Adjust AI Logic testing for model deprecation#8140
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. |
📝 PRs merging into main branchOur main branch should always be in a releasable state. If you are working on a larger change, or if you don't want this change to see the light of the day just yet, consider using a feature branch first, and only merge into the main branch when the code complete and ready to be released. |
| FirebaseAI.getInstance(app!!, GenerativeBackend.googleAI()) | ||
| .generativeModel( | ||
| modelName = "gemini-2.5-flash", | ||
| modelName = "gemini-3-flash-preview", |
There was a problem hiding this comment.
Test using gemini-3.1-flash-lite please
internal http://shortn/_KnijomiNeU
2 participants
Adjust Google AI testing to use
gemini-3-flash-previewinstead ofgemini-2.5-flash. No changes to tests were required for this migration.Additionally, coincides with internal changes to our templates to allow different backends to run different templates, using different model versions. This also moves away from
gemini-2.5-flashfor our Google AI models while staying on it for Vertex AI models (later versions are not released for Vertex).Some template testing was adjusted to deal with variable output (punctuation, spacing) that could not be resolved easily on the template end.