fix(platform): reimplement MiniMax usage accounting patch

[QwertyJack]

Summary

• replace the MiniMax usage accounting monkey patch with a runtime wrapper implementation instead of source-text rewriting
• preserve MiniMax reasoning-token semantics when </think> is missing by counting the emitted output as reasoning tokens
• add unit coverage for usage tracking helpers and MiniMax reasoning-token counting

Why

The previous implementation rewrote OpenAIServingChat by matching exact source blocks. That was brittle against vllm source drift and could crash during early plugin initialization with:
RuntimeError: Failed to locate expected block while patching OpenAIServingChat usage accounting.

This change keeps the usage-accounting backport, but applies it by wrapping the original stream/full generators and tracking output token ids at runtime.

For MiniMax reasoning counting, a missing </think> should not be treated as zero reasoning tokens. It can mean the whole output is still in thinking mode, or that generation stopped before the closing token was produced. In that case, the emitted output should still be counted as reasoning.

Validation

• pytest -q tests/ut/patch/platform/test_patch_minimax_usage_accounting.py
• vllm serve --help

[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 improves the stability and reliability of the MiniMax usage accounting mechanism by moving away from source-code manipulation. By implementing a runtime wrapper, the system is now less susceptible to upstream source drift in vllm. Additionally, it refines the reasoning token counting logic to ensure accurate reporting and adds necessary test coverage to validate these changes.

Highlights

• Refactored Usage Accounting: Replaced the brittle source-text rewriting monkey patch for MiniMax usage accounting with a more robust runtime wrapper implementation.
• Reasoning Token Logic: Corrected reasoning token counting to return 0 when the tag is absent, preventing inaccurate token reporting.
• Improved Test Coverage: Added comprehensive unit tests for usage tracking helpers and verified the corrected reasoning-token behavior.

🧠 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

Suggested PR Title:

[Ops][BugFix] Refactor MiniMax usage accounting to wrapper-based patching and fix reasoning token count

Suggested PR Summary:

### What this PR does / why we need it?
This PR refactors the MiniMax usage accounting implementation in `vllm_ascend`. It replaces the previous AST-based method patching with a more maintainable wrapper-based approach for `chat_completion_stream_generator` and `chat_completion_full_generator`. Additionally, it fixes a bug in `_count_minimax_reasoning_tokens` where the absence of an end token incorrectly counted all tokens as reasoning tokens; it now correctly returns 0.

### Does this PR introduce _any_ user-facing change?
Yes, it improves the accuracy of token usage reporting for MiniMax models when the reasoning block is not properly terminated.

### How was this patch tested?
The patch was tested using updated and new unit tests in `tests/ut/patch/platform/test_patch_minimax_usage_accounting.py` covering usage tracking state, SSE payload handling, and final usage summation.

I have no further feedback to provide.