Back to Copilotkit

Reading agent state

showcase/shell-docs/src/content/docs/integrations/aws-strands/shared-state/in-app-agent-read.mdx

1.57.04.3 KB
Original Source

<IframeSwitcher id="shared-state-read-example" exampleUrl="https://feature-viewer.copilotkit.ai/aws-strands/feature/shared_state?sidebar=false&chatDefaultOpen=false" codeUrl="https://feature-viewer.copilotkit.ai/aws-strands/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/aws-strands/feature/shared_state). </Callout>

What is this?

You can easily use the realtime agent state not only in the chat UI, but also in the native application UX.

When should I use this?

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.

Implementation

<Steps> <Step> ### Run and connect your agent <RunAndConnect /> </Step> <Step> ### Setup your agent with state
Define your agent's state schema. AWS Strands maintains state throughout execution.

```python title="agent/main.py"
from ag_ui_strands import StrandsAgent, StrandsAgentConfig, create_strands_app
from strands import Agent
from strands.models.openai import OpenAIModel

model = OpenAIModel(
    client_args={"api_key": os.getenv("OPENAI_API_KEY", "")},
    model_id="gpt-4o",
)

# Create the Strands agent
strands_agent = Agent(
    model=model,
    system_prompt="Always communicate in the preferred language of the user as defined in your state. Do not communicate in any other language.",
)

# Inject state into the prompt
def language_prompt(input_data, user_message: str) -> str:
    state_dict = getattr(input_data, "state", None)
    if isinstance(state_dict, dict) and "language" in state_dict:
        return f"Current language: {state_dict['language']}\n\nUser request: {user_message}"
    return user_message

config = StrandsAgentConfig(state_context_builder=language_prompt)

# Wrap with AG-UI integration
agui_agent = StrandsAgent(
    agent=strands_agent,
    name="languageAgent",
    description="Always communicate in the preferred language of the user",
    config=config,
)

app = create_strands_app(agui_agent)
```
</Step> <Step> ### Use the `useAgent` Hook
With your agent connected and running, call the `useAgent` hook, pass the agent's name, and
optionally provide an initial state.

```tsx title="ui/app/page.tsx"

// Define the agent state type to match your Strands agent
type AgentState = {
  language: "english" | "spanish";
};

function YourMainContent() {
  // [!code highlight:5]
  const { agent } = useAgent({
    agentId: "strands_agent",
    // optionally provide a type-safe initial state
    initialState: { language: "spanish" }
  });

  // ...

  return (
    // style excluded for brevity
    <div>
      <h1>Your main content</h1>
      <p>Language: {agent.state?.language}</p>
    </div>
  );
}
```
<Callout type="info">
  The `agent.state` in `useAgent` is reactive and will automatically update when the agent state changes.
</Callout>
</Step> <Step> ### Give it a try!
As the agent state updates, your `state` variable will automatically update with it! In this case, you'll see the
language set to "spanish" as that's the initial state we set.
</Step> </Steps>

Rendering agent state in the chat

You can also render the agent state in the chat UI. This is useful for informing the user about the state in a more in-context way. To do this, you can use the useAgent hook with a render function.

tsx
// 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: "strands_agent",
    render: ({ state }) => {
      if (!state.language) return null;
      return <div>Language: {state.language}</div>;
    },
  });
  // ...
}
<Callout type="info"> The `agent.state` in `useAgent` is reactive and will automatically update when the agent state changes. </Callout>