Skip to content

Conversation

@ywqwancbx
Copy link

Passthrough Propagation to Plugins

  • Add top-level passthrough to InvokePluginRequest and Session, and include it in Session.Message() so it reaches the Python SDK as a first-class field (similar to conversation_id).
  • Keep InvokeTool data payload strictly for business parameters; carry passthrough via session to avoid schema drift.
  • Remove temporary debug logs and unused helpers; retain only necessary code for passthrough propagation.
  • Backward compatible; existing tools continue to work without changes.
  • Corresponding upstream changes in Dify main repo: feat: add passthrough parameter support for workflow tools.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @ywqwancbx, 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 a flexible passthrough mechanism to enable the seamless propagation of additional, non-business-critical data to plugins. By integrating a dedicated passthrough field into core session and plugin invocation structures, it ensures that extra context can be carried through the system and made available to the Python SDK, all while preserving the integrity of existing InvokeTool schemas and maintaining full backward compatibility.

Highlights

  • Passthrough Field Introduction: A new passthrough field has been added to InvokePluginRequest and Session structs to allow for the propagation of additional, arbitrary data to plugins.
  • Python SDK Integration: The passthrough data is now included in the Session.Message() output, ensuring it reaches the Python SDK as a first-class field, similar to conversation_id.
  • Schema Integrity: The InvokeTool data payload remains strictly for business parameters, preventing schema drift and maintaining a clean separation of concerns for passthrough data via the session.
  • Backward Compatibility: The changes are fully backward compatible, meaning existing tools will continue to function without any modifications.
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.

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 introduces support for passthrough propagation to plugins by adding a passthrough field to InvokePluginRequest and Session structs. The changes are logical and correctly implemented to pass this new field through the system. My review found one minor formatting issue that should be addressed for code consistency.

AppID *string `json:"app_id"`
EndpointID *string `json:"endpoint_id"`
Context map[string]any `json:"context"`
Passthrough *string `json:"passthrough"`
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

The indentation for the new Passthrough field is using spaces instead of a tab. Standard Go formatting, enforced by tools like gofmt, uses tabs for indentation. Please correct the indentation to maintain code style consistency.

Suggested change
Passthrough *string `json:"passthrough"`
Passthrough *string `json:"passthrough"`

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant