Repository navigation
chore: sync new models - #1717
github-actions[bot] wants to merge 1 commit into
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 9735720b8e
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "Codex (@codex) review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "Codex (@codex) address that feedback".
| "gpt-image-2.6-flare": ["openai", "azure"], | ||
| "gpt-image-2.6-sunburst": ["openai", "azure"], |
There was a problem hiding this comment.
Move the new provider mappings to the gateway
These additions modify AvailableEndpointTypes, which is model-routing configuration in the deprecated proxy; production routing changes belong in the parent repository's gateway/ directory, while only model_list.json is an exception that should remain here. Remove this routing edit and apply the corresponding mapping in the gateway so the newly cataloged models are routed by the production implementation.
AGENTS.md reference: AGENTS.md:L6-L15
Useful? React with 👍 / 👎.
| "available_providers": [ | ||
| "openai", | ||
| "azure" |
There was a problem hiding this comment.
Remove the unsupported Azure provider
For either new GPT-Image 2.6 model, an Azure-only configuration now treats Azure as a usable provider and can route requests to it, but Microsoft's current Foundry model catalog and regional availability table list image models only through GPT-Image 2.5 and do not offer these 2.6 IDs. Keep these entries OpenAI-only until Azure documents deployment support; the same correction applies to the adjacent Sunburst entry.
Useful? React with 👍 / 👎.
Automated sync of model metadata and newly available models from the approved provider allowlist.