Antoine/Atomizer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add Studio UI, intake system, and extractor improvements

Browse Source 
Dashboard:
- Add Studio page with drag-drop model upload and Claude chat
- Add intake system for study creation workflow
- Improve session manager and context builder
- Add intake API routes and frontend components

Optimization Engine:
- Add CLI module for command-line operations
- Add intake module for study preprocessing
- Add validation module with gate checks
- Improve Zernike extractor documentation
- Update spec models with better validation
- Enhance solve_simulation robustness

Documentation:
- Add ATOMIZER_STUDIO.md planning doc
- Add ATOMIZER_UX_SYSTEM.md for UX patterns
- Update extractor library docs
- Add study-readme-generator skill

Tools:
- Add test scripts for extraction validation
- Add Zernike recentering test

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Anto01
2026-01-27 12:02:30 -05:00
parent 3193831340
commit a26914bbe8
56 changed files with 14173 additions and 646 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
atomizer-dashboard/backend/api/services/context_builder.py
View File

@@ -26,6 +26,7 @@ class ContextBuilder:
study_id: Optional[str] = None,
conversation_history: Optional[List[Dict[str, Any]]] = None,
canvas_state: Optional[Dict[str, Any]] = None,
spec_path: Optional[str] = None,
) -> str:
"""
Build full system prompt with context.
@@ -35,6 +36,7 @@ class ContextBuilder:
study_id: Optional study name to provide context for
conversation_history: Optional recent messages for continuity
canvas_state: Optional canvas state (nodes, edges) from the UI
spec_path: Optional path to the atomizer_spec.json file
Returns:
Complete system prompt string
@@ -45,7 +47,7 @@ class ContextBuilder:
if canvas_state:
node_count = len(canvas_state.get("nodes", []))
print(f"[ContextBuilder] Including canvas context with {node_count} nodes")
parts.append(self._canvas_context(canvas_state))
parts.append(self._canvas_context(canvas_state, spec_path))
else:
print("[ContextBuilder] No canvas state provided")
@@ -57,7 +59,7 @@ class ContextBuilder:
if conversation_history:
parts.append(self._conversation_context(conversation_history))
parts.append(self._mode_instructions(mode))
parts.append(self._mode_instructions(mode, spec_path))
return "\n\n---\n\n".join(parts)
@@ -298,7 +300,7 @@ Important guidelines:
return context
def _canvas_context(self, canvas_state: Dict[str, Any]) -> str:
def _canvas_context(self, canvas_state: Dict[str, Any], spec_path: Optional[str] = None) -> str:
"""
Build context from canvas state (nodes and edges).
@@ -317,6 +319,8 @@ Important guidelines:
context += f"**Study Name**: {study_name}\n"
if study_path:
context += f"**Study Path**: {study_path}\n"
if spec_path:
context += f"**Spec File**: `{spec_path}`\n"
context += "\n"
# Group nodes by type
@@ -438,61 +442,100 @@ Important guidelines:
context += f"Total edges: {len(edges)}\n"
context += "Flow: Design Variables → Model → Solver → Extractors → Objectives/Constraints → Algorithm\n\n"
# Canvas modification instructions
context += """## Canvas Modification Tools
**For AtomizerSpec v2.0 studies (preferred):**
Use spec tools when working with v2.0 studies (check if study uses `atomizer_spec.json`):
- `spec_modify` - Modify spec values using JSONPath (e.g., "design_variables[0].bounds.min")
- `spec_add_node` - Add design variables, extractors, objectives, or constraints
- `spec_remove_node` - Remove nodes from the spec
- `spec_add_custom_extractor` - Add a Python-based custom extractor function
**For Legacy Canvas (optimization_config.json):**
- `canvas_add_node` - Add a new node (designVar, extractor, objective, constraint)
- `canvas_update_node` - Update node properties (bounds, weights, names)
- `canvas_remove_node` - Remove a node from the canvas
- `canvas_connect_nodes` - Create an edge between nodes
**Example user requests you can handle:**
- "Add a design variable called hole_diameter with range 5-15 mm" → Use spec_add_node or canvas_add_node
- "Change the weight of wfe_40_20 to 8" → Use spec_modify or canvas_update_node
- "Remove the constraint node" → Use spec_remove_node or canvas_remove_node
- "Add a custom extractor that computes stress ratio" → Use spec_add_custom_extractor
Always respond with confirmation of changes made to the canvas/spec.
"""
# Instructions will be in _mode_instructions based on spec_path
return context
def _mode_instructions(self, mode: str) -> str:
def _mode_instructions(self, mode: str, spec_path: Optional[str] = None) -> str:
"""Mode-specific instructions"""
if mode == "power":
return """# Power Mode Instructions
instructions = """# Power Mode Instructions
You have **FULL ACCESS** to modify Atomizer studies. **DO NOT ASK FOR PERMISSION** - just do it.
## Direct Actions (no confirmation needed):
- **Add design variables**: Use `canvas_add_node` or `spec_add_node` with node_type="designVar"
- **Add extractors**: Use `canvas_add_node` with node_type="extractor"
- **Add objectives**: Use `canvas_add_node` with node_type="objective"
- **Add constraints**: Use `canvas_add_node` with node_type="constraint"
- **Update node properties**: Use `canvas_update_node` or `spec_modify`
- **Remove nodes**: Use `canvas_remove_node`
- **Edit atomizer_spec.json directly**: Use the Edit tool
## CRITICAL: How to Modify the Spec
## For custom extractors with Python code:
Use `spec_add_custom_extractor` to add a custom function.
## IMPORTANT:
- You have --dangerously-skip-permissions enabled
- The user has explicitly granted you power mode access
- **ACT IMMEDIATELY** when asked to add/modify/remove things
- Explain what you did AFTER doing it, not before
- Do NOT say "I need permission" - you already have it
Example: If user says "add a volume extractor", immediately use canvas_add_node to add it.
"""
if spec_path:
instructions += f"""**The spec file is at**: `{spec_path}`
When asked to add/modify/remove design variables, extractors, objectives, or constraints:
1. **Read the spec file first** using the Read tool
2. **Edit the spec file** using the Edit tool to make precise changes
3. **Confirm what you changed** in your response
### AtomizerSpec v2.0 Structure
The spec has these main arrays you can modify:
- `design_variables` - Parameters to optimize
- `extractors` - Physics extraction functions
- `objectives` - What to minimize/maximize
- `constraints` - Limits that must be satisfied
### Example: Add a Design Variable
To add a design variable called "thickness" with bounds [1, 10]:
1. Read the spec: `Read({spec_path})`
2. Find the `"design_variables": [...]` array
3. Add a new entry like:
```json
{{
"id": "dv_thickness",
"name": "thickness",
"expression_name": "thickness",
"type": "continuous",
"bounds": {{"min": 1, "max": 10}},
"baseline": 5,
"units": "mm",
"enabled": true
}}
```
4. Use Edit tool to insert this into the array
### Example: Add an Objective
To add a "minimize mass" objective:
```json
{{
"id": "obj_mass",
"name": "mass",
"direction": "minimize",
"weight": 1.0,
"source": {{
"extractor_id": "ext_mass",
"output_name": "mass"
}}
}}
```
### Example: Add an Extractor
To add a mass extractor:
```json
{{
"id": "ext_mass",
"name": "mass",
"type": "mass",
"builtin": true,
"outputs": [{{"name": "mass", "units": "kg"}}]
}}
```
"""
else:
instructions += """No spec file is currently set. Ask the user which study they want to work with.
"""
instructions += """## IMPORTANT Rules:
- You have --dangerously-skip-permissions enabled
- **ACT IMMEDIATELY** when asked to add/modify/remove things
- Use the **Edit** tool to modify the spec file directly
- Generate unique IDs like `dv_<name>`, `ext_<name>`, `obj_<name>`, `con_<name>`
- Explain what you changed AFTER doing it, not before
- Do NOT say "I need permission" - you already have it
"""
return instructions
else:
return """# User Mode Instructions
@@ -503,29 +546,11 @@ You can help with optimization workflows:
- Generate reports
- Explain FEA concepts
**For code modifications**, suggest switching to Power Mode.
**For modifying studies**, the user needs to switch to Power Mode.
Available tools:
- `list_studies`, `get_study_status`, `create_study`
- `run_optimization`, `stop_optimization`, `get_optimization_status`
- `get_trial_data`, `analyze_convergence`, `compare_trials`, `get_best_design`
- `generate_report`, `export_data`
- `explain_physics`, `recommend_method`, `query_extractors`
**AtomizerSpec v2.0 Tools (preferred for new studies):**
- `spec_get` - Get the full AtomizerSpec for a study
- `spec_modify` - Modify spec values using JSONPath (e.g., "design_variables[0].bounds.min")
- `spec_add_node` - Add design variables, extractors, objectives, or constraints
- `spec_remove_node` - Remove nodes from the spec
- `spec_validate` - Validate spec against JSON Schema
- `spec_add_custom_extractor` - Add a Python-based custom extractor function
- `spec_create_from_description` - Create a new study from natural language description
**Canvas Tools (for visual workflow builder):**
- `validate_canvas_intent` - Validate a canvas-generated optimization intent
- `execute_canvas_intent` - Create a study from a canvas intent
- `interpret_canvas_intent` - Analyze intent and provide recommendations
When you receive a message containing "INTENT:" followed by JSON, this is from the Canvas UI.
Parse the intent and use the appropriate canvas tool to process it.
In user mode you can:
- Read and explain study configurations
- Analyze optimization results
- Provide recommendations
- Answer questions about FEA and optimization
"""