|
|
d228ccec66
|
refactor: Archive experimental LLM features for MVP stability (Phase 1.1)
Moved experimental LLM integration code to optimization_engine/future/:
- llm_optimization_runner.py - Runtime LLM API runner
- llm_workflow_analyzer.py - Workflow analysis
- inline_code_generator.py - Auto-generate calculations
- hook_generator.py - Auto-generate hooks
- report_generator.py - LLM report generation
- extractor_orchestrator.py - Extractor orchestration
Added comprehensive optimization_engine/future/README.md explaining:
- MVP LLM strategy (Claude Code skills, not runtime LLM)
- Why files were archived
- When to revisit post-MVP
- Production architecture reference
Production runner confirmed: optimization_engine/runner.py is sole active runner.
This establishes clear separation between:
- Production code (stable, no runtime LLM dependencies)
- Experimental code (archived for post-MVP exploration)
Part of Phase 1: Core Stabilization & Organization for MVP
Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-24 09:12:36 -05:00 |
|
|
|
dd7f0c0f82
|
Phase 3.3: Multi-objective optimization fix, updated docs & Claude skill
- Fixed drone gimbal optimization to use proper semantic directions
- Changed from ['minimize', 'minimize'] to ['minimize', 'maximize']
- Updated Claude skill (v2.0) with Phase 3.3 integration
- Added centralized extractor library documentation
- Added multi-objective optimization (Protocol 11) section
- Added NX multi-solution protocol documentation
- Added dashboard integration documentation
- Fixed Pareto front degenerate issue with proper NSGA-II configuration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-24 07:49:48 -05:00 |
|
|
|
f76bd52894
|
feat: Implement Protocol 13 - Real-Time Dashboard Tracking
Complete implementation of Protocol 13 featuring real-time web dashboard
for monitoring multi-objective optimization studies.
## New Features
### Backend (Python)
- Real-time tracking system with per-trial JSON writes
- New API endpoints for metadata, optimizer state, and Pareto fronts
- Unit inference from objective descriptions
- Multi-objective support using Optuna's best_trials API
### Frontend (React + TypeScript)
- OptimizerPanel: Real-time optimizer state (phase, strategy, progress)
- ParetoPlot: Pareto front visualization with normalization toggle
- 3 modes: Raw, Min-Max [0-1], Z-Score standardization
- Pareto front line connecting optimal points
- ParallelCoordinatesPlot: High-dimensional interactive visualization
- Objectives + design variables on parallel axes
- Click-to-select, hover-to-highlight
- Color-coded feasibility
- Dynamic units throughout all visualizations
### Documentation
- Comprehensive Protocol 13 guide with architecture, data flow, usage
## Files Added
- `docs/PROTOCOL_13_DASHBOARD.md`
- `atomizer-dashboard/frontend/src/components/OptimizerPanel.tsx`
- `atomizer-dashboard/frontend/src/components/ParetoPlot.tsx`
- `atomizer-dashboard/frontend/src/components/ParallelCoordinatesPlot.tsx`
- `optimization_engine/realtime_tracking.py`
## Files Modified
- `atomizer-dashboard/frontend/src/pages/Dashboard.tsx`
- `atomizer-dashboard/backend/api/routes/optimization.py`
- `optimization_engine/intelligent_optimizer.py`
## Testing
- Tested with bracket_stiffness_optimization_V2 (30 trials, 20 Pareto solutions)
- Dashboard running on localhost:3001
- All P1 and P2 features verified working
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-21 15:58:00 -05:00 |
|
