Installation

To get started with PR-Agent quickly, you first need to acquire two tokens:

An OpenAI key from here, with access to GPT-4.
A GitHub\GitLab\BitBucket personal access token (classic) with the repo scope.

There are several ways to use PR-Agent:

Locally

Using Docker image (no installation required)
Run from source

GitHub specific methods

Run as a GitHub Action
Run as a polling server
Run as a GitHub App
Deploy as a Lambda Function
AWS CodeCommit

GitLab specific methods

Run a GitLab webhook server

BitBucket specific methods

Run as a Bitbucket Pipeline
Run on a hosted app

Use Docker image (no installation required)

To request a review for a PR, or ask a question about a PR, you can run directly from the Docker image. Here's how:

For GitHub:

docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review

For GitLab:

docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review

For BitBucket:

docker run --rm -it -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=<pr_url> review

For other git providers, update CONFIG.GIT_PROVIDER accordingly, and check the pr_agent/settings/.secrets_template.toml file for the environment variables expected names and values.

Similarly, to ask a question about a PR, run the following command:

docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"

A list of the relevant tools can be found in the tools guide.

Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest:

docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> review

in addition, you can run a specific released versions of pr-agent, for example:

codiumai/pr-agent@v0.8

Run from source

Clone this repository:

git clone https://github.com/Codium-ai/pr-agent.git

Install the requirements in your favorite virtual environment:

pip install -r requirements.txt

Copy the secrets template file and fill in your OpenAI key and your GitHub user token:

cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
chmod 600 pr_agent/settings/.secrets.toml
# Edit .secrets.toml file

Add the pr_agent folder to your PYTHONPATH, then run the cli.py script:

export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
python3 -m pr_agent.cli --pr_url <pr_url> review
python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
python3 -m pr_agent.cli --pr_url <pr_url> describe
python3 -m pr_agent.cli --pr_url <pr_url> improve
python3 -m pr_agent.cli --pr_url <pr_url> add_docs
python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
...

Run as a GitHub Action

You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.

Add the following file to your repository under .github/workflows/pr_agent.yml:

on:
  pull_request:
  issue_comment:
jobs:
  pr_agent_job:
    runs-on: ubuntu-latest
    permissions:
      issues: write
      pull-requests: write
      contents: write
    name: Run pr agent on every pull request, respond to user comments
    steps:
      - name: PR Agent action step
        id: pragent
        uses: Codium-ai/pr-agent@main
        env:
          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

** if you want to pin your action to a specific release (v0.7 for example) for stability reasons, use:

on:
  pull_request:
  issue_comment:

jobs:
  pr_agent_job:
    runs-on: ubuntu-latest
    permissions:
      issues: write
      pull-requests: write
      contents: write
    name: Run pr agent on every pull request, respond to user comments
    steps:
      - name: PR Agent action step
        id: pragent
        uses: Codium-ai/pr-agent@v0.7
        env:
          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

Add the following secret to your repository under Settings > Secrets:

OPENAI_KEY: <your key>

The GITHUB_TOKEN secret is automatically created by GitHub.

Merge this change to your main branch. When you open your next PR, you should see a comment from github-actions bot with a review of your PR, and instructions on how to use the rest of the tools.
You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the configuration file. Some examples:

      env:
        # ... previous environment values
        OPENAI.ORG: "<Your organization name under your OpenAI account>"
        PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
        PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions

Run as a polling server

Request reviews by tagging your GitHub user on a PR

Follow steps 1-3 of the GitHub Action setup.

Run the following command to start the server:

python pr_agent/servers/github_polling.py

Run as a GitHub App

Allowing you to automate the review process on your private or public repositories.

Create a GitHub App from the Github Developer Portal.
- Set the following permissions:
  - Pull requests: Read & write
  - Issue comment: Read & write
  - Metadata: Read-only
  - Contents: Read-only
- Set the following events:
  - Issue comment
  - Pull request
Generate a random secret for your app, and save it for later. For example, you can use:

WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")

Acquire the following pieces of information from your app's settings page:
- App private key (click "Generate a private key" and save the file)
- App ID
Clone this repository:

git clone https://github.com/Codium-ai/pr-agent.git

Copy the secrets template file and fill in the following:
```
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
# Edit .secrets.toml file
```
- Your OpenAI key.
- Copy your app's private key to the private_key field.
- Copy your app's ID to the app_id field.
- Copy your app's webhook secret to the webhook_secret field.
- Set deployment_type to 'app' in configuration.toml

The .secrets.toml file is not copied to the Docker image by default, and is only used for local development. If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file. In most production environments, you would inject the secrets file as environment variables or as mounted volumes. For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following, assuming you have a secret named pr-agent-settings with a key named .secrets.toml:

       volumes:
        - name: settings-volume
          secret:
            secretName: pr-agent-settings
// ...
       containers:
// ...
          volumeMounts:
            - mountPath: /app/pr_agent/settings_prod
              name: settings-volume

Another option is to set the secrets as environment variables in your deployment environment, for example OPENAI.KEY and GITHUB.USER_TOKEN.

Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:

docker build . -t codiumai/pr-agent:github_app --target github_app -f docker/Dockerfile
docker push codiumai/pr-agent:github_app  # Push to your Docker repository

Host the app using a server, serverless function, or container environment. Alternatively, for development and debugging, you may use tools like smee.io to forward webhooks to your local machine. You can check Deploy as a Lambda Function
Go back to your app's settings, and set the following:
- Webhook URL: The URL of your app's server or the URL of the smee.io channel.
- Webhook secret: The secret you generated earlier.
Install the app by navigating to the "Install App" tab and selecting your desired repositories.

Note: When running PR-Agent from GitHub App, the default configuration file (configuration.toml) will be loaded.
However, you can override the default tool parameters by uploading a local configuration file .pr_agent.toml
For more information please check out the USAGE GUIDE

Deploy as a Lambda Function

Follow steps 1-5 of Method 5.

Build a docker image that can be used as a lambda function

docker buildx build --platform=linux/amd64 . -t codiumai/pr-agent:serverless -f docker/Dockerfile.lambda

Push image to ECR

docker tag codiumai/pr-agent:serverless <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
docker push <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless

Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
Configure the lambda function to have a Function URL.
Go back to steps 8-9 of Method 5 with the function url as your Webhook URL. The Webhook URL would look like https://<LAMBDA_FUNCTION_URL>/api/v1/github_webhooks

AWS CodeCommit Setup

Not all features have been added to CodeCommit yet. As of right now, CodeCommit has been implemented to run the pr-agent CLI on the command line, using AWS credentials stored in environment variables. (More features will be added in the future.) The following is a set of instructions to have pr-agent do a review of your CodeCommit pull request from the command line:

Create an IAM user that you will use to read CodeCommit pull requests and post comments
- Note: That user should have CLI access only, not Console access
Add IAM permissions to that user, to allow access to CodeCommit (see IAM Role example below)
Generate an Access Key for your IAM user
Set the Access Key and Secret using environment variables (see Access Key example below)
Set the git_provider value to codecommit in the pr_agent/settings/configuration.toml settings file
Set the PYTHONPATH to include your pr-agent project directory
- Option A: Add PYTHONPATH="/PATH/TO/PROJECTS/pr-agent to your .env file
- Option B: Set PYTHONPATH and run the CLI in one command, for example:
  - PYTHONPATH="/PATH/TO/PROJECTS/pr-agent python pr_agent/cli.py [--ARGS]

AWS CodeCommit IAM Role Example

Example IAM permissions to that user to allow access to CodeCommit:

Note: The following is a working example of IAM permissions that has read access to the repositories and write access to allow posting comments
Note: If you only want pr-agent to review your pull requests, you can tighten the IAM permissions further, however this IAM example will work, and allow the pr-agent to post comments to the PR
Note: You may want to replace the "Resource": "*" with your list of repos, to limit access to only those repos

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": [
                "codecommit:BatchDescribe*",
                "codecommit:BatchGet*",
                "codecommit:Describe*",
                "codecommit:EvaluatePullRequestApprovalRules",
                "codecommit:Get*",
                "codecommit:List*",
                "codecommit:PostComment*",
                "codecommit:PutCommentReaction",
                "codecommit:UpdatePullRequestDescription",
                "codecommit:UpdatePullRequestTitle"
            ],
            "Resource": "*"
        }
    ]
}

AWS CodeCommit Access Key and Secret

Example setting the Access Key and Secret using environment variables

export AWS_ACCESS_KEY_ID="XXXXXXXXXXXXXXXX"
export AWS_SECRET_ACCESS_KEY="XXXXXXXXXXXXXXXX"
export AWS_DEFAULT_REGION="us-east-1"

AWS CodeCommit CLI Example

After you set up AWS CodeCommit using the instructions above, here is an example CLI run that tells pr-agent to review a given pull request. (Replace your specific PYTHONPATH and PR URL in the example)

PYTHONPATH="/PATH/TO/PROJECTS/pr-agent" python pr_agent/cli.py \
  --pr_url https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/MY_REPO_NAME/pull-requests/321 \
  review

Run a GitLab webhook server

From the GitLab workspace or group, create an access token. Enable the "api" scope only.
Generate a random secret for your app, and save it for later. For example, you can use:

WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")

Follow the instructions to build the Docker image, setup a secrets file and deploy on your own server from Method 5 steps 4-7.
In the secrets file, fill in the following:
- Your OpenAI key.
- In the [gitlab] section, fill in personal_access_token and shared_secret. The access token can be a personal access token, or a group or project access token.
- Set deployment_type to 'gitlab' in configuration.toml
Create a webhook in GitLab. Set the URL to the URL of your app's server. Set the secret token to the generated secret from step 2. In the "Trigger" section, check the ‘comments’ and ‘merge request events’ boxes.
Test your installation by opening a merge request or commenting or a merge request using one of CodiumAI's commands.

Run as a Bitbucket Pipeline

You can use the Bitbucket Pipeline system to run PR-Agent on every pull request open or update.

Add the following file in your repository bitbucket_pipelines.yml

pipelines:
    pull-requests:
      '**':
        - step:
            name: PR Agent Review
            image: python:3.10
            services:
              - docker
            script:
              - docker run -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=https://bitbucket.org/$BITBUCKET_WORKSPACE/$BITBUCKET_REPO_SLUG/pull-requests/$BITBUCKET_PR_ID review

Add the following secure variables to your repository under Repository settings > Pipelines > Repository variables. OPENAI_API_KEY: BITBUCKET_BEARER_TOKEN:

You can get a Bitbucket token for your repository by following Repository Settings -> Security -> Access Tokens.

Run on a hosted Bitbucket app

Please contact support@codium.ai if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the bitbucket_app.py implmentation.

=======

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

INSTALL.md

INSTALL.md

Installation

Use Docker image (no installation required)

Run from source

Run as a GitHub Action

Run as a polling server

Run as a GitHub App

Deploy as a Lambda Function

AWS CodeCommit Setup

AWS CodeCommit IAM Role Example

AWS CodeCommit Access Key and Secret

AWS CodeCommit CLI Example

Run a GitLab webhook server

Run as a Bitbucket Pipeline

Run on a hosted Bitbucket app

Files

INSTALL.md

Latest commit

History

INSTALL.md

File metadata and controls

Installation

Use Docker image (no installation required)

Run from source

Run as a GitHub Action

Run as a polling server

Run as a GitHub App

Deploy as a Lambda Function

AWS CodeCommit Setup

AWS CodeCommit IAM Role Example

AWS CodeCommit Access Key and Secret

AWS CodeCommit CLI Example

Run a GitLab webhook server

Run as a Bitbucket Pipeline

Run on a hosted Bitbucket app