fix(core): Allow model to be set from settings.json

[richieforeman]

TLDR

This allows model setting to be applied from settings.json, defaulting only to the DEFAULT_MODEL (Gemini 2.5 Pro) iff there is nothing in argv && merged settings.

Dive Deeper

I felt it made sense to have the --model flag always take priority over other values, since that's always invoked by the user on demand rather than a passive config file.

Reviewer Test Plan

• If settings.json && --model are empty, then the default model should kick in
• --model always wins over settings.json

Testing Matrix

	🍏	🪟	🐧
npm run	x	❓	x
npx	❓	❓	❓
Docker	x	❓	❓
Podman	❓	-	-
Seatbelt	x	-	-

Linked issues / bugs

• Resolves Hardcoded DEFAULT_GEMINI_MODEL overrides settings.json configuration #5373

[gemini-code-assist]

Summary of Changes

Hello @richieforeman, 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 enhances the configuration system by allowing the AI model to be specified in settings.json. It establishes a clear precedence: command-line arguments (--model) override settings.json settings, and if neither is present, a default model (gemini-2.5-pro) is used. This change provides greater flexibility for users to manage their preferred AI model.

Highlights

• Flexible Model Configuration: I've enabled the model setting to be read from settings.json, giving users another way to configure their preferred AI model.
• Model Precedence Logic: I've implemented a clear hierarchy for model selection: command-line arguments (--model) take priority, followed by the settings.json entry, and finally, a default model (gemini-2.5-pro) is used if no other model is specified.
• Comprehensive Test Coverage: I've added new unit tests to config.test.ts to thoroughly validate the model selection logic, ensuring that settings.json settings, command-line arguments, and the default fallback all behave as expected.

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 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 or fill out our survey to provide feedback.

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 correctly implements the ability to set the model from settings.json, with a clear precedence order of CLI arguments, then settings, then a default. The new logic is well-tested. However, a debugger statement was left in the code, which is a critical issue that must be addressed before merging.

[jacob314]

[jacob314]

wow didn't realize 9.0 pro was out :)

[NGS-NEGUS]

TLDR

This allows model setting to be applied from settings.json, defaulting only to the DEFAULT_MODEL (Gemini 2.5 Pro) iff there is nothing in argv && merged settings.

Dive Deeper

I felt it made sense to have the --model flag always take priority over other values, since that's always invoked by the user on demand rather than a passive config file.

Reviewer Test Plan

• If settings.json && --model are empty, then the default model should kick in
• --model always wins over settings.json

Testing Matrix

	🍏	🪟	🐧
npm run	x	❓	x
npx	❓	❓	❓
Docker	x	❓	❓
Podman	❓	-	-
Seatbelt	x	-	-

Linked issues / bugs

• Resolves Hardcoded DEFAULT_GEMINI_MODEL overrides settings.json configuration #5373