feat(model): support passing usage (e.g., cached_tokens)

[MengsD]

AgentScope Version

[The version of AgentScope you are working on, e.g. import agentscope; print(agentscope.__version__)]
1.0.10 (hot fix)

Description

[Please describe the background, purpose, changes made, and how to test this PR]

Checklist

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

• Code has been formatted with pre-commit run --all-files command
• All tests are passing
• Docstrings are in Google style
• Related documentation has been updated (e.g. links, examples, etc.)
• Code is ready for review

[gemini-code-assist]

Summary of Changes

Hello @MengsD, 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 model usage reporting capabilities within AgentScope. By introducing a new metadata field to the ChatUsage object, it enables the system to store and access more granular and provider-specific usage information, such as cached_tokens, directly from the model API responses. This change improves the richness of available usage data for analysis and debugging without altering the existing core token count fields.

Highlights

• Enhanced Usage Reporting: The ChatUsage dataclass now includes a flexible metadata field, allowing for the capture of additional, provider-specific usage details beyond just input and output tokens.
• Integration with Model Providers: The DashScope and OpenAI model parsers have been updated to populate this new metadata field with the raw usage objects received from their respective APIs, ensuring more comprehensive usage data is retained.

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 adds support for passing raw usage data from model APIs by introducing a metadata field to the ChatUsage class. The implementation is straightforward across the DashScope and OpenAI model wrappers.

However, there are a couple of points to address:

1. Missing Tests: The repository's style guide (rule #38) requires that new features must include unit tests. This PR adds a new feature, but the corresponding tests in tests/model_dashscope_test.py and tests/model_openai_test.py have not been updated to verify that the metadata field is correctly populated. Please add tests for this new functionality. The unchecked item [ ] All tests are passing in the PR description also suggests this needs attention.
2. Code Correction: I've found an issue in the definition of the new metadata field in ChatUsage which will cause a runtime error, and a type hint mismatch. I've left a specific comment with a suggestion to fix it.

Once these points are addressed, the PR will be in good shape.