feat: add gpt-5.4-mini codex model definitions

[WormW]

Summary
Add gpt-5.4-mini to the Codex model catalogs so the registry exposes it consistently.

Changes
• Added gpt-5.4-mini entries to internal/registry/models/models.json
• Included the model in codex-team, codex-plus, and codex-pro
• Reused the existing gpt-5.4 metadata shape for display name, context length, completion tokens, and thinking support

Notes
• This is a metadata-only change for registry/model listing support
• No runtime behavior changes beyond model discovery and model info lookup

[gemini-code-assist]

Summary of Changes

Hello, 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 the gpt-5.4-mini model into the system's model catalog. This ensures the new model is discoverable via the registry and /models API responses, primarily by updating its metadata without altering any existing model behaviors.

Highlights

• Model Definition Addition: Added gpt-5.4-mini entries to the internal/registry/models/models.json file.
• Metadata Mirroring: Mirrored gpt-5.4 metadata for display name, context length, completion tokens, and thinking levels for the new gpt-5.4-mini model.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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.

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 adds the gpt-5.4-mini model definition to the codex-team, codex-plus, and codex-pro model catalogs. The changes introduce syntactically incorrect JSON due to missing commas between properties, which will break parsing. I've provided suggestions to fix the syntax and also to improve the model's description for better user clarity.

[gemini-code-assist]

This new JSON object for gpt-5.4-mini is syntactically incorrect as it's missing commas between the key-value pairs. This will cause JSON parsing to fail.

While fixing this, please also consider making the description more informative. To help users, you could clarify what 'Mini' implies (e.g., faster, more cost-effective) compared to the base gpt-5.4 model.

This feedback applies to all three locations where this model definition is added.

      "id": "gpt-5.4-mini",
      "object": "model",
      "created": 1772668800,
      "owned_by": "openai",
      "type": "openai",
      "display_name": "GPT 5.4 Mini",
      "version": "gpt-5.4-mini",
      "description": "Stable version of GPT 5.4 Mini, a faster and more cost-effective variant of GPT 5.4.",
      "context_length": 1050000,
      "max_completion_tokens": 128000,
      "supported_parameters": [
        "tools"
      ],
      "thinking": {
        "levels": [
          "low",
          "medium",
          "high",
          "xhigh"
        ]
      }

[gemini-code-assist]

Similar to the other additions, this JSON object is missing commas between key-value pairs, which will break JSON parsing. Please also consider improving the description for better clarity as suggested previously.

      "id": "gpt-5.4-mini",
      "object": "model",
      "created": 1772668800,
      "owned_by": "openai",
      "type": "openai",
      "display_name": "GPT 5.4 Mini",
      "version": "gpt-5.4-mini",
      "description": "Stable version of GPT 5.4 Mini, a faster and more cost-effective variant of GPT 5.4.",
      "context_length": 1050000,
      "max_completion_tokens": 128000,
      "supported_parameters": [
        "tools"
      ],
      "thinking": {
        "levels": [
          "low",
          "medium",
          "high",
          "xhigh"
        ]
      }

[gemini-code-assist]

Similar to the other additions, this JSON object is missing commas between key-value pairs, which will break JSON parsing. Please also consider improving the description for better clarity as suggested previously.

      "id": "gpt-5.4-mini",
      "object": "model",
      "created": 1772668800,
      "owned_by": "openai",
      "type": "openai",
      "display_name": "GPT 5.4 Mini",
      "version": "gpt-5.4-mini",
      "description": "Stable version of GPT 5.4 Mini, a faster and more cost-effective variant of GPT 5.4.",
      "context_length": 1050000,
      "max_completion_tokens": 128000,
      "supported_parameters": [
        "tools"
      ],
      "thinking": {
        "levels": [
          "low",
          "medium",
          "high",
          "xhigh"
        ]
      }

[Sixzero]

+1

[hkfires]

The model list is mainly updated in another repository, while the one embedded in the program is only used as a fallback and will no longer be updated frequently.