fix(gemini): normalize model listing output

[hkfires]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @hkfires, 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 aims to enhance the consistency and clarity of model listings, particularly for Gemini and OpenAI compatibility models. It standardizes model display names, introduces canonical naming for internal model configurations, and normalizes the API output for Gemini models to ensure a predictable and well-structured response, improving the overall model management and discovery experience.

Highlights

• Model Naming Standardization: Updated display names and descriptions for several GPT 5 models to reflect 'GPT 5.1' and its variants, ensuring consistency in model identification.
• Canonical Model Names for Gemini: Introduced a Name field in AntigravityModelConfig to store canonical model names (e.g., prefixed with models/) and updated the model fetching logic to utilize this field.
• Gemini Model Listing Normalization: Implemented a normalization step in the Gemini models API handler to ensure all model names are prefixed with models/ and that supportedGenerationMethods is always present, defaulting to ["generateContent"].
• New Gemini Model Definitions: Added new Gemini models, gemini-2.5-computer-use-preview-10-2025 and gemini-3-pro-image-preview, to the AntigravityModelConfig.
• OpenAI Compatibility Display Name: Adjusted the DisplayName for OpenAI compatibility models to use the modelID for better clarity and consistency.

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 focuses on normalizing the model listing output, particularly for Gemini models. The changes include updating OpenAI model definitions to version 5.1, adding a canonical Name field to AntigravityModelConfig to standardize model names, and updating the Gemini API handler to ensure model names are correctly formatted in the response. Additionally, there's a fix to make the DisplayName for OpenAI-compatibility models consistent with their ID. The changes are logical and well-aligned with the PR's goal. I have one suggestion to improve consistency in the new model definitions.

[gemini-code-assist]

The new Name field has been added to AntigravityModelConfig and is populated for most models in GetAntigravityModelConfig. However, gemini-claude-sonnet-4-5-thinking and gemini-claude-opus-4-5-thinking are missing this field. While the code in antigravity_executor.go has a fallback, for consistency and to avoid relying on fallbacks, it would be better to add the Name field to these model configurations as well.

Suggested change

	"gemini-claude-sonnet-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000},
	"gemini-claude-opus-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000},
	"gemini-claude-sonnet-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000, Name: "models/gemini-claude-sonnet-4-5-thinking"},
	"gemini-claude-opus-4-5-thinking": {Thinking: &ThinkingSupport{Min: 1024, Max: 200000, ZeroAllowed: false, DynamicAllowed: true}, MaxCompletionTokens: 64000, Name: "models/gemini-claude-opus-4-5-thinking"},