Memory strategies

Each agent has a memory strategy that decides what conversation history it sees on each turn. Memory is scoped per (agent, session), so an agent resumes with the right history when it runs again in the same chat or graph run.

The strategies

Strategy	What it does
None	No memory — every turn starts fresh.
Window	Keep only the last N messages.
Full transcript	Store and replay the entire conversation.
Summarized	Keep a rolling summary, refreshed every N messages by a chosen model.
Episodic	Retrieve relevant past messages from a vector collection (top_k, threshold).
Semantic	Extract structured facts (via an extractor prompt) before storing them.
Composite	Stack several strategies as ordered layers, consulted and written in order.

Tip

Choosing one: short tool-running tasks → Window or None; long advisory chats → Summarized; knowledge that must persist and be recalled by relevance → Episodic or Semantic; production agents that need both recency and recall → Composite (e.g. Window + Episodic).

Where it’s set & how it resolves

• Agent default: every agent definition carries a memory_strategy (default None).
• Per-slot override: an Agent (SubAgent) node can set a memory_override for that one slot in the graph.

The effective strategy is memory_override.unwrap_or(agent.memory_strategy) — the node-level override wins for that slot, otherwise the agent’s own default applies.

Notes

• Episodic and Semantic rely on embeddings — configure your embedding model first.
• Memory writes happen automatically as the agent records each message; you don’t manage storage.
• The canonical definition is MemoryStrategy in backend/src/agents/memory/mod.rs.