Tool calls sometimes fail due to missing positional argument #34029
Description
Checked other resources
- This is a bug, not a usage question.
- I added a clear and descriptive title that summarizes this issue.
- I used the GitHub search to find a similar question and didn't find it.
- I am sure that this is a bug in LangChain rather than my code.
- The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
- This is not related to the langchain-community package.
- I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
Package (Required)
- langchain
- langchain-openai
- langchain-anthropic
- langchain-classic
- langchain-core
- langchain-cli
- langchain-model-profiles
- langchain-tests
- langchain-text-splitters
- langchain-chroma
- langchain-deepseek
- langchain-exa
- langchain-fireworks
- langchain-groq
- langchain-huggingface
- langchain-mistralai
- langchain-nomic
- langchain-ollama
- langchain-perplexity
- langchain-prompty
- langchain-qdrant
- langchain-xai
- Other / not sure / general
Example Code (Python)
from langchain_openai import ChatOpenAI
from langchain.agents import create_agent
from langchain.tools import tool, ToolRuntime
from langchain.agents.middleware import wrap_tool_call, AgentState
llm = ChatOpenAI(
model="Qwen3-8B-GGUF",
openai_api_key="sk-local", # Or a placeholder if required by the local server
openai_api_base="http://localhost:8002/v1"
)
@tool
def addConfig(config: str, runtime: ToolRuntime):
"""
Add a configuration file name to the list of configurations
Args:
config: The file name, formatted as a path (relative or absolute)
"""
print("(Dummy) Appending configuration ",config)
@wrap_tool_call
def printToolCalls(request, handler):
print(request)
return handler(request)
agent = create_agent(
model=llm,
tools=[addConfig],
system_prompt="You are a helpful assistant.",
middleware = [printToolCalls]
)
response = agent.invoke(
{"messages": [{"role": "user", "content": "Add the configuration config.0"}]}
)Error Message and Stack Trace (if applicable)
Traceback (most recent call last):
File "/home/ckelly/test/langchain/qcd_workflow/config_state/weird_err_reproducer/repro.py", line 36, in <module>
response = agent.invoke(
{"messages": [{"role": "user", "content": "Add the configuration config.0"}]}
)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/pregel/main.py", line 3050, in invoke
for chunk in self.stream(
~~~~~~~~~~~^
input,
^^^^^^
...<10 lines>...
**kwargs,
^^^^^^^^^
):
^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/pregel/main.py", line 2633, in stream
for _ in runner.tick(
~~~~~~~~~~~^
[t for t in loop.tasks.values() if not t.writes],
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
...<2 lines>...
schedule_task=loop.accept_push,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
):
^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/pregel/_runner.py", line 167, in tick
run_with_retry(
~~~~~~~~~~~~~~^
t,
^^
...<10 lines>...
},
^^
)
^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/pregel/_retry.py", line 42, in run_with_retry
return task.proc.invoke(task.input, config)
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/_internal/_runnable.py", line 656, in invoke
input = context.run(step.invoke, input, config, **kwargs)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/_internal/_runnable.py", line 400, in invoke
ret = self.func(*args, **kwargs)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 727, in _func
outputs = list(
executor.map(self._run_one, tool_calls, input_types, tool_runtimes)
)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/concurrent/futures/_base.py", line 619, in result_iterator
yield _result_or_cancel(fs.pop())
~~~~~~~~~~~~~~~~~^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/concurrent/futures/_base.py", line 317, in _result_or_cancel
return fut.result(timeout)
~~~~~~~~~~^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/concurrent/futures/_base.py", line 456, in result
return self.__get_result()
~~~~~~~~~~~~~~~~~^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/concurrent/futures/thread.py", line 59, in run
result = self.fn(*self.args, **self.kwargs)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain_core/runnables/config.py", line 546, in _wrapped_fn
return contexts.pop().run(fn, *args)
~~~~~~~~~~~~~~~~~~^^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 957, in _run_one
content = _handle_tool_error(e, flag=self._handle_tool_errors)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 404, in _handle_tool_error
content = flag(e) # type: ignore [assignment, call-arg]
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 361, in _default_handle_tool_errors
raise e
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 951, in _run_one
return self._wrap_tool_call(tool_request, execute)
~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain/agents/middleware/types.py", line 1604, in wrapped
return func(request, handler)
File "/home/ckelly/test/langchain/qcd_workflow/config_state/weird_err_reproducer/repro.py", line 27, in printToolCalls
return handler(request)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 947, in execute
return self._execute_tool_sync(req, input_type, config)
~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 891, in _execute_tool_sync
content = _handle_tool_error(e, flag=self._handle_tool_errors)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 404, in _handle_tool_error
content = flag(e) # type: ignore [assignment, call-arg]
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 361, in _default_handle_tool_errors
raise e
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 844, in _execute_tool_sync
response = tool.invoke(call_args, config)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain_core/tools/base.py", line 605, in invoke
return self.run(tool_input, **kwargs)
~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain_core/tools/base.py", line 932, in run
raise error_to_raise
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain_core/tools/base.py", line 898, in run
response = context.run(self._run, *tool_args, **tool_kwargs)
File "/home/ckelly/miniconda3/envs/ai-py313/lib/python3.13/site-packages/langchain_core/tools/structured.py", line 93, in _run
return self.func(*args, **kwargs)
~~~~~~~~~^^^^^^^^^^^^^^^^^
TypeError: addConfig() missing 1 required positional argument: 'config'
During task with name 'tools' and id '947599f3-98b7-5563-3987-38d0d47f7223'Description
I am trying to use LangChain agents to assist in putting together a job plan / configuration for an HPC application. The simple tool call above consistently fails due to its positional argument being missing. By wrapping the tool call I confirm that the argument (config.0) is actually being passed to the tool correctly so the issue is happening at a lower level within the tool execution chain:
ToolCallRequest(tool_call={'name': 'addConfig', 'args': {'config': 'config.0'}, 'id': 'WnemfvoElnQZJnjhgfT7wlBvzWm1jNXt', 'type': 'tool_call'}, tool=StructuredTool(name='addConfig', description='Add a configuration file name to the list of configurations\nArgs:\n config: The file name, formatted as a path (relative or absolute)', args_schema=<class 'langchain_core.utils.pydantic.addConfig'>, func=<function addConfig at 0x7ff9bb3d67a0>), state=...
The issue appears to go away if the argument is renamed. For example, with
def addConfig(configf: str, runtime: ToolRuntime):
"""
Add a configuration file name to the list of configurations
Args:
configf: The file name, formatted as a path (relative or absolute)
"""
print("(Dummy) Appending configuration ",configf)
the tool is executed correctly:
ToolCallRequest(tool_call={'name': 'addConfig', 'args': {'configf': 'config.0'}, 'id': 'L3kzDmy7D8bN0NtYdjTEcOXOlqqe4NQQ', 'type': 'tool_call'}, ...
...
...
(Dummy) Appending configuration config.0
This suggests some sort of keyword / name collision somewhere within the bowels of the software.
System Info
System Information
OS: Linux
OS Version: #15~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Jan 12 18:54:30 UTC 2
Python Version: 3.13.9 | packaged by Anaconda, Inc. | (main, Oct 21 2025, 19:16:10) [GCC 11.2.0]
Package Information
langchain_core: 1.0.6
langchain: 1.0.8
langchain_community: 0.4.1
langsmith: 0.4.43
langchain_classic: 1.0.0
langchain_openai: 1.0.3
langchain_text_splitters: 1.0.0
langgraph_sdk: 0.2.9
Optional packages not installed
langserve
Other Dependencies
aiohttp: 3.13.2
dataclasses-json: 0.6.7
httpx: 0.28.1
httpx-sse: 0.4.3
jsonpatch: 1.33
langgraph: 1.0.3
numpy: 2.3.5
openai: 2.8.1
orjson: 3.11.4
packaging: 25.0
pydantic: 2.12.4
pydantic-settings: 2.12.0
pyyaml: 6.0.3
PyYAML: 6.0.3
requests: 2.32.5
requests-toolbelt: 1.0.0
sqlalchemy: 2.0.44
SQLAlchemy: 2.0.44
tenacity: 9.1.2
tiktoken: 0.12.0
typing-extensions: 4.15.0
zstandard: 0.25.0