feat: add conversation memory pipeline

README.md

@@ -16,6 +16,7 @@ The project is framework-first rather than product-first. The current core libra
 - availability snapshots with current + next transition calculation
 - DM-style conversation orchestration for inbound replies and proactive openings
 - delegated mandatory/contextual memory retrieval pipelines for conversation turns
+- optional two-stage conversation memory extraction pipeline for durable inbound/outbound memories
 - human-like first-reply delay and typing delay utilities
 - farewell-style refusal flows that can trigger availability-changing tool calls
 
@@ -49,6 +50,16 @@ The library is now grouped by domain under `src/`:
 
 Each domain now exposes a class-based service API in addition to the existing functional helpers so consumers can organize stateful integrations more cleanly.
 
+## Conversation memory pipeline
+
+Conversation turns can now optionally run a two-stage durable-memory pipeline:
+
+1. a `classifierModel` decides whether each inbound or first-pass outbound message is worth remembering
+2. an `extractorModel` converts only approved messages into IdentityDB-ready fact drafts
+3. extracted facts are stored back into the persona space with conversation-turn trace metadata
+
+The optional `memoryPipeline` input is available on both `replyToConversation(...)` and `startConversation(...)`, so app integrations can enable long-term relationship memory without changing their storage layer.
+
 ## Release
 
 Tagging `vX.Y.Z` or `X.Y.Z` triggers the Gitea npm release workflow under `.gitea/workflows/npm-release.yml`.