---
title: "Comment by Vlad Zoff on \"Session memory is not project memory. It fixes the same complaint.\" | Hashnode"
description: "I'd add validity metadata to promoted knowledge: source or commit, scope, owner, and what superseded it. An architectural decision can be durable but apply only"
url: "https://hashnode.com/posts/session-memory-is-not-project-memory-it-fixes-the-same-complaint/6ab3ae06ab5703ad22d98586/comment/6ae833e119be44d2c35fb36b"
---

[Discussion](https://hashnode.com/posts/session-memory-is-not-project-memory-it-fixes-the-same-complaint/6ab3ae06ab5703ad22d98586)

Comment [Session memory is not project memory. It fixes the same complaint.](https://hashnode.com/posts/session-memory-is-not-project-memory-it-fixes-the-same-complaint/6ab3ae06ab5703ad22d98586)

[Vlad Zoff](https://hashnode.com/@vladzoff)

[Nov 2](https://hashnode.com/posts/session-memory-is-not-project-memory-it-fixes-the-same-complaint/6ab3ae06ab5703ad22d98586/comment/6ae833e119be44d2c35fb36b)

I'd add validity metadata to promoted knowledge: source or commit, scope, owner, and what superseded it. An architectural decision can be durable but apply only to one module or version. Without scope and freshness, project memory becomes another stale source of truth. Agents should revalidate older notes against the current code and tests before treating them as constraints.