State Streaming
Stream partial agent state updates to the UI while a tool call is still running.
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?
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
Map the tool call to a state snapshot
AGUIStreamOptions.MapCall maps a tool call to AG-UI events. Return a
StateSnapshotEvent built from the tool's arguments, and attach the
options to the endpoint with WithMetadata:
using System.ComponentModel;
using System.Text.Json;
using AGUI.Abstractions;
using AGUI.Server;
#pragma warning disable OPENAI001
using Microsoft.Extensions.AI;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Hosting.AGUI.AspNetCore;
using Microsoft.Extensions.AI;
using OpenAI;
using OpenAI.Chat;
var builder = WebApplication.CreateBuilder(args);
builder.Services.AddAGUIServer();
var app = builder.Build();
string openAiApiKey = builder.Configuration["OPENAI_API_KEY"]
?? throw new InvalidOperationException("Set OPENAI_API_KEY");
// Define a tool the LLM may call to report its progress
[Description("Report current step progress.")]
static string StepProgress([Description("Steps completed so far")] string[] steps)
=> "Progress received.";
AITool stepProgress = AIFunctionFactory.Create(StepProgress, name: "step_progress");
var agent = new OpenAIClient(openAiApiKey)
.GetChatClient("gpt-6-luna")
.AsIChatClient().AsBuilder()
.ConfigureOptions(options => options.RawRepresentationFactory = _ =>
new OpenAI.Chat.ChatCompletionOptions { ReasoningEffortLevel = new("none") })
.Build()
.AsAIAgent(
name: "AGUIAssistant",
instructions: "You are a helpful assistant that may call the 'step_progress' tool to report intermediate steps.",
tools: [stepProgress]);
// Map the completed tool arguments to a shared-state snapshot
AGUIStreamOptions streamOptions = new AGUIStreamOptions()
.MapCall("step_progress", call =>
{
if (call.Arguments?.TryGetValue("steps", out object? steps) is not true)
{
return [];
}
JsonElement snapshot = JsonSerializer.SerializeToElement(
new { observed_steps = steps });
return [new StateSnapshotEvent { Snapshot = snapshot }];
});
app.MapAGUIServer("/", agent).WithMetadata(streamOptions);
await app.RunAsync();Know what streams and what does not
MapCall runs on the completed FunctionCallContent, so the state key
updates once, when the tool call finishes. It does not grow token by
token while the model writes the arguments. To stream partial arguments
into state, register a provider-specific extractor with
MapStreamingToolCallArguments.
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:
StateStreamingMiddlewarewithStateItem(...)entries. - LangGraph TypeScript:
copilotkitCustomizeConfigwith anemitIntermediateStatemapping. - Direct SDK adapters: parse partial tool arguments in the streaming loop,
and emit
STATE_SNAPSHOTwhenever 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.
Missing snippet
state-streaming-middleware not found in ms-agent-dotnet::shared-state-streaming. Tag the source lines with // @region[state-streaming-middleware] / // @endregion[state-streaming-middleware].Available: frontend-use-coagent-stateA few things to note:
- The state key must exist in your agent state (
documentin this demo). - The tool and argument names must match the exact LLM-facing tool call
you want to forward (
write_document.documenthere). - 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 UI side is the same as any other shared-state subscription:
useAgent with OnStateChanged gives you a reactive agent.state.
Add OnRunStatusChanged if you want a "LIVE" / "done" indicator.
// 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
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.
How is this guide?