PatchWork

An open-source framework for automating development chores using large language models. PatchWork allows you to automate workflows like PR reviews, bug fixing, security patching, and more using a self-hosted CLI agent and your preferred LLMs.

Key Components

Steps: A set of reusable atomic actions that define various operations.
Patchflows: LLM-assisted automations such as PR reviews, code fixing, debugging.

Patchflows can be run locally in your CLI and IDE, or as part of your CI/CD pipeline.

Installation

Using Pip

PatchWork is available on PyPI and can be installed using pip:

pip install patchwork-cli --upgrade

Using Poetry

PatchWork is built using Poetry, a dependency management and packaging tool for Python. To install PatchWork using Poetry, follow these steps:

Make sure you have Poetry installed. If you don't have it installed, you can install it by running:
```
curl -sSL https://install.python-poetry.org | python3 -
```

Clone the PatchWork repository:

git clone https://github.com/patched-codes/patchwork.git

Navigate to the project directory:
```
cd patchwork
```
Activate a shell using virtual environment:
```
poetry shell
```
Install the dependencies using Poetry:
```
poetry install
```

PatchWork CLI

The CLI runs Patchflows, as follows:

patchwork <Patchflow> <?Arguments>

Where

Arguments: Allow for overriding default/optional attributes of the Patchflow in the format of key=value. If key does not have any value, it is considered a boolean True flag.

Example

For an AutoFix patchflow which patches vulnerabilities based on a scan using Semgrep:

patchwork AutoFix openai_api_key=<YOUR_OPENAI_API_KEY> github_api_key=<YOUR_GITHUB_TOKEN>

The above command will default to patching code in the current directory, by running Semgrep to identify the vulnerabilities.

You can take a look at the default.yml file for the list of configurations you can set to manage the AutoFix patchflow. You will need to pass your own openai_api_key to call the LLM. Otherwise, to get started, you can get a patched_api_key for free by by signing in at https://app.patched.codes/signin and generating an API key from the integrations tab. You can then call the patchflow with the key as follows:

patchwork AutoFix patched_api_key=<YOUR_PATCHED_API_KEY> github_api_key=<YOUR_GITHUB_TOKEN>

The patchwork-configs repository contains the default configuration and prompts for all the patchflows. You can clone that repo and pass it as a flag to the CLI:

patchwork AutoFix --config /path/to/patchwork-configs/patchflows

Patchflows

Patchwork comes with a set of predefined patchflows, and more will be added over time. Below is a sample list of patchflows:

AutoFix: Generate and apply fixes to code vulnerabilities in a repository.
DependencyUpgrade: Update your dependencies from vulnerable to fixed versions.
PRReview: On PR creation, extract code diff, summarize changes, and comment on PR.
GenerateREADME: Create a README.md file for a given folder, to add documentation to your repository.
ResolveIssue: Identify the files in your repository that need to be updated to resolve an issue (or bug) and create a PR to fix it.

Prompt Templates

Prompt templates are used by patchflows and passed as queries to LLMs. Templates contain prompts with placeholder variables enclosed by {{}} which are replaced by the data from the steps or inputs on every run.

Below is a sample prompt template:

{
  "id": "diffreview_summary",
    "prompts": [
      {
        "role": "user",
        "content": "Summarize the following code change descriptions in 1 paragraph. {{diffreviews}}"
      }
    ]
}

Each patchflow comes with an optimized default prompt template. But you can specify your own using the prompt_template_file=/path/to/prompt/template/file option.

Contributing

To create a new patchflow, follow these instructions.

To create a new step, follow these instructions.

We also provide chat assitants to help you create new steps and patchflows easily.

Patchwork Assistant GPT (requires ChatGPT pro subscription)
Patchwork Assistant on HuggingChat (free)

patched-codes / patchwork