Home / File/ tools.py — langchain Source File

tools.py — langchain Source File

Architecture documentation for tools.py, a python file in the langchain codebase. 3 imports, 0 dependents.

File python LangChainCore Runnables 3 imports 1 classes

Entity Profile

Dependency Diagram

graph LR
  0bc03109_78de_8833_5b42_f274acec5b0f["tools.py"]
  9444498b_8066_55c7_b3a2_1d90c4162a32["langchain_core.messages"]
  0bc03109_78de_8833_5b42_f274acec5b0f --> 9444498b_8066_55c7_b3a2_1d90c4162a32
  121262a1_0bd6_d637_bce3_307ab6b3ecd4["langchain_core.tools"]
  0bc03109_78de_8833_5b42_f274acec5b0f --> 121262a1_0bd6_d637_bce3_307ab6b3ecd4
  ec9efe46_d0fe_78e9_5d13_f2067019cee1["langchain_tests.unit_tests.tools"]
  0bc03109_78de_8833_5b42_f274acec5b0f --> ec9efe46_d0fe_78e9_5d13_f2067019cee1
  style 0bc03109_78de_8833_5b42_f274acec5b0f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

"""Integration tests for tools."""

from langchain_core.messages import ToolCall
from langchain_core.tools import BaseTool

from langchain_tests.unit_tests.tools import ToolsTests


class ToolsIntegrationTests(ToolsTests):
    """Base class for tools integration tests."""

    def test_invoke_matches_output_schema(self, tool: BaseTool) -> None:
        """Test invoke matches output schema.

        If invoked with a `ToolCall`, the tool should return a valid `ToolMessage`
        content.

        If you have followed the [custom tool guide](https://docs.langchain.com/oss/python/contributing/implement-langchain#tools),
        this test should always pass because `ToolCall` inputs are handled by the
        `langchain_core.tools.BaseTool` class.

        If you have not followed this guide, you should ensure that your tool's
        `invoke` method returns a valid ToolMessage content when it receives
        a `dict` representing a `ToolCall` as input (as opposed to distinct args).
        """
        tool_call = ToolCall(
            name=tool.name,
            args=self.tool_invoke_params_example,
            id="123",
            type="tool_call",
        )
        result = tool.invoke(tool_call)

        tool_message = result
        if tool.response_format == "content_and_artifact":
            # artifact can be anything, except none
            assert tool_message.artifact is not None

        # check content is a valid ToolMessage content
        assert isinstance(tool_message.content, str | list)
        if isinstance(tool_message.content, list):
            # content blocks must be str or dict
            assert all(isinstance(c, str | dict) for c in tool_message.content)

    async def test_async_invoke_matches_output_schema(self, tool: BaseTool) -> None:
        """Test async invoke matches output schema.

        If ainvoked with a `ToolCall`, the tool should return a valid `ToolMessage`
        content.

        For debugging tips, see `test_invoke_matches_output_schema`.
        """
        tool_call = ToolCall(
            name=tool.name,
            args=self.tool_invoke_params_example,
            id="123",
            type="tool_call",
        )
        result = await tool.ainvoke(tool_call)

        tool_message = result
        if tool.response_format == "content_and_artifact":
            # artifact can be anything, except none
            assert tool_message.artifact is not None

        # check content is a valid ToolMessage content
        assert isinstance(tool_message.content, str | list)
        if isinstance(tool_message.content, list):
            # content blocks must be str or dict
            assert all(isinstance(c, str | dict) for c in tool_message.content)

    def test_invoke_no_tool_call(self, tool: BaseTool) -> None:
        """Test invoke without `ToolCall`.

        If invoked without a `ToolCall`, the tool can return anything
        but it shouldn't throw an error.

        If this test fails, your tool may not be handling the input you defined
        in `tool_invoke_params_example` correctly, and it's throwing an error.

        This test doesn't have any checks. It's just to ensure that the tool
        doesn't throw an error when invoked with a `dict` of `**kwargs`.
        """
        tool.invoke(self.tool_invoke_params_example)

    async def test_async_invoke_no_tool_call(self, tool: BaseTool) -> None:
        """Test async invoke without `ToolCall`.

        If ainvoked without a `ToolCall`, the tool can return anything
        but it shouldn't throw an error.

        For debugging tips, see `test_invoke_no_tool_call`.
        """
        await tool.ainvoke(self.tool_invoke_params_example)

Domain

Subdomains

Dependencies

  • langchain_core.messages
  • langchain_core.tools
  • langchain_tests.unit_tests.tools

Frequently Asked Questions

What does tools.py do?
tools.py is a source file in the langchain codebase, written in python. It belongs to the LangChainCore domain, Runnables subdomain.
What does tools.py depend on?
tools.py imports 3 module(s): langchain_core.messages, langchain_core.tools, langchain_tests.unit_tests.tools.
Where is tools.py in the architecture?
tools.py is located at libs/standard-tests/langchain_tests/integration_tests/tools.py (domain: LangChainCore, subdomain: Runnables, directory: libs/standard-tests/langchain_tests/integration_tests).

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free