codex - 💡(How to fix) Fix Codex App: add a None Intelligence/reasoning-effort option for supported models [1 participants]

TL;DR

Add a "None" option to the Intelligence/reasoning-effort selector in the Codex App to match the API and provide a low-latency choice.

Guidance

• Review the Codex App's UI code to identify where the Intelligence/reasoning-effort selector options are defined and updated.
• Check the API documentation to confirm the supported models and their corresponding reasoning effort options.
• Consider adding a conditional statement to display the "None" option only for models that support it.
• Verify that the updated UI correctly sends the reasoning.effort = "none" parameter to the API for the selected models.

Example

No code snippet is provided as the issue does not contain specific code references.

Notes

The solution assumes that the Codex App's UI is customizable and that the API documentation is accurate. Additional testing may be required to ensure compatibility with different models and use cases.

Recommendation

Apply workaround: Add the "None" option to the Intelligence/reasoning-effort selector, as this will provide users with an explicit low-latency choice and align the Codex App with the API.