Writing agent state

This example demonstrates writing to shared state in the CopilotKit Feature Viewer.

What is this?#

This guide shows you how to write to your agent's state from your application.

When should I use this?#

You can use this when you want to provide the user with feedback about what your agent is doing, specifically when your agent is calling tools. CopilotKit allows you to fully customize how these tools are rendered in the chat.

Implementation#

Run and connect your agent#

You'll need to run your agent and connect it to CopilotKit before proceeding. If you haven't done so already, you can follow the instructions in the Getting Started guide.

If you don't already have an agent, you can use the coagent starter as a starting point as this guide uses it as a starting point.

Define the Agent State#

Create your ADK agent with a stateful structure. Here's a complete example that tracks language:

agent.py

from typing import Dict
from fastapi import FastAPI
from pydantic import BaseModel
from ag_ui_adk import ADKAgent, add_adk_fastapi_endpoint
from google.adk.agents import LlmAgent
from google.adk.tools import ToolContext


class AgentState(BaseModel):
    """State for the agent."""
    language: str = "english"


def set_language(tool_context: ToolContext, new_language: str) -> Dict[str, str]:
    """Sets the language preference for the user.

    Args:
        tool_context (ToolContext): The tool context for accessing state.
        new_language (str): The language to save in state.

    Returns:
        Dict[str, str]: A dictionary indicating success status and message.
    """
    tool_context.state["language"] = new_language
    return {"status": "success", "message": f"Language set to {new_language}"}


agent = LlmAgent(
    name="my_agent",
    model="gemini-2.5-flash",
    instruction="""
    You are a helpful assistant. Help users by answering their questions.
    Please use the language specified in state when responding to the user.
    You can set the language in state by using the set_language tool.
    """,
    tools=[set_language],
)

adk_agent = ADKAgent(
    adk_agent=agent,
    app_name="demo_app",
    user_id="demo_user",
    session_timeout_seconds=3600,
    use_in_memory_services=True,
)

app = FastAPI()
add_adk_fastapi_endpoint(app, adk_agent, path="/")

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=8000)

Call `agent.setState` from the `useAgent` hook#

useAgent returns an agent object with a setState method that you can use to update the agent state. Calling this will update the agent state and trigger a rerender of anything that depends on the agent state.

ui/app/page.tsx


// Define the agent state type, should match the actual state of your agent
type AgentState = {
language: "english" | "spanish";
}

// Example usage in a pseudo React component
function YourMainContent() {
  const { agent } = useAgent({ 
    agentId: "my_agent",
    initialState: { language: "english" }  // optionally provide an initial state
  });

  // ...

  const toggleLanguage = () => {
    agent.setState({ language: agent.state?.language === "english" ? "spanish" : "english" }); 
  };

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      <p>Language: {agent.state?.language}</p>
      <button onClick={toggleLanguage}>Toggle Language</button>
    </div>
  );
}

Important

The name parameter must exactly match the agent name you defined in your CopilotRuntime configuration (e.g., my_agent from the quickstart).

Give it a try!#

You can now use agent.setState to update the agent state and agent.state to read it. Try toggling the language button and talking to your agent. You'll see the language change to match the agent's state.

Advanced Usage#

Re-run the agent with a hint about what's changed#

The new agent state will be used next time the agent runs. If you want to re-run it manually, use copilotkit.runAgent().

The agent will be re-run with the latest updated state. You can also add a hint message before re-running.