State Rendering
Render your agent's state with your own React Native components in real time.
What is this?
State rendering lets you build UI that reflects your agent's state in real time. As your agent works and writes to its state, your app renders those changes: progress, drafts, or intermediate results.
When should I use this?
Use state rendering when you want to:
- Show real-time progress (for example, "Researching... 2/5 complete")
- Display drafts that update as the agent works
- Build dashboards that reflect agent state
- Render structured output outside the chat
How it works in code
Put shared state in the system prompt and tools
The demo exposes frontend preferences to Claude and gives the agent a tool for writing notes back into CopilotKit state. Keep the state contract small, typed, and mirrored by the UI components that read the same values.
SYSTEM_PROMPT = dedent("""
You are a helpful, concise assistant.
The user's preferences are supplied via shared state and added at the
start of every turn — always respect them. Address the user by name
when known, match the requested tone, and respond in the requested
language.
When the user asks you to "remember" something, or you observe
something worth surfacing in the UI's notes panel, call the
``set_notes`` tool with the FULL updated list of short notes
(existing notes + new ones, not a diff). Keep each note short
(< 120 characters). After updating notes, briefly acknowledge what
you remembered.
""").strip()
SET_NOTES_TOOL: dict[str, Any] = {
"name": "set_notes",
"description": (
"Replace the notes array in shared state with the FULL updated "
"list. Always include every existing note plus any new ones, "
"not a diff. Keep each note short (< 120 chars)."
),
"input_schema": {
"type": "object",
"properties": {
"notes": {
"type": "array",
"items": {"type": "string"},
"description": "Full list of short note strings to persist.",
},
},
"required": ["notes"],
},
}
def build_preferences_block(prefs: dict[str, Any] | None) -> str | None:
"""Render the user-supplied preferences as an injectable prompt block.
Returns ``None`` when no recognised keys are present so the system
prompt is left untouched.
"""
if not isinstance(prefs, dict) or not prefs:
return None
lines = ["The user has shared these preferences with you:"]
if prefs.get("name"):
lines.append(f"- Name: {prefs['name']}")
if prefs.get("tone"):
lines.append(f"- Preferred tone: {prefs['tone']}")
if prefs.get("language"):
lines.append(f"- Preferred language: {prefs['language']}")
interests = prefs.get("interests") or []
if isinstance(interests, list) and interests:
lines.append(f"- Interests: {', '.join(str(i) for i in interests)}")
if len(lines) == 1:
# No recognised fields — don't emit a header with no content.
return None
lines.append(
"Tailor every response to these preferences. Address the user "
"by name when appropriate."
)
return "\n".join(lines)
def _state_dict(state: dict[str, Any]) -> dict[str, Any]:
"""Coerce the AG-UI raw state envelope into the slots we care about."""
return {
"preferences": state.get("preferences") or {},
"notes": list(state.get("notes") or []),
}
Register set_notes with Claude
This dedicated demo uses the Anthropic Messages API directly. Pass the
schema to client.messages.stream so Claude can call set_notes.
stream_request = client.messages.stream(
model=normalize_claude_model(
os.getenv("ANTHROPIC_MODEL", DEFAULT_ANTHROPIC_MODEL)
),
max_tokens=2048,
system=system,
messages=messages,
tools=[SET_NOTES_TOOL],
)Write the tool result back to shared state
When Claude calls set_notes, replace the notes array, emit a
StateSnapshotEvent for the UI, and return a ToolCallResultEvent to
Claude before the loop continues.
# Execute set_notes by mutating shared state and emitting a
# StateSnapshotEvent so the UI re-renders the agent-authored
# notes. This is the agent-side half of the WRITE direction.
tool_results: list[dict[str, Any]] = []
for tc in tool_calls:
if tc["name"] == "set_notes":
notes = tc["input"].get("notes") or []
if isinstance(notes, list):
state["notes"] = [str(n) for n in notes]
result_text = json.dumps({"status": "ok", "count": len(state["notes"])})
yield encoder.encode(
StateSnapshotEvent(type=EventType.STATE_SNAPSHOT, snapshot=state)
)
else:
result_text = json.dumps({"error": f"unknown tool {tc['name']}"})
yield encoder.encode(
ToolCallResultEvent(
type=EventType.TOOL_CALL_RESULT,
tool_call_id=tc["id"],
message_id=f"{msg_id}-tool-result-{tc['id']}",
content=result_text,
)
)
tool_results.append(
{
"type": "tool_result",
"tool_use_id": tc["id"],
"content": result_text,
}
)
messages.append({"role": "user", "content": tool_results})Serve the shared-state loop
Mount the dedicated runner on /shared-state-read-write and return its
AG-UI events as a streaming response.
@app.post("/shared-state-read-write")
async def shared_state_read_write_endpoint(request: Request) -> StreamingResponse:
"""Bidirectional shared state demo — UI writes preferences, agent writes notes.
Uses its own streaming loop (not the shared sales-assistant
``run_agent``) because the state schema, tools, and prompt-injection
middleware are all demo-specific.
"""
body = await request.json()
input_data = RunAgentInput(**body)
async def event_stream() -> AsyncIterator[str]:
async for chunk in run_shared_state_read_write_agent(input_data):
yield chunk
return StreamingResponse(
event_stream(),
media_type="text/event-stream",
headers={
"Cache-Control": "no-cache",
"X-Accel-Buffering": "no",
},
)
This Python route intentionally uses its own Messages API loop. It does not
use ClaudeAgentAdapter or an MCP server.
- On the backend, write the value to a key in the agent state. To stream a tool argument into a state key token by token, see State Streaming.
- On the frontend, subscribe to the agent's state with
useAgent. Each time the state changes, your component renders again with the latest value. - Read the keys from
agent.stateand render them.
import { Text, View } from "react-native";
import { useAgent, UseAgentUpdate } from "@copilotkit/react-native/headless";
type ResearchState = {
status?: string;
draft?: string;
completed?: number;
total?: number;
};
export function ResearchProgress() {
const { agent } = useAgent({
agentId: "researcher",
updates: [UseAgentUpdate.OnStateChanged, UseAgentUpdate.OnRunStatusChanged],
});
const state = (agent.state ?? {}) as ResearchState;
return (
<View style={{ padding: 16, gap: 8 }} accessibilityLiveRegion="polite">
<Text style={{ fontWeight: "600" }}>
{state.status ?? (agent.isRunning ? "Working..." : "Idle")}
</Text>
<Text>
{state.completed ?? 0} of {state.total ?? "?"} complete
</Text>
{state.draft ? <Text>{state.draft}</Text> : null}
</View>
);
}updates picks which changes re-render the component. OnStateChanged fires on state changes, and OnRunStatusChanged fires when a run starts or ends, so agent.isRunning stays current. Leave updates out to re-render on messages too.
Render it next to your chat, under the same provider. The chat and ResearchProgress share one agent:
import { View } from "react-native";
import { CopilotKitProvider } from "@copilotkit/react-native/headless";
import { CopilotChat } from "@copilotkit/react-native/components";
import { ResearchProgress } from "./src/ResearchProgress";
const runtimeUrl = "http://localhost:8200/api/copilotkit";
export default function App() {
return (
<CopilotKitProvider runtimeUrl={runtimeUrl}>
<View style={{ flex: 1 }}>
<ResearchProgress />
<CopilotChat agentName="researcher" />
</View>
</CopilotKitProvider>
);
}To check it, ask the researcher agent to write a report. The status line and the counter change while the agent runs, and the draft grows as the agent updates draft in its state.
Inside the chat
The rendered CopilotChat has no slot for extra content between messages. To show state inside the conversation, build your own chat and add a row for it to your FlatList data. See Headless UI.
Treat state as untrusted
Treat agent state as external data. Validate it before you use it for a privileged action, and don't put secrets in state that is streamed to the device.
How is this guide?