Harmony: bad request on gpt-oss-120b and tool calls with `create_react_agent`

### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [x] I added a clear and detailed title that summarizes the issue. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python from langgraph.prebuilt import create_react_agent from langchain_openai import ChatOpenAI from dotenv import load_dotenv from os import environ from httpx import Client, AsyncClient from langchain_core.messages import HumanMessage from langchain_core.tools import tool import pprint import httpx import logging from langgraph.checkpoint.memory import InMemorySaver from threading import get_ident reasoning = { "effort": "high", "summary": "auto", } model = ChatOpenAI( model="openai/gpt-oss-120b", api_key=environ.get("TOKEN"), streaming=True, base_url=environ.get("API_BASE"), http_async_client=AsyncClient(), http_client=Client(), reasoning=reasoning, use_responses_api=True, output_version="responses/v1", ) @tool def get_cve(cve_id: str) -> dict: """ Get CVE details from the MITRE API using a CVE-ID Args: cve_id (str): The CVE ID to fetch details for, e.g., "CVE-2024-0018". """ cve_id = cve_id.strip().upper() response = httpx.get( f"https://cveawg.mitre.org/api/cve/{cve_id}", ) if response.status_code == 200: return response.json() else: logging.error(f"Error fetching CVE {cve_id}: {response.status_code} - {response.text}") return {"error": "CVE not found or API error."} max_iterations = 20 recursion_limit = 2 * max_iterations + 1 agent = create_react_agent( model, [get_cve], checkpointer=InMemorySaver(), prompt="You are a…