Bugfix/Supervisor Node AzureChatOpenAI

[HenryHengZJ]

Integrate AzureChatOpenAI into the Supervisor node to handle user requests alongside ChatOpenAI. This enhancement allows for improved multi-agent conversation management.

[gemini-code-assist]

Summary of Changes

Hello @HenryHengZJ, 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 introduces support for AzureChatOpenAI within the Supervisor node. By integrating Azure's OpenAI service, the system gains increased flexibility in managing multi-agent conversations, enabling the supervisor to utilize AzureChatOpenAI instances alongside existing ChatOpenAI models for processing user requests.

Highlights

• AzureChatOpenAI Integration: The Supervisor node now supports AzureChatOpenAI, allowing it to handle user requests using this model in addition to ChatOpenAI.
• Multi-Agent Conversation Management: This integration enhances the Supervisor node's capability to manage multi-agent conversations by expanding the range of supported language models.

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 integrates AzureChatOpenAI into the Supervisor node by updating the logic to handle it alongside ChatOpenAI. While the approach is correct, the change is incomplete as it was not applied to the code path where summarization is enabled. This will cause AzureChatOpenAI to fail in that scenario. I've left a critical comment to address this bug. Additionally, I've pointed out a maintainability issue due to significant code duplication, which likely contributed to this bug, and suggested a refactoring to prevent similar issues in the future.

[gemini-code-assist]

While this correctly adds support for AzureChatOpenAI in the createTeamSupervisor function, the same logic is missing in the createTeamSupervisorWithSummarize function. This will cause issues when using AzureChatOpenAI with summarization enabled. Please apply a similar change to the if condition on line 504 to handle AzureChatOpenAI and ensure consistent behavior.

[gemini-code-assist]

There is significant code duplication between the createTeamSupervisor and createTeamSupervisorWithSummarize functions. This makes the code harder to maintain and can lead to bugs like the one where AzureChatOpenAI support was missed in one function. Consider refactoring to a single function that handles both cases, perhaps by passing a flag or a configuration object to determine whether to include summarization in the output.