Skip to documentation
Docs navigation
Docs/graft()
MemoGrafterAgent

graft()

Assemble prompt context from explicitly selected topics.

What it does

Assemble prompt context from explicitly selected topics.

When to use it

Use when the application already knows which topic IDs should supply broader context.

Signature

TypeScript
graft(topicIds?: string[]): Promise<InjectionResult>

Parameters

topicIds? (string[]) — Topic identifiers to include in the generated context.

InjectionResult fields

systemPrompt is the assembled context; this operation does not itself call the chat model.
nodes are selected topics and memories contains their active structured facts when included.
tokenCount is the assembled size; tokenBudget is present when a budget governed assembly.

Result

The selected memory context and prompt text ready to pass to an LLM.

Behavior

Loads active memories for the selected topics and assembles an LLM-ready system prompt. With no IDs, it uses eligible topics from the agent session.

Side effects and completion

Read-only; grafting previews context and does not copy memory or call the LLM.

Example

example.ts
const injection = await agent.graft([topicId]);