ff

[QIN2DIM]

Related Issues or Context

This PR contains Changes to Non-Plugin

• Documentation
• Other

This PR contains Changes to Non-LLM Models Plugin

• I have Run Comprehensive Tests Relevant to My Changes

This PR contains Changes to LLM Models Plugin

• My Changes Affect Message Flow Handling (System Messages and User→Assistant Turn-Taking)

• My Changes Affect Tool Interaction Flow (Multi-Round Usage and Output Handling, for both Agent App and Agent Node)

• My Changes Affect Multimodal Input Handling (Images, PDFs, Audio, Video, etc.)

• My Changes Affect Multimodal Output Generation (Images, Audio, Video, etc.)

• My Changes Affect Structured Output Format (JSON, XML, etc.)

• My Changes Affect Token Consumption Metrics

• My Changes Affect Other LLM Functionalities (Reasoning Process, Grounding, Prompt Caching, etc.)

• Other Changes (Add New Models, Fix Model Parameters etc.)

Version Control (Any Changes to the Plugin Will Require Bumping the Version)

• I have Bumped Up the Version in Manifest.yaml (Top-Level Version Field, Not in Meta Section)

Dify Plugin SDK Version

• I have Ensured dify_plugin>=0.3.0,<0.6.0 is in requirements.txt (SDK docs)

Environment Verification (If Any Code Changes)

Local Deployment Environment

• Dify Version is: , I have Tested My Changes on Local Deployment Dify with a Clean Environment That Matches the Production Configuration.

SaaS Environment

• I have Tested My Changes on cloud.dify.ai with a Clean Environment That Matches the Production Configuration

[gemini-code-assist]

Summary of Changes

Hello @QIN2DIM, 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 focuses on enhancing the configuration and capabilities of the DeepSeek-V3.2 large language model. It introduces support for advanced features like multi-tool calls and structured output, while also refining its parameter definitions for better clarity and control. A new dynamic schema patching mechanism is implemented to ensure consistent and correct model setup.

Highlights

• DeepSeek-V3.2 Model Enhancements: The DeepSeek-V3.2 model now explicitly supports multi-tool calls, document processing, and structured output, expanding its capabilities within the platform.
• Refined Temperature Parameter for DeepSeek-V3.2: The temperature parameter for DeepSeek-V3.2 has been explicitly defined with a default value of 1.0, a range of 0 to 2, and clear internationalized labels and help text, ensuring consistent behavior.
• Simplified Model Parameters: Redundant parameters such as top_p, top_k, and frequency_penalty have been removed from the DeepSeek-V3.2 YAML configuration, streamlining its definition.
• Dynamic Model Schema Configuration: A new RecommendModelSchema class has been introduced to programmatically apply specific configurations to models like DeepSeek-V3.2, ensuring essential features (tooling, agent thought) and default parameters (e.g., temperature, JSON schema) are correctly set.

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 updates the configuration for the DeepSeek V3.2 model and refactors how customizable model schemas are handled. The changes in the YAML file add new features and redefine the temperature parameter. The Python code introduces a helper class to apply model-specific patches and modifies the logic for generating customizable model schemas.

My review has identified a few issues that should be addressed:

• A copy-paste error in a user-facing help text.
• Leftover debug code that should be removed.
• Opportunities to improve maintainability by using constants for static data.

Please see the detailed comments below.

[gemini-code-assist]

This print() statement appears to be for debugging purposes. It should be removed before merging to avoid polluting logs in a production environment and potentially exposing sensitive information.

[gemini-code-assist]

The help text for temperature appears to be incorrect. It mentions "Gemini 3", but this configuration is for a DeepSeek model. This was likely a copy-paste error and should be corrected to refer to the correct model to avoid confusing users.

      en_US: For DeepSeek V3.2, best results at default 1.0. Lower values may impact reasoning.
      zh_Hans: 对于 DeepSeek V3.2，使用默认值 1.0 可获得最佳效果。数值过低可能会影响推理能力.

[gemini-code-assist]

This list of features is defined inside the method. For better organization and to make it clear that it's a static configuration, consider defining it as a private class-level constant (e.g., _DEEPSEEK_V32_FEATURES). This improves readability and maintainability.

[gemini-code-assist]

For better maintainability and performance, consider defining these model names as a module-level set constant. Using a set is more efficient for membership testing than a list.

Suggested change

	if model in ["deepseek-ai/DeepSeek-V3.2", "Pro/deepseek-ai/DeepSeek-V3.2"]:
	if model in {"deepseek-ai/DeepSeek-V3.2", "Pro/deepseek-ai/DeepSeek-V3.2"}: