Uh oh!
There was an error while loading. Please reload this page.
fix: add xAI models grok-4.20-multi-agent-0309 - #668
Conversation
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit:11e22a5b02
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".
| "format": "openai", | ||
| "flavor": "chat", |
There was a problem hiding this comment.
For this model, flavor: "chat" makes the proxy's /auto path select /chat/completions (see packages/proxy/src/proxy.ts switch on modelSpec.flavor), and normal chat-completion calls are forwarded to xAI's /chat/completions. xAI's current multi-agent docs state that grok-4.20-multi-agent does not work with the OpenAI Chat Completions API and must use the xAI SDK or Responses API instead, so users who pick the newly added model through the standard chat route will get provider errors rather than a working model.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
this is correct, will need to revisit this PR after landing support
fix: add xAI models grok-4.20-multi-agent-0309
Closes#666
Source issue: #666
Summary
grok-4.20-multi-agent-0309grok-4.20-multi-agent-03092
Verified metadata
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 differences. Official provider verification was used for the applied values, and sync_models discrepancies are listed below for review.