includes example for openai js sdk#323
Conversation
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2b02961887
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 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 address that feedback".
| modelSettings: { | ||
| reasoning: { summary: "auto" }, |
There was a problem hiding this comment.
Avoid sending reasoning settings for every model override
When users set OPENAI_MODEL to a non-reasoning model such as gpt-4o-mini or another supported Agents SDK model, this example still sends modelSettings.reasoning.summary, which the OpenAI model settings docs describe as model-dependent rather than universally supported. Because the README presents OPENAI_MODEL as a general optional override, those users can hit an API/runtime error before seeing any PromptLayer trace; gate these settings to known reasoning models or document/enforce that only reasoning-capable models are valid here.
Useful? React with 👍 / 👎.
No description provided.