fix(patch): cherry-pick c31f053 to release/v0.23.0-preview.4-pr-16004 to patch version v0.23.0-preview.4 and create version 0.23.0-preview.5

[gemini-cli-robot]

This PR automatically cherry-picks commit c31f053 to patch version v0.23.0-preview.4 in the preview release to create version 0.23.0-preview.5.

[gemini-code-assist]

Summary of Changes

Hello @gemini-cli-robot, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a more robust token estimation mechanism for image content within the packages/core module. It ensures that when the primary API for token counting is unavailable, image parts receive a more accurate fixed token estimate, improving the reliability of token calculations. Additionally, it refines model handling in the client and enhances error logging for token counting failures.

Highlights

• Improved Image Token Estimation: When the API fails to count tokens for image parts, a fixed estimate of 3000 tokens is now used, aligning with Gemini API guidelines for vision models to provide a more accurate fallback.
• Enhanced Token Counting Fallback Logic: The estimateTokenCountSync function now specifically identifies image parts and applies a dedicated IMAGE_TOKEN_ESTIMATE instead of a generic JSON string length heuristic for non-text parts.
• Model Resolution Integration: The GeminiClient now utilizes a resolveModel utility to process the active model, likely to handle model aliases or configurations more robustly within the system.
• Debug Logging for Token Counting Failures: Added debug logging to capture errors when the countTokens API call fails, providing more insight into why the system falls back to local estimation.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request cherry-picks a fix to improve token calculation and model resolution. The changes correctly enhance the fallback estimation for image tokens and ensure model aliases are resolved. However, I've identified a high-severity issue where the model resolution logic doesn't account for whether preview features are enabled. This could lead to incorrect model selection for critical operations like token limit checks. My review includes a specific suggestion to address this.

[github-actions]

Size Change: +503 B (0%)

Total Size: 22 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	22 MB	+503 B (0%)
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B

_{compressed-size-action}

[jacob314]

[jacob314]