[v0.18.0][Bugfix][Platform] Fix MiniMax M2 reasoning token usage accounting

[QwertyJack]

What this PR does / why we need it?

This backports the MiniMax M2 reasoning-token usage accounting fix onto releases/v0.18.0 for vllm-ascend.

The release branch does not include the other local GLM patch commit, so this PR keeps the MiniMax change self-contained by:

• registering patch_minimax_usage_accounting on the release branch
• backporting completion_tokens_details.reasoning_tokens into chat usage generation
• fixing MiniMax reasoning token counting for </think>-delimited outputs without depending on the GLM suffix patch

Does this PR introduce any user-facing change?

Yes. OpenAI-compatible chat usage accounting for MiniMax M2 responses now reports corrected reasoning token counts on the release branch.

How was this patch tested?

• python -m compileall vllm_ascend/patch/platform/patch_minimax_usage_accounting.py
• python - <<'PY' import check for vllm_ascend.patch.platform.patch_minimax_usage_accounting on top of releases/v0.18.0

No targeted automated regression test exists for this release-branch backport yet, so I validated syntax and module import compatibility on the release branch.

[gemini-code-assist]

Summary of Changes

Hello, 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 backports a critical bugfix to the releases/v0.18.0 branch of vllm-ascend, addressing inaccurate reasoning token accounting for MiniMax M2 responses in OpenAI-compatible chat usage. The changes ensure that the completion_tokens_details.reasoning_tokens field is correctly populated, providing accurate usage metrics for models that use </think> as a boundary token.

Highlights

• MiniMax M2 Reasoning Token Accounting Fix: Corrected the accounting of reasoning tokens for MiniMax M2 responses in OpenAI-compatible chat usage.
• Backport to Release Branch: Backported the fix to the releases/v0.18.0 branch for vllm-ascend to ensure stability and accuracy.
• Self-Contained Patch: Implemented the fix as a self-contained patch, avoiding dependencies on other local GLM patch commits.
• UsageInfo Extension: Extended UsageInfo with completion_tokens_details.reasoning_tokens to properly report reasoning token counts.
• Chat Usage Generation Update: Updated chat streaming and non-streaming usage generation to propagate the corrected reasoning token counts, specifically for </think>-delimited outputs.

🧠 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.

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 patch to vllm-ascend to implement MiniMax M2 reasoning token accounting for OpenAI chat usage. It extends usage information models and modifies chat completion generators to correctly track reasoning tokens. A critical issue was identified in the _count_minimax_reasoning_tokens function, which currently miscounts all completion tokens as reasoning tokens if the end_token_id is not found, leading to inaccurate usage accounting. This function should be updated to return 0 in such scenarios.