-
Notifications
You must be signed in to change notification settings - Fork 121
Add reviewbot.py #4129
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Add reviewbot.py #4129
Conversation
|
Commit: e180b82
12 interesting tests: 7 KNOWN, 4 flaky, 1 SKIP
Top 25 slowest tests (at least 2 minutes):
|
| ## Review Checklist | ||
|
|
||
| ### Code Quality | ||
| - [ ] Code follows the project's style guide and conventions |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Which are? Should it have a link?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I figured claude would figure out the style guide by osmosis. We can add a dedicated style guide later one. Things like acceptance tests could use style consolidation.
|
Good bot. Besides posting comments PRs, which is good for reviewing external contributions, can we just have a mode where it prints the review locally? |
|
@denik Printing the review locally is the default mode. You can at the end choose not to publish the review in the prompt. We can always add a flag later if you think that would make for a clearer interface. |
|
Here's a sample review today: This makes it explicit that these are request-only fields that should not affect drift detection. ================================================================================ Publish this review to GitHub? [y/N]: |
Changes
Adds a Python-based review bot tool (
tools/reviewbot.py) that uses Claude Code to assist with PR reviews.Features:
prompts/review.mdcovering:Usage
Why
An experimental tool to help out with initial PR reviews. Used it on: #4126