mirror of
https://github.com/CopilotKit/CopilotKit.git
synced 2026-09-14 16:26:20 +08:00
Markus Ecker
c2fca03ff7
AG-UI renamed the subagent attribution field because the old name implied a reusable subagent DEFINITION when the value identifies one INVOCATION -- two runs of the same subagent get two different values. See ag-ui-protocol/ag-ui#2350. subagentId -> subagentRunId parentSubagentId -> parentSubagentRunId Applied to both sides of this package's surface: - Reading the wire. SubagentRegistry consumes `event.subagentRunId` from SUBAGENT_STARTED / FINISHED / ERROR. This is the part that MUST move: the events are typed as SubagentStartedEvent etc. from @ag-ui/core, so against the renamed protocol the old field simply is not there and the registry would silently stay empty -- every subagent lookup returning undefined, with no error. - CopilotKit's own API. `useSubagent({ subagentRunId })` and `SubagentState.subagentRunId`. Renaming these is what makes the API self-consistent: the hook already distinguishes `subagentRunId` (exact, one invocation) from `subagentName` (the declared `subagent_type`, not unique), which is precisely the definition-vs-invocation split the old name blurred. This is a breaking change to `useSubagent`, taken now because the hook has never shipped -- it exists only on this unmerged branch, so there is no released consumer to migrate and no alias to maintain. The @ag-ui override repin is in the same commit rather than a separate `chore(deps)` one because the two are atomically coupled: the rename cannot typecheck against the old canaries, and the repin alone would leave the registry reading a field the stream no longer emits. Splitting them would mean one commit that is definitely broken either way. Verified: @copilotkit/core and @copilotkit/react-core typecheck against the renamed protocol, and react-core's 1424 tests pass. The typecheck is load-bearing here, not incidental -- injecting a deliberately wrong field name produces 5 TS errors, so a green check really does prove the field matches @ag-ui/core's types. Note: the registry and hook still have no test coverage of their own; the only subagent assertions live downstream in the AG-UI dojo demo.
CopilotKit - React Core
✨ Why CopilotKit?
- Minutes to integrate - Get started quickly with our CLI
- Framework agnostic - Works with React, Next.js, AGUI and more
- Production-ready UI - Use customizable components or build with headless UI
- Built-in security - Prompt injection protection
- Open source - Full transparency and community-driven
🧑💻 Real life use cases
Deploy deeply-integrated AI assistants & agents that work alongside your users inside your applications.
🖥️ Code Samples
Drop in these building blocks and tailor them to your needs.
Build with Headless APIs and Pre-Built Components
// Headless UI with full control
const { visibleMessages, appendMessage, setMessages, ... } = useCopilotChat();
// Pre-built components with deep customization options (CSS + pass custom sub-components)
<CopilotPopup
instructions={"You are assisting the user as best as you can. Answer in the best way possible given the data you have."}
labels={{ title: "Popup Assistant", initial: "Need any help?" }}
/>
// Frontend actions + generative UI, with full streaming support
useCopilotAction({
name: "appendToSpreadsheet",
description: "Append rows to the current spreadsheet",
parameters: [
{ name: "rows", type: "object[]", attributes: [{ name: "cells", type: "object[]", attributes: [{ name: "value", type: "string" }] }] }
],
render: ({ status, args }) => <Spreadsheet data={canonicalSpreadsheetData(args.rows)} />,
handler: ({ rows }) => setSpreadsheet({ ...spreadsheet, rows: [...spreadsheet.rows, ...canonicalSpreadsheetData(rows)] }),
});
Integrate In-App CoAgents with LangGraph
// Share state between app and agent
const { agentState } = useCoAgent({
name: "basic_agent",
initialState: { input: "NYC" }
});
// agentic generative UI
useCoAgentStateRender({
name: "basic_agent",
render: ({ state }) => <WeatherDisplay {...state.final_response} />,
});
// Human in the Loop (Approval)
useCopilotAction({
name: "email_tool",
parameters: [
{
name: "email_draft",
type: "string",
description: "The email content",
required: true,
},
],
renderAndWaitForResponse: ({ args, status, respond }) => {
return (
<EmailConfirmation
emailContent={args.email_draft || ""}
isExecuting={status === "executing"}
onCancel={() => respond?.({ approved: false })}
onSend={() =>
respond?.({
approved: true,
metadata: { sentAt: new Date().toISOString() },
})
}
/>
);
},
});
// intermediate agent state streaming (supports both LangGraph.js + LangGraph python)
const modifiedConfig = copilotKitCustomizeConfig(config, {
emitIntermediateState: [
{
stateKey: "outline",
tool: "set_outline",
toolArgument: "outline",
},
],
});
const response = await ChatOpenAI({ model: "gpt-4o" }).invoke(
messages,
modifiedConfig,
);
🏆 Featured Examples
Documentation
To get started with CopilotKit, please check out the documentation.