This project uses a pre-commit hook to analyze staged files with the Gemini AI model. It checks for potential bugs, typos, debug statements, and areas for improvement.

• Python 3.6+
• Git

1. Clone the repository:

   git clone <repository-url>
   cd <repository-name>

2. Set up a Python virtual environment:

   It's recommended to use a virtual environment to manage project dependencies.

   python3 -m venv .venv

3. Activate the virtual environment:

   • On macOS/Linux:

     source .venv/bin/activate

   • On Windows (Command Prompt):

     .venv\Scripts\activate.bat

   • On Windows (PowerShell):

     .venv\Scripts\Activate.ps1

4. Install project dependencies:

   pip install -r requirements.txt

5. Install pre-commit and set up the hooks:

   This project uses pre-commit to manage and run its Git hooks.

   First, install pre-commit (it will be installed into your active virtual environment):

   pip install pre-commit

   Then, from the root of this repository, install the Git hooks:

   pre-commit install

   This command sets up the Git hooks in your local .git/hooks directory, pointing them to the pre-commit framework. The hooks will then run automatically on git commit.

6. Set your Gemini API Key:

   The script requires a Gemini API key to be set as an environment variable.

   export GEMINI_API_KEY="YOUR_API_KEY"

   To make this permanent, add it to your shell's profile file (e.g., ~/.bashrc, ~/.zshrc).

Once installed, the pre-commit hook will run automatically every time you run git commit. It will analyze the staged files and report any issues found by the Gemini model.

• If the check passes, the commit will proceed.
• If the check fails, the commit will be aborted, and you will see a list of issues to fix.

To skip the pre-commit check for a specific commit, use the --no-verify flag:

git commit -m "Your message" --no-verify

To see the full request and response from the Gemini API, set the GEMINI_CHECK_DEBUG environment variable to true:

export GEMINI_CHECK_DEBUG=true