chore: update model catalog from bot issues#956
Conversation
github-actions
Bot
requested review from
Alex Z (CLowbrow),
aswink,
Caitlin Pinn (cpinn),
Erin McNulty (erin2722) and
Ken Jiang (knjiang)
|
Codex (@codex) review |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 0896254e27
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".
| "google.gemma-4-31b": ["bedrock"], | ||
| "google.gemma-4-26b-a4b": ["bedrock"], | ||
| "google.gemma-4-e2b": ["bedrock"], | ||
| "codex-mini-latest": ["openai", "azure"], |
There was a problem hiding this comment.
When an Azure credential is available, this advertises codex-mini-latest as Azure-routable, but the Microsoft Foundry model list linked by the commit lists Azure's model as codex-mini and says it is Responses API only; this proxy also only routes chat requests through the Responses translator when secret.type === "openai" (packages/proxy/src/proxy.ts), so Azure /chat/completions calls for this catalog id will be sent to a codex-mini-latest deployment and fail unless the user happens to have a custom deployment with that name. Please drop azure here or add the correct Azure id/routing.
Useful? React with 👍 / 👎.
| "bedrock" | ||
| ] | ||
| }, | ||
| "codex-mini-latest": { |
There was a problem hiding this comment.
This re-adds codex-mini-latest as an active catalog entry, but the same id is still present in packages/proxy/scripts/deprecated_model_ids.json:21, which sync_models.ts loads into SYNC_EXCLUDED_MODELS; the previous catalog entry for this id also carried deprecated: true before it was removed. In contexts where catalog consumers or automation rely on that deprecation list, this model is now simultaneously advertised as active and treated as provider-deprecated/excluded, so please remove it from the deprecation list if it is live again or keep the deprecated marker.
Useful? React with 👍 / 👎.
1 participant
Automated daily batch of model catalog updates from bot issues.
Included issues
Summary
codex-mini-latestcodex-mini-latest2
accounts/fireworks/models/glm-5p2accounts/fireworks/models/glm-5p2Verified metadata
#954: [BOT ISSUE] OpenAI: add missing codex-mini-latest model
Verification notes
No LLM verification step ran; model metadata was already complete in the issue.
sync_models vs proposed update
sync_models cross-check found no pricing/token discrepancies for the changed models.
No sync_models discrepancies were noted.
#955: [BOT ISSUE] Fireworks: fix GLM 5.2 cached input pricing ($0.26 → $0.14)
Verification notes
Verification Checklist
sync_models vs proposed update
sync_models cross-check found differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.