a2ui-renderer

This skill builds on copilotkit/react-core (for CopilotKit provider fundamentals) and copilotkit/runtime (for CopilotRuntime fundamentals). Read those first.

Setup

A2UI has two halves. The runtime declares a2ui middleware; the client enables the a2ui prop on the provider. Once both are set, /info flags A2UI and the client auto-mounts createA2UIMessageRenderer — you do NOT wire renderActivityMessages yourself.

Runtime side (app/routes/api.copilotkit.$.tsx)

import type { Route } from "./+types/api.copilotkit.
quot;;
import {
  CopilotRuntime,
  createCopilotRuntimeHandler,
  BuiltInAgent,
  convertInputToTanStackAI,
} from "@copilotkit/runtime/v2";
import { chat } from "@tanstack/ai";
import { openaiText } from "@tanstack/ai-openai";

const agent = new BuiltInAgent({
  type: "tanstack",
  factory: ({ input, abortController }) => {
    const { messages, systemPrompts } = convertInputToTanStackAI(input);
    return chat({
      adapter: openaiText("gpt-4o"),
      messages,
      systemPrompts,
      abortController,
    });
  },
});

const runtime = new CopilotRuntime({
  agents: { default: agent },
  // Enabling this key causes /info to advertise A2UI to the client.
  a2ui: {},
});

const handler = createCopilotRuntimeHandler({
  runtime,
  basePath: "/api/copilotkit",
});

export async function loader({ request }: Route.LoaderArgs) {
  return handler(request);
}
export async function action({ request }: Route.ActionArgs) {
  return handler(request);
}

Client side (app/root.tsx or the app shell)

import { CopilotKit, CopilotChat } from "@copilotkit/react-core/v2";
import "@copilotkit/react-core/v2/styles.css";

export default function App() {
  return (
    <CopilotKit
      runtimeUrl="/api/copilotkit"
      a2ui={{
        theme: {
          // Theme object forwarded to A2UIProvider → ThemeProvider.
          // Tokens map to A2UI's basic catalog CSS vars.
          colors: { primary: "#0ea5e9" },
        },
      }}
    >
      <CopilotChat agentId="default" className="h-full" />
    </CopilotKit>
  );
}

Core Patterns

Custom catalog

Pass a custom catalog to extend the built-in component set. createCatalog and extractSchema let the agent see what components it may render.

import { createCatalog } from "@copilotkit/a2ui-renderer";
import { z } from "zod";

const theme = { colors: { primary: "#0ea5e9" } };

// Definitions are platform-agnostic (Zod schemas + descriptions).
// Renderers are platform-specific (React components).
// TypeScript enforces that renderer keys match definition keys exactly.
const definitions = {
  ProductCard: {
    description: "A product card with title and price",
    props: z.object({ title: z.string(), price: z.number() }),
  },
};

const catalog = createCatalog(
  definitions,
  {
    ProductCard: ({ props }) => (
      <div className="rounded-xl border p-3">
        <div className="font-medium">{props.title}</div>
        <div className="text-sm text-muted-foreground">${props.price}</div>
      </div>
    ),
  },
  { includeBasicCatalog: true },
);

<CopilotKit runtimeUrl="/api/copilotkit" a2ui={{ theme, catalog }}>
  <CopilotChat agentId="default" />
</CopilotKit>;

extractSchema(definitions) is available for passing a JSON-serializable view of the definitions to the runtime's a2ui.schema config — it is not a generic type helper. Type parameters erase at runtime; the agent needs a real runtime schema value (Zod).

Override the loading skeleton

<CopilotKit
  runtimeUrl="/api/copilotkit"
  a2ui={{
    theme,
    loadingComponent: () => <div className="animate-pulse">Building UI…</div>,
  }}
>
  <CopilotChat agentId="default" />
</CopilotKit>

Common Mistakes

CRITICAL forgetting runtime.a2ui

Wrong:

// server
new CopilotRuntime({ agents: { default: agent } });
// client
<CopilotKit runtimeUrl="/api/copilotkit" a2ui={{ theme }} />;

Correct:

// server
new CopilotRuntime({ agents: { default: agent }, a2ui: {} });
// client
<CopilotKit runtimeUrl="/api/copilotkit" a2ui={{ theme }} />;

Without runtime.a2ui, /info never flags A2UI and the provider's a2ui prop silently no-ops — the renderer never mounts.

Source: packages/runtime/src/v2/runtime/core/runtime.ts:55-58,217,242

HIGH manually wiring renderActivityMessages for A2UI

Wrong:

import { createA2UIMessageRenderer } from "@copilotkit/react-core/v2";

<CopilotKit
  runtimeUrl="/api/copilotkit"
  renderActivityMessages={[createA2UIMessageRenderer({ theme })]}
/>;

Correct:

<CopilotKit runtimeUrl="/api/copilotkit" a2ui={{ theme }} />

The CopilotKit provider auto-detects runtime A2UI via /info and injects the built-in renderer. Passing it through renderActivityMessages duplicates the renderer and can race with the auto-injected one.

Source: packages/react-core/src/v2/providers/CopilotKitProvider.tsx:188-222,294-296

MEDIUM re-emitting createSurface on every snapshot

Wrong:

# Pseudocode — inside your agent generator. Exact API names/kwargs vary by
# A2UI SDK version; consult your SDK's docs for real call shapes.
async def agent_generator():
    # agent re-emits createSurface operation on every state delta
    async for update in stream:
        yield a2ui.create_surface(surface_id="main", ...)  # every tick
        yield a2ui.update_components(...)

Correct:

# Pseudocode — inside your agent generator.
# Emit createSurface once per surfaceId; use updateComponents / updateDataModel
# for changes.
async def agent_generator():
    yield a2ui.create_surface(surface_id="main", ...)  # once
    async for update in stream:
        yield a2ui.update_components(surface_id="main", ...)

The MessageProcessor dedups on surfaceId but re-emitting is an agent-side bug — the client re-runs reconciliation logic for nothing and flickers.

Source: packages/react-core/src/v2/a2ui/A2UIMessageRenderer.tsx:218-226

MEDIUM custom action bridge without a2uiAction cleanup

Wrong:

copilotkit.setProperties({ ...copilotkit.properties, a2uiAction: msg });
await copilotkit.runAgent({ agent });
// no finally — a2uiAction leaks into the next run's properties

Correct:

try {
  copilotkit.setProperties({ ...copilotkit.properties, a2uiAction: msg });
  await copilotkit.runAgent({ agent });
} finally {
  if (copilotkit.properties) {
    const { a2uiAction, ...rest } = copilotkit.properties;
    copilotkit.setProperties(rest);
  }
}

The built-in bridge always strips a2uiAction in finally, guarded by a copilotkit.properties null-check so it can't mask the original runAgent error with a TypeError during destructuring. Skipping cleanup keeps the previous action attached to subsequent runs.

Source: packages/react-core/src/v2/a2ui/A2UIMessageRenderer.tsx:146-167

MEDIUM installing @copilotkitnext/a2ui-renderer

Wrong:

import { createA2UIMessageRenderer } from "@copilotkitnext/a2ui-renderer";

Correct:

// Low-level primitives (rarely needed — the CopilotKit provider's a2ui prop is the default path):
import {
  A2UIProvider,
  A2UIRenderer,
  createCatalog,
} from "@copilotkit/a2ui-renderer";
// Auto-mounted renderer lives in react-core/v2:
import { createA2UIMessageRenderer } from "@copilotkit/react-core/v2";

This package ships as @copilotkit/a2ui-renderer, not @copilotkitnext/a2ui-renderer. The @copilotkitnext/ scope is reserved for other packages that ship under it separately — do not assume it applies here.

Source: packages/a2ui-renderer/package.json