-
Notifications
You must be signed in to change notification settings - Fork 118
Conversation
Summary of ChangesHello @rainsonGain, 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 refactors the handling and logging of trajectory information, specifically agent token ID trajectories. The primary goal is to centralize the logging mechanism 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 refactors the trajectory logging by moving the logic from TaskHandler to TaskEventRunner and enriching the logged data. The changes centralize the logging logic and add more context to the trajectory logs. My main feedback is on improving the structured logging format to ensure it's a valid and clean JSON, which is crucial for log processing and analysis. I've provided a suggestion to correct this.
| token_id_traj = None | ||
| if self.context.token_id_traj: | ||
| token_id_traj = json.dumps(to_serializable(self.context.token_id_traj)) | ||
|
|
||
| res = {"task_id": self.task.id, | ||
| "is_sub_task": self.task.is_sub_task, | ||
| "trajectory": json.dumps(self._task_response.trajectory, ensure_ascii=False), | ||
| "token_id_trajectory": token_id_traj} | ||
| trajectory_logger.info(f"{res}") |
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 current implementation for logging the trajectory serializes parts of the data into JSON strings (trajectory and token_id_trajectory) and then wraps them in a dictionary res. Logging this dictionary with an f-string (f"{res}") produces a string representation of a Python dictionary, not a valid JSON string. This makes the logs difficult to parse for any automated system.
To ensure the logged output is a clean, parseable JSON object, it's better to construct the dictionary with the raw data and then serialize the entire dictionary to a JSON string at the end.
| token_id_traj = None | |
| if self.context.token_id_traj: | |
| token_id_traj = json.dumps(to_serializable(self.context.token_id_traj)) | |
| res = {"task_id": self.task.id, | |
| "is_sub_task": self.task.is_sub_task, | |
| "trajectory": json.dumps(self._task_response.trajectory, ensure_ascii=False), | |
| "token_id_trajectory": token_id_traj} | |
| trajectory_logger.info(f"{res}") | |
| token_id_traj_data = None | |
| if self.context.token_id_traj: | |
| token_id_traj_data = to_serializable(self.context.token_id_traj) | |
| res = {"task_id": self.task.id, | |
| "is_sub_task": self.task.is_sub_task, | |
| "trajectory": self._task_response.trajectory, | |
| "token_id_trajectory": token_id_traj_data} | |
| trajectory_logger.info(json.dumps(res, ensure_ascii=False)) |