Repository navigation
chore: add model to catalog - #1549
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. |
![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: 68e65a168f
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".
| "displayName": "Beam", | ||
| "reasoning": true, | ||
| "max_input_tokens": 1048576, |
There was a problem hiding this comment.
Add max_output_tokens: 131072 to this entry. The provider-specific Beam listing reports a 131K maximum output for Baseten, while this record only stores the 1M context limit, so catalog consumers see no completion ceiling for the newly added model. This also appears to expose the existing convertBasetenToLocalModel omission: the Baseten response schema accepts max_completion_tokens, but the converter never copies it into the generated model.
Useful? React with 👍 / 👎.
This branch was successfully deployed
1 participant
Automated targeted model-catalog addition from the model-drop workflow.