ai-agents-tool-runtime-support-when-using-langgraph-s-built-in-toolnode-with-tool-c59f98f5

THEN Implement a custom ToolNode that manually passes the runtime context (e.g., `ToolRuntime` or `Runtime`) to each tool's `invoke` method. Inside the custom node, iterate over the tool calls from the state, look up the tool by name, and call `tool.invoke(tool_call['args'], runtime=runtime)`. This bypasses the missing support in the official ToolNode until the LangGraph team ports it over.

def runtime_aware_tool_node(state: dict, runtime: Runtime[ContextSchema]) -> dict:
    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}