[router][ci] Quick Improvement to make CI more stable

[key4ng]

Motivation

Current CI workflow is not very stable. did following improvement:

• The oss model we used in CI has really poor ability. Add clearer prompt guidance for the model to trigger a function call
• Use Qwen2.5-14b model to replace llama3.1-8b model for grpc test
• Using 4 tp oss-20b harmony grpc test. 120b is not stable when start the server

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @key4ng, 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 aims to enhance the robustness of the CI pipeline by improving the reliability of function call tests. It introduces a more explicit system prompt within the test_basic_function_call to better guide the underlying language model, ensuring that function calls are consistently triggered even with less capable models. This change is crucial for maintaining the integrity of automated tests related to function calling capabilities.

Highlights

• Improved Function Call Testing: A clearer system prompt has been added to the CI function call test to guide the model more effectively.
• Enhanced Model Reliability in CI: This change addresses the poor ability of the open-source models used in CI to reliably trigger function calls by providing explicit instructions.

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 a system prompt to the function call test to improve its reliability, especially with less capable models. The change is clear and addresses the motivation, but I've found a small typo in the updated user message content that should be corrected.

[key4ng]

this pr is ready for review ^^ @CatherineSue @slin1237