fix: missing content if assistant message with tool_calls

[leslie2046]

Important

1. Make sure you have read our contribution guidelines
2. Ensure there is an associated issue and you have been assigned to it
3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

Fixes #30063

• Root cause:These multi-turn thinking models(enable thinking) requires assistant message with reasoning_content filled back to LLM.
• Solution: we should ensure content not missing,write back to plugin,plugin has extract reasoning_content from via my plugin PRs.
  fix :invalid message without reasoning_content/tool_calls dify-official-plugins#2298
  feat(DeepSeek): supported deepseek-reasoner multi turn thinking with tool use . dify-official-plugins#2307

Screenshots

Before	After

These models with non-thinking still ok

Other thinking models still ok

Checklist

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[gemini-code-assist]

Summary of Changes

Hello @leslie2046, 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 critical bug where the textual content of an assistant message would be inadvertently lost if the message also contained tool calls. The fix ensures that both the textual response and any associated tool calls are correctly preserved and represented within the AssistantPromptMessage structure. Additionally, the logic for determining if an AssistantPromptMessage is considered empty has been refined to accurately account for the presence of either content or tool calls.

Highlights

• Fixing Missing Content: Ensures that AssistantPromptMessage retains its textual content even when tool_calls are present, preventing information loss in agent responses.
• Corrected Message Initialization: The AssistantPromptMessage is now initialized with the response content directly, rather than an empty string, streamlining message construction and ensuring content is always present from the start.
• Improved is_empty Logic: Updated the is_empty method for AssistantPromptMessage to accurately reflect its non-empty status if it contains either text content or tool calls, resolving a logical flaw.

🧠 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.

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 correctly fixes a bug where the text content of an assistant's message would be lost if the message also included tool calls. The changes in fc_agent_runner.py ensure that the message content is preserved during the creation of the AssistantPromptMessage. The related fix in message_entities.py correctly updates the is_empty logic to consider messages with tool calls as non-empty. The changes are logical and well-implemented. I have added one suggestion to improve the readability of the code.