# Programmatic Control

> Drive agent runs directly from code, with no chat UI required.

## What is this? [#what-is-this]

Programmatic control is what you reach for when you want to drive an
agent run from code rather than from a chat composer: a button, a
form, a cron job, a keyboard shortcut, a graph callback. CopilotKit
exposes three primitives that cover every triggering pattern:

- `agent.addMessage(...)`: append a message to the conversation without running the agent. Pair with `copilotkit.runAgent({ agent })` when you want the appended message to kick off a turn.
- `copilotkit.runAgent({ agent })`: the same entry point `<CopilotChat />` calls internally. Orchestrates frontend tools, follow-up runs, and the subscriber lifecycle.
- `agent.subscribe(subscriber)`: low-level AG-UI event subscription (`onCustomEvent`, `onRunStartedEvent`, `onRunFinalized`, `onRunFailed`, …). Pairs with `copilotkit.runAgent({ agent, resume })` for standard AG-UI interrupts, or `copilotkit.runAgent({ agent, forwardedProps: { command: { resume, interruptEvent } } })` for the `on_interrupt` custom events that the LangGraph adapter emits, to drive interrupt resolution from arbitrary UI.

## When should I use this? [#when-should-i-use-this]

Use programmatic control when you want to:

- Trigger agent runs from buttons, forms, or other UI elements
- Execute specific tools directly from UI interactions (without an LLM turn)
- Build agent features without a chat window (to build your own chat UI, see [Headless UI](./headless))
- Access agent state and results programmatically
- Create fully custom agent-driven workflows

## Sending a message from code [#sending-a-message-from-code]

<Steps>
  <Step>
    ### Install the OpenAI Agents AG-UI adapter

    ```bash
    pip install ag-ui-openai-agents openai-agents
    ```

  </Step>
  <Step>
    ### Wire the agent once, and chat and code share it

    `copilotkit.runAgent`, `agent.subscribe` and `agent.addMessage` drive runs
    against the same AG-UI endpoint your chat UI posts to, so there is no
    second backend to set up. Mount the `OpenAIAgentsAgent` the way any chat
    demo does, and every entry point sees the same model, tools and
    instructions.

~~~~python title="agent_server.py"
app = FastAPI(title="OpenAI Agents SDK Agent Server", lifespan=lifespan)
for name, agent in AGENTS.items():
    add_openai_agents_fastapi_endpoint(app, agent, f"/{name}", include_health=False)
~~~~

    The server keeps no sessions. Every run carries the thread's messages
    from the client, so a headless run on the same agent continues its
    thread, and a fresh `threadId` starts a new one.

  </Step>
</Steps>

<Callout type="info" title="Headless interrupts come from approval-gated tools">
  The headless interrupt-resolver pattern (read the interrupt off the agent,
  answer it with a `resume`) works with a server tool marked
  `needs_approval=True`. The run ends with an interrupt for the call, and a
  `resume` of `{"approved": true}` runs it (see the human-in-the-loop setup).
  To ask the user from code without a backend tool, use the frontend-tool
  Promise pattern: register the tool with `useFrontendTool` and an `async`
  handler, and resolve its promise when your own UI has the answer.
</Callout>

The canonical pattern is to append a user message with
`agent.addMessage`, then call `copilotkit.runAgent({ agent })`. Use
`copilotkit.stopAgent({ agent })` to cancel an in-flight run.

```tsx title="frontend/src/app/agent-trigger.tsx"
"use client";

import { useAgent, useCopilotKit } from "@copilotkit/react-core/v2";

export function AgentTrigger({ agentId }: { agentId: string }) {
  const { agent } = useAgent({ agentId });
  const { copilotkit } = useCopilotKit();

  const run = async () => {
    if (agent.isRunning) return;

    agent.addMessage({
      id: crypto.randomUUID(),
      role: "user",
      content: "Summarize the latest sales data",
    });

    try {
      await copilotkit.runAgent({ agent });
    } catch (error) {
      console.error("CopilotKit runAgent failed:", error);
    }
  };

  return (
    <>
      <button onClick={run} disabled={agent.isRunning}>
        Run agent
      </button>
      <button
        onClick={() => copilotkit.stopAgent({ agent })}
        disabled={!agent.isRunning}
      >
        Stop
      </button>
    </>
  );
}
```

Click **Run agent**. The agent's reply arrives in `agent.messages`. To see it, render the last message, for example `agent.messages.at(-1)?.content`.

### `copilotkit.runAgent()` vs `agent.runAgent()` [#copilotkitrunagent-vs-agentrunagent]

Both methods trigger the agent, but they operate at different levels:

- **`copilotkit.runAgent({ agent })`**: the recommended default. Orchestrates the full lifecycle: executes frontend tools, handles follow-up runs, and routes errors through the subscriber system.
- **`agent.runAgent(options)`**: low-level method on the agent instance. Sends the request to the runtime but does **not** execute frontend tools or chain follow-ups. Reach for this only when you need direct control.

## Subscribing to agent events [#subscribing-to-agent-events]

`agent.subscribe(subscriber)` returns `{ unsubscribe }`. The subscriber
object accepts every AG-UI lifecycle callback: `onCustomEvent`,
`onRunStartedEvent`, `onRunFinalized`, `onRunFailed`, and the streaming
deltas. Use it to drive custom progress UI, forward events to
analytics, or catch framework pause/resume events and resolve them with
a payload (the pattern below).

## Resolving a pause from a button [#resolving-a-pause-from-a-button]

> **Interrupt-style pause/resume isn't available on this framework.**
> The headless interrupt pattern requires the underlying
> runtime to expose either a native `interrupt(...)` primitive
> (LangGraph) or a Promise-resolving frontend-tool path. For all other
> integrations, drive pauses through
> [`useHumanInTheLoop`](./human-in-the-loop) instead. It's the
> standard hook for tool-call-based pause/resume flows and works on
> every framework that supports tool calls. The `agent.addMessage`,
> `copilotkit.runAgent`, and `agent.subscribe` primitives above still
> apply. Only the interrupt-resolution path is framework-specific.

<IntegrationGrid path="programmatic-control" />
