updated CLAUDE.md and README.md

CLAUDE.md

@@ -21,13 +21,15 @@
   * Langfuse - Observability (planned)
 
 ## Model Configuration
-  * Environment-based configuration via .env file
-  * Local development: Ollama with qwen2.5-coder model via LiteLLMModel
+  * Environment-based configuration via .env file (optional)
+  * Local development: Ollama with llama3.2 model via LiteLLMModel
   * Production: OpenAI gpt-4o-mini via OpenAIServerModel
+  * Langfuse integration enabled only in production environment
   * Configuration variables:
-    * ENVIRONMENT (development|production)
-    * DEVELOPMENT_MODEL_ID (default: ollama/qwen2.5-coder)
+    * ENVIRONMENT (development|production) - defaults to development
+    * DEVELOPMENT_MODEL_ID (default: ollama/llama3.2)
     * PRODUCTION_MODEL_ID (default: gpt-4o-mini)
+    * LANGFUSE_* variables (only needed for production)
 
 ## Project Structure
 ```
@@ -37,7 +39,7 @@ src/
 │   ├── ada_converter.py    # AdaConverterAgent for Ada to Python conversion
 │   └── unit_test_generator.py  # UnitTestGeneratorAgent for reverse-engineering unit tests
 ├── tools/
-│   └── project_handler.py  # Zip extraction and file handling utilities
+│   └── project_handler.py  # Zip extraction and file handling utilities (with auto-cleanup)
 ├── ui.py                   # Gradio UI components and logic
 └── main.py                 # CLI interface for development/testing
 tests/
@@ -57,9 +59,10 @@ tests/
 │   └── test_project.zip               # Sample zip archive for testing
 └── conftest.py                      # Pytest configuration for Playwright
 app.py                      # Application entry point and agent initialization
-requirements.txt            # Generated from uv dependencies
-pyproject.toml             # Project configuration and dependencies
-.env                       # Environment configuration
+TESTING.md                  # Comprehensive testing documentation
+requirements.txt            # Generated from uv dependencies  
+pyproject.toml             # Project configuration, dependencies, and pytest settings
+uv.lock                    # UV lockfile for reproducible dependencies
 ```
 
 ## Agents
@@ -85,17 +88,34 @@ pyproject.toml             # Project configuration and dependencies
   * **Unit Tests**: Test individual agents and utilities in isolation
     * Located in `tests/unit/agents/` and `tests/unit/tools/`
     * Use mock LLM models to avoid external dependencies
+    * Fast execution (~0.15s for 11 tests)
     * Run with: `uv run pytest tests/unit/ -v`
   
   * **Integration Tests**: Test complete user workflows end-to-end
     * Located in `tests/integration/`
-    * Use Playwright for browser automation
-    * Test zip upload, file selection, and analysis display
+    * Use Playwright for browser automation with Chromium
+    * Test zip upload, file extraction, file selection, and UI workflows
+    * Requires Ollama running for local development
     * Run with: `uv run pytest tests/integration/ --browser chromium`
   
+  * **Test Configuration**: 
+    * All configuration in `pyproject.toml` with proper marker registration
+    * Markers: `integration` and `e2e` for test categorization
+    * Playwright settings in `tests/conftest.py`
+    * No warnings or configuration conflicts
+  
   * **Test Data**: Sample Ada files and zip archives for testing
-    * Calculator example with basic arithmetic functions
+    * Calculator example with basic arithmetic functions (add, subtract, multiply, divide, power, factorial)
     * Stored in `tests/test_data/` directory
+    * Automatic cleanup of temporary project folders
+
+## Development Workflow
+  * **Prerequisites**: 
+    * Ollama installed and running with llama3.2 model
+    * Python 3.10+ with UV package manager
+  * **Setup**: `uv sync` to install dependencies
+  * **Testing**: See TESTING.md for comprehensive test commands
+  * **Playwright Setup**: `uv run playwright install` for browser automation
 
 ## Hosting Platform
   * Hugging Face Spaces with Gradio SDK

README.md

@@ -1,73 +1,151 @@
 ---
 title: Ada Assistant
-emoji: 📊
-colorFrom: pink
+emoji: 🔄
+colorFrom: blue
 colorTo: purple
 sdk: gradio
 sdk_version: 5.33.2
 app_file: app.py
 pinned: false
+tags:
+  - ada
+  - python
+  - code-conversion
+  - legacy-code
+  - llm
+  - testing
 ---
 
-# Ada Conversion Assistant
+# Ada Assistant
 
-A modern tool for analyzing legacy Ada codebases and providing conversion recommendations to modern programming languages.
+A comprehensive tool for analyzing legacy Ada codebases and converting them to modern Python, with integrated testing and analysis capabilities.
 
 ## Features
 
-- **Business Logic Analysis**: Extracts core algorithms, data structures, and business rules from Ada code
-- **Conversion Recommendations**: Provides guidance on complexity and modernization approaches
-- **Web Interface**: Drag & drop file upload with Gradio UI
-- **LLM-Powered**: Uses AI models (Ollama for development, OpenAI for production) via smolagents
+- **📁 Project Upload**: Drag & drop ZIP file upload with automatic extraction and cleanup
+- **🔍 Business Logic Analysis**: Extracts core algorithms, data structures, and business rules from Ada code
+- **🐍 Ada to Python Conversion**: Converts Ada code to clean, PEP 8 compliant Python with type hints
+- **🧪 Unit Test Generation**: Automatically generates comprehensive pytest test suites for converted code
+- **🌐 Web Interface**: Modern Gradio UI with file explorer and real-time analysis
+- **🤖 LLM-Powered**: Uses AI models (Ollama for development, OpenAI for production) via smolagents
+- **🔧 Comprehensive Testing**: Full test suite with unit and integration tests using Playwright
 
 ## Architecture
 
-- **Framework**: Smolagents for LLM abstraction, Gradio for UI
-- **Agents**: Multi-agent architecture with specialized CodeAnalyzerAgent
+- **Framework**: Smolagents for LLM abstraction, Gradio for UI, Playwright for E2E testing
+- **Agents**: Multi-agent architecture with specialized agents:
+  - **CodeAnalyzerAgent**: Business logic extraction and analysis
+  - **AdaConverterAgent**: Ada to Python code conversion
+  - **UnitTestGeneratorAgent**: Automated test generation
+- **Testing**: Comprehensive test strategy with unit and integration tests
 - **Hosting**: Designed for Hugging Face Spaces deployment
-- **Observability**: Langfuse integration (planned)
+- **Observability**: Langfuse integration (production only)
 
 ## Usage
 
 ### Web Interface
-1. Upload Ada files (.ads, .adb, .ada)
-2. Click "Analyze Business Logic"
-3. View extracted business logic and conversion recommendations
+1. **Upload Project**: Drag & drop a ZIP file containing your Ada project
+2. **Browse Files**: Use the file explorer to navigate extracted files
+3. **Select Ada File**: Click on any `.ads` or `.adb` file
+4. **View Results**: See business analysis, Python conversion, and generated tests in real-time
 
 ### Command Line
 ```bash
-uv run src/main.py
+# Start the web interface
+uv run python app.py
+
+# Run CLI analysis (development)
+uv run python src/main.py
 ```
 
 ## Development
 
+### Prerequisites
+- **Python 3.10+** with UV package manager
+- **Ollama** installed and running with llama3.2 model
+- **Git** for version control
+
 ### Setup
 ```bash
+# Clone the repository
+git clone <repository-url>
+cd ada-assistant2
+
 # Install dependencies
-uv install
+uv sync
 
-# Set environment variables
-cp .env.example .env
+# Install Playwright browsers for testing
+uv run playwright install
 ```
 
-### Configuration
-- `ENVIRONMENT`: "development" or "production"
-- `DEVELOPMENT_MODEL_ID`: Ollama Model for local development (default: ollama/qwen2.5-coder)
-- `PRODUCTION_MODEL_ID`: OpenAI Model for production (default: gpt-4o-mini)
+### Configuration (Optional)
+Create a `.env` file for custom configuration:
+```bash
+ENVIRONMENT=development              # or "production"
+DEVELOPMENT_MODEL_ID=ollama/llama3.2 # or your preferred Ollama model
+PRODUCTION_MODEL_ID=gpt-4o-mini      # for production deployment
+```
 
 ### Testing
 ```bash
-uv run pytest tests/
+# Run all tests
+uv run pytest tests/ -v
+
+# Run only unit tests (fast)
+uv run pytest tests/unit/ -v
+
+# Run only integration tests (requires Ollama)
+uv run pytest tests/integration/ --browser chromium
+
+# Run tests with specific markers
+uv run pytest -m "not integration" -v    # Skip integration tests
+uv run pytest -m "integration" -v        # Only integration tests
 ```
 
+For detailed testing information, see [TESTING.md](TESTING.md).
+
 ## Project Structure
 ```
 src/
 ├── agents/
-│   └── code_analyzer.py    # Business logic analysis agent
-└── main.py                 # CLI interface
+│   ├── code_analyzer.py        # Business logic analysis agent
+│   ├── ada_converter.py        # Ada to Python conversion agent
+│   └── unit_test_generator.py  # Unit test generation agent
+├── tools/
+│   └── project_handler.py      # ZIP extraction and file handling
+├── ui.py                       # Gradio UI components and logic
+└── main.py                     # CLI interface
+
 tests/
-├── test_code_analyzer_agent.py
-└── tictactoe.ads          # Test Ada file
-app.py                     # Gradio web interface
+├── unit/                       # Unit tests (isolated, fast)
+│   ├── agents/                 # Agent unit tests
+│   │   ├── test_code_analyzer_agent.py
+│   │   ├── test_ada_converter_agent.py
+│   │   ├── test_unit_test_generator_agent.py
+│   │   └── tictactoe.ads       # Test Ada file
+│   └── tools/
+│       └── test_project_handler.py
+├── integration/                # E2E tests (browser automation)
+│   └── test_e2e_ada_analysis.py
+├── test_data/                  # Sample test files
+│   ├── calculator.ads          # Sample Ada specification
+│   ├── calculator.adb          # Sample Ada implementation
+│   └── test_project.zip        # Sample ZIP archive
+└── conftest.py                 # Pytest configuration
+
+app.py                          # Application entry point
+TESTING.md                      # Comprehensive testing guide
+pyproject.toml                  # Project config, dependencies, test settings
+uv.lock                        # Dependency lockfile
 ```
+
+## Contributing
+
+1. **Follow TDD**: Write tests first, implement minimal code, refactor
+2. **Run tests**: Always run `uv run pytest tests/unit/ -v` after changes
+3. **Integration tests**: Run `uv run pytest tests/integration/ --browser chromium` for full E2E validation
+4. **Documentation**: Update CLAUDE.md with architectural changes
+
+## License
+
+[Your License Here]