fix: stop thinking when use tool_calls.

[jiangbo721]

close: #221

Pull Request Checklist

Thank you for your contribution! Before submitting your PR, please make sure you have completed the following checks:

Compatibility Check

• I have checked whether this change affects the backward compatibility of the plugin declared in README.md
• I have checked whether this change affects the forward compatibility of the plugin declared in README.md
• If this change introduces a breaking change, I have discussed it with the project maintainer and specified the release version in the README.md
• I have described the compatibility impact and the corresponding version number in the PR description
• I have checked whether the plugin version is updated in the README.md

Available Checks

• Code has passed local tests
• Relevant documentation has been updated (if necessary)

[gemini-code-assist]

Summary of Changes

Hello @jiangbo721, 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 and resolves a bug where the large language model's internal "thinking" state was not properly concluded when tool_calls were part of the response. The core change ensures that the model correctly transitions out of its reasoning phase by explicitly checking for tool_calls, thereby preventing erroneous continuous "thinking" output. This update improves the reliability of the plugin's interaction with LLMs, and the package version has been updated accordingly.

Highlights

• Tool Call Handling Fix: Modified the _wrap_thinking_by_reasoning_content method to correctly terminate the "thinking" state when tool_calls are present in the response delta, resolving an issue where the model might continue to "think" incorrectly.
• Version Update: The dify_plugin package version has been incremented from 0.5.0 to 0.5.1 in pyproject.toml to reflect this fix.

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 fix to ensure the <think> tag is properly closed when tool_calls are present in a streaming response. The logic in _wrap_thinking_by_reasoning_content is correctly updated to check for tool_calls in addition to content before exiting the 'thinking' state. The patch also includes a version bump in pyproject.toml, which is appropriate for this bug fix. The changes are correct and well-implemented.