[Vertex AI] Fix decoding ModalityTokenCount when tokenCount is 0

[andrewheard]

Decodes ModalityTokenCount.tokenCount as 0 when it is not returned in the response. This fixes #14745.

Context: When the backend sets a tokenCount of 0 for a ContentModality in a ModalityTokenCount, the tokenCount field is omitted from the JSON response since 0 is the default value. This results in a DecodingError.keyNotFound when decoding the tokenCount.

#no-changelog

[gemini-code-assist]

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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]

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 decoding ModalityTokenCount.tokenCount when it is not returned in the response by using decodeIfPresent and providing a default value of 0.
• Unit test for missing tokenCount: The pull request includes a unit test (testDecodeModalityTokenCount_missingTokenCount_defaultsToZero) to verify that the tokenCount defaults 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.

[paulb777]

LGTM on acceptable CI