[Firebase AI] Handle empty or unknown Part data#15262
Merged
andrewheard merged 15 commits intomainfrom Sep 3, 2025
Merged
Conversation
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces robust handling for empty or unknown Part data in GenerateContentResponse. For streaming calls, responses with only empty candidates are now skipped, improving the developer experience. For unary calls, an error is thrown only if all candidates in a response are empty. This is a solid improvement that also resolves decoding issues with newer models. The changes are well-structured, and the addition of new tests and updates to existing ones ensure the new logic is covered. I have one minor suggestion to use a more specific log code.
paulb777
approved these changes
Sep 3, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Added handling for
GenerateContentResponsevalues that contain noparts. When streaming, these are skipped since the developer can't act upon them. In unary calls, throws only if all candidates are empty since, unlike streaming, no additional responses will be returned by the backend (and therefore an empty response would be an error).This PR resolves decoding issues when using the
gemini-2.5-flash-image-preview("nano banana") model with the Gemini Developer API to generate images, as well as hardening the decoding against malformed responses that were being returned by Vertex AI (now fixed in the backend).