Atomizer/DEVELOPMENT.md

# Development Guide

## Project Setup Complete! ✅

Your Atomizer project has been initialized with the following structure:

```
C:\Users\antoi\Documents\Atomaste\Atomizer\
├── .git/                           # Git repository
├── .gitignore                      # Ignore patterns
├── LICENSE                         # Proprietary license
├── README.md                       # Main documentation
├── GITHUB_SETUP.md                 # GitHub push instructions
├── DEVELOPMENT.md                  # This file
├── pyproject.toml                  # Python package configuration
├── requirements.txt                # Pip dependencies
│
├── config/                         # Configuration templates
│   ├── nx_config.json.template
│   └── optimization_config_template.json
│
├── mcp_server/                     # MCP Server (Phase 1)
│   ├── __init__.py
│   ├── tools/                      # MCP tool implementations
│   │   └── __init__.py
│   ├── schemas/                    # JSON schemas for validation
│   └── prompts/                    # LLM system prompts
│       └── examples/               # Few-shot examples
│
├── optimization_engine/            # Core optimization (Phase 4)
│   ├── __init__.py
│   └── result_extractors/          # Pluggable metric extractors
│       └── __init__.py             # Base classes + registry
│
├── nx_journals/                    # NXOpen scripts (Phase 3)
│   ├── __init__.py
│   └── utils/                      # Helper functions
│
├── dashboard/                      # Web UI (Phase 2)
│   ├── frontend/                   # React app
│   └── backend/                    # FastAPI server
│
├── tests/                          # Unit tests
├── docs/                           # Documentation
└── examples/                       # Example projects
```

## Current Status: Phase 0 - Foundation ✅

- [x] Project structure created
- [x] Git repository initialized
- [x] Python package configuration
- [x] License and documentation
- [x] Initial commit ready

## Next Development Phases

### 🎯 Immediate Next Steps (Choose One)

#### Option A: Start with MCP Server (Recommended)
**Goal**: Get conversational FEA model discovery working

1. **Implement `discover_fea_model` tool**:
   ```bash
   # Create the tool
   touch mcp_server/tools/model_discovery.py
   ```

   - Parse .sim files to extract solutions, expressions, FEM info
   - Use existing Atomizer patterns from your P04 project
   - Return structured JSON for LLM consumption

2. **Set up MCP server skeleton**:
   ```bash
   # Install MCP SDK
   pip install mcp

   # Create server entry point
   touch mcp_server/server.py
   ```

3. **Test with a real .sim file**:
   - Point it to one of your existing models
   - Verify it extracts expressions correctly

#### Option B: Port Atomizer Optimization Engine
**Goal**: Get core optimization working independently

1. **Copy Atomizer modules**:
   ```bash
   # From your P04/Atomizer project, copy:
   cp ../Projects/P04/Atomizer/code/multi_optimizer.py optimization_engine/
   cp ../Projects/P04/Atomizer/code/config_loader.py optimization_engine/
   cp ../Projects/P04/Atomizer/code/surrogate_optimizer.py optimization_engine/
   ```

2. **Adapt for general use**:
   - Remove Zernike-specific code
   - Generalize result extraction to use plugin system
   - Update import paths

3. **Create a simple test**:
   ```python
   # tests/test_optimizer.py
   def test_basic_optimization():
       config = load_config("config/optimization_config_template.json")
       optimizer = MultiParameterOptimizer(config)
       # ...
   ```

#### Option C: Build Dashboard First
**Goal**: Get real-time monitoring UI working

1. **Set up React frontend**:
   ```bash
   cd dashboard/frontend
   npx create-react-app . --template typescript
   npm install plotly.js recharts
   ```

2. **Set up FastAPI backend**:
   ```bash
   cd dashboard/backend
   touch server.py
   # Implement WebSocket endpoint for live updates
   ```

3. **Create mock data endpoint**:
   - Serve fake optimization history
   - Test plots and visualizations

## Recommended Workflow: Iterative Development

### Week 1: MCP + Model Discovery
- Implement `discover_fea_model` tool
- Test with real .sim files
- Get LLM integration working

### Week 2: Optimization Engine Port
- Copy and adapt Atomizer core modules
- Create pluggable result extractors
- Test with simple optimization

### Week 3: NXOpen Bridge
- Build file-based communication
- Create generic journal dispatcher
- Test expression updates

### Week 4: Dashboard MVP
- React frontend skeleton
- FastAPI backend with WebSocket
- Real-time iteration monitoring

## Development Commands

### Python Environment

```bash
# Create conda environment
conda create -n atomizer python=3.10
conda activate atomizer

# Install in development mode
pip install -e .

# Install dev dependencies
pip install -e ".[dev]"
```

### Testing

```bash
# Run all tests
pytest

# With coverage
pytest --cov=mcp_server --cov=optimization_engine

# Run specific test
pytest tests/test_model_discovery.py -v
```

### Code Quality

```bash
# Format code
black .

# Lint
ruff check .

# Type checking
mypy mcp_server optimization_engine
```

### Git Workflow

```bash
# Create feature branch
git checkout -b feature/model-discovery

# Make changes, test, commit
git add .
git commit -m "feat: implement FEA model discovery tool"

# Push to GitHub
git push -u origin feature/model-discovery

# Merge to main
git checkout main
git merge feature/model-discovery
git push origin main
```

## Integration with Existing Atomizer

Your existing Atomizer project is at:
```
C:\Users\antoi\Documents\Atomaste\Projects\P04\Atomizer\
```

You can reference and copy modules from there as needed. Key files to adapt:

| Atomizer File | New Location | Adaptation Needed |
|--------------|--------------|-------------------|
| `code/multi_optimizer.py` | `optimization_engine/multi_optimizer.py` | Minimal - works as-is |
| `code/config_loader.py` | `optimization_engine/config_loader.py` | Extend schema for extractors |
| `code/zernike_Post_Script_NX.py` | `optimization_engine/result_extractors/zernike.py` | Convert to plugin class |
| `code/journal_NX_Update_and_Solve.py` | `nx_journals/update_and_solve.py` | Generalize for any .sim |
| `code/nx_post_each_iter.py` | `nx_journals/post_process.py` | Use extractor registry |

## Useful Resources

- **Optuna Docs**: https://optuna.readthedocs.io/
- **NXOpen API**: https://docs.sw.siemens.com/en-US/doc/209349590/
- **MCP Protocol**: https://modelcontextprotocol.io/
- **FastAPI**: https://fastapi.tiangolo.com/
- **React + TypeScript**: https://react-typescript-cheatsheet.netlify.app/

## Questions to Consider

Before starting development, decide on:

1. **Which phase to tackle first?** (MCP, Engine, Dashboard, or NXOpen)
2. **Target NX version?** (NX 2412 | Future: multi-version support, or multi-version support)
3. **Deployment strategy?** (Local only or client-server architecture)
4. **Testing approach?** (Unit tests only or integration tests with real NX)
5. **Documentation format?** (Markdown, Sphinx, MkDocs)

## Getting Help

When you're ready to start coding:

1. Choose a phase from the options above
2. Tell me which component you want to build first
3. I'll create the detailed implementation with working code
4. We'll test it with your existing .sim files
5. Iterate and expand

---

**You're all set!** The foundation is ready. Choose your starting point and let's build! 🚀