-
Notifications
You must be signed in to change notification settings - Fork 119
Conversation
Summary of ChangesHello @ahgpt, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request addresses parameter handling within the Highlights
New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with and on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
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.
Code Review
This pull request updates the async_policy method in serial_llm_agent.py, changing its signature and the way exec_agent is called. While the changes seem intended to pass more context, they introduce a critical bug. The new message parameter can be None, but its context attribute is accessed without a null check, which will cause an AttributeError. I've provided a comment with a code suggestion to fix this critical issue and also improve the code's readability.
| if not observation.info: | ||
| observation = observation.content | ||
| result = await exec_agent(observation, agent, message.context, sub_task=True) |
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.
This block has a critical issue and a readability concern:
- Critical Bug: The
messageparameter can beNone(as per the signature on line 32), butmessage.contextis used on line 40 without a null check. This will cause anAttributeErrorifmessageis not provided. - Readability: The
observationvariable is conditionally reassigned to a different type (Any) within the loop. This makes the code harder to follow and maintain.
I suggest refactoring this block to address both points for robustness and clarity.
raise ValueError("A 'message' object with context is required for serial agent execution.")
question = observation.content if not observation.info else observation
result = await exec_agent(question, agent, message.context, sub_task=True)