ToolRuntime isn't injected into BaseTool subclass's _run #34558
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 typing import Type
from langchain.tools import ToolRuntime
from langchain_core.tools import BaseTool
from pydantic import BaseModel, Field
class MultiplyInput(BaseModel):
a: int = Field(description="first number")
b: int = Field(description="second number")
class Multipler(BaseTool):
name: str = "Multiplier"
description: str = "a tool for multiplying two numbers"
args_schema: Type[BaseModel] = MultiplyInput
return_direct: bool = False
def _run(self, a: int, b: int, runtime: ToolRuntime) -> int:
print(f"runtime = {runtime}")
return a * b
if __name__ == "__main__":
import os
import dotenv
from langchain.agents import create_agent
from langchain_openai import ChatOpenAI
# load OPENAI_API_KEY, OPENAI_API_BASE_URL and OPENAI_MODEL from .env
dotenv.load_dotenv()
# model = ChatOpenAI(
# api_key=os.environ["OPENAI_API_KEY"],
# base_url=os.environ["OPENAI_API_BASE_URL"],
# model=os.environ["OPENAI_MODEL"],
# )
model = ChatOpenAI(model="gpt-4o")
agent = create_agent(
model, tools=[Multipler()], system_prompt="You are a helpful assistant."
)
r = agent.invoke({"messages": [{"role": "user", "content": "calculate 2 * 3"}]})
for v in r["messages"]:
v.pretty_print()Error Message and Stack Trace (if applicable)
Traceback (most recent call last):
File "/Users/sammyne/github.com/sammyne/langmem0/./examples/hi.py", line 46, in <module>
r = agent.invoke({"messages": [{"role": "user", "content": "calculate 2 * 3"}]})
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py", line 3068, in invoke
for chunk in self.stream(
~~~~~~~~~~~^
input,
^^^^^^
...<10 lines>...
**kwargs,
^^^^^^^^^
):
^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py", line 2643, 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 "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py", line 167, in tick
run_with_retry(
~~~~~~~~~~~~~~^
t,
^^
...<10 lines>...
},
^^
)
^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py", line 42, in run_with_retry
return task.proc.invoke(task.input, config)
~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py", line 656, in invoke
input = context.run(step.invoke, input, config, **kwargs)
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py", line 400, in invoke
ret = self.func(*args, **kwargs)
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 799, in _func
outputs = list(
executor.map(self._run_one, tool_calls, input_types, tool_runtimes)
)
File "/Users/xiangminli/.local/share/uv/python/cpython-3.13.11-macos-aarch64-none/lib/python3.13/concurrent/futures/_base.py", line 619, in result_iterator
yield _result_or_cancel(fs.pop())
~~~~~~~~~~~~~~~~~^^^^^^^^^^
File "/Users/xiangminli/.local/share/uv/python/cpython-3.13.11-macos-aarch64-none/lib/python3.13/concurrent/futures/_base.py", line 317, in _result_or_cancel
return fut.result(timeout)
~~~~~~~~~~^^^^^^^^^
File "/Users/xiangminli/.local/share/uv/python/cpython-3.13.11-macos-aarch64-none/lib/python3.13/concurrent/futures/_base.py", line 449, in result
return self.__get_result()
~~~~~~~~~~~~~~~~~^^
File "/Users/xiangminli/.local/share/uv/python/cpython-3.13.11-macos-aarch64-none/lib/python3.13/concurrent/futures/_base.py", line 401, in __get_result
raise self._exception
File "/Users/xiangminli/.local/share/uv/python/cpython-3.13.11-macos-aarch64-none/lib/python3.13/concurrent/futures/thread.py", line 59, in run
result = self.fn(*self.args, **self.kwargs)
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langchain_core/runnables/config.py", line 551, in _wrapped_fn
return contexts.pop().run(fn, *args)
~~~~~~~~~~~~~~~~~~^^^^^^^^^^^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 1010, in _run_one
return self._execute_tool_sync(tool_request, input_type, config)
~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 959, in _execute_tool_sync
content = _handle_tool_error(e, flag=self._handle_tool_errors)
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 424, in _handle_tool_error
content = flag(e) # type: ignore [assignment, call-arg]
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 381, in _default_handle_tool_errors
raise e
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langgraph/prebuilt/tool_node.py", line 916, in _execute_tool_sync
response = tool.invoke(call_args, config)
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langchain_core/tools/base.py", line 629, in invoke
return self.run(tool_input, **kwargs)
~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langchain_core/tools/base.py", line 981, in run
raise error_to_raise
File "/Users/sammyne/github.com/sammyne/langmem0/.venv/lib/python3.13/site-packages/langchain_core/tools/base.py", line 947, in run
response = context.run(self._run, *tool_args, **tool_kwargs)
TypeError: Multipler._run() missing 1 required positional argument: 'runtime'
During task with name 'tools' and id '4967121b-b0b3-7ca9-cc4e-818167697ccb'Description
- I'm trying to build a custom tool by subclassing BaseTool, and want to access
runtimearg of type ToolRuntime within the overriden_runmethod - Expect to access ToolRuntime successfuly
- But it failed
System Info
System Information
OS: Darwin
OS Version: Darwin Kernel Version 24.6.0: Mon Jul 14 11:30:30 PDT 2025; root:xnu-11417.140.69~1/RELEASE_ARM64_T6020
Python Version: 3.13.11 (main, Dec 17 2025, 20:55:16) [Clang 21.1.4 ]
Package Information
langchain_core: 1.2.5
langchain: 1.2.0
langsmith: 0.5.2
langchain_openai: 1.1.6
langgraph_sdk: 0.3.1
Optional packages not installed
langserve
Other Dependencies
httpx: 0.28.1
jsonpatch: 1.33
langgraph: 1.0.5
openai: 2.14.0
orjson: 3.11.5
packaging: 25.0
pydantic: 2.12.5
pyyaml: 6.0.3
requests: 2.32.5
requests-toolbelt: 1.0.0
tenacity: 9.1.2
tiktoken: 0.12.0
typing-extensions: 4.15.0
uuid-utils: 0.12.0
zstandard: 0.25.0