3.1 KiB
Contributing
We welcome Pull Requests for general contributions. If you have a larger new feature or any questions on how to develop a fix, we recommend you open an issue before starting.
Prerequisites
Goose uses uv for dependency management, and formats with ruff.
Clone goose and make sure you have installed uv to get started. When you use
uv below in your local goose directly, it will automatically setup the virtualenv
and install dependencies.
We provide a shortcut to standard commands using just in our justfile.
Development
Now that you have a local environment, you can make edits and run our tests!
Run Goose
If you've made edits and want to try them out, use
uv run goose session start
or other goose commands.
If you want to run your local changes but in another directory, you can use the path in the virtualenv created by uv:
alias goosedev=`uv run which goose`
You can then run goosedev from another dir and it will use your current changes.
Run Tests
To run the test suite against your edges, use pytest:
uv run pytest tests -m "not integration"
or, as a shortcut,
just test
Exchange
The lower level generation behind goose is powered by the exchange package, also in this repo.
Thanks to uv workspaces, any changes you make to exchange will be reflected in using your local goose. To run tests
for exchange, head to packages/exchange and run tests just like above
uv run pytest tests -m "not integration"
Evaluations
Given that so much of Goose involves interactions with LLMs, our unit tests only go so far to confirming things work as intended.
We're currently developing a suite of evaluations, to make it easier to make improvements to Goose more confidently.
In the meantime, we typically incubate any new additions that change the behavior of the Goose through opt-in plugins - Toolkits, Moderators, and Providers. We welcome contributions of plugins that add new capabilities to goose. We recommend sending in several examples of the new capabilities in action with your pull request.
Additions to the developer toolkit change the core performance, and so will need to be measured carefully.
Conventional Commits
This project follows the Conventional Commits specification for PR titles. Conventional Commits make it easier to understand the history of a project and facilitate automation around versioning and changelog generation.