Skip to content

Conversation

@MengqinShen
Copy link
Contributor

@MengqinShen MengqinShen commented Feb 1, 2026

Update the Genkit framework's serialization utility (dump_dict) in the core framework (py/packages/genkit/src/genkit/codec.py) to handle lists and dicts recursively. This is a better fix than modifying the sample, as it benefits all flows returning lists of models.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @MengqinShen, 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 issues related to data serialization and model usage within the genkit Python package. It enhances the dump_dict function to recursively handle Pydantic models within complex data structures, ensuring robust data conversion. Additionally, it updates a sample application to utilize newer Gemini models and introduces dynamic prompting for image generation, improving the sample's functionality and demonstrating current best practices.

Highlights

  • Recursive Serialization Fix: The dump_dict utility now correctly serializes Pydantic BaseModel instances embedded within lists and dictionaries, ensuring proper data conversion for complex structures.
  • Enhanced Test Coverage: New unit tests have been added for dump_dict to validate its recursive handling of lists of models and nested model structures, preventing regressions.
  • Model Update in Sample: The short-n-long sample application has been updated to use the gemini-3-pro-preview model by default, aligning with newer model versions.
  • Dynamic Image Generation Prompt: The generate_images function in the sample now uses gemini-3-pro-image-preview and constructs a dynamic prompt based on user input, improving flexibility.

🧠 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.

@MengqinShen MengqinShen changed the title fix(py): fix broken flows fix(py): fix broken flows in short-n-long sample Feb 1, 2026
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request fixes an issue in dump_dict where it didn't correctly serialize Pydantic models nested within lists or dictionaries. The change adds recursive handling for these container types. Corresponding unit tests have been added to verify the fix. Additionally, a sample application has been updated to use a newer model and to make a function more generic. My main feedback is to add cycle detection to the new recursive logic in dump_dict to prevent potential stack overflows with self-referencing data structures.

@MengqinShen MengqinShen changed the title fix(py): fix broken flows in short-n-long sample fix(py): fix broken flows in short-n-long and tool-interrupts sample Feb 1, 2026
@MengqinShen MengqinShen changed the title fix(py): fix broken flows in short-n-long and tool-interrupts sample fix(py): fix broken flows in short-n-long sample Feb 1, 2026
@MengqinShen MengqinShen marked this pull request as ready for review February 1, 2026 07:30
@MengqinShen MengqinShen enabled auto-merge (squash) February 1, 2026 08:18
@MengqinShen MengqinShen requested a review from yesudeep February 1, 2026 08:18
@MengqinShen MengqinShen merged commit 888c868 into main Feb 2, 2026
23 checks passed
@MengqinShen MengqinShen deleted the elisa/fix/sample-short-n-long branch February 2, 2026 14:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

4 participants