Skip to content

Conversation

@hsubox76
Copy link
Contributor

This also required updating the LiveAPI integration tests, as the new models don't allow ResponseModality.TEXT and the Vertex model currently requires region us-central1.

The Developer API handles multiple chunks strangely and often returns only a thinking part.

@changeset-bot
Copy link

changeset-bot bot commented Dec 12, 2025

⚠️ No Changeset found

Latest commit: 5bc3a66

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @hsubox76, 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 updates the LiveAPI integration tests to accommodate recent changes in AI model behavior and requirements. It specifically addresses the need to use new model names, enforce a particular region for Vertex AI, and adapt test expectations from text-based responses to audio-based responses, including handling cases where the model might indicate a 'thinking' state. These changes ensure the tests accurately reflect the current operational characteristics of the LiveAPI.

Highlights

  • Model Name Updates: Updated LiveAPI model names for both Google AI and Vertex AI backends in integration tests to reflect current model identifiers.
  • Vertex AI Region Specificity: Configured Vertex AI LiveAPI to specifically use the 'us-central1' region, as required by the current model for proper functionality.
  • Response Modality Shift: Changed the default response modality in LiveAPI tests from 'TEXT' to 'AUDIO' to align with new model capabilities that prioritize audio output.
  • Enhanced Test Helper: Refactored the 'nextTurnText' helper function to 'nextTurnData' to capture not only text but also the presence of audio data and 'thinking' states from model responses, providing more comprehensive test results.
  • Updated Test Assertions: Modified integration tests to assert the presence of audio data in responses rather than specific text content, accommodating the new audio-centric response modality and handling potential 'thinking' responses from the API.
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 updates constants and integration tests for the Live API. The constants.ts file was modified to introduce liveBackends specifically for Vertex AI in us-central1 and Google AI, update liveModelNames to newer model identifiers, and ensure liveTestConfigs utilize these new backends. In live.test.ts, the nextTurnText helper function was refactored and renamed to nextTurnData, now returning an object that includes text, hasAudioData, and hasThinking flags. This change aligns with the updated textLiveGenerationConfig which now expects ResponseModality.AUDIO. As a result, many test assertions were updated to check for the presence of audio data rather than specific text content. Review comments noted that these updated assertions weaken the tests by no longer validating the model's actual response content, suggesting a need for transcription or an explanation. Additionally, a misleading error message in the nextTurnData function was identified, and a typo in the finalresponseData variable name was pointed out.

@google-oss-bot
Copy link
Contributor

google-oss-bot commented Dec 12, 2025

@google-oss-bot
Copy link
Contributor

google-oss-bot commented Dec 12, 2025

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.

2 participants