gpt-4o doesn't work, because model selection requires reasoning effort

### Describe the bug

The cli requires selecting a reasoning level, and the model does not support reasoning effort. Thus I get:
on 1.0.49, when selecting medium (the default):
✗ Execution failed: CAPIError: 400 reasoning_effort "medium" was provided, but model gpt-4o-2024-11-20 does not support reasoning effort (Request ID: F37B:1A2D15:3BAED3A:418C4B7:6A0C1C5D)

on 1.0.49, when selecting None:
✗ Execution failed: CAPIError: 400 Invalid 'tools[5].function.name': empty string. Expected a string with minimum length 1, but got an empty string instead. (Request ID: F37B:1A2D15:3BC6C56:41A56B6:6A0C1C91)

on 1.0.48:
✗ Execution failed: CAPIError: 400 reasoning_effort "medium" was provided, but model gpt-4o-2024-11-20 does not support reasoning effort (Request ID:
FBD0:67726:274293C:2B4A64A:6A0C1AF4)

### Affected version

GitHub Copilot CLI 1.0.49 and 1.0.48

### Steps to reproduce the behavior

type /model

select gpt-4o

select any thinking level

the error appears

### Expected behavior

I expect the model to just work

### Additional context

_No response_

Start with the /model flow and the request construction reached after selecting gpt-4o and a thinking level. Reproduce the reported cases in GitHub Copilot CLI 1.0.49, including selecting None, and verify that gpt-4o works without an unsupported reasoning_effort value or an empty tool name. No source file or test is named in the issue.

Scritto dal modello di indicizzazione a partire dal testo della issue.