Pausing the Agent for Input

Pause an agent run, hand control to a React Native 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 Native component, and resumes the run with the answer. How the pause works depends on your agent framework.

Your agent framework has a native pause primitive, such as LangGraph's interrupt(). A running step suspends itself and hands control to the app. The run stays frozen on the server until the app answers with a payload. Then the step resumes as if interrupt() had returned that payload.

CopilotKit's useInterrupt is the frontend half of that contract: it receives the paused run, renders your UI, and resumes the agent with the user's answer.

When should I use this?

Use useInterrupt when the pause is a checkpoint in your agent code, where the code path must stop and wait for a human. It is not for a tool call the model decides to make. Typical cases:

  • A sensitive action (payments, irreversible writes) must be approved
  • A required value isn't known and only the user can give it
  • The agent reaches an approval step in a longer workflow
  • You want the server-side contract to be an interrupt that resumes with a payload

When the model decides on the fly to ask the user, use useHumanInTheLoop instead.

The backend: pause the run in your agent

Install the CopilotKit LangGraph SDK

npm install @copilotkit/sdk-js

Wire 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.

frontend-tools.ts
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. This agent does it in its schedule_meeting tool:

interrupt-agent.ts
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 app 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.

Two things to note:

  • The payload ({ "topic": topic, "attendee": attendee }) is what the app reads from the interrupt. Keep it a plain, serializable object with the context your UI needs.
  • The answer's shape ({ chosen_label, chosen_time } or { cancelled: true }) is up to you. The app can send any serializable payload, and the tool gives it meaning. Validate it in the tool before any side effect.

The frontend: useInterrupt in the rendered chat

Register useInterrupt in a component under CopilotKitProvider. When the paused run arrives, render receives the event, the interrupt, and resolve(...), which resumes the run. Your agent framework decides where the payload is:

  • Custom-event interrupt (on_interrupt): in event.value. The LangGraph adapter sends it as a JSON string.
  • Standard AG-UI interrupt: in interrupt.metadata, or as a JSON string in interrupt.message.
src/MeetingChat.tsx
import { Pressable, Text, View } from "react-native";
import { useInterrupt, type Interrupt } from "@copilotkit/react-native/headless";
import { CopilotChat } from "@copilotkit/react-native/components";

type MeetingPayload = { topic?: string; attendee?: string };

// Read the payload from either interrupt shape. JSON strings are parsed.
function readPayload(eventValue: unknown, interrupt: Interrupt | null): MeetingPayload {
  const raw = interrupt ? (interrupt.metadata ?? interrupt.message) : eventValue;
  if (typeof raw !== "string") return (raw ?? {}) as MeetingPayload;
  try {
    return JSON.parse(raw) as MeetingPayload;
  } catch {
    return {};
  }
}

export function MeetingChat() {
  useInterrupt({
    agentId: "gen-ui-interrupt",
    render: ({ event, interrupt, resolve }) => (
      <View style={{ padding: 12, borderRadius: 12, backgroundColor: "#f4f4f8", gap: 8 }}>
        <Text style={{ fontWeight: "600" }}>
          Pick a time for {readPayload(event.value, interrupt).topic ?? "a call"}
        </Text>
        <Pressable
          onPress={() => resolve({ chosen_label: "Tomorrow", chosen_time: "2026-11-11T09:00:00Z" })}
        >
          <Text>Tomorrow at 09:00</Text>
        </Pressable>
        <Pressable onPress={() => resolve({ cancelled: true })}>
          <Text>Cancel</Text>
        </Pressable>
      </View>
    ),
  });

  return <CopilotChat agentName="gen-ui-interrupt" />;
}

The rendered CopilotChat and CopilotModal from /components draw the element after the last message. Whatever you pass to resolve goes back to the agent as the answer to the matching interrupt.

Match the agent on both sides

The rendered chat picks its agent with agentName, and it doesn't pass that agent to the hooks around it. Without an agentId, useInterrupt listens to the agent named "default". Give useInterrupt the same agent as the chat, or the interrupt never appears.

Ask the agent to book a call. The picker appears in the chat. Tap Tomorrow at 09:00, and the agent confirms the time.

Key props

  • agentId: must match a runtime-registered agent. If you leave it out, the hook uses the agent of the surrounding chat configuration, then "default". The root CopilotChat sets that configuration for its children. The rendered chat from /components doesn't. A mismatch means the interrupt never appears.
  • render: receives { event, interrupt, interrupts, result, resolve, cancel } and returns a React Native element.
  • renderInChat: true by default, which hands the element to the rendered chat. Set it to false to get the element back from the hook and place it yourself. See Headless Interrupts.
  • handler: runs before render. It can resolve the interrupt early, or return a value that render receives as result.
  • enabled: filters which interrupts this hook handles.

Multiple interrupts? Add a type and gate with enabled

If your agent issues more than one kind of interrupt, tag each payload with a type field and install one useInterrupt per shape, each gated by enabled:

// The LangGraph adapter sends `event.value` as a JSON string.
const readValue = (value: unknown): { type?: string; content?: string } =>
  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} />
  ),
});

AskCard and ApproveCard are your own components. For a standard interrupt, event.value is the primary Interrupt object, so read your tag from its metadata instead.

Preprocess with handler

When an interrupt can sometimes be answered without the user (for example, the current user already has permission), pass a handler. It runs before render. It can call resolve(...) to resume the agent early, 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 department = await lookupUserDepartment(); // your own lookup
    if (value.accessDepartment === department || department === "admin") {
      await resolve({ code: "AUTH_BY_DEPARTMENT" });
      return;
    }
    return { department };
  },
  render: ({ result, resolve }) => (
    <RequestAccessCard
      department={result?.department}
      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")

An agent that follows the AG-UI protocol signals an interrupt with a RUN_FINISHED event whose outcome carries the interrupts:

outcome.type === "interrupt"
outcome.interrupts  // Interrupt[]

The hook shows the interrupts after the run finalizes. render receives:

  • interrupt: the primary Interrupt (interrupts[0]), with shape { id, reason, message?, toolCallId?, responseSchema?, expiresAt?, metadata? }.
  • interrupts: every open interrupt.
  • resolve(payload?, interruptId?): records an answer for the targeted interrupt. The run resumes once every open interrupt has an answer.
  • cancel(interruptId?): records a cancellation for the targeted interrupt. The run also resumes once every open interrupt is addressed.

Custom-event flow (on_interrupt)

Agents can emit a custom on_interrupt event. The LangGraph adapter does this by default. render gets its payload in event.value, with interrupt set to null and interrupts to []. resolve(payload) resumes the run right away, through forwardedProps.command. cancel() only dismisses the interrupt without resuming, because this flow has no cancel answer.

If both signals arrive on the same run, the standard flow wins.

Approve / Cancel example

import { Button, Text, View } from "react-native";
import { useInterrupt } from "@copilotkit/react-native/headless";

function ApprovalPanel() {
  const element = useInterrupt({
    renderInChat: false,
    render: ({ interrupt, resolve, cancel }) => (
      <View style={{ padding: 12, gap: 8 }}>
        <Text>{interrupt?.message ?? "Approve this action?"}</Text>
        <Button title="Approve" onPress={() => resolve({ approved: true })} />
        <Button title="Cancel" onPress={() => cancel()} />
      </View>
    ),
  });

  return element;
}

Both methods return the run result once the run restarts, or nothing while other open interrupts still wait for an answer.

More than one open interrupt

Some agents issue more than one interrupt in a single run. Each has its own id, so answer them one by one:

render: ({ interrupts, resolve, cancel }) => (
  <View>
    {interrupts.map((item) => (
      <View key={item.id} style={{ flexDirection: "row", gap: 8 }}>
        <Text>{item.message}</Text>
        <Button title="Approve" onPress={() => resolve({ ok: true }, item.id)} />
        <Button title="Cancel" onPress={() => cancel(item.id)} />
      </View>
    ))}
  </View>
),

The run resumes only after every open interrupt is addressed. If you leave out interruptId, the primary interrupt is targeted, and the hook logs a warning when several are open.

responseSchema is not validated

An Interrupt can carry a responseSchema, a JSON Schema that describes the answer the agent expects. useInterrupt passes it to render as interrupt.responseSchema, but it does not check your resolve payload against it. The agent validates the answer when it resumes.

Provider setup

The component that calls useInterrupt or useHumanInTheLoop must be under CopilotKitProvider:

App.tsx
import { CopilotKitProvider } from "@copilotkit/react-native/headless";
import { MeetingChat } from "./src/MeetingChat";

const runtimeUrl = "http://localhost:8200/api/copilotkit";

export default function App() {
  return (
    <CopilotKitProvider runtimeUrl={runtimeUrl}>
      <MeetingChat />
    </CopilotKitProvider>
  );
}

How is this guide?