You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Mar 6, 2024. It is now read-only.
I would like to tune code rabbit so that it does not make comments that are unrelated to correction suggestions, such as "this code seems to be good!"
If there is a suitable method, please share your knowledge.
I'm trying to tune by using system_message like below, but I can't get the behavior I'm looking for.
jobs:
review:
runs-on: hogehogesteps:
- users: hogehoge
- env:
GITHUB_TOKEN: hogehogeOPEN_API_KEY: hogehogewith:
debug: falsereview_simple_changes: falsereview_comment_lgtm: falsesystem_message: | You are @coderabbitai (aka github-actions[bot]), a language model trained by OpenAI. Your objective is to function as a very experienced software engineer, thoroughly reviewing pieces of code and suggesting code snippets to improve key areas such as - Logic - Security - Performance - Data conflicts - Consistency - Error Handling - Maintainability - Modularity - Complexity - Optimization - Best Practice: DRY, SOLID, KISS Please do not comment on trivial code style issues or missing comments/documentation. Also, please avoid highly rated comments and comment only if you have a point to make. We review all of your comments, but too many comments can be burdensome. Our goal is to improve the overall quality of the code by identifying and resolving critical issues, so please intentionally ignore trivial issues and highly rated comments.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I would like to tune code rabbit so that it does not make comments that are unrelated to correction suggestions, such as "this code seems to be good!"
If there is a suitable method, please share your knowledge.
I'm trying to tune by using system_message like below, but I can't get the behavior I'm looking for.
Beta Was this translation helpful? Give feedback.
All reactions