Tool Call Rendering

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

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?

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)

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.

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

useDefaultRenderTool();
</script>

<template><CopilotChat /></template>

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.

src/components/AgentExperience.vue
useDefaultRenderTool({ render: BrandedToolCard });

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:

    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:

    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:

    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.

The name you pass to useRenderTool must match the tool name the agent exposes. That is how CopilotKit routes the call to your component.

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:

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

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.

tool_rendering_agent.py
from random import choice, randint

from langchain.agents import create_agent
from langchain.tools import tool
from langchain_openai import ChatOpenAI
from copilotkit import CopilotKitMiddleware

# Multi-tool chaining prompt.
#
# The goal of this demo is to surface MULTIPLE tool-call cards per turn so
# the rendering patterns (per-tool + catch-all) get exercised visibly. The
# prompt nudges the model toward an explore-then-enrich pattern (e.g.
# `get_weather("Tokyo")` -> `search_flights(..., "Tokyo")`) without forcing
# a rigid recipe: we describe the *habit*, not a chain.
SYSTEM_PROMPT = (
    "You are a helpful travel & lifestyle concierge. You have mock tools "
    "for weather, flights, stock prices, and dice rolls - they all return "
    "fake data, so call them liberally.\n\n"
    "Your habit is to CHAIN tools when one answer naturally invites another. "
    "For a single user question, call at least TWO tools in succession when "
    "the topic allows before composing your final reply. Examples of "
    "helpful chains you should default to:\n"
    "  - 'What's the weather in Tokyo?' -> call get_weather('Tokyo'), then "
    "call search_flights(origin='SFO', destination='Tokyo') so the user "
    "also sees how to get there.\n"
    "  - 'How is AAPL doing?' -> call get_stock_price('AAPL'), then call "
    "get_stock_price on a related ticker (e.g. 'MSFT' or 'GOOGL') for "
    "comparison.\n"
    "  - 'Roll a d20' -> call roll_dice(20), then call roll_dice again with "
    "a different number of sides so the user sees a contrast.\n"
    "  - 'Find flights from SFO to JFK' -> call search_flights, then call "
    "get_weather on the destination city.\n\n"
    "Only skip chaining when the user has clearly asked for a single, "
    "atomic answer and more tool calls would feel intrusive. Never "
    "fabricate data that a tool could provide."
)


@tool
def get_weather(location: str) -> dict:
    """Get the current weather for a given location.

    Useful on its own for weather questions, and a great companion to
    `search_flights` - always consider checking the weather at a
    destination the user is flying to, and checking flights to any
    city whose weather the user has just asked about.
    """
    return {
        "city": location,
        "temperature": 68,
        "humidity": 55,
        "wind_speed": 10,
        "conditions": "Sunny",
    }

How is this guide?