_get_tool_return() — langchain Function Reference

Architecture documentation for the _get_tool_return() function in agent.py from the langchain codebase.

Function python AgentOrchestration ActionLogic called by 2

Entity Profile

AgentOrchestration→ ActionLogic→ _get_tool_return() — langchain Function Reference

Dependency Diagram

graph TD
  6318fe2c_c718_cc8e_b66f_30bc2f54d1dc["_get_tool_return()"]
  493d4ce4_2303_08e0_2337_2bee34fe2662["AgentExecutor"]
  6318fe2c_c718_cc8e_b66f_30bc2f54d1dc -->|defined in| 493d4ce4_2303_08e0_2337_2bee34fe2662
  edf0069e_99f2_31ed_6ba2_2ed571e40c37["_call()"]
  edf0069e_99f2_31ed_6ba2_2ed571e40c37 -->|calls| 6318fe2c_c718_cc8e_b66f_30bc2f54d1dc
  0af1a14d_a510_7165_2c6d_4a48bbb56e65["_acall()"]
  0af1a14d_a510_7165_2c6d_4a48bbb56e65 -->|calls| 6318fe2c_c718_cc8e_b66f_30bc2f54d1dc
  style 6318fe2c_c718_cc8e_b66f_30bc2f54d1dc fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/agent.py lines 1697–1716

    def _get_tool_return(
        self,
        next_step_output: tuple[AgentAction, str],
    ) -> AgentFinish | None:
        """Check if the tool is a returning tool."""
        agent_action, observation = next_step_output
        name_to_tool_map = {tool.name: tool for tool in self.tools}
        return_value_key = "output"
        if len(self._action_agent.return_values) > 0:
            return_value_key = self._action_agent.return_values[0]
        # Invalid tools won't be in the map, so we return False.
        if (
            agent_action.tool in name_to_tool_map
            and name_to_tool_map[agent_action.tool].return_direct
        ):
            return AgentFinish(
                {return_value_key: observation},
                "",
            )
        return None