Agent Read-Only Context

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.

<InlineDemo demo="readonly-state-agent-context" />

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".

How it works in code

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.
• Surfaced to the agent via the backend's CopilotKitMiddleware, which threads the entries into the model's message history on every turn.

<Snippet region="use-agent-context-call" title="frontend/src/app/page.tsx — useAgentContext" />

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.

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.

<Snippet region="context-provider-sketch" title="frontend/src/app/page.tsx — sourcing context values" />

Read-only, by design

Because the agent never sees a setter or a mutation tool for these values, there's no way for a confused LLM to "update" them. That makes useAgentContext the right tool whenever the value in question is an input, not a field: the "context object passed to the agent on every turn", rather than "shared workspace you both edit".

When you need both reads and writes, you want full shared state instead.

Related

• Shared State (overview) — bidirectional reads + writes.
• State streaming — stream agent-written state back to the UI during a run.

<FeatureIntegrations feature="readonly-state-agent-context" />