[Vertex AI] Fix decoding ModalityTokenCount when tokenCount is 0
#14747
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 in your pull request via creating an issue comment (i.e. comment on the pull request page) 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 is currently in preview and 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 to provide feedback. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request addresses an issue where the tokenCount field in ModalityTokenCount was not being properly decoded when it was omitted from the JSON response (specifically when the value was 0). The changes include updating the ModalityTokenCount struct to handle the missing tokenCount field and adding a unit test to verify the fix. Overall, the changes are well-structured and address the issue effectively.
Summary of Findings
- Decoding
tokenCount: The pull request correctly addresses the issue of decodingModalityTokenCount.tokenCountwhen it is not returned in the response by usingdecodeIfPresentand providing a default value of 0. - Unit test for missing
tokenCount: The pull request includes a unit test (testDecodeModalityTokenCount_missingTokenCount_defaultsToZero) to verify that thetokenCountdefaults to 0 when it is missing from the JSON response.
Merge Readiness
The pull request is well-structured and includes a unit test to verify the fix. The changes address the issue effectively and are ready to be merged. I am unable to directly approve this pull request, and recommend that others review and approve this code before merging.
Decodes
ModalityTokenCount.tokenCountas0when it is not returned in the response. This fixes #14745.Context: When the backend sets a
tokenCountof0for aContentModalityin aModalityTokenCount, thetokenCountfield is omitted from the JSON response since0is the default value. This results in aDecodingError.keyNotFoundwhen decoding thetokenCount.#no-changelog