Headless Interrupts

What is this?#

useInterrupt's render callback is the 80% path: it keeps the UI glued to a <CopilotChat> transcript and handles "when to show the picker" logic for you. This page covers the escape hatch: a render-less interrupt resolver you assemble from the same primitives useInterrupt uses internally — a pattern that lives anywhere in your React tree, takes any shape you like (button grid, form, modal, keyboard shortcut), and resolves the interrupt without mounting a chat at all.

On LangGraph the underlying primitive is the framework's interrupt() call, surfaced to the client as an on_interrupt custom event. The headless variant subscribes to that event directly and resumes the run by calling copilotkit.runAgent({...}) with the matching resume payload — no chat surface required.

When should I use this?#

• Testing / Playwright fixtures — a deterministic, chat-less button grid is easier to drive than a chat surface where the picker only appears after an LLM call.
• Non-chat UIs — dashboards, side panels, inspector surfaces, or any place where you want the agent's interrupt without the chat transcript.
• Custom flow control — when you need to know exactly when the interrupt arrived (e.g. to gate other UI) and when it was resolved.
• Research / debugging — when you want to observe the raw AG-UI custom events without the abstraction layer.

If you just want "a picker in chat", just use useInterrupt.

The primitives#

uv add copilotkit

poetry add copilotkit

pip install copilotkit --extra-index-url https://copilotkit.gateway.scarf.sh/simple/

conda install copilotkit -c copilotkit-channel

from langchain.agents import create_agent
from langchain_openai import ChatOpenAI
from copilotkit import CopilotKitMiddleware

graph = create_agent(
    model=ChatOpenAI(model="gpt-5.4"),
    tools=[],
    middleware=[CopilotKitMiddleware()],
    system_prompt="You are a helpful, concise assistant.",
)

The simplest headless pattern uses useInterrupt with renderInChat: false. Instead of publishing the element into <CopilotChat>, the hook returns the interrupt element directly so you can place it anywhere in your tree:

function ApprovalPanel() {
  const element = useInterrupt({
    renderInChat: false,
    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>
    ),
  });

  // `element` is null while no interrupt is active; render it wherever you like.
  return <div className="approval-panel">{element}</div>;
}

interrupt carries the primary AG-UI Interrupt object ({ id, reason, message?, responseSchema?, expiresAt?, ... }). resolve(payload) submits the user's response and resumes the agent. cancel() cancels the interrupt and resumes. Both return a Promise<RunAgentResult | void> — void while waiting on further interrupts when more than one is open.

Under the hood, useInterrupt composes two public APIs:

1. agent.subscribe({ onCustomEvent, onRunStartedEvent, onRunFinishedEvent, onRunFinalized, onRunFailed }) — every AbstractAgent exposes an AG-UI event subscription. Standard interrupts arrive on onRunFinishedEvent with { outcome: "interrupt", interrupts: [...] }; legacy LangGraph interrupts arrive as a custom event named on_interrupt.
2. copilotkit.runAgent({ agent, resume }) (standard) or copilotkit.runAgent({ agent, forwardedProps: { command: { resume, interruptEvent } } }) (legacy) — the same call useInterrupt's resolve() / cancel() makes to resume a paused run.

For cases where you need full control over the subscription (e.g. testing fixtures, custom accumulation logic), you can still wire up the raw primitives yourself:

A few things this hook is careful about:

• It stages the incoming event in a local ref and only commits it to React state on onRunFinalized, mirroring useInterrupt, which doesn't surface the interrupt until the run has actually paused (not just when the event fires mid-stream).
• onRunStartedEvent clears any stale pending state, so kicking off a new turn always starts from a clean slate.
• onRunFailed drops the staged event so a transport hiccup doesn't leave the UI stuck showing a picker for a run that never paused.

Driving it from plain UI#

The preferred approach uses useInterrupt with renderInChat: false — no hand-rolled subscription, no <CopilotChat>, no render prop:

function HeadlessInterruptPanel() {
  const { copilotkit } = useCopilotKit();
  const { agent } = useAgent({ agentId: "interrupt-headless" });

  const kickOff = (prompt: string) => {
    agent.addMessage({ id: crypto.randomUUID(), role: "user", content: prompt });
    void copilotkit.runAgent({ agent });
  };

  const interruptElement = useInterrupt({
    renderInChat: false,
    render: ({ interrupt, resolve, cancel }) => (
      <div>
        <p>Pick a slot for {interrupt?.message ?? "a call"}:</p>
        {SLOTS.map((s) => (
          <button key={s.iso} onClick={() => resolve({ chosen_time: s.iso, chosen_label: s.label })}>
            {s.label}
          </button>
        ))}
        <button onClick={() => cancel()}>Cancel</button>
      </div>
    ),
  });

  if (interruptElement) {
    return interruptElement;
  }

  return <button onClick={() => kickOff("Book a call with sales.")}>Book call</button>;
}

If you need full control over the subscription (e.g. for a custom useHeadlessInterrupt fixture used in Playwright tests), you can still use the raw primitives from useHeadlessInterrupt defined above:

function HeadlessInterruptPanelRaw() {
  const { copilotkit } = useCopilotKit();
  const { agent } = useAgent({ agentId: "interrupt-headless" });
  const { pending, resolve } = useHeadlessInterrupt("interrupt-headless");

  const kickOff = (prompt: string) => {
    agent.addMessage({ id: crypto.randomUUID(), role: "user", content: prompt });
    void copilotkit.runAgent({ agent });
  };

  if (pending) {
    return (
      <div>
        <p>Pick a slot for {pending.value.topic ?? "a call"}:</p>
        {SLOTS.map((s) => (
          <button key={s.iso} onClick={() => resolve({ chosen_time: s.iso, chosen_label: s.label })}>
            {s.label}
          </button>
        ))}
        <button onClick={() => resolve({ cancelled: true })}>Cancel</button>
      </div>
    );
  }

  return <button onClick={() => kickOff("Book a call with sales.")}>Book call</button>;
}

Going further#

• Tool-based HITL with useHumanInTheLoop — for LLM-initiated pauses where the model decides on the fly to ask the user, rather than the runtime forcing the pause itself.
• useInterrupt — the render-prop version of this page, with enabled gating and handler preprocessing.