Skip to content

Add learnings from code review analysis #2280

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.

Sign up for GitHub

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

Merged
xingyaoww merged 5 commits into from
Mar 7, 2026
Merged

Add learnings from code review analysis #2280

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
ba822a3
Add learnings from code review analysis
openhands-agent Mar 3, 2026
38d1306
Remove code review references from generated content
openhands-agent Mar 3, 2026
c24bbfb
Remove redundant CODING_GUIDELINES section
openhands-agent Mar 3, 2026
dbabdd8
Simplify eval-risk to single AGENTS.md line
openhands-agent Mar 5, 2026
ec1b77d
Update eval-risk guidance to mention integration-test label
openhands-agent Mar 5, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -337,6 +337,7 @@ These are enforced by `check_sdk_api_breakage.py` (runs on release PRs). Depreca
- DON'T write TEST CLASSES unless absolutely necessary!
- If you find yourself duplicating logics in preparing mocks, loading data etc, these logic should be fixtures in conftest.py!
- Please test only the logic implemented in the current codebase. Do not test functionality (e.g., BaseModel.model_dumps()) that is not implemented in this repository.
- For changes to prompt templates, tool descriptions, or agent decision logic, add the `integration-test` label to trigger integration tests and verify no unexpected impact on benchmark performance.

# Behavior Tests

Expand Down Expand Up @@ -423,4 +424,5 @@ For examples that use the critic model (e.g., `34_critic_example.py`), the criti
- Ruff ignores `ARG` (unused arguments) under `tests/**/*.py` to allow pytest fixtures.
- Repository guidance lives in `AGENTS.md` (loaded as a third-party skill file).
</REPO_CONFIG_NOTES>

</REPO>
Loading