# State Streaming

> Stream partial agent state updates to the UI while a tool call is still running.

<!-- interactive demo: shared-state-streaming -->

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

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

**State streaming** copies one tool argument into an agent state key
while the model writes the argument.
The UI, subscribed via `useAgent`, re-renders every token.

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

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

- A collaborative writing agent that emits a document
- A research agent that accumulates a list of findings
- A planning agent that builds up a step-by-step plan

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

<Steps>
  <Step>
    ### Install the ADK + AG-UI bridge

    ```bash
    pip install ag-ui-adk
    ```

  </Step>
  <Step>
    ### Declare the predicted state mapping

    ADK state streaming uses `PredictStateMapping` to map the streaming
    `write_document` tool argument into `state["document"]`. Add
    `AGUIToolset()` to the agent so CopilotKit can forward the state deltas to
    the UI.

~~~~python title="shared_state_streaming_agent.py"
from __future__ import annotations

from ag_ui_adk import AGUIToolset
from ag_ui_adk.config import PredictStateMapping
from google.adk.agents import LlmAgent
from google.adk.tools import ToolContext

from agents.shared_chat import get_model, stop_on_terminal_text


def write_document(tool_context: ToolContext, document: str) -> dict:
    """Write a document into shared state.

    Whenever the user asks you to write or draft anything (essay, poem,
    email, summary, etc.), call this tool with the full content as a
    single string. The UI renders state["document"] live as you type.

    Argument name `document` mirrors langgraph-python's `write_document`
    signature so the shared D5 fixture (`tool_argument="document"`) and
    the LGP-aligned PredictStateMapping below stay in lock-step.
    """
    tool_context.state["document"] = document
    return {"status": "ok", "length": len(document)}


_INSTRUCTION = (
    "You are a collaborative writing assistant. Whenever the user asks "
    "you to write, draft, or revise any piece of text, ALWAYS call the "
    "`write_document` tool with the full content as a single string. "
    "Never paste the document into a chat message directly — the document "
    "belongs in shared state and the UI renders it live as you type."
)

shared_state_streaming_agent = LlmAgent(
    name="SharedStateStreamingAgent",
    model=get_model(),
    instruction=_INSTRUCTION,
    tools=[write_document, AGUIToolset()],
    after_model_callback=stop_on_terminal_text,
)


SHARED_STATE_STREAMING_PREDICT_STATE = [
    PredictStateMapping(
        state_key="document",
        tool="write_document",
        tool_argument="document",
        emit_confirm_tool=False,
        stream_tool_call=True,
    ),
]
~~~~

  </Step>
  <Step>
    ### Pass the mapping to `ADKAgent`

    The mapping does nothing until it reaches the `ADKAgent` middleware. Pass
    it as `predict_state`, and turn on `streaming_function_call_arguments` so
    the middleware receives the tool arguments while the model writes them.
    The showcase server builds each endpoint this way:

    ```python title="src/agent_server.py"
    from ag_ui_adk import ADKAgent, add_adk_fastapi_endpoint

    middleware = ADKAgent(
        adk_agent=shared_state_streaming_agent,
        user_id="demo_user",
        session_timeout_seconds=3600,
        use_in_memory_services=True,
        predict_state=SHARED_STATE_STREAMING_PREDICT_STATE,
        streaming_function_call_arguments=True,
    )
    add_adk_fastapi_endpoint(app, middleware, path="/shared-state-streaming")
    ```

    With `predict_state`, the frontend gets `document` while the model writes
    the `document` argument of `write_document`. When the tool runs,
    `tool_context.state` stores the final value.

    Per-token streaming needs `google-adk` 1.24.0 or later through Vertex AI.
    On older versions, or through Gemini in Google AI Studio, the middleware
    logs a `UserWarning` at startup and streams in larger chunks. The state
    still updates, only less often.

  </Step>
  <Step>
    ### Stop after the final model response

    The agent above imports `stop_on_terminal_text` and registers it as its
    `after_model_callback`. This prevents Gemini from issuing the same tool
    call again after its final text response. See the canonical
    [`stop_on_terminal_text` implementation](https://github.com/CopilotKit/CopilotKit/blob/main/showcase/integrations/google-adk/src/agents/shared_chat.py)
    when adapting the callback for your project.

  </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 LLM streams that argument, CopilotKit writes every partial value
into shared state before the tool even finishes executing.

```python title="src/agents/shared_state_streaming_agent.py"
from __future__ import annotations

from ag_ui_adk import AGUIToolset
from ag_ui_adk.config import PredictStateMapping
from google.adk.agents import LlmAgent
from google.adk.tools import ToolContext

from agents.shared_chat import get_model, stop_on_terminal_text


def write_document(tool_context: ToolContext, document: str) -> dict:
    """Write a document into shared state.

    Whenever the user asks you to write or draft anything (essay, poem,
    email, summary, etc.), call this tool with the full content as a
    single string. The UI renders state["document"] live as you type.

    Argument name `document` mirrors langgraph-python's `write_document`
    signature so the shared D5 fixture (`tool_argument="document"`) and
    the LGP-aligned PredictStateMapping below stay in lock-step.
    """
    tool_context.state["document"] = document
    return {"status": "ok", "length": len(document)}


_INSTRUCTION = (
    "You are a collaborative writing assistant. Whenever the user asks "
    "you to write, draft, or revise any piece of text, ALWAYS call the "
    "`write_document` tool with the full content as a single string. "
    "Never paste the document into a chat message directly — the document "
    "belongs in shared state and the UI renders it live as you type."
)

shared_state_streaming_agent = LlmAgent(
    name="SharedStateStreamingAgent",
    model=get_model(),
    instruction=_INSTRUCTION,
    tools=[write_document, AGUIToolset()],
    after_model_callback=stop_on_terminal_text,
)


SHARED_STATE_STREAMING_PREDICT_STATE = [
    PredictStateMapping(
        state_key="document",
        tool="write_document",
        tool_argument="document",
        emit_confirm_tool=False,
        stream_tool_call=True,
    ),
]
```

A few things to note:

- The state key must exist in your agent state (`document` in this demo).
- The tool and argument names must match the exact LLM-facing tool call
  you want to forward (`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 + OnStateChanged [#the-frontend-useagent--onstatechanged]

The UI side is the same as any other [shared-state](/google-adk/shared-state) subscription:
`useAgent` with `OnStateChanged` gives you a reactive `agent.state`.
Add `OnRunStatusChanged` if you want a "LIVE" / "done" indicator.

```typescript title="src/app/demos/shared-state-streaming/page.tsx"
  // Subscribe to BOTH state changes and run-status changes. The former
  // drives the per-token document rerender; the latter toggles the
  // "LIVE" badge when the agent starts / stops.
  const { agent } = useAgent({
    agentId: "shared-state-streaming",
    updates: [UseAgentUpdate.OnStateChanged, UseAgentUpdate.OnRunStatusChanged],
  });
```

From there, `agent.state.document` is just a string that grows on every
token, and `agent.isRunning` tells you whether to show a streaming
indicator.

## Try it [#try-it]

Ask the agent to write a short poem. The `document` text grows in your UI
while the agent writes. When the run ends, `agent.isRunning` is `false`, so
your streaming indicator turns off.

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