Pausing the Agent for Input
Pause an agent run mid-tool, hand control to a custom React component, and resume with the user's answer.
/** * LangGraph TypeScript agent for the Interrupt-based Generative UI demos. * * Defines a backend tool `schedule_meeting(topic, attendee)` that uses * langgraph's `interrupt()` primitive to pause the run and surface the * meeting context to the frontend. The frontend `useInterrupt` renderer * shows a time picker and resolves with `{chosen_time, chosen_label}` or * `{cancelled: true}`, which this tool turns into a human-readable result. * * Ported from `src/agents/interrupt_agent.py` in the langgraph-python package. */import { z } from "zod";import type { RunnableConfig } from "@langchain/core/runnables";import { tool } from "@langchain/core/tools";import { ToolNode } from "@langchain/langgraph/prebuilt";import type { AIMessage } from "@langchain/core/messages";import { SystemMessage } from "@langchain/core/messages";import { MemorySaver, START, StateGraph, Annotation, interrupt,} from "@langchain/langgraph";import { ChatOpenAI } from "@langchain/openai";import { convertActionsToDynamicStructuredTools, CopilotKitStateAnnotation,} from "@copilotkit/sdk-js/langgraph";// Demo-only fixed timezone offset (Pacific = UTC-7 in PDT, UTC-8 in PST).// A real app would use the user's calendar + locale; we hardcode Pacific so// screenshots are stable. Mirrors interrupt_agent.py.const DEMO_TZ_OFFSET_HOURS = -7; // PDTinterface TimeSlot { label: string; iso: string;}function candidateSlots(): TimeSlot[] { const now = new Date(); // "Tomorrow" const tomorrow = new Date(now); tomorrow.setDate(now.getDate() + 1); // "Monday" — at least 2 days away to avoid collisions with "Tomorrow" const dayOfWeek = now.getDay(); // 0=Sun, 1=Mon, ..., 6=Sat let daysToMonday = (1 - dayOfWeek + 7) % 7; if (daysToMonday <= 1) daysToMonday += 7; const nextMonday = new Date(now); nextMonday.setDate(now.getDate() + daysToMonday); const fmt = (d: Date, hour: number, minute = 0): string => { // Build an ISO-like string with the demo timezone offset const sign = DEMO_TZ_OFFSET_HOURS >= 0 ? "+" : "-"; const absOffset = Math.abs(DEMO_TZ_OFFSET_HOURS); const hh = String(absOffset).padStart(2, "0"); return `${d.getFullYear()}-${String(d.getMonth() + 1).padStart(2, "0")}-${String(d.getDate()).padStart(2, "0")}T${String(hour).padStart(2, "0")}:${String(minute).padStart(2, "0")}:00${sign}${hh}:00`; }; return [ { label: "Tomorrow 10:00 AM", iso: fmt(tomorrow, 10) }, { label: "Tomorrow 2:00 PM", iso: fmt(tomorrow, 14) }, { label: "Monday 9:00 AM", iso: fmt(nextMonday, 9) }, { label: "Monday 3:30 PM", iso: fmt(nextMonday, 15, 30) }, ];}const SYSTEM_PROMPT = "You are a scheduling assistant. Whenever the user asks you to book a " + "call / schedule a meeting, you MUST call the `schedule_meeting` tool. " + "Pass a short `topic` describing the purpose and `attendee` describing " + "who the meeting is with. After the tool returns, confirm briefly " + "whether the meeting was scheduled and at what time, or that the user " + "cancelled.";const AgentStateAnnotation = Annotation.Root({ ...CopilotKitStateAnnotation.spec,});export type AgentState = typeof AgentStateAnnotation.State;const scheduleMeeting = tool( async ({ topic, attendee }: { topic: string; attendee?: string | null }) => { // langgraph's `interrupt()` pauses execution and forwards the payload to // the client. The frontend v2 `useInterrupt` hook renders the picker and // calls `resolve(...)` with the user's selection, which comes back here. const response: unknown = interrupt({ topic, attendee: attendee ?? null, slots: candidateSlots(), }); if (response && typeof response === "object") { const resp = response as Record<string, unknown>; if (resp.cancelled) { return `User cancelled. Meeting NOT scheduled: ${topic}`; } const chosenLabel = (resp.chosen_label as string | undefined) ?? (resp.chosen_time as string | undefined); if (chosenLabel) { return `Meeting scheduled for ${chosenLabel}: ${topic}`; } } return `User did not pick a time. Meeting NOT scheduled: ${topic}`; }, { name: "schedule_meeting", description: "Ask the user to pick a time slot for a call, via an in-chat picker.", schema: z.object({ topic: z .string() .describe("Short human-readable description of the call's purpose."), attendee: z .string() .nullable() .optional() .describe("Who the call is with (optional)."), }), },);const tools = [scheduleMeeting];async function chatNode(state: AgentState, config: RunnableConfig) { const model = new ChatOpenAI({ temperature: 0, model: "gpt-4o-mini" }); const modelWithTools = model.bindTools!([ ...convertActionsToDynamicStructuredTools(state.copilotkit?.actions ?? []), ...tools, ]); const systemMessage = new SystemMessage({ content: SYSTEM_PROMPT }); const response = await modelWithTools.invoke( [systemMessage, ...state.messages], config, ); return { messages: response };}function shouldContinue({ messages, copilotkit }: AgentState) { const lastMessage = messages[messages.length - 1] as AIMessage; if (lastMessage.tool_calls?.length) { const actions = copilotkit?.actions; const toolCallName = lastMessage.tool_calls![0].name; if (!actions || actions.every((action) => action.name !== toolCallName)) { return "tool_node"; } } return "__end__";}const workflow = new StateGraph(AgentStateAnnotation) .addNode("chat_node", chatNode) .addNode("tool_node", new ToolNode(tools)) .addEdge(START, "chat_node") .addEdge("tool_node", "chat_node") .addConditionalEdges("chat_node", shouldContinue as any);const memory = new MemorySaver();export const graph = workflow.compile({ checkpointer: memory,});What is this?#
useInterrupt lets your agent pause mid-run, hand control to the user
through a custom React component, and resume with whatever the user
returns. How that pause is implemented depends on the framework's
runtime.
LangGraph ships a first-class
interrupt()
primitive that lets a running node suspend itself and hand control to
the client. The run is frozen server-side until the client resolves the
interrupt with a payload, at which point the node resumes as if
interrupt() had simply returned that payload.
CopilotKit's useInterrupt is the frontend half of that contract: it
subscribes to the paused run, renders whatever component you give it,
and calls the agent back with the user's answer.
When should I use this?#
Reach for useInterrupt when the pause is a graph-enforced
checkpoint where the code path must stop and wait for a human,
not an LLM-initiated tool call. Typical cases:
- A sensitive action (payments, irreversible writes) must be approved
- A required piece of state isn't known and can only be collected from the user
- The agent explicitly reaches an approval node in a longer workflow
- You want the server-side contract to be
interrupt(...)and resume with a payload
For LLM-initiated pauses where the model decides on the fly to ask
the user, prefer useHumanInTheLoop.
The backend: interrupt() inside a tool#
The example agent exposes a schedule_meeting tool. When the model
calls it, the tool issues a langgraph.interrupt(...)
with the meeting context. The run freezes here until the client
resolves; the resolution becomes the return value of interrupt(),
which the tool then turns into a final string for the model:
import { z } from "zod";import type { RunnableConfig } from "@langchain/core/runnables";import { tool } from "@langchain/core/tools";import { ToolNode } from "@langchain/langgraph/prebuilt";import type { AIMessage } from "@langchain/core/messages";import { SystemMessage } from "@langchain/core/messages";import { MemorySaver, START, StateGraph, Annotation, interrupt,} from "@langchain/langgraph";import { ChatOpenAI } from "@langchain/openai";import { convertActionsToDynamicStructuredTools, CopilotKitStateAnnotation,} from "@copilotkit/sdk-js/langgraph";// Demo-only fixed timezone offset (Pacific = UTC-7 in PDT, UTC-8 in PST).// A real app would use the user's calendar + locale; we hardcode Pacific so// screenshots are stable. Mirrors interrupt_agent.py.const DEMO_TZ_OFFSET_HOURS = -7; // PDTinterface TimeSlot { label: string; iso: string;}function candidateSlots(): TimeSlot[] { const now = new Date(); // "Tomorrow" const tomorrow = new Date(now); tomorrow.setDate(now.getDate() + 1); // "Monday" — at least 2 days away to avoid collisions with "Tomorrow" const dayOfWeek = now.getDay(); // 0=Sun, 1=Mon, ..., 6=Sat let daysToMonday = (1 - dayOfWeek + 7) % 7; if (daysToMonday <= 1) daysToMonday += 7; const nextMonday = new Date(now); nextMonday.setDate(now.getDate() + daysToMonday); const fmt = (d: Date, hour: number, minute = 0): string => { // Build an ISO-like string with the demo timezone offset const sign = DEMO_TZ_OFFSET_HOURS >= 0 ? "+" : "-"; const absOffset = Math.abs(DEMO_TZ_OFFSET_HOURS); const hh = String(absOffset).padStart(2, "0"); return `${d.getFullYear()}-${String(d.getMonth() + 1).padStart(2, "0")}-${String(d.getDate()).padStart(2, "0")}T${String(hour).padStart(2, "0")}:${String(minute).padStart(2, "0")}:00${sign}${hh}:00`; }; return [ { label: "Tomorrow 10:00 AM", iso: fmt(tomorrow, 10) }, { label: "Tomorrow 2:00 PM", iso: fmt(tomorrow, 14) }, { label: "Monday 9:00 AM", iso: fmt(nextMonday, 9) }, { label: "Monday 3:30 PM", iso: fmt(nextMonday, 15, 30) }, ];}const SYSTEM_PROMPT = "You are a scheduling assistant. Whenever the user asks you to book a " + "call / schedule a meeting, you MUST call the `schedule_meeting` tool. " + "Pass a short `topic` describing the purpose and `attendee` describing " + "who the meeting is with. After the tool returns, confirm briefly " + "whether the meeting was scheduled and at what time, or that the user " + "cancelled.";const AgentStateAnnotation = Annotation.Root({ ...CopilotKitStateAnnotation.spec,});export type AgentState = typeof AgentStateAnnotation.State;const scheduleMeeting = tool( async ({ topic, attendee }: { topic: string; attendee?: string | null }) => { // langgraph's `interrupt()` pauses execution and forwards the payload to // the client. The frontend v2 `useInterrupt` hook renders the picker and // calls `resolve(...)` with the user's selection, which comes back here. const response: unknown = interrupt({ topic, attendee: attendee ?? null, slots: candidateSlots(), }); if (response && typeof response === "object") { const resp = response as Record<string, unknown>; if (resp.cancelled) { return `User cancelled. Meeting NOT scheduled: ${topic}`; } const chosenLabel = (resp.chosen_label as string | undefined) ?? (resp.chosen_time as string | undefined); if (chosenLabel) { return `Meeting scheduled for ${chosenLabel}: ${topic}`; } } return `User did not pick a time. Meeting NOT scheduled: ${topic}`; }, { name: "schedule_meeting", description: "Ask the user to pick a time slot for a call, via an in-chat picker.", schema: z.object({ topic: z .string() .describe("Short human-readable description of the call's purpose."), attendee: z .string() .nullable() .optional() .describe("Who the call is with (optional)."), }), },);Two things to note:
- The payload (
{"topic": topic, "attendee": attendee}) is what the frontend receives asevent.value. Keep it a plain, serializable object. It's the "pause-time context" the UI needs to render. - The return-side contract (
{chosen_label, chosen_time}or{cancelled: true}) is entirely yours. The client can send anything as the resolve payload; the tool is the one that gives it meaning.
The frontend: useInterrupt render prop#
On the client you register a useInterrupt hook per agent. When the
paused run arrives, its payload is handed to render as event.value,
and resolve(...) is how you resume the run:
import { CopilotKit, CopilotChat, useInterrupt,} from "@copilotkit/react-core/v2";import type { TimeSlot } from "./_components/time-picker-card";import { TimePickerCard } from "./_components/time-picker-card";import { generateFallbackSlots } from "../_shared/interrupt-fallback-slots";import { useGenUiInterruptSuggestions } from "./suggestions";export default function GenUiInterruptDemo() { return ( <CopilotKit runtimeUrl="/api/copilotkit" agent="gen-ui-interrupt"> <div className="flex justify-center items-center h-screen w-full"> <div className="h-full w-full max-w-4xl"> <Chat /> </div> </div> </CopilotKit> );}function Chat() { useGenUiInterruptSuggestions(); // `useInterrupt` is the low-level primitive for handling LangGraph // `interrupt(...)` events. The backend's `schedule_meeting` tool surfaces // a structured payload — `{ topic, attendee, slots }` — which we render // inline in the chat as a message bubble. Calling `resolve(...)` resumes // the LangGraph run with the user's selection. useInterrupt({ agentId: "gen-ui-interrupt", renderInChat: true, render: ({ event, resolve }) => { // The AG-UI adapter JSON-stringifies interrupt values, so parse // when needed to extract the structured payload. const raw = event.value ?? {}; const payload = (typeof raw === "string" ? JSON.parse(raw) : raw) as { topic?: string; attendee?: string; slots?: TimeSlot[]; }; const slots = payload.slots && payload.slots.length > 0 ? payload.slots : generateFallbackSlots(); return ( <TimePickerCard topic={payload.topic ?? "a call"} attendee={payload.attendee} slots={slots} onSubmit={(result) => { // Defer resolve so React commits the picked/cancelled state // before useInterrupt clears the interrupt element. A single // requestAnimationFrame is not reliable — rAF fires before // React's commit in some scheduling scenarios. Using a short // setTimeout ensures the commit lands first and the user sees // the "Booked"/"Cancelled" badge before the card unmounts. setTimeout(() => resolve(result), 500); }} /> ); }, });Whatever you pass to resolve is round-tripped back to the agent as
the return value of the matching interrupt(...) call.
Key props#
agentId— must match a runtime-registered agent. If omitted, the hook assumes"default". A mismatch means the interrupt never fires.render— receives{ event, resolve }.event.valueis the payload you passed tointerrupt(...)on the server.renderInChat— whentrue(as above), the picker appears inline in the chat transcript, between the paused assistant turn and the still-pending continuation.
Multiple interrupts? Add a type and gate with enabled#
If your graph issues more than one kind of interrupt (e.g. "ask" vs
"approval"), tag each with a type field on the payload and install
one useInterrupt per shape, each gated by an enabled predicate:
useInterrupt({
agentId: "gen-ui-interrupt",
enabled: ({ eventValue }) => eventValue.type === "ask",
render: ({ event, resolve }) => (
<AskCard question={event.value.content} onAnswer={resolve} />
),
});
useInterrupt({
agentId: "gen-ui-interrupt",
enabled: ({ eventValue }) => eventValue.type === "approval",
render: ({ event, resolve }) => (
<ApproveCard content={event.value.content} onAnswer={resolve} />
),
});Preprocess with handler#
For cases where the interrupt can sometimes be resolved without user
input (e.g. the current user already has permission), pass a handler
that runs before render. The handler can call resolve(...) itself
to short-circuit the UI, or return a value that render receives as
result:
useInterrupt({
agentId: "gen-ui-interrupt",
handler: async ({ event, resolve }) => {
const dept = await lookupUserDepartment();
if (event.value.accessDepartment === dept || dept === "admin") {
resolve({ code: "AUTH_BY_DEPARTMENT" });
return; // skip render
}
return { dept };
},
render: ({ result, event, resolve }) => (
<RequestAccessCard
dept={result.dept}
onRequest={() => resolve({ code: "REQUEST_AUTH" })}
onCancel={() => resolve({ code: "CANCEL" })}
/>
),
});Going further#
- Tool-based HITL with
useHumanInTheLoop— for LLM-initiated pauses. - Headless interrupts — compose the lower-level primitives
(
useAgent,agent.subscribe,copilotkit.runAgent) to resolve interrupts outside a chat surface.
