Back to Copilotkit

Reading agent state

docs/content/docs/integrations/microsoft-agent-framework/shared-state/in-app-agent-read.mdx

1.58.08.1 KB
Original Source

import { ImageZoom } from 'fumadocs-ui/components/image-zoom'; import RunAndConnect from "@/snippets/integrations/microsoft-agent-framework/run-and-connect.mdx" import { IframeSwitcher } from "@/components/content" <IframeSwitcher id="shared-state-example" exampleUrl="https://feature-viewer.copilotkit.ai/microsoft-agent-framework-dotnet/feature/shared_state?sidebar=false&chatDefaultOpen=false" codeUrl="https://feature-viewer.copilotkit.ai/microsoft-agent-framework-dotnet/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/microsoft-agent-framework-dotnet/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 components={props.components} /> </Step> <Step> ### Define the Agent State Decide which parts of agent state you want to reflect in the UI and allow updating from the UI.
<Tabs groupId="language_microsoft-agent-framework_agent" items={['.NET', 'Python']} persist>
  <Tab value=".NET">
    ```csharp title="agent/Program.cs (excerpt)"
    public class AgentStateSnapshot
    {
        public string Language { get; set; } = "english";
    }
    ```
  </Tab>
  <Tab value="Python">
    ```python title="main.py"
    from __future__ import annotations
    import os
    import uvicorn
    from agent_framework import Agent, tool, SupportsChatGetResponse
    from agent_framework.openai import OpenAIChatClient
    from agent_framework.ag_ui import add_agent_framework_fastapi_endpoint
    from agent_framework.ag_ui import AgentFrameworkAgent
    from dotenv import load_dotenv
    from fastapi import FastAPI
    from typing import Annotated
    from pydantic import BaseModel, Field

    load_dotenv()

    class SearchItem(BaseModel):
        query: str
        done: bool
        
    STATE_SCHEMA: dict[str, object] = {
        "language": {
            "type": "string",
            "enum": ["english", "spanish"],
            "description": "Preferred language.",
        }
    }
    PREDICT_STATE_CONFIG: dict[str, dict[str, str]] = {
        "language": {"tool": "update_language", "tool_argument": "language"}
    }

    @tool
    def update_language(
        language: Annotated[str, Field(description="Preferred language: 'english' or 'spanish'")],
    ) -> str:
        normalized = (language or "").strip().lower()
        if normalized not in ("english", "spanish"):
            return "Language unchanged. Use 'english' or 'spanish'."
        return f"Language updated to {normalized}."


    def _build_chat_client():
        if os.getenv("AZURE_OPENAI_ENDPOINT"):
            return OpenAIChatClient(
                model=os.getenv("AZURE_OPENAI_CHAT_DEPLOYMENT_NAME", "gpt-4o-mini"),
                api_key=os.getenv("AZURE_OPENAI_API_KEY"),
                azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
            )
        if os.getenv("OPENAI_API_KEY"):
            return OpenAIChatClient(
                model=os.getenv("OPENAI_CHAT_MODEL_ID", "gpt-4o-mini"),
                api_key=os.getenv("OPENAI_API_KEY"),
            )
        raise RuntimeError(
            "Set either AZURE_OPENAI_ENDPOINT + AZURE_OPENAI_API_KEY, or OPENAI_API_KEY."
        )



    def create_agent(chat_client: SupportsChatGetResponse) -> AgentFrameworkAgent:
        base_agent = Agent(
            name="sample_agent",
            instructions="You are a helpful assistant.",
            client=chat_client,
            tools=[update_language],   
        )
        return AgentFrameworkAgent(
            agent=base_agent,
            name="CopilotKitMicrosoftAgentFrameworkAgent",
            description="Assistant that tracks a simple language state.",
            state_schema=STATE_SCHEMA,               
            predict_state_config=PREDICT_STATE_CONFIG, 
            require_confirmation=False,
        )
        

    chat_client = _build_chat_client()

    agent = create_agent(chat_client)

    app = FastAPI(title="Microsoft Agent Framework - Quickstart")
    add_agent_framework_fastapi_endpoint(app=app, agent=agent, path="/")

    if __name__ == "__main__":
        uvicorn.run("main:app", host="0.0.0.0", port=8000, reload=True)
    ```
  </Tab>
</Tabs>

```ts title="ui/app/page.tsx"
type AgentState = {
  language: "english" | "spanish";
}
```
</Step> <Step> ### Use the `useAgent` Hook With your agent connected and running all that is left is to call the `useAgent` hook, pass the agent's name, and optionally provide an initial state.
```tsx title="ui/app/page.tsx"
import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

// 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: "sample_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="info">
  The `agent.state` in `useAgent` is reactive and will automatically update when the agent's 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 "english" as that's the initial state we set.
<Frame>
  <ImageZoom src="https://cdn.copilotkit.ai/docs/copilotkit/images/microsoft-agent-framework/read-agent-state.png" alt="read agent state" width={1000} height={1000} className="my-0"/>
</Frame>

<Callout type="info">
  Pictured above is the [agent starter](https://github.com/copilotkit/copilotkit/tree/main/examples/agents-starter) with
  the implementation section applied!
</Callout>
</Step> </Steps>

Rendering agent state in the chat

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.

tsx
import { useAgent } from "@copilotkit/react-core/v2"; // [!code highlight]

// 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: "sample_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's state changes. </Callout>

Advanced: Emitting Intermediate State

By default, agent state updates arrive at natural checkpoints during agent execution. For more granular, real-time updates during long-running operations, you can emit state snapshots from within your agent logic. Consult the Microsoft Agent Framework documentation for patterns on streaming custom state events during execution.