Documentation and default model updates

What's Changed

• Add pre-commit hooks and linting check on PR by @johnlk in #46
• Update the default gpt model by @johnlk in #51
• Update readme by @johnlk in #52
• Fix broken lint action by @johnlk in #53

Full Changelog: v1.7.1...v1.7.2

Refactoring and slightly modified prompt engineering

What's Changed

• Revise the prompt for simplicity by @johnlk in #43
• Introduce PR template; new GH action; bump model by @johnlk in #44
• Refactoring to match bash standards by @johnlk in #45

Full Changelog: v1.7.0...v1.7.1

Exclude diffs from file deletions

What's Changed

• Update the readme to include release badge by @johnlk in #39
• Ensure files_to_ignore is passed as a single arg by @johnlk in #38
• Center the new badges in the readme by @johnlk in #40
• Adjust the readme to center tags by @johnlk in #41
• Optimization: skip deleted files by @johnlk in #42

Full Changelog: v1.6.1...v1.7.0

Prompt escape character fixing

This change includes a prompt escape character fix which was causing formatting issues with Robin's responses, as well as a slimmed docker image and some better logging strategies. Huge thanks to a new contributor @RytisBa who spearheaded these fixes! 🥳 🎉

Improved prompting directions

Thanks to our first external contributor @RockyNiu !! 🎉

This release includes an updated prompt to better follow the conventions of good prompt engineering as well as a format change to nest the details of the code review score in a dropdown.

Classic Prompt

Despite tons of tweaks and parameterization, the original prompt seems to perform the best.

Stricter prompt for inputs and ouputs

Code base language is now being inferred and there are more explicit callouts with respect to the inputs and outputs to be given. yet to be tested extensively with gpt4 model

Drop root language parameter

This was a regression in performances in most cases, so we're ripping it out for now.

Parameterized prompt

The initial prompt that feeds into GPT's API is now parameterized! You can set:

• project code language
• principles for GPT to pay special attention to
• principles for GPT to ignore

These new variables are optional and so no action is necessary and the logic should behave the same. Consider trying to update the coding_principles to be something like "efficiency, code complexity, or edge case handling".

Updated default model

This updates the default model option to be the more stable 3.5-turbo