showcase/shell-docs/src/content/docs/integrations/adk/shared-state/in-app-agent-read.mdx
<IframeSwitcher id="shared-state-read-example" exampleUrl="https://feature-viewer.copilotkit.ai/adk-middleware/feature/shared_state?sidebar=false&chatDefaultOpen=false" codeUrl="https://feature-viewer.copilotkit.ai/adk-middleware/feature/shared_state?view=code&sidebar=false&codeLayout=tabs" exampleLabel="Demo" codeLabel="Code" height="700px" />
<Callout type="info"> This example demonstrates reading from shared state in the [CopilotKit Feature Viewer](https://feature-viewer.copilotkit.ai/adk-middleware/feature/shared_state). </Callout>You can easily use the realtime agent state not only in the chat UI, but also in the native application UX.
You can use this when you want to provide the user with feedback about your agent's state. As your agent's state updates, you can reflect these updates natively in your application.
Create your ADK agent with a stateful structure. Here's a complete example that tracks language:
```python title="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)
```
```tsx title="ui/app/page.tsx"
// Define the agent state type, should match the actual state of your agent
type AgentState = {
language: "english" | "spanish";
}
function YourMainContent() {
// [!code highlight:4]
const { agent } = useAgent({
agentId: "my_agent",
initialState: { language: "english" } // optionally provide an initial state
});
// ...
return (
// style excluded for brevity
<div>
<h1>Your main content</h1>
<p>Language: {agent.state?.language}</p>
</div>
);
}
```
<Callout type="warn" title="Important">
The `name` parameter must exactly match the agent name you defined in your CopilotRuntime configuration (e.g., `my_agent` from the quickstart).
</Callout>
<Callout type="info">
The `agent.state` in `useAgent` is reactive and will automatically update when the agent's state changes.
</Callout>
You can also render the agent's state in the chat UI. This is useful for informing the user about the agent's state in a
more in-context way. To do this, you can use the useAgent hook with a render function.
// Define the agent state type, should match the actual state of your agent
type AgentState = {
language: "english" | "spanish";
};
function YourMainContent() {
// ...
// [!code highlight:7]
useAgent({
agentId: "my_agent",
render: ({ state }) => {
if (!state.language) return null;
return <div>Language: {state.language}</div>;
},
});
// ...
}