# Agent Read-Only Context

> Publish UI values to the agent as a one-way read-only channel via useAgentContext.

<!-- interactive demo: readonly-state-agent-context -->

<Callout type="info" title="See this in Inspector">
  Open Inspector on localhost. Go to **Inspect**, then **Context**.
  The values you publish with `useAgentContext` appear here.

  More detail: [Inspector](/ag2/inspector).
</Callout>

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

Sometimes you want the agent to *know* something about the current UI, like the logged-in user, the current page, or a recent activity log, but you don't want the agent to be able to modify it. That's what
`useAgentContext` is for: a one-way **UI → agent** channel for
read-only context.

Unlike full shared state (where the agent can call tools that mutate
the state back to the UI), `useAgentContext` values are pure inputs.
The agent sees them on every turn via the runtime's context injection,
but it has no setter and no tool to write them back.

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

Reach for `useAgentContext` instead of full shared state when:

- The value is **UI-owned** and has no meaning to the agent beyond
  "what the user is looking at right now".
- The agent should read but never write (user identity, feature flags,
  selected record, scroll position).
- You want the value to automatically unregister on unmount (e.g. the
  "current record" context disappears when you leave the page).

Think of it as "props for the agent".

If the agent must also write the value, use **[shared state](/ag2/shared-state)**. To stream agent-written state to the UI during a run, see [State streaming](/ag2/shared-state/streaming).

## How it works in code [#how-it-works-in-code]

<Steps>
  <Step>
    ### Use AG2 1.1.2 or later

    With AG2 1.1.2 or later, `AGUIStream` hands every `useAgentContext` entry
    to the model, so a plain AG-UI endpoint needs no extra code. On AG2 1.0.x
    the entries never reach the model, and nothing reports an error. Upgrade
    first:

    ```bash
    pip install "ag2[ag-ui,openai]>=1.1.2"
    ```

  </Step>
  <Step>
    ### Serve the agent as usual

    `AGUIStream` adds the entries from `RunAgentInput.context` to the run's
    system prompt, after the agent's own prompt, as one block:

    ```text
    ## Context from the application

    - The current user's colleagues: [{"id":1,"name":"John Doe","role":"Developer"}, ...]
    ```

    Each line is the entry's `description`, then its `value` exactly as the
    client sent it. The block is prose for the model, not variables, so tool
    code does not see it.

    Do not add the entries to `dispatch(prompt=...)` yourself. That repeats
    them, and `prompt=` replaces the agent's own prompt rather than adding to
    it.

    To render the entries differently, pass `context_prompt=` to `dispatch`. It
    receives the entries and returns the block, or `None` to leave them out:

    ```python title="agent.py"
    def colleagues_only(entries):
        lines = [f"- {e.value}" for e in entries if "colleagues" in e.description]
        return "## Colleagues\n\n" + "\n".join(lines) if lines else None

    stream.dispatch(message, accept=accept, context_prompt=colleagues_only)
    ```

  </Step>
  <Step>
    ### Pass a context value to your tools (optional)

    To give a tool the value itself, decode the entry from
    `RunAgentInput.context` and pass it as a conversation variable. The
    `Variable()` annotation injects it into the tool, so the model does not
    have to pass it around. A value that the frontend passed as an object or an
    array arrives as a JSON string.

    ```python title="agent.py"
    import json
    from typing import Annotated

    from fastapi import FastAPI, Header
    from fastapi.responses import StreamingResponse

    from ag2 import Agent, Variable, tool
    from ag2.ag_ui import AGUIStream, RunAgentInput
    from ag2.config import OpenAIResponsesConfig

    def get_readable(message: RunAgentInput, description: str):
        raw = next(
            (item.value for item in message.context if item.description == description),
            None,
        )
        if raw is None:
            return None
        # `useAgentContext` JSON-encodes objects and arrays, but passes a
        # plain string through untouched — so decoding is best-effort.
        try:
            return json.loads(raw)
        except json.JSONDecodeError:
            return raw

    @tool
    def get_colleagues(
        colleagues: Annotated[list, Variable(default_factory=list)],
    ) -> list:
        """Return the current user's colleagues from CopilotKit readables."""
        return colleagues

    agent = Agent(
        name="assistant",
        prompt="You are a helpful assistant that can help emailing colleagues.",
        config=OpenAIResponsesConfig(model="gpt-6-luna"),
        tools=[get_colleagues],
    )

    stream = AGUIStream(agent)
    app = FastAPI()

    @app.post("/chat")
    async def run_agent(
        message: RunAgentInput,
        accept: str | None = Header(None),
    ) -> StreamingResponse:
        colleagues = get_readable(message, "The current user's colleagues") or []
        return StreamingResponse(
            stream.dispatch(message, variables={"colleagues": colleagues}, accept=accept),
            media_type=accept or "text/event-stream",
        )
    ```

    Everything in `dispatch(variables=...)` is sent back to the browser in
    `STATE_SNAPSHOT`. Do not put secrets there. Pass them with
    `dispatch(dependencies=...)`, which never leaves the server.

  </Step>
</Steps>

Call `useAgentContext({ description, value })` once per value you want
to publish. Each call registers a dynamic context entry with the
runtime that is:

- Refreshed whenever `value` changes (React re-renders).
- Automatically removed when the component unmounts.
- Sent to the agent with every run. The Built-in Agent adds each entry to
  the system prompt. Python LangGraph agents need `CopilotKitMiddleware`
  to add the entries, and ADK agents need an instruction provider.
  Microsoft Agent Framework, CrewAI Flows and Pydantic AI agents drop the
  entries silently unless you wire them. The setup above shows the code
  for your framework.

```typescript title="src/app/demos/readonly-state-agent-context/page.tsx"
  useAgentContext({
    description: "The currently logged-in user's display name",
    value: userName,
  });
  useAgentContext({
    description: "The user's IANA timezone (used when mentioning times)",
    value: userTimezone,
  });
  useAgentContext({
    description: "The user's recent activity in the app, newest first",
    value: recentActivity,
  });
```

The `description` is important: it's a short human-readable label the
agent sees alongside the value, so it knows what to do with it. Treat
it like a parameter docstring.

Call `useAgentContext` in as many components as you like. The agent
receives every registered entry.

<Callout type="warn" title="Context values arrive as JSON strings">
  The AG-UI protocol defines a context value as a string. Therefore
  `useAgentContext` calls `JSON.stringify` on any `value` that is not already a
  string, and your agent receives the JSON text instead of the object or the
  array.

  Parse the value before you read a field from it. Use `json.loads(item["value"])`
  in Python, or `JSON.parse(item.value)` in TypeScript. If you skip the parse
  step, an index such as `colleagues[0]` returns a single character, and a shape
  check such as `isinstance(value, list)` can never pass.

  Do not stringify the value again, because that produces double encoding. A
  `value` that is already a string is sent unchanged, so no parse step is needed
  for it.
</Callout>

## Wire it to your own state [#wire-it-to-your-own-state]

`useAgentContext` doesn't care where the value comes from: local
state, a React Context, Redux, a query cache, anything. The only
requirement is that the identity of the value is stable enough for
React to avoid a render loop. In the demo we use a handful of
`useState` hooks; in a real app these would likely come from an auth
provider, a router hook, and your domain state stores.

```typescript title="src/app/demos/readonly-state-agent-context/page.tsx"
import React, { useState } from "react";
import {
  CopilotKit,
  CopilotPopup,
  useAgentContext,
} from "@copilotkit/react-core/v2";

import { ACTIVITIES, DemoLayout } from "./demo-layout";
import { useReadonlyStateAgentContextSuggestions } from "./suggestions";

export default function ReadonlyStateAgentContextDemo() {
  return (
    <CopilotKit
      runtimeUrl="/api/copilotkit"
      agent="readonly-state-agent-context"
    >
      <DemoContent />
      <CopilotPopup
        agentId="readonly-state-agent-context"
        defaultOpen={true}
        labels={{ chatInputPlaceholder: "Ask about your context..." }}
      />
    </CopilotKit>
  );
}

function DemoContent() {
  const [userName, setUserName] = useState("Atai");
  const [userTimezone, setUserTimezone] = useState("America/Los_Angeles");
  const [recentActivity, setRecentActivity] = useState<string[]>([
    ACTIVITIES[0],
    ACTIVITIES[2],
  ]);
```

## Treat entries as untrusted input [#treat-entries-as-untrusted-input]

Every entry is a claim your frontend made, and a user can change it. It
never proves who is making the request. Let entries inform the agent's
answer, but take facts that grant access, such as the authenticated user,
the workspace, or the tenant, from your server. If your agent builds its
prompt from entries, keep them apart from your own instructions, so text in
an entry can't override them.

## Try it [#try-it]

Ask the agent: "What is my name?" It answers with the value of `userName`. Change the name in your UI and ask again: the answer changes.
