ai-agents-tool-runtime-support-when-using-langgraph-s-built-in-toolnode-with-tool-948ed710

THEN As a temporary workaround, either use LangChain's internal ToolNode (with leading underscore) or implement a custom tool node that manually passes the 'runtime' parameter to tool.invoke(). The LangGraph maintainers have acknowledged the issue and plan to add support in an upcoming release, so after updating, the official ToolNode will handle ToolRuntime natively.

def custom_tool_node(state: dict, runtime: Runtime):
    result = []
    for tool_call in state["messages"][-1].tool_calls:
        tool = tools_by_name[tool_call["name"]]
        observation = tool.invoke(tool_call["args"], runtime=runtime)
        result.append(ToolMessage(content=observation, tool_call_id=tool_call["id"]))
    return {"messages": result}