feat: update agent graders

[jc200808]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @jc200808, 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 focuses on enhancing the consistency, clarity, and maintainability of the agent grader modules. It standardizes prompt string formatting, refines type hints for better code quality, and updates example usage to reflect best practices for asynchronous operations. These changes contribute to a more robust and user-friendly grading system for agent behaviors.

Highlights

• Prompt Formatting Standardization: All multi-line prompt strings across various agent graders (e.g., ACTION_ALIGNMENT_PROMPT_EN, MEMORY_ACCURACY_PROMPT_ZH) have been updated to use textwrap.dedent() and .strip() for consistent and correct indentation, removing leading whitespace.
• Improved Type Hinting: The history parameter in _format_history and aevaluate methods within the grader classes now uses more precise type hints, changing from Optional[list] to Optional[List[Dict[str, Any]]], enhancing code readability and maintainability.
• Asynchronous Example Updates: The example usage blocks for all graders have been modified to correctly demonstrate asynchronous execution by adding import asyncio and wrapping await grader.aevaluate(...) calls with asyncio.run(...).
• Refined History Step Numbering: The _format_history method now enumerates history steps starting from 1 instead of 0, providing more natural and human-readable step numbering in the output.
• Simplified Context String Formatting: The logic for formatting the context_str has been streamlined into a single conditional expression, making the code more concise.

🧠 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 Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces a series of consistent refactorings and improvements across multiple agent grader files. The changes enhance code quality, readability, and maintainability. Key improvements include: using textwrap.dedent().strip() for cleaner multiline prompt strings, updating type hints for more specificity, making docstring examples runnable, and adopting more Pythonic constructs. The changes are well-executed and represent a good step forward for the codebase. I've pointed out a couple of issues where doctest examples seem to have been inadvertently broken by the changes.

[ployts]

Please install pre-commit and format your code first to merge