> ## Documentation Index
> Fetch the complete documentation index at: https://docs.compose.market/llms.txt
> Use this file to discover all available pages before exploring further.

# Recall

> Assemble relevant context before an agent turn.

Recall is the first step of the memory loop. Before the agent responds, you ask the memory system for context relevant to the upcoming message. It returns a single prompt string — ranked, deduplicated, and packed to a character budget — ready to drop into the agent's system prompt.

## Assemble context

```typescript theme={null}
const context = await sdk.memory.context("What did we decide about pricing?", {
  agentWallet: "0xa7abfd271130c3ee5c8f8862a123f3697e75af0d",
  userAddress: "0xYourWalletAddress",
  threadId: "sales-7",
});

console.log(context);
// "Memory context:\n- User prefers annual billing...\n- Last discussed the Pro tier..."
```

The returned string is the only thing the model sees. You don't handle raw database rows, ranking, or deduplication — the memory system does that internally and hands you a compact block.

## Parameters

| Field               | Type     | Description                                                                  |
| ------------------- | -------- | ---------------------------------------------------------------------------- |
| `query`             | `string` | The user's upcoming message or a summary of it. Used for semantic retrieval. |
| `scope.agentWallet` | `string` | The agent whose memory you're reading.                                       |
| `scope.userAddress` | `string` | The user paired with the agent.                                              |
| `scope.threadId`    | `string` | The conversation thread. Short-term layers stay thread-local.                |

## Injecting into the agent

Pass the context as part of the system prompt when you start the stream:

```typescript theme={null}
const stream = sdk.agent.stream({
  agentWallet: "0xa7abfd271130c3ee5c8f8862a123f3697e75af0d",
  message: "What did we decide about pricing?",
  threadId: "sales-7",
});

for await (const event of stream) {
  if (event.type === "text-delta") process.stdout.write(event.delta);
}
```

The agent now answers with the prior conversation and stored facts in mind, without you manually loading history.

## Scope rules

Recall respects the same scope as the rest of memory: the **agent + user pair**. Working context and transcripts are thread-scoped, so they only appear when `threadId` matches. Durable facts cross thread boundaries, so the agent still remembers pinned preferences even in a brand-new thread.

## Related

* [Memory](/sdk/memory/overview) — the full three-step loop
* [Persist](/sdk/memory/persist) — record the turn after the agent responds
* [Memory Loop guide](/sdk/guides/memory-loop) — end-to-end example