[Bugfix] Fix Mistral tool-parser regex for nested JSON

[mgoin]

Purpose

FIX #19193 (comment)

Capture the full outermost argument block (including nested braces) and add a unit test validating correct parsing of nested JSON tool calls.

Test Plan

pytest -s -v tests/models/language/generation/test_mistral.py -k "test_mistral_function_call_nested_json"

Test Result

Passed

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Summary of Changes

Hello @mgoin, 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 addresses a parsing issue in the Mistral tool parser, specifically when handling tool calls with nested JSON arguments. It introduces a more robust regular expression to accurately extract these complex arguments and includes a dedicated unit test to verify the fix and prevent regressions.

Highlights

• Mistral Tool Parser Fix: I've updated the MistralToolParser's regular expression (fn_name_regex) to correctly capture the full outermost JSON argument block, including cases with nested JSON structures. This was achieved by changing the non-greedy match from .*? to [\s\S]*? and adding a positive lookahead (?=\s*$|,|\s) to properly delimit the JSON arguments.
• New Unit Test: I've added a new unit test, test_mistral_function_call_nested_json, to validate the improved MistralToolParser's ability to parse tool calls containing deeply nested JSON arguments, ensuring the entire argument structure is captured without truncation.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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

The pull request fixes a bug in the Mistral tool-parser regex to correctly parse nested JSON structures within tool calls. A unit test has been added to validate the fix. The regex pattern for function name extraction has been updated to capture the full outermost argument block, including nested braces.

[gemini-code-assist]

The regex [sS] is not the most efficient way to match any character including newlines. Consider using . with the re.DOTALL flag, which is already enabled, or (?s:.) for inline application. While this change might not have a significant impact on small inputs, it could affect performance with larger inputs or frequent use. It's better to use the most efficient pattern possible.

r'([a-zA-Z0-9_-]+)(\{.*?\})(?=\s*$|,|\s)'