-
Notifications
You must be signed in to change notification settings - Fork 1.7k
[AI] Make Integration tests green #15637
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Using Gemini Code AssistThe 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
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 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. |
|
/gemini summarize |
Summary of ChangesThis pull request focuses on stabilizing and updating the integration test suite. It introduces a new Gemini model, Highlights
🧠 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. Changelog
Activity
|
|
/gemini review |
Danger has errored[!] Invalid Generated by 🚫 Danger |
There was a problem hiding this 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 the new gemini-3-flash-preview model by adding it to the ModelNames enum and including it in integration tests for content generation. The changes update token count assertions in GenerateContentIntegrationTests.swift to specifically handle thoughtsTokenCount and candidatesTokenCount for gemini-3 models. Additionally, several existing test configurations related to googleAI_v1beta_freeTier and gemini2_5_Flash models have been commented out across test files and the InstanceConfig enum, and an Xcode project file was modified to exclude LiveSessionTests.swift from a build target. A review comment suggests improving the robustness of the totalTokenCount assertion for gemini-3 models by calculating it as the sum of promptTokenCount, candidatesTokenCount, and thoughtsTokenCount instead of using a hardcoded value.
FirebaseAI/Tests/TestApp/Tests/Integration/GenerateContentIntegrationTests.swift
Outdated
Show resolved
Hide resolved
|
/gemini review |
There was a problem hiding this 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 aims to fix failing integration tests by adding support for the gemini-3-flash-preview model and adjusting test configurations. Key changes include adding new test cases for the new model, updating token count assertions to match its behavior, and disabling some tests for freeTier configurations. Additionally, LiveSessionTests.swift has been excluded from the build.
My review focuses on improving code maintainability and ensuring test coverage isn't unnecessarily reduced. I've suggested refactoring some conditional logic in the tests to make it cleaner. I've also raised a concern about disabling an entire test file and suggested a more targeted approach if possible.
FirebaseAI/Tests/TestApp/FirebaseAITestApp.xcodeproj/project.pbxproj
Outdated
Show resolved
Hide resolved
andrewheard
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks, Paul!
#no-changelog