StructuredTool - is possible to have a tool that receive both positional and a list of dict arguments?

[thiagopo]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

#
# The code has simplified to hide some project details.
# 

from langchain_core.tools import BaseTool, StructuredTool
from pydantic import Field, BaseModel


class ArgsSchemaCustom(BaseModel):
    param1: str = Field(default="", description="description param1")
    param2: str = Field(default="master", description="description param2 (default is master)")
    param3: str = Field(default="", description="description param3")
    param4: str = Field(default="", description="description param4")
    changes: list = Field(default=[],
                          description="list of dict with elements \"path\" and \"content\". The path of file. The content has the changes for the file.")


#  Due to LangChain Tool limitation (
class FileChange(BaseTool):
    name: str = "create_file_change"
    description: str = """
        Create file change1
        :param param1: description param1
        :param param2: description param2
        :param param3: description param3
        :param param4: description param4
        :param changes: list of dict with elements "path" and "content". The path of file. The content has the changes for the file.
        :return: the JSON response from the changes details
        """
    args_schema: Type[ArgsSchemaCustom] = ArgsSchemaCustom

    def _run(self, param1: str, param2: str, param3: str, param4: str, changes: list):

        # implementation

        return "my_string"

# Tool creation
change = FileChange()
tools = [
    StructuredTool.from_function(name=change.name, description=change.description, func=change.run,
                                              args_schema=change.args_schema)
    ]

# Agent creation
llm = get_llm_chat_openai() #custom function to get a ChatOpenAI

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "My prompt for the agent"),
        MessagesPlaceholder("chat_history", optional=True),
        ("human", "{input}"),
        MessagesPlaceholder("agent_scratchpad"),
    ]
)

agent = create_openai_tools_agent(llm, tools, prompt)

agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)

analysis_out = agent_executor.invoke({"input": "The input text"})

Description

When my agent try to use the StructuredTool mentioned on example, I got an error

BaseTool.run() missing 1 required positional argument: 'tool_input' 

I check that this error occurs on langchain_core.tools.structured.StructuredTool._run.

    def _run(
        self,
        *args: Any,
        config: RunnableConfig,
        run_manager: Optional[CallbackManagerForToolRun] = None,
        **kwargs: Any,
    ) -> Any:
        """Use the tool."""
        if self.func:
            if run_manager and signature(self.func).parameters.get("callbacks"):
                kwargs["callbacks"] = run_manager.get_child()
            if config_param := _get_runnable_config_param(self.func):
                kwargs[config_param] = config
            return self.func(*args, **kwargs)    <<<<<  HERE the *args is empty ()
        msg = "StructuredTool does not support sync invocation."
        raise NotImplementedError(msg)

The *args is empty because of this other method

langchain_core.tools.base.BaseTool._to_args_and_kwargs

This method does not accept a mix of *args and **kwargs

    def _to_args_and_kwargs(
        self, tool_input: Union[str, dict], tool_call_id: Optional[str]
    ) -> tuple[tuple, dict]:
        if (
            self.args_schema is not None
            and isinstance(self.args_schema, type)
            and is_basemodel_subclass(self.args_schema)
            and not get_fields(self.args_schema)
        ):
            # StructuredTool with no args
            return (), {}
        tool_input = self._parse_input(tool_input, tool_call_id)
        # For backwards compatibility, if run_input is a string,
        # pass as a positional argument.
        if isinstance(tool_input, str):
            return (tool_input,), {}
        if isinstance(tool_input, dict):
            # Make a shallow copy of the input to allow downstream code
            # to modify the root level of the input without affecting the
            # original input.
            # This is used by the tool to inject run time information like
            # the callback manager.
            return (), tool_input.copy()     <<<<< FOR MY CASE, THIS IS THE RETURN
        # This code path is not expected to be reachable.
        msg = f"Invalid tool input type: {type(tool_input)}"
        raise TypeError(msg)

System Info

System Information

OS: Windows
OS Version: 10.0.22631
Python Version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]

Package Information

langchain_core: 0.3.65
langchain: 0.3.25
langchain_community: 0.3.25
langsmith: 0.3.45
langchain_openai: 0.3.22
langchain_text_splitters: 0.3.8

Optional packages not installed

langserve

Other Dependencies

aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
httpx: 0.28.1
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-azure-ai;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core<1.0.0,>=0.3.51: Installed. No version info available.
langchain-core<1.0.0,>=0.3.58: Installed. No version info available.
langchain-core<1.0.0,>=0.3.64: Installed. No version info available.
langchain-core<1.0.0,>=0.3.65: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-perplexity;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.25: Installed. No version info available.
langsmith-pyo3: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
langsmith<0.4,>=0.1.17: Installed. No version info available.
langsmith<0.4,>=0.3.45: Installed. No version info available.
numpy>=1.26.2;: Installed. No version info available.
numpy>=2.1.0;: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.68.2: Installed. No version info available.
opentelemetry-api: Installed. No version info available.
opentelemetry-exporter-otlp-proto-http: Installed. No version info available.
opentelemetry-sdk: Installed. No version info available.
orjson: 3.10.18
packaging: 24.2
packaging<25,>=23.2: Installed. No version info available.
pydantic: 2.11.5
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic>=2.7.4: Installed. No version info available.
pytest: Installed. No version info available.
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.4
requests-toolbelt: 1.0.0
requests<3,>=2: Installed. No version info available.
rich: Installed. No version info available.
SQLAlchemy<3,>=1.4: Installed. No version info available.
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
zstandard: 0.23.0

[thiagopo]

When I change my implementation to use a simple function like this:

def file_changes_tool(param1: str, param2: str, param3: str, param4: str, changes: list):
        """
        Create file change1
        :param param1: description param1
        :param param2: description param2
        :param param3: description param3
        :param param4: description param4
        :param changes: list of dict with elements "path" and "content". The path of file. The content has the changes for the file.
        :return: the JSON response from the changes details
        """
      #  implementation 
      return "my return"

And declare that like this:

tools = [ StructuredTool.from_function(file_changes_tool) ]

Then it runs with success! No errors.