### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

Calling /chat/completions on a self-hosted LiteLLM proxy with function tools set for any model in the OpenAI gpt-5.6 family (gpt-5.6-sol, gpt-5.6-luna, gpt-5.6-terra) fails with a 400 BadRequestError, even without explicitly setting reasoning_effort in the request body.

### Steps to Reproduce

1. Request (via curl):

``` curl --location 'http://localhost:4000/chat/completions' \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer 1234' \ --data '{ "model": "openai/gpt-5.6-sol", "stream": false, "messages": [ { "role": "user", "content": "What'\''s the weather like in Boston today? in celsius" } ], "tools": [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA" }, …