test(core): remove hardcoded model from TestRig

[NTaylorMullen]

Summary

This PR removes the hardcoded DEFAULT_GEMINI_MODEL (gemini-2.5-pro) override from TestRig in behavioral evaluations. By omitting the model key from the generated settings.json, the CLI is allowed to fall back to its internal dynamic default (currently auto-gemini-3 which resolves to gemini-3-pro-preview).

Details

• Why: Allows evaluations to naturally track the CLI's default model, ensuring that "always passing" evals are tested against the same model a typical user would experience by default.
• Impact: Behavioral evals in CI will now run against Gemini 3 instead of being pinned to Gemini 2.5 Pro.

Related Issues

None.

How to Validate

1. Run an evaluation locally: npm run test:always_passing_evals -- evals/shell-efficiency.eval.ts
2. Inspect the network logs in evals/logs/*.jsonl.
3. Verify the user-agent header or request URL reflects the current default model (gemini-3-pro-preview) rather than gemini-2.5-pro.

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed) - Verified via local evaluation run.
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run

[gemini-code-assist]

Summary of Changes

Hello @NTaylorMullen, 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 updates the testing infrastructure to ensure that behavioral evaluations utilize the CLI's dynamic default model rather than a static, hardcoded version. This change allows tests to naturally track the latest default model, providing more relevant and up-to-date validation of the user experience.

Highlights

• Model Defaulting: The hardcoded DEFAULT_GEMINI_MODEL (gemini-2.5-pro) override has been removed from TestRig in behavioral evaluations.
• Dynamic Model Selection: By omitting the model key from settings.json, the CLI will now fall back to its internal dynamic default model (currently auto-gemini-3, resolving to gemini-3-pro-preview).
• Evaluation Impact: Behavioral evaluations in CI will now run against Gemini 3 instead of being pinned to Gemini 2.5 Pro, ensuring tests align with the typical user experience.

Changelog

• packages/test-utils/src/test-rig.ts
  • Removed the import of DEFAULT_GEMINI_MODEL.
  • Eliminated the explicit model configuration block from the TestRig setup.

Activity

• No activity has occurred on this pull request yet.

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 removes the hardcoded model from the TestRig configuration, allowing behavioral evaluations to default to the CLI's standard model, which improves the accuracy of tests reflecting the user experience. No security vulnerabilities were found.

[github-actions]

Size Change: -2 B (0%)

Total Size: 23.9 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	23.9 MB	-2 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}