[Bug]:The error "unexpected keyword argument 'config'" occurred when integrating langgraph

[soulcape]

Contact Details

No response

📦 Package Version

0.4.21

🎞️ Framework Version

langchain 0.3.25 langchain-anthropic 0.3.15 langchain-classic 1.0.0 langchain-community 0.3.19 langchain-core 0.3.81 langchain-experimental 0.3.4 langchain-huggingface 1.1.0 langchain-mcp-adapters 0.1.0 langchain-openai 0.3.23 langchain-text-splitters 0.3.8 langfuse 3.10.1 langgraph 0.4.10 langgraph-checkpoint 2.0.26 langgraph-prebuilt 0.2.3 langgraph-sdk 0.1.69

🔎 Describe the Bug

My example:
import agentops
import asyncio
from typing import Annotated, Literal, TypedDict

from langchain_core.runnables import RunnableConfig
from langgraph.graph import StateGraph, END
from langgraph.graph.message import add_messages
from langchain_openai import ChatOpenAI
from pydantic import SecretStr

Initialize AgentOps

agentops.init(api_key="66c3a0e1-cee9-4fe9-8dfd-6ba819bf5923")

Define your graph state

class AgentState(TypedDict):
messages: Annotated[list, add_messages]

Create your LLM

model = ChatOpenAI(
model="Qwen3-32B-23-new", # 根据你的实际模型调整
base_url="http://10.19.154.22:38009/v1", # 本地模型服务地址
api_key=SecretStr("sk-aaaa"), # 如果服务不需要认证，可以随意填写
temperature=0.7,
max_tokens=1000
)

def agent_node(state: AgentState, config: RunnableConfig):
messages = state["messages"]
response = model.invoke(messages, config=config)
return {"messages": [response]}

Build the graph

workflow = StateGraph(AgentState)
workflow.add_node("agent", agent_node)
workflow.set_entry_point("agent")
workflow.add_edge("agent", END)

Compile the graph

app = workflow.compile()

使用 astream 方式处理

async def process_stream():
async for chunk in app.astream({"messages": [{"role": "user", "content": "Hello!"}]}):
print(chunk)

运行异步函数

if name == "main":
asyncio.run(process_stream())

error info:
D:\software\python\envs\py312\Scripts\python.exe E:\workspace\pycharmws\test\agentops\example2.py
🖇 AgentOps: Session Replay for default trace: https://app.agentops.ai/sessions?trace_id=98034f9f6512bdf1083f24ed4316fdba
🖇 AgentOps: You're on the agentops free plan 🤔
--- Logging error ---
Traceback (most recent call last):
File "D:\software\python\Python312\Lib\logging_init_.py", line 1163, in emit
stream.write(msg + self.terminator)
UnicodeEncodeError: 'gbk' codec can't encode character '\U0001f914' in position 66: illegal multibyte sequence
Call stack:
File "D:\software\python\Python312\Lib\threading.py", line 1032, in _bootstrap
self._bootstrap_inner()
File "D:\software\python\Python312\Lib\threading.py", line 1075, in _bootstrap_inner
self.run()
File "D:\software\python\Python312\Lib\threading.py", line 1012, in run
self._target(*self._args, **self._kwargs)
File "D:\software\python\envs\py312\Lib\site-packages\agentops\client\client.py", line 131, in run_async_auth
asyncio.run(self._fetch_auth_async(api_key))
File "D:\software\python\Python312\Lib\asyncio\runners.py", line 195, in run
return runner.run(main)
File "D:\software\python\Python312\Lib\asyncio\runners.py", line 118, in run
return self._loop.run_until_complete(task)
File "D:\software\python\Python312\Lib\asyncio\base_events.py", line 678, in run_until_complete
self.run_forever()
File "D:\software\python\Python312\Lib\asyncio\windows_events.py", line 322, in run_forever
super().run_forever()
File "D:\software\python\Python312\Lib\asyncio\base_events.py", line 645, in run_forever
self._run_once()
File "D:\software\python\Python312\Lib\asyncio\base_events.py", line 1999, in _run_once
handle._run()
File "D:\software\python\Python312\Lib\asyncio\events.py", line 88, in _run
self._context.run(self._callback, *self._args)
File "D:\software\python\envs\py312\Lib\site-packages\agentops\client\client.py", line 99, in _fetch_auth_async
response = await self.api.v3.fetch_auth_token(api_key)
File "D:\software\python\envs\py312\Lib\site-packages\agentops\client\api\versions\v3.py", line 57, in fetch_auth_token
logger.info(
Message: "You're on the agentops free plan 🤔"
Arguments: ()
Traceback (most recent call last):
File "E:\workspace\pycharmws\test\agentops\example2.py", line 49, in
asyncio.run(process_stream())
File "D:\software\python\Python312\Lib\asyncio\runners.py", line 195, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "D:\software\python\Python312\Lib\asyncio\runners.py", line 118, in run
return self.loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\Python312\Lib\asyncio\base_events.py", line 691, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "E:\workspace\pycharmws\test\agentops\example2.py", line 44, in process_stream
async for chunk in app.astream({"messages": [{"role": "user", "content": "Hello!"}]}):
File "D:\software\python\envs\py312\Lib\site-packages\langgraph\pregel_init.py", line 2655, in astream
async for _ in runner.atick(
File "D:\software\python\envs\py312\Lib\site-packages\langgraph\pregel\runner.py", line 295, in atick
await arun_with_retry(
File "D:\software\python\envs\py312\Lib\site-packages\langgraph\pregel\retry.py", line 136, in arun_with_retry
return await task.proc.ainvoke(task.input, config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\envs\py312\Lib\site-packages\langgraph\utils\runnable.py", line 672, in ainvoke
input = await asyncio.create_task(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\envs\py312\Lib\site-packages\langgraph\utils\runnable.py", line 440, in ainvoke
ret = await self.afunc(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\envs\py312\Lib\site-packages\langchain_core\runnables\config.py", line 611, in run_in_executor
return await asyncio.get_running_loop().run_in_executor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\Python312\Lib\concurrent\futures\thread.py", line 59, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\software\python\envs\py312\Lib\site-packages\langchain_core\runnables\config.py", line 602, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
TypeError: agent_node() got an unexpected keyword argument 'config'
During task with name 'agent' and id '55afc527-f2be-f645-f8de-8a7f40b42632'
🖇 AgentOps: Session Replay for default.session trace: https://app.agentops.ai/sessions?trace_id=98034f9f6512bdf1083f24ed4316fdba

Process finished with exit code 1

🤝 Contribution

• Yes, I'd be happy to submit a pull request with these changes.
• I need some guidance on how to contribute.
• I'd prefer the AgentOps team to handle this update.