# useCopilotKit

> Low-level React hook for accessing the CopilotKit context

## Overview [#overview]

`useCopilotKit` is a low-level React hook that returns the CopilotKit context: the core instance and the provider-level state. The component re-renders when the runtime connection status changes.

<Callout type="info">
  `useCopilotKit` is a low-level hook. Most applications should use higher-level
  hooks like [`useAgent`](/reference/hooks/useAgent) or [`useFrontendTool`](/reference/hooks/useFrontendTool) instead.
</Callout>

**Throws an error** if used outside [`CopilotKitProvider`](/reference/components/CopilotKit) (or the v1 `<CopilotKit>` wrapper, which renders it).

## Signature [#signature]

```tsx
import { useCopilotKit } from "@copilotkit/react-core/v2";

function useCopilotKit(): CopilotKitContextValue;
```

## Parameters [#parameters]

This hook takes no parameters.

## Return Value [#return-value]

<PropertyReference name="context" type="CopilotKitContextValue">
  The context object containing the core instance and provider-level state.

  <PropertyReference name="copilotkit" type="CopilotKitCoreReact">
    The live CopilotKit core instance. This is the central coordinator that manages agents, tools, suggestions, and runtime communication. It exposes methods for:
    - Agent management (`agents`, `getAgent`)
    - Tool registration and execution
    - Suggestion configuration and retrieval
    - Runtime connection management
    - Event subscription via `subscribe()`

    The core instance is created once per `CopilotKitProvider` and is stable across re-renders.

  </PropertyReference>

  <PropertyReference name="executingToolCallIds" type="ReadonlySet<string>">
    Set of tool call IDs currently being executed. This is tracked at the provider level so that tool execution events are captured even before child components mount. This is important for scenarios like human-in-the-loop reconnection, where pending tool calls may already exist when the component tree mounts.
  </PropertyReference>
</PropertyReference>

## Usage [#usage]

### Accessing the Core Instance [#accessing-the-core-instance]

```tsx
function DebugPanel() {
  const { copilotkit } = useCopilotKit();

  const agents = Object.keys(copilotkit.agents ?? {});

  return (
    <div>
      <h3>Registered Agents</h3>
      <ul>
        {agents.map((id) => (
          <li key={id}>{id}</li>
        ))}
      </ul>
    </div>
  );
}
```

### Subscribing to Core Events [#subscribing-to-core-events]

```tsx
function ConnectionMonitor() {
  const { copilotkit } = useCopilotKit();

  useEffect(() => {
    const subscription = copilotkit.subscribe({
      onRuntimeConnectionStatusChanged: () => {
        console.log("Runtime connection status changed");
      },
    });

    return () => {
      subscription.unsubscribe();
    };
  }, [copilotkit]);

  return null;
}
```

### Running a Tool Programmatically [#running-a-tool-programmatically]

`copilotkit.runTool()` lets you execute a frontend tool registered with [`useFrontendTool`](/reference/hooks/useFrontendTool) directly from code. No LLM turn is required. The tool's handler runs, render components appear in the UI, and both the tool call and result are added to the agent's message history.

```tsx
import { useCopilotKit, useFrontendTool } from "@copilotkit/react-core/v2";
import { z } from "zod";

function ExportButton() {
  const { copilotkit } = useCopilotKit();

  // Register the tool
  useFrontendTool({
    name: "exportData",
    description: "Export data as CSV",
    parameters: z.object({ format: z.string() }),
    handler: async ({ format }) => {
      const csv = await generateCsv(format);
      downloadFile(csv);
      return `Exported as ${format}`;
    },
  });

  // Trigger it from a button — no LLM needed
  const handleExport = async () => {
    try {
      const { result, error } = await copilotkit.runTool({
        name: "exportData",
        parameters: { format: "csv" },
      });
      if (error) console.error(error);
    } catch (e) {
      // The tool or its agent was not found.
      console.error(e);
    }
  };

  return <button onClick={handleExport}>Export CSV</button>;
}
```

#### `runTool` Parameters [#runtool-parameters]

<PropertyReference name="params" type="CopilotKitCoreRunToolParams">
  <PropertyReference name="name" type="string" required>
    Name of the registered frontend tool to execute.
  </PropertyReference>

<PropertyReference name="agentId" type="string">
  Agent ID for tool and message scoping. Defaults to `"default"`.
</PropertyReference>

<PropertyReference
  name="parameters"
  type="Record<string, unknown>"
  default="{}"
>
  Arguments passed to the tool handler.
</PropertyReference>

  <PropertyReference name="followUp" type="string | false" default="false">
    Controls whether an LLM follow-up is triggered after execution:
    - `false`: execute tool and stop (default)
    - `"generate"`: trigger an agent run so the LLM responds to the tool result
    - Any other string: add a user message with this text, then trigger an agent run
  </PropertyReference>
</PropertyReference>

#### `runTool` Return Value [#runtool-return-value]

<PropertyReference name="result" type="CopilotKitCoreRunToolResult">
  <PropertyReference name="toolCallId" type="string">
    Unique ID of the tool call, matching the message added to history.
  </PropertyReference>

<PropertyReference name="result" type="string">
  Stringified return value from the tool handler (empty string for render-only
  tools).
</PropertyReference>

  <PropertyReference name="error" type="string | undefined">
    Error message if the handler threw. The tool result message will contain `"Error: ..."`.
  </PropertyReference>
</PropertyReference>

`runTool` throws `Tool not found: <name>` or `Agent not found: <agentId>` when either lookup fails. The `error` field does not report these failures.

### Checking Tool Execution State [#checking-tool-execution-state]

```tsx
function ToolExecutionIndicator() {
  const { executingToolCallIds } = useCopilotKit();

  if (executingToolCallIds.size === 0) {
    return null;
  }

  return <div>Executing {executingToolCallIds.size} tool call(s)...</div>;
}
```

## Behavior [#behavior]

- **Error on Missing Provider**: Throws an error if the hook is used outside `CopilotKitProvider` or the v1 `<CopilotKit>` wrapper component.
- **Runtime Status Subscription**: The hook subscribes to `onRuntimeConnectionStatusChanged` events, so components re-render when the runtime connection completes or fails.
- **Stable Core Reference**: The `copilotkit` instance is created once per provider and remains stable across re-renders. Only the `executingToolCallIds` set changes as tool calls begin and complete.
- **Provider-Level Tool Tracking**: `executingToolCallIds` is tracked at the provider level rather than in individual components. As a result, tool execution start events fired before child components mount are not lost.
