP surrogate)
- Mirror Zernike (optical optimization)
- Frequency Optimization (modal)
- Create TemplateSelector component with category filters
- Enhanced BaseNode with animations, glow effects, status indicators
- Add colorBg to all node types for visual distinction
- Add notification toast system
- Update all exports
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-14 20:30:28 -05:00
1ae35382da
feat: Phase 2 - LLM Integration for Canvas
...
- Add canvas.ts MCP tool with validate_canvas_intent, execute_canvas_intent, interpret_canvas_intent
- Add useCanvasChat.ts bridge hook connecting canvas to chat system
- Update context_builder.py with canvas tool instructions
- Add ExecuteDialog for study name input
- Add ChatPanel for canvas-integrated Claude responses
- Connect AtomizerCanvas to Claude via useCanvasChat
Canvas workflow now:
1. Build graph visually
2. Click Validate/Analyze/Execute
3. Claude processes intent via MCP tools
4. Response shown in integrated chat panel
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-14 20:18:46 -05:00
7919511bb2
feat: Phase 1 - Canvas with React Flow
...
- 8 node types (Model, Solver, DesignVar, Extractor, Objective, Constraint, Algorithm, Surrogate)
- Drag-drop from palette to canvas
- Node configuration panels
- Graph validation with error/warning display
- Intent JSON serialization
- Zustand state management
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-14 20:00:35 -05:00
