# Tool Call Rendering

> Render your agent's tool calls with custom UI components.

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

Tools are how an LLM invokes predefined, typically-deterministic functions. Tool rendering lets you decide how each of those tool calls appears in the chat. Instead of showing raw JSON, you register a Vue component that draws a branded card for the call (arguments, live status, and the eventual result). This is the **Generative UI** variant CopilotKit calls **tool rendering**.

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

Render tool calls when you want to:

- Show users exactly what tools the agent is invoking and with what arguments
- Display live progress indicators while a tool executes
- Render rich, polished results once a tool completes
- Give tool-heavy agents a transparent, on-brand chat experience

## Default tool rendering (zero-config) [#default-tool-rendering-zero-config]

The simplest entry point is `useDefaultRenderTool()` with no arguments. CopilotKit registers its built-in default renderer as the `*` wildcard: every tool call renders as a status card (tool name, live **Running → Done** state, collapsible arguments/result) without you writing any UI.

Without this composable, CopilotKit has no `*` renderer and tool calls are not shown. The user only sees the assistant's final text summary.

```vue title="src/components/AgentExperience.vue"
<script setup lang="ts">
import { CopilotChat, useDefaultRenderTool } from "@copilotkit/vue/v2";

useDefaultRenderTool();
</script>

<template><CopilotChat /></template>
```

## Custom catch-all [#custom-catch-all]

Once you want on-brand chrome, pass a `render` component or function to `useDefaultRenderTool`. It's a convenience wrapper around `useRenderTool({ name: "*", ... })`: one wildcard renderer handles every tool call, named or not.

```ts title="src/components/AgentExperience.vue"
useDefaultRenderTool({ render: BrandedToolCard });
```

## Per-tool renderers [#per-tool-renderers]

The most expressive path is one renderer per tool name. Each renderer receives the tool's parsed arguments, a live `status`, and, once the agent returns, the `result`.

1. Write the card component:

   ```vue title="src/components/WeatherToolCard.vue"
   <script setup lang="ts">
   defineProps<{
     parameters: { city?: string };
     status: "inProgress" | "executing" | "complete";
     result?: string;
   }>();
   </script>

   <template>
     <p v-if="status !== 'complete'">Checking {{ parameters.city ?? "…" }}</p>
     <article v-else>
       <strong>{{ parameters.city }}</strong>
       <pre>{{ result }}</pre>
     </article>
   </template>
   ```

2. Register it with `useRenderTool` in a component:

   ```vue title="src/components/AgentExperience.vue"
   <script setup lang="ts">
   import { z } from "zod";
   import { CopilotChat, useDefaultRenderTool, useRenderTool } from "@copilotkit/vue/v2";
   import WeatherToolCard from "./WeatherToolCard.vue";

   useRenderTool({
     name: "get_weather",
     parameters: z.object({ city: z.string() }),
     render: WeatherToolCard,
   });

   useDefaultRenderTool(); // wildcard fallback for every other tool
   </script>

   <template><CopilotChat /></template>
   ```

3. Mount that component under `CopilotKitProvider`:

   ```vue title="src/App.vue"
   <script setup lang="ts">
   import { CopilotKitProvider } from "@copilotkit/vue/v2";
   import AgentExperience from "./components/AgentExperience.vue";
   </script>

   <template>
     <CopilotKitProvider runtime-url="/api/copilotkit"><AgentExperience /></CopilotKitProvider>
   </template>
   ```

`parameters` is partial while arguments stream. Read required fields only after the status advances from `inProgress`. The result is a string when status is `complete`; parse it only if your backend deliberately returns a documented serialized shape.

<Callout type="info">
  The `name` you pass to `useRenderTool` must match the tool name the agent exposes. That is how CopilotKit routes the call to your component.
</Callout>

Per-tool renderers compose with a catch-all: named renderers claim the "interesting" tools and a wildcard handles everything else. The example registers the built-in wildcard after the named `get_weather` renderer.

If the renderer closes over reactive values, pass Vue watch sources as the second argument:

```ts
useRenderTool({ name: "get_weather", parameters, render: WeatherToolCard }, [locale]);
```

## The backend tool definition [#the-backend-tool-definition]

The frontend renderer only sees what the agent sends down. The matching backend must expose a tool named `get_weather`, return structured data, and let the frontend renderer with the same name paint the card. The Vue renderer does not create or execute that backend tool.

```python title="src/agents/agent.py"
from __future__ import annotations

import json
import logging
from typing import Annotated, Any

import openai
from ag2 import Agent
from ag2.ag_ui import AGUIStream
from ag2.config.openai import OpenAIResponsesConfig
from dotenv import load_dotenv
from pydantic import Field, ValidationError

load_dotenv()

# Import shared tool implementations
from tools import (
    get_weather_impl,
    query_data_impl,
    manage_sales_todos_impl,
    get_sales_todos_impl,
    schedule_meeting_impl,
    search_flights_impl,
    build_a2ui_operations_from_tool_call,
    RENDER_A2UI_TOOL_SCHEMA,
)
from tools.types import Flight

from ._header_forwarding import get_forwarded_headers
from ._loop_cap import loop_cap
from ._request_context import get_latest_user_message

logger = logging.getLogger(__name__)

# Module-level async client: re-used across requests (httpx connection pool is
# thread-safe). Using AsyncOpenAI inside an `async def` avoids blocking the
# ASGI event loop on the secondary LLM call.
_async_openai_client = openai.AsyncOpenAI()


# =====
# Tools
# =====
async def get_weather(
    location: Annotated[str, Field(description="City name to get weather for")],
) -> str:
    """Get current weather for a location."""
    result = get_weather_impl(location)
    # Return a JSON string (not a dict): non-string tool returns are serialized
    # with str(), producing a Python repr (single quotes) that the frontend's
    # parseJsonResult/JSON.parse cannot parse — the weather card then renders
    # "--" placeholders. Same pattern as search_flights below.
    return json.dumps(
        {
            "city": result["city"],
            "temperature": result["temperature"],
            "feels_like": result["feels_like"],
            "humidity": result["humidity"],
            "wind_speed": result["wind_speed"],
            "conditions": result["conditions"],
        }
    )

```

<IntegrationGrid path="generative-ui/tool-rendering" />
