Fix: Add temperature param for azure openai gpt-5.1 and gpt-5.2 if reasoning_effort is 'None'

[henry-fung]

Fix: Add temperature param for azure openai gpt-5.1 and gpt-5.2 if reasoning_effort is 'None'

Related Issues or Context

• This change ensures that the temperature parameter is correctly passed to Azure OpenAI GPT-5.1 and GPT-5.2 models when reasoning_effort is set to 'None', fixing unexpected behavior where temperature was ignored.

This PR contains Changes to LLM Models Plugin

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

[gemini-code-assist]

Summary of Changes

Hello @henry-fung, 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 issue where the temperature parameter was not being correctly utilized by Azure OpenAI GPT-5.1 and GPT-5.2 models under specific conditions. The changes ensure that when the reasoning_effort is set to 'None', the temperature parameter is properly recognized and passed to the models, thereby rectifying unexpected behavior and allowing for more precise control over model output randomness in these scenarios.

Highlights

• Parameter Configuration Update: The temperature parameter has been explicitly added as a configurable option for Azure OpenAI GPT-5.1 and GPT-5.2 models within the constants.py file. This ensures that the temperature setting can be properly defined for these specific models.
• Conditional Parameter Handling: Logic has been introduced in llm.py to manage the temperature parameter based on the reasoning_effort setting. Specifically, if reasoning_effort is anything other than 'none', the temperature parameter will be removed from the model parameters before the API call, ensuring it is only passed when reasoning_effort is 'none'.

🧠 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 adds the temperature parameter to the gpt-5.1 and gpt-5.2 models and introduces logic to handle its mutual exclusivity with reasoning_effort. The changes in models/azure_openai/models/constants.py are appropriate. However, I've found a bug in the conditional logic in models/azure_openai/models/llm/llm.py. The current implementation incorrectly removes the temperature parameter when reasoning_effort is not specified for certain models. I've included a suggested fix to address this issue.

[crazywoola]

Please sync the main branch and try it again, bump the version in the manifest as well.