Please allow us to disable reasoning for low-latency interactions

GPT 5.2 and 5.4 support the following reasoning levels:

- none
- low
- medium
- high
- xhigh

where **none** disables reasoning entirely.

However, the API doesn't allow us to use **none** - it's not exposed through `SupportedReasoningEfforts`, and attempting to use it results in fallback to the default of **medium**. Can support for **none** be added, please?

The same applies to Sonnet, for which there is no means to disable reasoning completely.

Right now, the only available model suitable for low-latency interactions is GPT 4.1.

Empieza rastreando SupportedReasoningEfforts y la configuración de razonamiento del modelo utilizada por GPT 5.2, GPT 5.4 y Sonnet. Comprueba cómo un valor no compatible recurre actualmente a medium y, a continuación, verifica que se acepta la compatibilidad con none y que se desactiva el razonamiento para interacciones de baja latencia.

Escrito por el modelo de indexación a partir del texto del issue.