Feature/Gemini Nano Banana

[HenryHengZJ]

nanobanana.mp4

[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 significantly enhances the platform's multimodal capabilities, particularly for Gemini models. It introduces new model definitions and refines the handling of image artifacts throughout the chat flow. The changes ensure that images, whether from user uploads, generated by tools, or embedded in LLM responses, are consistently processed, stored, and presented, leading to a more robust and visually aware conversational experience.

Highlights

• New Gemini Models: Added support for new Gemini models, specifically gemini-3-pro-image-preview and gemini-2.5-flash-image, expanding the available multimodal capabilities.
• Enhanced Multimodal Message Handling: Introduced new utility functions to process and manage image artifacts within chat messages. This includes converting stored image references to base64 for LLM input and replacing inline base64 image data in responses with file references for storage.
• Centralized Artifact Extraction: Refactored artifact extraction logic into a shared utility, extractArtifactsFromResponse, which now handles various types of artifacts, including container file citations, image generation outputs, and Gemini's inline image data.
• Improved Chat History for Images: Implemented a mechanism to temporarily add image artifacts from previous assistant messages as user messages. This allows multimodal LLMs to 'see' and reference generated images in the conversation, with these temporary messages being removed before database storage.
• Gemini Inline Data Processing: Added specific handling for Gemini's inline image data within the ChatGoogleGenerativeAI node, ensuring these images are properly extracted, saved, and referenced in the chat flow.

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 support for image generation and vision capabilities, particularly for Gemini models, within the agent and LLM nodes. It includes a significant and beneficial refactoring, moving shared artifact and image handling logic from the Agent node into a new utils.ts file. This greatly improves code organization and reusability. The implementation correctly handles passing image artifacts between conversation turns by adding temporary messages, and it properly manages the storage of these artifacts by replacing base64 data with file references. The changes are well-structured and address the new feature requirements effectively. I've included a few suggestions to further improve maintainability and type safety.