v0.4.0

This release significantly improves GPT-4o-mini's performance with the following steps:

adding a separate reasoning step with a structured response over each label
PrefectHQ/ControlFlow#372, in particular how success tool instructions are generated
tweaking instructions to better reflect the objective
4o-mini is now capable of handling more complex instructions like "never apply this label" (when a label is otherwise obviously appropriate) or contextual application that would fail previously and require 4o proper.

What's Changed

• Improve 4o-mini output via reasoning by @jlowin in #12

Full Changelog: v0.3.0...v0.4.0

v0.3.0

What's Changed

• Fix issue with parsing fine tune config file by @jlowin in #4
• Refactor code by @jlowin in #5
• Update config to include repo labels by default by @jlowin in #6
• Fix context arg by @jlowin in #8
• Bump to 0.3.0 by @jlowin in #11

New Contributors

• @jlowin made their first contribution in #4

Full Changelog: v0.2.1...v0.3.0

v0.2.1

Bugfix: accessing the config as a dict instead of a list
Bugfix: update README YAML formatting

v0.2.0

Add files to context, such as CODEOWNERS, contribution guides, and more.

Initial release

v0.1.0

Update action.yml