Skip to content

Fix: Map interrupted field from Gemini backend to LlmResponse#481

Merged
copybara-service[bot] merged 1 commit intogoogle:mainfrom
jinnigu:fix/add-interrupted
Oct 7, 2025
Merged

Fix: Map interrupted field from Gemini backend to LlmResponse#481
copybara-service[bot] merged 1 commit intogoogle:mainfrom
jinnigu:fix/add-interrupted

Conversation

@jinnigu
Copy link
Copy Markdown
Contributor

@jinnigu jinnigu commented Oct 7, 2025

Context

This PR fixes #462.

Problem

When Gemini sends an interruption signal during streaming ({"serverContent":{"interrupted":true}}), the ADK was dropping this field and never propagating it to clients. This prevented applications from stopping audio streams immediately upon interruption.

Solution

Added the missing field mapping in GeminiLlmConnection.convertToServerResponse():

.interrupted(serverContent.interrupted())

Added new tests to verify interrupted field mapping for true/false/empty cases.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist bot commented Oct 7, 2025

Summary of Changes

Hello @jinnigu, 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 bug in the ADK's handling of Gemini streaming responses by ensuring that interruption signals are correctly mapped and propagated to client applications. This enhancement allows for more responsive and accurate control over audio streams based on backend signals, improving the overall user experience when dealing with interrupted LLM interactions.

Highlights

  • Bug Fix: Resolved an issue where the interrupted field from the Gemini backend was not being propagated to client applications, preventing immediate audio stream cessation upon interruption.
  • Field Mapping: Implemented the missing mapping for the interrupted field within the GeminiLlmConnection.convertToServerResponse() method to ensure it is correctly included in the LlmResponse.
  • New Tests: Added comprehensive unit tests to validate the correct mapping of the interrupted field for true, false, and empty (not present) scenarios, ensuring robust behavior.
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[bot]
gemini-code-assist bot reviewed Oct 7, 2025
View reviewed changes
Copy link
Copy Markdown
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 correctly maps the interrupted field from the Gemini backend to the LlmResponse, fixing a bug where interruption signals were dropped. The change in GeminiLlmConnection is straightforward and correct. New tests have been added to cover this change, which is great. However, the new tests in GeminiLlmConnectionTest.java have a significant flaw: they duplicate the implementation logic instead of calling the method they are intended to test. I've left a detailed comment with suggestions on how to refactor the tests to properly verify the production code.

Comment thread core/src/test/java/com/google/adk/models/GeminiLlmConnectionTest.java
@jinnigu jinnigu mentioned this pull request Oct 7, 2025
Closed
@jinnigu jinnigu force-pushed the fix/add-interrupted branch from 2a826e6 to 64a68e6 Compare October 7, 2025 07:16
@vorburger vorburger force-pushed the fix/add-interrupted branch from 64a68e6 to 15b7044 Compare October 7, 2025 09:58
@copybara-service copybara-service bot merged commit 7350cd5 into google:main Oct 7, 2025
5 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@vorburger vorburger vorburger approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

ready to pull

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Not Receiving 'interrupted' Event from runLive method

2 participants

@jinnigu @vorburger