# State Streaming

> Stream partial agent state to your React Native UI while a tool call is still running.

## What is this? [#what-is-this]

By default, agent state only updates *between* backend checkpoints, so a long tool call (writing a full document, drafting an email) reaches the UI as one burst at the end. In an agent-native app, that feels broken: users expect to watch the output appear.

**State streaming** copies one tool argument into an agent state key while the model writes the argument. Your screen, subscribed with `useAgent`, re-renders on every token.

## When should I use this? [#when-should-i-use-this]

Use state streaming when a tool's output is long-form text or a growing structured value, and you want the user to see it build up in real time. Common shapes:

- A writing agent that produces a document
- A research agent that collects a list of findings
- A planning agent that builds a step-by-step plan

<WhenFrameworkSupports feature="shared-state-streaming" not>

<Callout type="info">
  **Not available on this framework yet.** This framework's showcase doesn't support state streaming. The UI gets the agent's state between checkpoints, which the [Shared State](/react-native/deepagents/shared-state) page covers.
</Callout>

</WhenFrameworkSupports>

## The backend: one streaming state mapping [#the-backend-one-streaming-state-mapping]

<Steps>
  <Step>
    ### Build an agent that streams a tool argument into state

    Deep Agents has no live demo on this page yet, so the demo code on this
    page does not show for it. Define the state key, add a tool that saves the
    completed value, and add `StateStreamingMiddleware` with one `StateItem`
    that maps the tool argument to the state key. This example streams a
    `searches` list:

    <Tabs groupId="agent_language" items={['Python', 'TypeScript']} persist>
      <Tab value="Python">
        ```python title="agent.py"
        from typing import Any, TypedDict

        from copilotkit import (
            CopilotKitMiddleware,
            CopilotKitState,
            StateItem,
            StateStreamingMiddleware,
        )
        from deepagents import create_deep_agent
        from langchain_openai import ChatOpenAI
        from langchain.agents.middleware import AgentMiddleware
        from langchain.messages import ToolMessage
        from langchain.tools import ToolRuntime, tool
        from langgraph.types import Command

        class Search(TypedDict):
            query: str
            done: bool

        class AgentState(CopilotKitState):
            searches: list[Search]

        class SearchesStateMiddleware(AgentMiddleware[AgentState, Any, Any]):
            state_schema = AgentState

        @tool
        def report_research_progress(
            searches: list[Search],
            runtime: ToolRuntime[None, AgentState],
        ) -> Command:
            """Report the current research tasks and completion status."""
            return Command(
                update={
                    "searches": searches,
                    "messages": [
                        ToolMessage(
                            content="Research progress saved.",
                            tool_call_id=runtime.tool_call_id,
                        )
                    ],
                }
            )

        agent = create_deep_agent(
            model=ChatOpenAI(model="gpt-6-luna", reasoning_effort="none"),
            tools=[report_research_progress],
            middleware=[
                SearchesStateMiddleware(),
                CopilotKitMiddleware(),
                StateStreamingMiddleware(
                    StateItem(
                        state_key="searches",
                        tool="report_research_progress",
                        tool_argument="searches",
                    )
                ),
            ],
            system_prompt=(
                "You are a research assistant. Use report_research_progress "
                "to show each task and mark it done when complete."
            ),
        )
        ```
      </Tab>
      <Tab value="TypeScript">
        ```ts title="agent.ts"
        import { ToolMessage } from "@langchain/core/messages";
        import { tool, type ToolRuntime } from "@langchain/core/tools";
        import { Command } from "@langchain/langgraph";
        import {
          copilotkitMiddleware,
          zodState,
        } from "@copilotkit/sdk-js/langgraph";
        import {
          stateItem,
          stateStreamingMiddleware,
        } from "@copilotkit/sdk-js/langgraph-middlewares";
        import { createDeepAgent } from "deepagents";
        import { createMiddleware } from "langchain";
        import { z } from "zod";

        const SearchSchema = z.object({
          query: z.string(),
          done: z.boolean(),
        });
        type Search = z.infer<typeof SearchSchema>;

        const SearchesStateSchema = z.object({
          searches: z.array(SearchSchema),
        });

        const searchesStateMiddleware = createMiddleware({
          name: "SearchesState",
          stateSchema: z.object({
            searches: zodState(z.array(SearchSchema).default(() => [])),
          }),
        });

        const reportResearchProgress = tool(
          (
            input: { searches: Search[] },
            runtime: ToolRuntime<typeof SearchesStateSchema>,
          ) =>
            new Command({
              update: {
                searches: input.searches,
                messages: [
                  new ToolMessage({
                    content: "Research progress saved.",
                    tool_call_id: runtime.toolCallId,
                  }),
                ],
              },
            }),
          {
            name: "report_research_progress",
            description:
              "Report the current research tasks and completion status.",
            schema: z.object({ searches: z.array(SearchSchema) }),
          },
        );

        export const agent = createDeepAgent({
          model: "openai:gpt-6-luna",
          tools: [reportResearchProgress],
          middleware: [
            searchesStateMiddleware,
            copilotkitMiddleware,
            stateStreamingMiddleware(
              stateItem({
                stateKey: "searches",
                tool: "report_research_progress",
                toolArgument: "searches",
              }),
            ),
          ],
          systemPrompt:
            "You are a research assistant. Use report_research_progress " +
            "to show each task and mark it done when complete.",
        });
        ```
      </Tab>
    </Tabs>

  </Step>
  <Step>
    ### Understand the two update phases

    The state-streaming middleware sends the partial `searches` argument while
    the model writes it. The frontend can show each partial value at once.

    The tool then returns a `Command` that saves the completed list. Its
    `ToolMessage` closes the active tool call.

    When the run finishes, the agent's final state is the single source of
    truth. A streamed value that the tool does not also save in its `Command`
    disappears at the end of the run, with no error.

    Each setting must match your code. A mismatch sends updates to the wrong
    state field, or to none:

    - `state_key` (`stateKey`): the state field.
    - `tool`: the name of the tool.
    - `tool_argument` (`toolArgument`): the argument of the tool.

  </Step>
  <Step>
    ### Render the state in the UI

    Use `useAgent` to read the state anywhere in your app: in the chat, in a
    dashboard, in a sidebar.

    ```tsx title="app/page.tsx"
    import { useAgent } from "@copilotkit/react-core/v2";

    function YourMainContent() {
      const { agent } = useAgent({
        agentId: "sample_agent",
      });

      const state = (agent.state ?? {}) as {
        searches?: { query: string; done: boolean }[];
      };
      const searches = state.searches ?? [];

      return (
        <div>
          {searches.map((search, index) => (
            <div key={index}>
              {search.done ? "✅" : "⏳"} {search.query}
            </div>
          ))}
        </div>
      );
    }
    ```

    Ask the agent to research a topic. The search items appear and update
    while the agent works.

  </Step>
</Steps>

The backend pattern is always the same: map one streaming tool argument to one shared-state key. Each framework does this in its own way:

- LangGraph Python: `StateStreamingMiddleware` with `StateItem(...)` entries.
- LangGraph TypeScript: `copilotkitCustomizeConfig` with an `emitIntermediateState` mapping.
- Direct SDK adapters: parse partial tool arguments in the streaming loop, and emit `STATE_SNAPSHOT` whenever the mapped value changes.
- LlamaIndex and Pydantic AI: there is no per-token mapping. A backend tool sends a state snapshot after each step or tool call instead (see the setup above).

When the model streams that argument, CopilotKit writes every partial value into shared state before the tool finishes.

<WhenFrameworkSupports feature="shared-state-streaming">

> **Not available for Langchain DeepAgents yet.** This sample comes from the showcase's `shared-state-streaming` demo, and Langchain DeepAgents doesn't have it yet.

</WhenFrameworkSupports>

A few things to note:

- The state key must exist in your agent state (`document` in this example).
- The tool and argument names must match the exact tool call the model makes (`write_document.document` here).
- Streamed values are previews. When the step ends, the state the agent saves replaces them, so save the final value when the tool finishes. On CrewAI, LlamaIndex, and Pydantic AI, write the final value to the agent state yourself, or it is overwritten when the step returns.

## The frontend: useAgent and OnStateChanged [#the-frontend-useagent-and-onstatechanged]

The app side is the same as any other [shared-state](/react-native/deepagents/shared-state) subscription: `useAgent` with `OnStateChanged` gives you a live `agent.state`. Add `OnRunStatusChanged` for a "writing" indicator.

```tsx title="src/DocumentView.tsx"
import { ActivityIndicator, ScrollView, Text, View } from "react-native";
import { useAgent, UseAgentUpdate } from "@copilotkit/react-native/headless";

export function DocumentView() {
  const { agent } = useAgent({ // [!code highlight:4]
    agentId: "default",
    updates: [UseAgentUpdate.OnStateChanged, UseAgentUpdate.OnRunStatusChanged],
  });
  const document = (agent.state as { document?: string } | undefined)?.document ?? "";

  return (
    <View style={{ padding: 16, gap: 8 }}>
      {agent.isRunning ? <ActivityIndicator /> : null}
      <ScrollView style={{ maxHeight: 320 }}>
        <Text>{document}</Text>
      </ScrollView>
    </View>
  );
}
```

`agent.state.document` is a string that grows on every token, and `agent.isRunning` tells you whether to show the indicator. The `ScrollView` with a `maxHeight` keeps a long document from pushing the rest of the screen away.

If a fast stream re-renders a heavy screen too often, pass `throttleMs` to `useAgent` to batch the updates.

## Try it [#try-it]

Ask the agent to write a short poem. The `document` text grows on your screen while the agent writes. When the run ends, `agent.isRunning` is `false`, so the indicator goes away.

<IntegrationGrid path="shared-state/streaming" exclude={["agno", "agent-spec", "spring-ai", "langroid"]} />
