system agents: generalise the scheduler and add the two memory lints
Nightly Build / build (push) Successful in 7m14s

Memory is kept as a maintained wiki, and a wiki nobody prunes rots. This adds
the scheduled maintenance pass, and generalises the machinery TIC had grown so
that a background agent is a trait impl rather than a loop of its own.

Two lint agents, not one. The private pass runs per user over `user-memory/`
and reports to them; the shared pass runs once over `shared-memory/`, where the
interesting defect is different — a note failing the table rule, i.e. private
business written where every member can read it. It names the note and the
category without repeating the content, since restating it spreads the very
thing being flagged. Both share `agents/common/memory-lint.md`.

Both are read-only, and that is enforced twice: the prompt says report-never-
repair, and `shared-memory/*` writes are already `@fs_write require`, so an
agent that tried to fix something would raise an approval card from an
unattended pass, which is auto-denied. Read-only is the only design that works
here, not merely the safe one.

One scheduler for cadences three orders of magnitude apart. TIC runs every few
minutes, a lint weekly — the case that tempts a second loop. It stays one
because the wake-up decides nothing: `base_tick` picks only how often to look,
and whether an agent runs for a user is `is_due` against persisted state.

Due-ness moves out of the run log into a new owner table, `system_agent_state`.
The two answer different questions: the run log skips idle ticks so it stays a
history rather than a heartbeat, while scheduling needs every attempt. Reading
due-ness off the log would re-run an idle agent on every tick and never bring a
weekly one due once its last productive run aged out. Persisting it is also
what makes a long interval survive a restart — an in-memory deadline is fine at
TIC's scale, but a weekly agent on a box rebooted every few days would have it
re-armed before it ever fired.

The shared store belongs to nobody, so `AgentScope::Instance` runs that pass as
the first unlocked admin. An ownerless run would write its trace into system.db,
which the runs endpoint shows to nobody by design, and its notify() would have
no recipient; attributing it to a user keeps the whole per-user surface working
unchanged.

Settings move to where the run log is. `ConfigSet` gains `owner`, so placement
is data on the set rather than a page that knows set names; the System agents
page grows one tab per agent holding its description, its settings (admin only)
and its runs — "why did this do nothing last night?" is half a schedule
question and half a log question. The form is shared with the Config page, and
writes still go through PUT /api/config/{key}.

Fixes an authorization gap found on the way: neither /api/config handler took
the caller into account, so any authenticated session could read and write
instance-wide config. The sidebar hiding the page is presentation, not access
control. Both are now admin-gated.
This commit is contained in:
2026-07-28 21:24:16 +01:00
parent 4b1affa600
commit 434e27d7c2
34 changed files with 2194 additions and 612 deletions
+19
View File
@@ -0,0 +1,19 @@
{
"name": "Shared memory lint",
"description": "Hidden background agent. Spawned periodically by the system-agent scheduler, once per instance, running as the admin. Reads the group's `shared-memory/` store and reports drift via notify(), with particular attention to notes that fail the table rule — private business written where every member can read it. Read-only: it never edits memory, and reports such a note without repeating its contents. Ephemeral: the session is discarded as soon as the turn ends.",
"friendly_description": "Weekly check-up of the group's shared memory: flags private things written in a place everyone can read, facts nobody is attached to, questions still waiting on someone, and notes that have gone out of date. It only ever reports — it never changes anything.",
"i18n": {
"it": {
"name": "Manutenzione memoria condivisa",
"friendly_description": "Controllo settimanale della memoria condivisa: segnala cose private finite dove tutti possono leggerle, fatti senza un nome accanto, domande ancora in attesa di risposta e note ormai scadute. Si limita a segnalare — non modifica mai nulla."
},
"fr": {
"name": "Entretien de la mémoire partagée",
"friendly_description": "Vérification hebdomadaire de la mémoire partagée : signale ce qui est privé mais écrit là où tout le monde peut le lire, les faits sans auteur, les questions encore en attente et les notes périmées. Elle se contente de signaler — elle ne modifie jamais rien."
}
},
"type": "system",
"inject_skills": false,
"inject_memory": ["shared-memory/index.md"],
"strength": "medium"
}