### Check for existing issues

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

### What happened?

Using LiteLLM with the [openai-agents SDK](https://github.com/openai/openai-agents-python) with an OpenAI GPT-5.4 model and function tool calls fails if `reasoning_effort` is set.

Observed behavior: - model: `openai/gpt-5.4` - tools: function tools enabled - reasoning: `reasoning_effort="low"` - request fails with:

`OpenAIException - Function tools with reasoning_effort are not supported for gpt-5.4 in /v1/chat/completions. Please use /v1/responses instead.`

Expected behavior: - Either LiteLLM should automatically route this OpenAI GPT-5.4 + tools + reasoning request to `/v1/responses` - LiteLLM should reject this combination

### Steps to Reproduce

You can run the following script to repro: ``` OPENAI_API_KEY=your_token_here \ uv run \ --with "litellm==1.82.0" \ --with "openai-agents[litellm]==0.11.1" \ python - <<'PY' import asyncio import os

from agents import Agent, ModelSettings, Runner, function_tool from agents.extensions.models.litellm_model import LitellmModel from openai.types.shared import Reasoning

@function_tool async …