[AI] Add proposed doc snippet to integration tests#16166
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 the 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 counterproductive. 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 review |
There was a problem hiding this comment.
Code Review
This pull request adds a new integration test, generateContentWithTemplateMapsGroundingSnippet, to verify that server prompt templates correctly return Google Maps grounding metadata. The test validates the presence of map chunks, including URLs, titles, and place IDs. Feedback was provided to use try #require instead of #expect when checking if mapChunks is empty; this ensures the test fails immediately if the expected data is missing, preventing the test from potentially passing silently if the subsequent validation loop is skipped.
|
/gemini review |
There was a problem hiding this comment.
Code Review
This pull request adds a new integration test, generateContentWithTemplateMapsGroundingSnippet, to verify grounding metadata mapping for Google Maps snippets. The feedback suggests including InstanceConfig.vertexAI_v1beta in the test arguments to ensure cross-platform consistency between Google AI and Vertex AI.
| @Test(arguments: [ | ||
| InstanceConfig.googleAI_v1beta, | ||
| ]) |
There was a problem hiding this comment.
Consider including InstanceConfig.vertexAI_v1beta in the test arguments. This ensures that the prompt template and grounding metadata mapping are verified across both Google AI and Vertex AI platforms, maintaining consistency with other integration tests in this file.
@Test(arguments: [
InstanceConfig.googleAI_v1beta,
InstanceConfig.vertexAI_v1beta,
])There was a problem hiding this comment.
Caught error: BackendError(httpResponseCode: 404, message: "Publisher Model projects/ios-opensource-samples/locations/us-central1/publishers/google/models/gemini-3-flash-preview was not found or your project does not have access to it. Please ensure you are using a valid model version. For more information, see: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", status: FirebaseAILogic.RPCStatus.notFound, details: [])
and
Caught error: BackendError(httpResponseCode: 404, message: "Publisher Model projects/ios-opensource-samples/locations/us-central1/publishers/google/models/gemini-3-flash was not found or your project does not have access to it. Please ensure you are using a valid model version. For more information, see: https://cloud.google.com/vertex-ai/generative-ai/docs/learn/model-versions", status: FirebaseAILogic.RPCStatus.notFound, details: [])
And there is no location specifier in the template ...
9118ccf to
1390106
Compare
#no-changelog