The store, the remember tool and the recall path are deployed, and the strings
were grepped out of the running binary rather than inferred from a green test
run. So "built but not wired" is now wrong in the direction that undersells it.
The replacement is careful about the opposite error. A live memory and a
populated memory are different things: it accumulates from use, starts empty on
any deployment, and a memory only enters a prompt on a LATER run — so the
conversation that creates one shows no difference at all. That is the thing
most likely to be mistaken for the feature not working, so it is stated where
somebody checking would look.
The claims list is updated accordingly. "It already knows your workspace" has
replaced "the agent remembers across sessions" as the sentence most likely to
be said by accident, because the feature now works and the table is still
empty.
Also records the write trigger and why the two cheaper designs were rejected —
an extraction pass costs a whole model call per run against an 8,000 token
ceiling, and a heuristic remembers the wrong things because the shape of a run
says nothing about whether a fact outlives it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
internal/memory and migration 000017 are built and applied in production, so
the earlier "not built, deliberately" is now wrong in the direction that gets
overclaimed: the code exists, the table exists, and no answer has ever been
shaped by a memory because nothing in loop.go reads or writes one.
The document now says what the store IS — org-scoped, every personal memory
named to a subject so it can be produced or erased, provenance on each row,
ninety-day expiry, and a block that states a memory can never on its own be a
reason to accept or reject anybody — and says separately that none of it is
wired.
The claims section gains the sentence that matters: "the agent remembers across
sessions" is the thing most likely to be said by accident now, because the code
and the table both exist. Built is not the same as switched on.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Read from the code rather than from intent, after a conversation in which the
honest answer to "are we using RAG and memory correctly" took an hour of
digging that nobody should have to repeat.
It records three things that are easy to get wrong when describing this system
to somebody else: that retrieval is hybrid with the permission predicate as a
PRE-filter rather than a post-filter, that only two of nine agents use it and
that is the design, and that long-term memory is absent on purpose rather than
by omission — with the schema comment that says so quoted in place.
It also states what the document does NOT support claiming, because the failure
this guards against is overclaiming to a client, not under-documenting.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
