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

useHumanInTheLoop: nothing to wire on the agent

The AG-UI Mastra adapter forwards each tool you register with useHumanInTheLoop to the agent as a client tool. When the model calls it, the run hands control to the browser, and the user's answer comes back as the tool result. Do not declare the tool on the Mastra agent.

useInterrupt: return suspend() from a tool

A Mastra tool pauses with suspend(), not interrupt(). Declare a suspendSchema for the payload your UI reads and a resumeSchema for the answer it sends back. The @ag-ui/mastra bridge sends the pause to the frontend as an AG-UI interrupt. When the user answers, Mastra runs execute again with the answer in resumeData.

src/mastra/tools/interrupt.ts — schedule_meeting suspend tool
// Native interrupt backend for the `gen-ui-interrupt` + `interrupt-headless`
// cells (OSS-383). Unlike the old Strategy-B workaround (a frontend-only
// `schedule_meeting` satisfied by `useHumanInTheLoop`), this is a REAL Mastra
// suspend tool: the model calls `schedule_meeting`, the tool `suspend()`s with
// a time-picker payload, and the @ag-ui/mastra bridge maps that to an AG-UI
// interrupt (legacy `on_interrupt` CUSTOM event + the standard `RUN_FINISHED`
// interrupt-outcome, on by default in the v1 bridge). The frontend `useInterrupt`
// hook renders the picker and `resolve(...)`s, which resumes the run — the tool's
// `execute` is re-invoked with `resumeData` carrying the user's selection.
//
// Load-bearing (see the Mastra capability-map memory):
//   - `return suspend(...)` DIRECTLY. `await suspend(); return x` completes the
//     tool, so under fast streaming the agentic loop continues past the pause.
//   - Resume needs instance `storage` (configured on `new Mastra({ storage })`)
//     and the suspend-chunk runId — both handled by the bridge + src/mastra/index.ts.
import { createTool } from "@mastra/core/tools";
import { z } from "zod";

export interface InterruptTimeSlot {
  label: string;
  iso: string;
}

// Mirror of `src/app/demos/_shared/interrupt-fallback-slots.ts` so the backend
// supplies future-relative candidate slots inside the suspend payload (the
// frontend only falls back to its own generator if these are absent).
function atLocal(date: Date, hour: number, minute = 0): Date {
  return new Date(
    date.getFullYear(),
    date.getMonth(),
    date.getDate(),
    hour,
    minute,
    0,
    0,
  );
}

function nextMonday(from: Date): Date {
  const day = from.getDay();
  let offset = (1 - day + 7) % 7;
  if (offset <= 1) offset += 7;
  const next = new Date(from);
  next.setDate(from.getDate() + offset);
  return next;
}

export function generateCandidateSlots(
  now: Date = new Date(),
): InterruptTimeSlot[] {
  const tomorrow = new Date(now);
  tomorrow.setDate(now.getDate() + 1);
  const monday = nextMonday(now);
  const candidates: Array<[string, Date]> = [
    ["Tomorrow 10:00 AM", atLocal(tomorrow, 10)],
    ["Tomorrow 2:00 PM", atLocal(tomorrow, 14)],
    ["Monday 9:00 AM", atLocal(monday, 9)],
    ["Monday 3:30 PM", atLocal(monday, 15, 30)],
  ];
  return candidates.map(([label, date]) => ({
    label,
    iso: date.toISOString(),
  }));
}

export const scheduleMeetingInterruptTool = createTool({
  id: "schedule_meeting",
  description:
    "Ask the user to pick a meeting time. Surfaces an interactive time-picker " +
    "to the user and returns their selection. Call this whenever the user asks " +
    "to book or schedule a meeting.",
  inputSchema: z.object({
    topic: z
      .string()
      .describe("What the meeting is about (e.g. 'Intro with sales')."),
    attendee: z
      .string()
      .optional()
      .describe("Who the meeting is with (e.g. 'Alice'), if known."),
  }),
  suspendSchema: z.object({
    topic: z.string(),
    attendee: z.string().optional(),
    slots: z.array(z.object({ label: z.string(), iso: z.string() })),
  }),
  resumeSchema: z.object({
    chosen_time: z.string().optional(),
    chosen_label: z.string().optional(),
    cancelled: z.boolean().optional(),
  }),
  // Mastra createTool execute signature is `(inputData, executionContext)`:
  // the validated INPUT is the first arg; the ToolExecutionContext is the
  // second. `suspend` / `resumeData` live under `executionContext.agent`
  // (the `AgentToolExecutionContext` sub-object), NOT at the top level.
  // Destructuring them off `executionContext` directly yields `undefined`, so
  // `return suspend(...)` throws `suspend is not a function`; the model gets a
  // tool-error, re-calls, and the loop spins to the step cap with no
  // `tool-call-suspended` chunk. Mirrors the proven @ag-ui/mastra dojo tool.
  execute: async (inputData, executionContext) => {
    const { suspend, resumeData } = executionContext?.agent ?? {};
    // Second pass: the user resolved the interrupt — the run resumes here with
    // their selection. Return a short confirmation the agent narrates.
    if (resumeData) {
      if (resumeData.cancelled) {
        return "The user cancelled — no meeting was scheduled.";
      }
      const when =
        resumeData.chosen_label ?? resumeData.chosen_time ?? "the chosen time";
      return `Scheduled "${inputData.topic}" for ${when}.`;
    }
    // First pass: suspend with the picker payload. Returned directly so the
    // agentic loop pauses here instead of continuing.
    return suspend?.({
      topic: inputData.topic,
      attendee: inputData.attendee,
      slots: generateCandidateSlots(),
    });
  },
});

Two details fail without an error:

  • suspend and resumeData are on executionContext.agent, the second argument of execute. Read from the top level of the context, they are undefined, and the model retries the tool until the run reaches its step limit.
  • return suspend(...) directly. With await suspend() followed by another return, the tool completes and the agent keeps going past the pause.

Give the Mastra instance storage

Resume reloads the paused run from storage, so the Mastra instance that registers the agent needs storage:

src/mastra/index.ts
import { Mastra } from "@mastra/core/mastra";
import { LibSQLStore } from "@mastra/libsql";

export const mastra = new Mastra({
  agents: { interruptAgent },
  storage: new LibSQLStore({
    id: "mastra-storage",
    url: ":memory:",
  }),
});

Read the payload under suspendPayload

The bridge wraps your suspend() value, so useInterrupt does not receive it as is:

  • In the custom-event flow, event.value is a JSON string. Parse it and read suspendPayload.
  • In the standard AG-UI flow, the payload is in interrupt.metadata.mastra.suspendPayload.
app/page.tsx
useInterrupt({
  render: ({ interrupt, event, resolve }) => {
    const payload = interrupt
      ? interrupt.metadata?.mastra?.suspendPayload
      : JSON.parse(event.value).suspendPayload;
    return (
      <div>
        <p>Pick a time for {payload?.topic}</p>
        <button onClick={() => resolve({ chosen_time: "Tomorrow 10:00 AM" })}>
          Tomorrow 10:00 AM
        </button>
        <button onClick={() => resolve({ cancelled: true })}>Cancel</button>
      </div>
    );
  },
});

Whatever you pass to resolve(...) arrives in the tool as resumeData, so shape it to match the tool's resumeSchema.

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:

index.ts
/**
 * Scheduling agent for the interrupt-adapted demos (gen-ui-interrupt,
 * interrupt-headless).
 *
 * This agent powers the NATIVE interrupt path (OSS-383). The backend
 * `schedule_meeting` tool `suspend()`s with a time-picker payload; the
 * @ag-ui/mastra v1 bridge maps that to an AG-UI interrupt (legacy
 * `on_interrupt` CUSTOM event + the standard `RUN_FINISHED` interrupt-outcome,
 * on by default). The frontend `useInterrupt` (gen-ui-interrupt, in-chat) /
 * hand-rolled headless subscription (interrupt-headless, app-surface) renders
 * the picker and resolves it, which resumes the run — re-invoking the tool's
 * `execute` with `resumeData`. Replaces the prior `useHumanInTheLoop`
 * frontend-tool workaround.
 *
 * Resume requires instance `storage` (see src/mastra/index.ts) so the
 * suspended agentic-loop snapshot can be reloaded.
 */
export const interruptAgent = new Agent({
  id: "interrupt-agent",
  name: "Interrupt Agent",
  tools: { schedule_meeting: scheduleMeetingInterruptTool },
  model: openai("gpt-6-luna"),
  instructions: `You are a scheduling assistant. Whenever the user asks you to book a call or schedule a meeting, you MUST call the \`schedule_meeting\` tool. Pass a short \`topic\` describing the purpose of the meeting and, if known, an \`attendee\` describing who the meeting is with.

The \`schedule_meeting\` tool surfaces an interactive time-picker to the user and pauses until they pick a slot (or cancel), then returns their selection to you. After it returns, briefly confirm whether the meeting was scheduled and at what time, or note that the user cancelled. Do NOT ask for approval yourself — always call the tool and let the picker handle the decision.

Keep responses short and friendly. After you finish executing tools, always send a brief final assistant message summarizing what happened so the message persists.`,
  memory: new Memory({
    storage: new LibSQLStore({
      id: "interrupt-agent-memory",
      url: WORKING_MEMORY_DB_URL,
    }),
    options: {
      workingMemory: {
        enabled: true,
        schema: AgentState,
      },
    },
  }),
});

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?