[router] add minmax m2 reasoning parser

[slin1237]

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 @slin1237, 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 enhances the router's capability to process reasoning outputs from Large Language Models by adding specific support for MiniMax M2 models. It introduces a new parser that automatically manages the unique <think> token requirement of these models, ensuring their reasoning steps are correctly identified and extracted. This integration allows the system to seamlessly work with MiniMax M2 models, improving the overall flexibility and compatibility of the reasoning parser framework.

Highlights

• New MiniMax M2 Reasoning Parser: Introduced a dedicated MiniMaxParser to correctly handle reasoning outputs from MiniMax M2 models, which require a specific <think> token at the beginning of their output.
• Automatic Token Prepending: The new parser automatically prepends the <think> token to the input text for both one-shot and the initial chunk of streaming parsing, ensuring compatibility with MiniMax M2's expected format.
• Parser Factory Integration: The MiniMaxParser has been integrated into the ParserFactory, allowing it to be instantiated via various model patterns such as 'minimax', 'minimax-m2', and 'mm-m2'.
• Comprehensive Unit Tests: Added new unit tests to validate the MiniMaxParser's functionality, covering one-shot parsing, streaming behavior, reset logic, and factory integration.

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 new reasoning parser for MiniMax M2 models. The implementation is clean and follows existing patterns by creating a MiniMaxParser that wraps the BaseReasoningParser to prepend the <think> token. The changes are well-integrated into the factory, with appropriate model matching patterns and comprehensive unit tests. I have one suggestion to improve the performance of the streaming implementation by avoiding an unnecessary string allocation.