# Agent Read-Only Context

> Send UI values to the agent as a one-way, read-only channel with useAgentContext.

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

Sometimes you want the agent to *know* something about the current UI, like the signed-in user, the open screen, or a recent activity log, but you don't want the agent to change 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 write state back to the UI, `useAgentContext` values are pure inputs. The agent sees them on every turn, but it has no setter and no tool to write them back.

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

Use `useAgentContext` instead of full shared state when:

- The value is **UI-owned** and means nothing 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, open screen).
- You want the value to go away when the component unmounts. For example, the "current record" context disappears when the user leaves that screen.

Think of it as "props for the agent".

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

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

<Callout type="warn" title="CrewAI needs a `context` field on your state class">
  A CrewAI Flow does **not** receive `useAgentContext` entries automatically,
  and nothing tells you so. The AG-UI bridge writes the entries to a `context`
  key in the run state, but `CopilotKitState` does not declare `context`. Flow
  state is a Pydantic model, so Pydantic drops the key before any `@start()`
  method runs. Reading it raises nothing, and the Flow still answers fluently,
  in the right shape, from nothing.
</Callout>

<Steps>
  <Step>
    ### Declare `context` on your state class

    Subclass `CopilotKitState` as usual and add the field yourself.

    ```python title="flow.py"
    from typing import Any

    from ag_ui_crewai import CopilotKitState
    from pydantic import Field


    class ChatState(CopilotKitState):
        # Without this field Pydantic drops the entries the bridge just wrote.
        context: list[Any] = Field(default_factory=list)
    ```

    Each entry is a dict with the `description` and `value` you registered on
    the frontend. `value` arrives JSON-encoded as a string for anything that is
    not already a string.

  </Step>
  <Step>
    ### Put the entries in front of the model

    Declaring the field makes the entries reachable. It does not put them in
    the prompt. Fold them into the text your model reads:

    ```python title="flow.py"
    import json

    from crewai.flow.flow import Flow, start
    from litellm import acompletion

    from ag_ui_crewai import copilotkit_stream


    class ChatFlow(Flow[ChatState]):
        @start()
        async def chat(self) -> None:
            state = self.state.model_dump(exclude={"messages", "copilotkit"})
            state_context = json.dumps(state, default=str, sort_keys=True)
            response = await copilotkit_stream(
                await acompletion(
                    reasoning_effort="none",
                    allowed_openai_params=["reasoning_effort"],
                    model="openai/gpt-6-luna",
                    messages=[
                        {
                            "role": "system",
                            "content": (
                                f"{SYSTEM_PROMPT}\n\n"
                                f"Application context: {state_context}"
                            ),
                        },
                        *self.state.messages,
                    ],
                    tools=self.state.copilotkit.actions or None,
                    stream=True,
                )
            )
            # A Flow's return value is not sent to the UI. Append the answer to
            # `messages`, or the turn finishes with nothing rendered.
            self.state.messages.append(response.choices[0].message)
    ```

    <Callout>
      If a Crew does the work, pass the rendered context through
      `crew.kickoff_async(inputs={...})` and reference it as a
      `{placeholder}` in the task description. Do not format it into the
      description string yourself: CrewAI interpolates `{placeholder}` from
      `inputs`, so context full of JSON braces would be read as more
      placeholders.
    </Callout>

  </Step>
  <Step>
    ### Check it against an empty context

    This integration fails quietly, so check the answer against your own
    records. The reliable check is a control: send the same request once with
    the context and once with an empty context. Two answers that describe the
    same record mean the context changed nothing.

  </Step>
</Steps>

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

- Refreshed whenever `value` changes.
- 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.

```tsx title="src/ProfileScreen.tsx"
import { Text, View } from "react-native";
import { useAgentContext } from "@copilotkit/react-native/headless";

export function ProfileScreen({
  userName,
  timezone,
  recentActivity,
}: {
  userName: string;
  timezone: string;
  recentActivity: string[];
}) {
  useAgentContext({ // [!code highlight:4]
    description: "The signed-in user's name and timezone",
    value: { userName, timezone },
  });

  useAgentContext({
    description: "The last actions the user took in the app, newest first",
    value: recentActivity,
  });

  return (
    <View style={{ padding: 16 }}>
      <Text>Signed in as {userName}</Text>
    </View>
  );
}
```

The `description` matters. It's a short label the agent sees next to 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 entry that is registered at the time of the run.

<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, or your navigation state. The value must be JSON-serializable. Its serialized form is compared on each render, so a new object with the same contents does not register the entry again.

## Rendering data does not send it [#rendering-data-does-not-send-it]

A screen that renders a list has put the list in the view tree, not in the agent's context. Those are separate steps. An agent without the second step still answers: the text reads well, the values look plausible, and nothing errors.

Register the data with `useAgentContext`, and tell the agent in its instructions to refuse to answer about records that the context doesn't carry. Then check one answer against the records your app actually holds.

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

Every entry is a claim your app 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 app and ask again: the answer changes.

For every option, see the [`useAgentContext` reference](/reference/react-native/hooks/useAgentContext).
