2026-09-05 10:27:11 +00:00
1 changed files with 27 additions and 5 deletions
@@ -115,6 +115,33 @@ states for an agent's config directory, with the root standing in for it.
 a licence is observed and its binding changed; the binding is then declared as usual. Nothing here
 grows a conditional in the declaration language.

+## What it remembers, and where
+
+**A session's memory lives in its context root**, beside its engram and its tools. That is the
+same rule as everything else here rather than a new one: the root is the whole of what makes one
+session a different agent from another, and memory is part of what makes it *that* agent.
+
+**The mesh session's memory is its own.** It is not assembled from the node sessions on demand,
+and it is not a view over theirs. What the mesh has been asked, and what it worked out, is held
+in the mesh's root — not in the root of the node that happens to host it.
+
+**That distinction is the point of putting it there.** The control-plane node runs two sessions
+on one machine. If memory belonged to the machine rather than to the root, they would share it,
+and the mesh's recollection of a fortnight of questions would be indistinguishable from that
+node's own — which is the collision ADR 0026 exists to avoid, arriving through the back door.
+
+**The root holds two kinds of thing, and confusing them destroys the memory.** The engram and the
+tools are **declared**: the mesh says what they are and the host writes them, so editing one on
+the machine survives until the next heartbeat and no longer
+([ADR 0011](../../02-DECISIONS/0011-managed-files-are-generated-never-edited.md)). The memory is
+**written by the session itself** and is declared by nobody — the mesh does not get to say what a
+session remembers, and a mechanism that regenerates the root wholesale would erase a fortnight of
+it on the next pass, silently, while reporting success.
+
+So the root is not uniformly managed, and **which parts are must be explicit rather than
+inferred**. A session's memory is its own output, kept across restarts, backed up as data rather
+than reproduced from a declaration — because there is nothing to reproduce it from.
+
 ## What the mesh session knows

 **It holds the design record by reading it**
@@ -182,11 +209,6 @@ stopped telling the truth.

 ## Deliberately not decided

-**Whether the mesh session's memory is its own or assembled from the node sessions each time.**
-It remembers what it has been asked, which is settled. Whether *what the mesh knows* is a thing it
-holds or a thing it gathers on demand is a real question with a cost either way, and nothing here
-depends on the answer yet.
-
 **How a person's identity reaches a session.** Callers are distinguished, but who a caller *is*,
 and whether a session should act differently for different people, is the human-agent question
 ADR 0001 leaves open and this does not close.