Shared State
Create a two-way connection between your React Native UI and agent state.
What is shared state?
Shared state connects your app's UI with the agent's run. With shared state you can:
- Display the agent's current progress and intermediate results
- Update the agent's state through UI interactions
- React to state changes in real time across your app
When should I use this?
Use shared state when you want the agent and the user to work on the same app state. The UI shows what the agent writes. The agent reads what the user changes in the UI.
Building stateful agents?Persistent threads ship with CopilotKit Intelligence on the free Developer tier.Get CopilotKit Intelligence freeReading agent state
Show the model the state in its instructions
The page's state arrives with every run as RunAgentInput.state, and the
adapter makes it the run's shared state. It does not reach the prompt by
itself. Give the agent dynamic instructions that read it with the
adapter's shared_state(), so the model sees the current value on every
turn, including edits the user made with agent.setState:
def with_state(prompt: str) -> Callable[[RunContextWrapper[Any], Agent[Any]], str]:
"""Dynamic instructions: ``prompt`` plus the run's shared state as JSON."""
def instructions(_ctx: RunContextWrapper[Any], _agent: Agent[Any]) -> str:
state = shared_state().value
if not state:
return prompt
return (
f"{prompt}\n\nCurrent shared application state (JSON; the user may "
f"have edited it since your last turn):\n{json.dumps(state)}"
)
return instructions
READ_WRITE_PROMPT = (
"You are a helpful, concise assistant. The shared application state below "
"has a `preferences` object with the user's name, preferred tone, "
"language and interests, which the user edits in the app: always respect "
"them, and address the user by name when you know it. Its `notes` list "
"holds what you have remembered so far. When the user asks you to "
"remember something, or when you observe something worth surfacing in "
"the UI, call `set_notes` with the FULL updated list of short note "
"strings (existing notes + new)."
)
shared_state_read_write_agent = Agent(
name="preferences_assistant",
instructions=with_state(READ_WRITE_PROMPT),
model=MODEL,
model_settings=chat_settings(),
tools=[set_notes],
)
Write state from a server tool
Server tools are ordinary @function_tool functions. Inside one,
shared_state().update(...) merges top-level keys into the state and
streams a STATE_SNAPSHOT to the browser before the tool's own result, so
any component subscribed with useAgent re-renders while the agent is
still running.
@function_tool
def set_notes(notes: list[str]) -> str:
"""Replace the notes array in shared state with the full updated list.
Use this tool whenever the user asks you to "remember" something, or
when you have an observation about the user worth surfacing in the
UI's notes panel. Always pass the FULL notes list (existing notes +
any new ones), not a diff. Keep each note short (< 120 chars).
"""
shared_state().update(notes=notes)
return "Notes updated."
shared_state().set(value) replaces the whole state instead. The
request's own state is never changed.
Inside an OpenAIAgentsAgent run
OpenAIAgentsAgent sets up shared_state() for every request. If you
drive the SDK yourself with the adapter's translator, start the run inside
use_shared_state(SharedState(run_input.state)) and pass the same object
to to_agui.
Subscribe a component to the agent's state with useAgent. Each time the agent changes its state, for example from a tool call, the hook re-renders your component with the new values.
import { Text, View } from "react-native";
import { useAgent, UseAgentUpdate } from "@copilotkit/react-native/headless";
type NotesState = {
notes?: string[];
preferences?: { tone?: string };
};
export function NotesCard() {
const { agent } = useAgent({
agentId: "default",
updates: [UseAgentUpdate.OnStateChanged],
});
const state = (agent.state ?? {}) as NotesState;
return (
<View style={{ padding: 16, gap: 4 }}>
{(state.notes ?? []).map((note) => (
<Text key={note}>• {note}</Text>
))}
</View>
);
}agent.state is a plain object. Read it like any other React data and render the parts you care about: notes the agent wrote, structured output, progress, or anything else the agent put there.
Writing agent state
The same agent has a setState method. Call it from a UI event, and the agent reads the new value on its next turn. The UI's writes steer the model.
import { Button } from "react-native";
// In NotesCard, below the list:
<Button
title="Prefer short answers"
onPress={() =>
agent.setState({
...state,
preferences: { ...state.preferences, tone: "concise" },
})
}
/>This makes shared state two-way. The UI can send the agent new inputs, such as preferences, selections, or partial work, without the chat.
The agent reads the new state on its next run. To run it right away, call copilotkit.runAgent({ agent }) (from useCopilotKit) after setState. Running through copilotkit also sends your frontend tools and context with the run. To tell the model what changed, add a message first:
const { copilotkit } = useCopilotKit();
agent.setState({ ...state, language: newLanguage });
agent.addMessage({
id: `user-${Date.now()}`,
role: "user",
content: `The language has been updated to ${newLanguage}.`,
});
await copilotkit.runAgent({ agent });See Programmatic Control for more ways to run the agent from code.
Rendering shared state in the UI
Because agent.state is plain React data, the UI layer is whatever you'd normally build. Nothing about it is chat-specific: useAgent works in any component under CopilotKitProvider, so you can render the state on your main screen, not just next to the chat. See Render agent state in your app for the full pattern.
Streaming partial state updates
By default, agent state only updates between backend checkpoints, so a long tool call shows up as one burst at the end. State streaming copies one tool argument into a state key while the model writes it, so the UI shows the answer token by token.
def _document_so_far(arguments: str) -> str | None:
"""The ``document`` argument as far as the model has written it."""
try:
# Unfinished JSON: a string cut off mid-way is kept as it stands.
value = from_json(arguments, allow_partial="trailing-strings")
except ValueError:
return None
document = value.get("document") if isinstance(value, dict) else None
return document if isinstance(document, str) else None
class DocumentStreamingAgent(OpenAIAgentsAgent):
"""Streams ``write_document``'s ``document`` argument into the state."""
async def run_streamed(self, input: RunAgentInput) -> AsyncIterator[BaseEvent]:
arguments: dict[str, str] = {} # tool call id -> arguments so far
async with aclosing(super().run_streamed(input)) as events:
async for event in events:
yield event
if (
event.type == EventType.TOOL_CALL_START
and event.tool_call_name == write_document.name
):
arguments[event.tool_call_id] = ""
elif (
event.type == EventType.TOOL_CALL_ARGS
and event.tool_call_id in arguments
):
arguments[event.tool_call_id] += event.delta
document = _document_so_far(arguments[event.tool_call_id])
if document is not None:
yield StateDeltaEvent(
type=EventType.STATE_DELTA,
delta=[
{"op": "add", "path": "/document", "value": document}
],
)
See State Streaming for the full walkthrough, including the useAgent subscription on the frontend.
Read-only context
When a value is UI-owned, and the agent should read it but never write it back, use useAgentContext instead of shared state. Examples are the current user, the selected record, or the open screen. It sends values one way, from the UI to the agent, and removes them when the component unmounts.
See Agent Read-Only Context for the full pattern.
How is this guide?