Enhance AgentScope Workflow Adapter

[pan-x-c]

Description

As the title says

Checklist

Please check the following items before code is ready to be reviewed.

• Code has passed all tests
• Docstrings have been added/updated in Google Style
• Documentation has been updated
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @pan-x-c, 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 significantly enhances the integration capabilities with AgentScope by introducing a new, more versatile workflow adapter. This adapter facilitates the use of advanced AgentScope features, such as trainable workflows and judge functions, within the Trinity ecosystem, alongside updating necessary dependency versions to support these new functionalities.

Highlights

• New Workflow Adapter: Introduced AgentScopeWorkflowAdapterV1, a more general adapter designed to seamlessly integrate AgentScope's trainable workflows and judge functions into the Trinity framework.
• Dependency Updates: Updated the minimum required agentscope version for both the existing AgentScopeWorkflowAdapter (to 1.0.7) and the new AgentScopeWorkflowAdapterV1 (to 1.0.11), ensuring compatibility with the latest features.
• Enhanced Experience Construction: The construct_experiences method in AgentScopeWorkflowAdapterV1 now supports attaching metrics to the generated experiences, providing richer data for analysis.
• Dynamic Reward and Metric Handling: The new adapter's run_async method intelligently handles WorkflowOutput and JudgeOutput to collect metrics and determine rewards, offering flexible evaluation mechanisms for workflows.

🧠 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 enhances the AgentScope workflow adapter by introducing a new AgentScopeWorkflowAdapterV1 and updating dependencies. The new adapter is more flexible, supporting judge functions. My review has identified a critical issue in exception handling that could lead to a crash, a high-severity bug that may cause an IndexError, and an inconsistency in model initialization. I have provided suggestions to fix these issues and improve code quality and robustness.