"No call message found for call_*" with gpt-oss-20b in LangGraph

### 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 langchain.agents import create_agent from langchain_openai import ChatOpenAI from langchain.agents.middleware import before_model, after_model, wrap_model_call from langchain.agents.middleware import AgentState, ModelRequest, ModelResponse, dynamic_prompt from langchain.messages import AIMessage,HumanMessage, ToolMessage from langchain.agents import create_agent from langgraph.runtime import Runtime from typing import Any, Callable import json from typing import Any, Literal, Union from pydantic import Field, model_validator from langchain_core.messages.base import BaseMessage from langchain_core.messages.tool import ToolMessage, ToolOutputMixin # ✅ 模型 llm = ChatOpenAI( model="gpt-oss-20b", base_url="http://172.16.13.9:8000/v1", api_key="st", temperature=0, use_responses_api=True, ) # ✅ 工具函数 def check_weather(location: str) -> str: """Return the weather forecast for the specified location.""" print("######## Checking weather for :", location) return f"It's always sunny in {location}" # ✅ 创建 Agent graph = create_agent( model=llm, tools=[check_weather], system_prompt="You are a helpful assistant", # middleware=[remove_reasoning_before_model], ) # ✅ 输入消息 inputs = {"messages": [{"role": "user", "content": "what is the weather in sf"}]} # ✅ 运行并流式输出（过滤 reasoning） for chunk in graph.stream( inputs, stream_mode="updates", config={"configurable": {"thread_id": "test-001"}}, ): print(chunk) ``` ### Er…