CodexAgent

CodexAgent is an AI-powered command-line tool for code analysis, documentation generation, and refactoring. It uses Google's Gemini AI to provide intelligent code analysis and suggestions.

✨ Features

• Code Summarization: Generate high-level summaries of code repositories
• Documentation Generation: Automatically generate documentation for Python code with multiple style support (numpy, google, rest)
• Code Refactoring: Get AI-powered refactoring suggestions and apply them with a single command
• Code Analysis: Detect code quality issues and get improvement suggestions
• Linting & Formatting: Integrated with flake8, ruff, and black for code quality
• Testing: Comprehensive test suite with pytest
• CI/CD: GitHub Actions workflow for testing and linting
• Modern CLI: User-friendly command-line interface with rich output

🎥 Watch & Learn

Check out our YouTube channel for tutorials and demos:

🆕 Recent Updates

• Enhanced Documentation Generation: Added support for multiple docstring styles
• Improved Code Analysis: Better detection of code quality issues
• Refactoring Tools: More reliable code refactoring with detailed reports
• Bug Fixes: Fixed various linting and formatting issues
• Improved Error Handling: Better error messages and user feedback

🚀 Getting Started

Prerequisites

• Python 3.8+
• Poetry (recommended) or pip
• Google Gemini API Key

Installation

1. Clone the repository

   git clone https://github.com/sylvester-francis/CodexAgent.git
   cd CodexAgent

2. Set up the environment

   # Using Poetry (recommended)
   poetry install
   poetry shell
   
   # Or using pip
   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -r requirements.txt
   pip install -r requirements-dev.txt  # For development

3. Configure environment variables

   cp .env.example .env
   # Edit .env and add your Gemini API key

🛠️ Usage

Basic Commands

Show help:

python cli.py --help

Get version:

python cli.py --version

🔍 Code Analysis

Analyze code quality and get suggestions:

python cli.py analyze /path/to/your/code

Documentation Generation

Single file with specific style (numpy/google/rest):

python cli.py docgen file /path/to/your/file.py --style numpy

Directory with custom output:

python cli.py docgen dir /path/to/your/directory --output-dir ./docs

Code Refactoring

Analyze without changes:

python cli.py refactor file /path/to/your/file.py

Apply refactoring with backup:

python cli.py refactor file /path/to/your/file.py --apply --output-dir ./refactored

Repository Summary

Generate a summary of a code repository:

python cli.py summarize run /path/to/your/repo --output summary.md

Summarize a Repository

python cli.py summarize run /path/to/your/repo

Generate Documentation

Single file:

python cli.py docgen file /path/to/your/file.py

Directory:

python cli.py docgen dir /path/to/your/directory

Refactor Code

Analyze a file:

python cli.py refactor file /path/to/your/file.py

Apply refactoring:

python cli.py refactor file /path/to/your/file.py --apply --output-dir ./refactored

🧪 Testing & Quality

Run the complete test suite:

# Run all tests with coverage
pytest --cov=app --cov-report=term-missing

# Run specific test file with verbose output
pytest tests/test_summarize.py -v

# Run all tests in parallel (requires pytest-xdist)
pytest -n auto

# Run linters
flake8 app tests
ruff check .

# Auto-fix linting issues
ruff check --fix .
ruff format .

🏗️ Architecture

graph TD
    subgraph CodexAgent[CodexAgent CLI Tool]
        CLI[CLI Commands] -->|Parse & Validate| Agents[Agents]
        
        subgraph Agents[Agents Layer]
            direction TB
            DocGen[Documentation Generator] -->|Generate| DocOutput[Documentation]
            Refactor[Code Refactoring] -->|Analyze/Modify| CodeOutput[Refactored Code]
            Summarizer[Code Summarizer] -->|Generate| SummaryOutput[Summaries]
        end
        
        subgraph LLM[LLM Integration]
            direction LR
            Gemini[Google Gemini API] -->|Process| Agents
            Agents -->|Send Requests| Gemini
        end
        
        subgraph Utils[Utilities]
            direction TB
            Config[Configuration]
            Logging[Logging]
            FileIO[File I/O]
            Validators[Input Validation]
        end
        
        CLI -->|Use| Utils
        Agents -->|Use| Utils
    end
    
    style CLI fill:#f9f,stroke:#333,stroke-width:2px
    style Agents fill:#bbf,stroke:#333,stroke-width:2px
    style LLM fill:#f96,stroke:#333,stroke-width:2px
    style Utils fill:#9f9,stroke:#333,stroke-width:2px

Loading

Component Overview

1. CLI Commands

   • Entry point for user interaction
   • Command parsing and validation
   • Rich terminal output formatting

2. Agents Layer

   • Documentation Generator: Creates comprehensive code documentation
   • Code Refactoring: Analyzes and improves code quality
   • Code Summarizer: Generates high-level code summaries

3. LLM Integration

   • Google Gemini API integration
   • Handles AI model interactions
   • Manages API rate limiting and retries

4. Utilities

   • Configuration management
   • Logging and error handling
   • File I/O operations
   • Input validation and sanitization

Data Flow

1. User invokes a command through the CLI
2. CLI parses arguments and routes to the appropriate agent
3. Agent processes the request using utility functions
4. For AI-powered features, the agent communicates with the Gemini API
5. Results are formatted and displayed to the user
6. Output is saved to disk if specified`

Component Interactions:

1. CLI Commands: Entry point for user interactions (summarize, docgen, refactor)
2. Agents: Core business logic for different functionalities
3. LLM Backend: Google Gemini API integration for AI capabilities
4. Output Formatters: Format results for console/file output
5. Utilities: Shared helper functions and common utilities

Project Structure

CodexAgent/
├── app/                    # Main application package
│   ├── agents/             # AI agents for different tasks
│   │   ├── docgen_agent.py # Documentation generation
│   │   ├── refactor_agent.py # Code refactoring
│   │   └── summarize_agent.py # Code summarization
│   ├── commands/           # CLI command implementations
│   ├── llm/                # Language model integrations
│   └── utils/              # Utility functions
├── tests/                  # Test suite
├── .github/workflows/      # GitHub Actions workflows
├── .flake8                 # Flake8 configuration
├── .pre-commit-config.yaml # Pre-commit hooks
├── pyproject.toml          # Project metadata and dependencies
└── README.md               # This file

🧹 Linting and Formatting

# Run flake8
flake8 app tests

# Run ruff
ruff check .
ruff format --check .

# Auto-fix with ruff
ruff check --fix .
ruff format .

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Google Gemini - For the powerful AI models
• Typer - For the CLI framework
• Pytest - For testing framework