[AI] Few more generable structured output tests#15873
[AI] Few more generable structured output tests#15873paulb777 wants to merge 3 commits intoah/ai-generative-model-sessionfrom
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. |
c24d550 to
33c057f
Compare
|
/gemini review |
There was a problem hiding this comment.
Code Review
This pull request adds more integration tests for structured output generation using @Generable. The new tests cover generating a single complex object (Recipe) and a list of objects (RecipeList). The changes are good and increase test coverage. I have a couple of minor suggestions to improve the assertions in the new tests for better readability and completeness.
FirebaseAI/Tests/TestApp/Tests/Integration/GenerativeModelSessionTests.swift
Show resolved
Hide resolved
FirebaseAI/Tests/TestApp/Tests/Integration/GenerativeModelSessionTests.swift
Outdated
Show resolved
Hide resolved
|
/gemini review |
There was a problem hiding this comment.
Code Review
The pull request adds comprehensive integration tests for structured output using the @Generable macro. It covers various data types including enums, nested structs, and arrays. I've suggested a minor improvement to the respondGenerableRecipeList test to include assertions for the rating property, ensuring consistency across tests and verifying that the model respects all defined constraints.
#no-changelog