[Bugfix] Fix the issue where reasoning_content is None when Thinkng is enabled and tool_choice is set to 'required'.

[chaunceyjiang]

FIX #20663

Test Result

Before:

ChatCompletion(id='chatcmpl-4e05fee0c73c4811ba8c7f21939c06c8', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='chatcmpl-tool-f227417118b24070b61554cc4416aba9', function=Function(arguments='{"city": "Beijing", "country": "China", "unit": "celsius"}', name='get_current_weather'), type='function')], reasoning_content=None), stop_reason=None)], created=1752032478, model='Qwen/Qwen3-8B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=228, prompt_tokens=247, total_tokens=475, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, kv_transfer_params=None)

After

ChatCompletion(id='chatcmpl-ccd1ac636c004d76821ed0e81c55014f', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='chatcmpl-tool-027f368f49084786a3728df40263bc9e', function=Function(arguments='{"city": "Beijing", "country": "China", "unit": "celsius"}', name='get_current_weather'), type='function')], reasoning_content="\nOkay, the user is asking about the weather in Beijing. Let me check the tools provided. There's a function called get_current_weather. The parameters required are country and unit, with city as optional but defaulting to Vienna. Since the user mentioned Beijing, I should specify the city as Beijing. The country parameter is required, so I need to set that to China. The unit isn't specified, so maybe I should default to celsius as it's commonly used. Let me make sure the function call includes all required parameters. Country is China, unit is celsius, and city is Beijing. That should work.\n"), stop_reason=None)], created=1752032282, model='Qwen/Qwen3-8B', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=173, prompt_tokens=247, total_tokens=420, completion_tokens_details=None, prompt_tokens_details=None), prompt_logprobs=None, kv_transfer_params=None)

[gemini-code-assist]

Summary of Changes

Hello @chaunceyjiang, 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 resolves a bug in the OpenAI API entrypoint that caused the reasoning_content field to be missing under specific conditions involving enabled 'Thinking' and required tool choices. My changes ensure that this crucial debugging and transparency information is always present when expected, and I've added a test to confirm the fix.

Highlights

• Bug Fix: I've addressed an issue where the reasoning_content field in the ChatMessage object was None when Thinking was enabled and tool_choice was set to 'required'.
• Core Logic Update: I've updated the chat_completion_full_generator to ensure that reasoning_content is correctly passed to the ChatMessage constructor when generating tool call messages.
• Test Coverage: I've added new assertions to the test_function_tool_use test case to verify that reasoning_content is properly populated (not None or empty) when enable_thinking is active.

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

This PR addresses a bug where reasoning_content was None when Thinking is enabled and tool_choice is set to 'required'. The changes include adding reasoning_content to the ChatMessage object and adding a test case to verify the fix. A suggestion to improve the streaming test case and a potential improvement to the ChatMessage initialization are provided.

[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.

🚀

[DarkLight1337]

Thanks for fixing!