_on_tool_start() — langchain Function Reference

Architecture documentation for the _on_tool_start() function in stdout.py from the langchain codebase.

Function python Observability Tracers calls 1

Entity Profile

Observability→ Tracers→ _on_tool_start() — langchain Function Reference

Dependency Diagram

graph TD
  442b4b55_0d0b_ec70_5d85_b110cbb0d4af["_on_tool_start()"]
  56d9fac7_db71_9c71_7cac_1d680d392fa0["FunctionCallbackHandler"]
  442b4b55_0d0b_ec70_5d85_b110cbb0d4af -->|defined in| 56d9fac7_db71_9c71_7cac_1d680d392fa0
  1bda6774_d332_dec5_ed8f_8d6eef57961e["get_breadcrumbs()"]
  442b4b55_0d0b_ec70_5d85_b110cbb0d4af -->|calls| 1bda6774_d332_dec5_ed8f_8d6eef57961e
  style 442b4b55_0d0b_ec70_5d85_b110cbb0d4af fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/tracers/stdout.py lines 169–175

    def _on_tool_start(self, run: Run) -> None:
        crumbs = self.get_breadcrumbs(run)
        self.function_callback(
            f"{get_colored_text('[tool/start]', color='green')} "
            + get_bolded_text(f"[{crumbs}] Entering Tool run with input:\n")
            + f'"{run.inputs["input"].strip()}"'
        )