feat: add gpt-5.4 to codex, close #999#1006
Conversation
Summary of ChangesHello, 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 integrates the new Highlights
Changelog
Activity
Using Gemini Code AssistThe 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
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 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
|
There was a problem hiding this comment.
Code Review
This pull request adds the gpt-5.4 model to the list of default Codex models. My review suggests a minor correction to the model name for consistency with other models in the list, proposing gpt-5.4-codex instead. This is to ensure the correct model is being referenced within the Codex context.
| "gpt-5.2", | ||
| "gpt-5.2-codex", | ||
| "gpt-5.3-codex", | ||
| "gpt-5.4", |
There was a problem hiding this comment.
The newly added model gpt-5.4 doesn't have the -codex suffix, unlike other recent additions such as gpt-5.3-codex. For consistency and to ensure the correct, codex-specific model is used, it should likely be named gpt-5.4-codex.
| "gpt-5.4", | |
| "gpt-5.4-codex", |
Claude Code 2.x ships claude-opus-4-7 as a first-class model, but `claudecode.DefaultModels()` still tops out at 4-6 / sonnet-4-6. As a result, channels of type `claudecode` (Claude MAX OAuth) cannot expose 4-7 via the UI's FetchModels probe — supportedModels never gets the new entry, so the orchestrator route table rejects requests with HTTP 422 `model not found: claude-opus-4-7`. Same one-line shape as #1605 (gpt-5.5 for codex) and #1006 (gpt-5.4). **Tested locally**: with this change, a Claude MAX OAuth channel whose supportedModels gets claude-opus-4-7 from FetchModels returns HTTP 200 from api.anthropic.com/v1/messages when claude code clients request claude-opus-4-7. Co-authored-by: qinkangdeid <qinkangdeid@gmail.com>
Claude Code 2.x ships claude-opus-4-7 as a first-class model, but `claudecode.DefaultModels()` still tops out at 4-6 / sonnet-4-6. As a result, channels of type `claudecode` (Claude MAX OAuth) cannot expose 4-7 via the UI's FetchModels probe — supportedModels never gets the new entry, so the orchestrator route table rejects requests with HTTP 422 `model not found: claude-opus-4-7`. Same one-line shape as looplj#1605 (gpt-5.5 for codex) and looplj#1006 (gpt-5.4). **Tested locally**: with this change, a Claude MAX OAuth channel whose supportedModels gets claude-opus-4-7 from FetchModels returns HTTP 200 from api.anthropic.com/v1/messages when claude code clients request claude-opus-4-7. Co-authored-by: qinkangdeid <qinkangdeid@gmail.com>
No description provided.