langchain Architecture Docs
Home / Function/ _build_cleared_tool_input_message() — langchain Function Reference

_build_cleared_tool_input_message() — langchain Function Reference

Architecture documentation for the _build_cleared_tool_input_message() function in context_editing.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

Dependency Diagram

graph TD
  ee42af87_4c5e_4b39_d0f1_983638d93ef0["_build_cleared_tool_input_message()"]
  342553be_63ff_6f10_00db_f8b52bed863a["ClearToolUsesEdit"]
  ee42af87_4c5e_4b39_d0f1_983638d93ef0 -->|defined in| 342553be_63ff_6f10_00db_f8b52bed863a
  03942334_6db9_570a_7836_af54672f2984["apply()"]
  03942334_6db9_570a_7836_af54672f2984 -->|calls| ee42af87_4c5e_4b39_d0f1_983638d93ef0
  style ee42af87_4c5e_4b39_d0f1_983638d93ef0 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/langchain/agents/middleware/context_editing.py lines 158–184

    def _build_cleared_tool_input_message(
        message: AIMessage,
        tool_call_id: str,
    ) -> AIMessage:
        updated_tool_calls = []
        cleared_any = False
        for tool_call in message.tool_calls:
            updated_call = dict(tool_call)
            if updated_call.get("id") == tool_call_id:
                updated_call["args"] = {}
                cleared_any = True
            updated_tool_calls.append(updated_call)

        metadata = dict(getattr(message, "response_metadata", {}))
        context_entry = dict(metadata.get("context_editing", {}))
        if cleared_any:
            cleared_ids = set(context_entry.get("cleared_tool_inputs", []))
            cleared_ids.add(tool_call_id)
            context_entry["cleared_tool_inputs"] = sorted(cleared_ids)
            metadata["context_editing"] = context_entry

        return message.model_copy(
            update={
                "tool_calls": updated_tool_calls,
                "response_metadata": metadata,
            }
        )

Domain

Subdomains

Defined In

Called By

Source

Frequently Asked Questions

What does _build_cleared_tool_input_message() do?
_build_cleared_tool_input_message() is a function in the langchain codebase, defined in libs/langchain_v1/langchain/agents/middleware/context_editing.py.
Where is _build_cleared_tool_input_message() defined?
_build_cleared_tool_input_message() is defined in libs/langchain_v1/langchain/agents/middleware/context_editing.py at line 158.
What calls _build_cleared_tool_input_message()?
_build_cleared_tool_input_message() is called by 1 function(s): apply.

Analyze Your Own Codebase

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

Try Supermodel Free