# 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.

<!-- interactive demo: gen-ui-interrupt -->

## What is this? [#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.

Some agent frameworks cannot pause a run mid-tool the way LangGraph's
`interrupt()` does, so this demo registers `schedule_meeting` with
`useHumanInTheLoop` instead. The agent calls `schedule_meeting` like
any other tool. The picker renders in the chat, and `respond(...)` sends
the user's choice back to the agent as the tool result.
The user sees the same flow: the agent pauses, the user answers, and the
agent continues. Only the mechanism is different.

## When should I use this? [#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`](../human-in-the-loop).

## The frontend: `useHumanInTheLoop` renders the picker [#the-frontend-usehumanintheloop-renders-the-picker]

`useHumanInTheLoop` registers `schedule_meeting` as a frontend tool and
renders the picker inline in the chat. When the user picks a slot or
cancels, `respond(...)` sends the choice back as the tool result. This is
the frontend-tool equivalent of
`useInterrupt`'s `event` / `resolve` pair:

```typescript title="src/app/demos/gen-ui-interrupt/page.tsx"
import {
  CopilotKit,
  CopilotChat,
  useHumanInTheLoop,
} from "@copilotkit/react-core/v2";
import { z } from "zod";
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();

  // MS Agent Framework has no `interrupt()` primitive, so the LangGraph
  // showcase's `useInterrupt({ renderInChat: true })` hook is silently dead
  // here — it listens for AG-UI `interrupt` events that the MAF backend
  // never emits, leaving the chat stuck on the "[Scheduling...]" tool-call
  // placeholder.
  //
  // `interrupt_agent.py` instead exposes `schedule_meeting` as a tool the
  // model is instructed to call; the frontend registers a matching
  // `useHumanInTheLoop` here, renders the picker inline, and resolves the
  // call via `respond(...)`. UX matches LGP's interrupt-rendered card; the
  // mechanism differs.
  useHumanInTheLoop({
    agentId: "gen-ui-interrupt",
    name: "schedule_meeting",
    description:
      "Ask the user to pick a meeting time. The picker renders inline in " +
      "the chat; the chosen slot is returned to the agent so it can confirm.",
    parameters: 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')"),
    }),
    render: ({ args, respond }: any) => {
      // `TimePickerCard` here is the gen-ui-interrupt-specific variant
      // (under `_components/`) that gates buttons on its own internal
      // `picked`/`cancelled` state — it doesn't take a `status` prop like
      // the hitl-in-chat version. That's fine: the buttons stay clickable
      // until the user makes a choice and `respond(...)` resolves the
      // tool call.
      const topic = (args?.topic as string | undefined) ?? "a call";
      const attendee = args?.attendee as string | undefined;
      const slots = generateFallbackSlots();
      return (
        <TimePickerCard
          topic={topic}
          attendee={attendee}
          slots={slots}
          onSubmit={(result) => respond?.(result)}
        />
      );
    },
  });
```

## The backend: agent instructed to call the frontend tool [#the-backend-agent-instructed-to-call-the-frontend-tool]

The agent has no local `schedule_meeting` implementation. The tool is
registered entirely on the frontend. The backend's only job is to
instruct the model to call `schedule_meeting` whenever the user wants
to book a meeting. AG-UI routes the tool call to the client, where
the Promise-returning handler takes over:

```python title="src/agents/interrupt_agent.py"
SYSTEM_PROMPT = dedent(
    """
    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 is implemented on the client: it surfaces a
    time-picker UI to the user and returns the user's selection. After the
    tool 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.
    """.strip()
)


def create_interrupt_agent(chat_client: BaseChatClient) -> AgentFrameworkAgent:
    """Instantiate the scheduling-only agent used by the interrupt-adapted demos."""
    base_agent = Agent(
        client=chat_client,
        name="scheduling_agent",
        instructions=SYSTEM_PROMPT,
        # No backend tools. `schedule_meeting` is registered on the frontend
        # via `useFrontendTool` and dispatched through the CopilotKit runtime.
        # When the agent calls `schedule_meeting`, the request is routed to
        # the frontend handler, which returns a Promise that only resolves
        # once the user picks a slot — equivalent to `interrupt()` in the
        # LangGraph reference.
        tools=[],
    )

    return AgentFrameworkAgent(
        agent=base_agent,
        name="CopilotKitMicrosoftAgentFrameworkInterruptAgent",
        description=(
            "Scheduling assistant for the interrupt-adapted demos. Delegates "
            "the time-picker interaction to a frontend tool."
        ),
        require_confirmation=False,
    )

```

Ask the agent to book a call. The time picker appears in the chat. Pick a
slot, and the agent confirms the booked time.

## AG-UI standard interrupt flow vs. custom-event flow [#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](/reference/hooks/useInterrupt) 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"`) [#standard-flow-run_finished-with-outcometype--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 primary `Interrupt` (`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`) [#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 [#priority]

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

### Approve / Cancel example [#approve--cancel-example]

```tsx
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 [#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:

```tsx
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 [#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.
