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.
What is this?
Some agent steps need a person's answer before the run can continue, such as
approving a payment or picking a meeting time. useInterrupt pauses the run,
shows your React component, and resumes the run with the answer. How the pause
works depends on your agent framework.
This framework ships a first-class interrupt primitive that lets running
work suspend itself and hand control to the client: interrupt() in
LangGraph,
interrupts in AWS Strands,
a tool that returns suspend() in Mastra, or a @human_feedback step in a
CrewAI Flow.
The run is frozen server-side until the client resolves the interrupt with a
payload. Then the run resumes, and the agent receives that payload as the
answer.
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 checkpoint in your
agent code 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 an interrupt that resumes with a payload
For LLM-initiated pauses where the model decides on the fly to ask
the user, prefer useHumanInTheLoop.
The backend: pause the run in your agent
Install the CopilotKit LangGraph SDK
npm install @copilotkit/sdk-jsWire CopilotKit state + tools into your graph
Tool-based HITL (useHumanInTheLoop) registers the tool on the frontend
and forwards it via state.copilotkit.actions — the same wiring as
frontend tools. The graph-paused pattern (useInterrupt) uses
LangGraph's native interrupt(...) primitive inside a node.
import type { RunnableConfig } from "@langchain/core/runnables";
import { SystemMessage } from "@langchain/core/messages";
import { MemorySaver, START, StateGraph } from "@langchain/langgraph";
import { ChatOpenAI } from "@langchain/openai";
import {
convertActionsToDynamicStructuredTools,
CopilotKitStateAnnotation,
} from "@copilotkit/sdk-js/langgraph";
// CopilotKit forwards frontend tools to the agent via
// `state.copilotkit.actions`. `CopilotKitStateAnnotation` adds that
// channel to your graph's state; `convertActionsToDynamicStructuredTools`
// turns the forwarded action schemas into LangChain tools you can bind
// at model-invocation time.
const AgentStateAnnotation = CopilotKitStateAnnotation;
export type AgentState = typeof AgentStateAnnotation.State;
const SYSTEM_PROMPT = "You are a helpful, concise assistant.";
async function runChatNode(
state: AgentState,
config: RunnableConfig,
model: ChatOpenAI,
) {
const modelWithTools = model.bindTools!([
...convertActionsToDynamicStructuredTools(state.copilotkit?.actions ?? []),
]);
const response = await modelWithTools.invoke(
[new SystemMessage({ content: SYSTEM_PROMPT }), ...state.messages],
config,
);
return { messages: response };
}
async function chatNode(state: AgentState, config: RunnableConfig) {
return runChatNode(
state,
config,
new ChatOpenAI({
modelKwargs: { reasoning_effort: "none" },
temperature: 0,
model: "gpt-6-luna",
}),
);
}
function compileGraph(node: typeof chatNode) {
return new StateGraph(AgentStateAnnotation)
.addNode("chat_node", node)
.addEdge(START, "chat_node")
.addEdge("chat_node", "__end__")
.compile({ checkpointer: new MemorySaver() });
}
export const graph = compileGraph(chatNode);In the tool or step that needs the user's answer, call your framework's
interrupt primitive with the data your UI needs: interrupt() in LangGraph,
suspend() in Mastra, or a @human_feedback step in a CrewAI Flow. The
example agent does this in its schedule_meeting tool:
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 {
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; // PDT
interface 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)."),
}),
},
);The run stops here until the client resolves the interrupt. The resolve
payload comes back to the agent as the answer: the return value of
interrupt() in LangGraph, resumeData in Mastra, or the
HumanFeedbackResult that the next step of a CrewAI Flow receives. The
example turns that value into a string for the model.
Two things to note:
- The payload (
{"topic": topic, "attendee": attendee}) is what the frontend reads off the interrupt. 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, render receives both the raw event and the
interrupt itself, and resolve(...) is how you resume the run. Your agent
framework decides where the payload sits:
- Custom-event interrupt (
on_interrupt):event.value. - Standard AG-UI interrupt:
interrupt.metadata, or a JSON string ininterrupt.message.
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 sent back to the agent as the answer to
the matching interrupt, for example the return value of interrupt(...) in
LangGraph.
Ask the agent to book a call. The time picker appears in the chat. Pick a slot, and the agent confirms the booked time.
Key props
agentId: must match a runtime-registered agent. If omitted, the hook uses the agent of the surrounding chat configuration, then theagentIdset onCopilotKitProvider, then"default". A mismatch means the interrupt never fires.render: receives{ event, interrupt, resolve }.renderInChat: whentrue(as above), the picker appears inline in the chat transcript, between the paused assistant turn and the still-pending continuation. To show it outside the chat, see Headless interrupts.
Multiple interrupts? Add a type and gate with enabled
If your agent 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:
// The LangGraph adapter sends `event.value` as a JSON string.
const readValue = (value: unknown) =>
typeof value === "string" ? JSON.parse(value) : value;
useInterrupt({
agentId: "gen-ui-interrupt",
enabled: (event) => readValue(event.value).type === "ask",
render: ({ event, resolve }) => (
<AskCard question={readValue(event.value).content} onAnswer={resolve} />
),
});
useInterrupt({
agentId: "gen-ui-interrupt",
enabled: (event) => readValue(event.value).type === "approval",
render: ({ event, resolve }) => (
<ApproveCard content={readValue(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 resume the agent early. The interrupt card unmounts when the resume
run starts. Or return a value that render receives as result:
useInterrupt({
agentId: "gen-ui-interrupt",
handler: async ({ event, resolve }) => {
const value =
typeof event.value === "string" ? JSON.parse(event.value) : event.value;
const dept = await lookupUserDepartment();
if (value.accessDepartment === dept || dept === "admin") {
resolve({ code: "AUTH_BY_DEPARTMENT" });
return; // agent will resume; card unmounts when the run starts
}
return { dept };
},
render: ({ result, event, resolve }) => (
<RequestAccessCard
dept={result?.dept}
onRequest={() => resolve({ code: "REQUEST_AUTH" })}
onCancel={() => resolve({ code: "CANCEL" })}
/>
),
});AG-UI standard interrupt flow vs. custom-event flow
This section is a reference for developers who write render code for their
own agent. The useInterrupt reference lists
every option. useInterrupt handles two kinds of interrupt, and your agent
framework decides which kind it sends.
Standard flow (RUN_FINISHED with outcome.type === "interrupt")
When the agent backend conforms to the AG-UI protocol, it signals an interrupt
by emitting a RUN_FINISHED event whose outcome carries the interrupts array:
outcome.type === "interrupt"
outcome.interrupts // Interrupt[]The hook detects this on onRunFinishedEvent and exposes the interrupts on the
render props after onRunFinalized fires. Your render function receives:
interrupt: the primaryInterrupt(interrupts[0]), with shape{ id, reason, message?, toolCallId?, responseSchema?, expiresAt?, metadata? }.interrupts: the full open set (usually one, but multi-interrupt is supported, as described below).resolve(payload?, interruptId?): records{ status: "resolved", payload }for the targeted interrupt (defaults to the primary). The agent run resumes once every open interrupt has a response.cancel(interruptId?): records{ status: "cancelled" }for the targeted interrupt. Same accumulate-then-submit logic applies.
Each resume entry carries the interrupt id, the status, and your payload.
resolve and cancel send no metadata.
Custom-event flow (on_interrupt)
Agents that emit a custom on_interrupt event use this flow. The LangGraph
adapter emits this event by default. The hook detects this on onCustomEvent and sets
interrupt to null and interrupts to []. The payload is in
event.value. Calling resolve(payload) resumes via forwardedProps.command
(the custom-event resume mechanism). cancel() dismisses the interrupt without
resuming. The agent never receives a response.
Priority
If both signals appear on the same run, the standard flow wins.
Approve / Cancel example
function ApprovalInterrupt() {
useInterrupt({
render: ({ interrupt, resolve, cancel }) => (
<div className="p-3 border rounded">
<p>{interrupt?.message ?? "Approve this action?"}</p>
<div className="mt-2 flex gap-2">
<button onClick={() => resolve({ approved: true })}>Approve</button>
<button onClick={() => cancel()}>Cancel</button>
</div>
</div>
),
});
return null;
}resolve({ approved: true }) records a resolved entry and submits the resume
array to the agent. cancel() records a cancelled entry and does the same.
Both return the RunAgentResult once the run restarts.
Multi-interrupt behavior
Some agents issue more than one interrupt in a single run (e.g. two independent
approvals). Each interrupt has its own id. Address them individually:
useInterrupt({
render: ({ interrupts, resolve, cancel }) => (
<ul>
{interrupts.map((i) => (
<li key={i.id}>
{i.message}
<button onClick={() => resolve({ ok: true }, i.id)}>Approve</button>
<button onClick={() => cancel(i.id)}>Cancel</button>
</li>
))}
</ul>
),
});The agent run only resumes once every open interrupt has been addressed.
Calling resolve or cancel with a specific interruptId marks that interrupt
done; the hook auto-submits the accumulated responses when the last one is
addressed. If you omit interruptId, the primary interrupt (interrupts[0])
is targeted.
responseSchema: surface only, no client-side validation
The Interrupt type exposes a responseSchema field (a JSON Schema object)
that the agent can use to describe the expected payload shape. useInterrupt
surfaces this field on interrupt.responseSchema for your UI to read
(e.g. to drive a form), but it does not validate resolve payloads against
it. Validation is the agent's responsibility on resume.
How is this guide?