-
Notifications
You must be signed in to change notification settings - Fork 0
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
Testing review-pr #3
Conversation
(cherry picked from commit b45bc16)
to avoid running as root.
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.
The changes in review-pr.yml seem to be mostly formatting and syntax updates.
However, I noticed that the Python version has been updated to 3.11.
Additionally, the LLM_MODEL variable has been added as an environment variable.
It would be good to test these changes to ensure they do not break any existing functionality.
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.
The changes in .github/workflows/review-pr.yml seem to be refactoring the workflow to use actions/checkout and actions/setup-python. However, it's not clear why the container image and volumes were removed.
In opendevin/runtime/docker/ssh_box.py, the hostname is replaced with 'localhost' when logging the SSH command. This might affect the logging output.
In opendevin/server/session/agent.py, the LLM configuration is overridden with default values. This might change the behavior of the agent.
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.
The changes in .github/workflows/review-pr.yml seem to be updating the workflow to use actions/checkout@v4 and actions/setup-python@v5. This is a good practice for consistency and security.
The changes in agenthub/browsing_agent/response_parser.py, agenthub/codeact_agent/action_parser.py, and agenthub/codeact_swe_agent/response_parser.py seem to be handling None values and adding proper stripping and formatting for code blocks. This is a good practice for error handling and code readability.
Overall, the changes look good and follow best practices. However, it would be great to see more descriptive commit messages and comments explaining the reasoning behind these changes.
Just make an inline comment.