From c7729b2ef64a47d377a8b20dd72fff79a9d67d0d Mon Sep 17 00:00:00 2001
From: dtoro <d.toro.v@pm.me>
Date: Wed, 29 Jul 2026 13:37:08 +0200
Subject: [PATCH] fix(scheduler): stop monitoring deprecated/destroyed targets
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ListEnabledCheckDefs now LEFT JOINs the target entity and excludes rows whose
target is deprecated or destroyed, so retired things (secrets-issuance,
homelab-mcp, the dead secrets ingress route) stop generating permanent false
alarms instead of waiting for an operator to disable the check_def by hand.

coverageSweep's None() branch previously did nothing, so a type changed from
declared monitoring to `monitoring: none` (dns-zone) left its open
`unmonitored` signals lingering forever — a None() entity never gains a check,
so the hasCheck resolution path never fired. It now resolves those signals.
---
 internal/db/queries/operations.sql    |  2 ++
 internal/db/sqlcgen/operations.sql.go |  2 ++
 internal/scheduler/coverage.go        | 11 ++++++++++-
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/internal/db/queries/operations.sql b/internal/db/queries/operations.sql
index 0742d55..03a261a 100644
--- a/internal/db/queries/operations.sql
+++ b/internal/db/queries/operations.sql
@@ -63,7 +63,9 @@ SELECT cd.entity_id, cd.target_id, cd.target_type, cd.kind, cd.config,
        e.slug AS entity_slug
 FROM check_defs cd
 JOIN entities e ON e.id = cd.entity_id
+LEFT JOIN entities tgt ON tgt.id = cd.target_id
 WHERE cd.enabled = true
+  AND (tgt.id IS NULL OR tgt.state NOT IN ('deprecated', 'destroyed'))
   AND (cd.last_run_at IS NULL
        OR cd.last_run_at <= now() - make_interval(secs => cd.interval_s));
 
diff --git a/internal/db/sqlcgen/operations.sql.go b/internal/db/sqlcgen/operations.sql.go
index 4424565..637d7b2 100644
--- a/internal/db/sqlcgen/operations.sql.go
+++ b/internal/db/sqlcgen/operations.sql.go
@@ -696,7 +696,9 @@ SELECT cd.entity_id, cd.target_id, cd.target_type, cd.kind, cd.config,
        e.slug AS entity_slug
 FROM check_defs cd
 JOIN entities e ON e.id = cd.entity_id
+LEFT JOIN entities tgt ON tgt.id = cd.target_id
 WHERE cd.enabled = true
+  AND (tgt.id IS NULL OR tgt.state NOT IN ('deprecated', 'destroyed'))
   AND (cd.last_run_at IS NULL
        OR cd.last_run_at <= now() - make_interval(secs => cd.interval_s))
 `
diff --git a/internal/scheduler/coverage.go b/internal/scheduler/coverage.go
index ae07051..be53fbf 100644
--- a/internal/scheduler/coverage.go
+++ b/internal/scheduler/coverage.go
@@ -85,7 +85,16 @@ func coverageSweep(ctx context.Context, pool *db.Pool) {
 		case !mon.Declared:
 			undeclared++
 		case mon.None():
-			// Explicitly unmonitorable. Nothing to say.
+			// Explicitly unmonitorable. Nothing to raise — but a type that
+			// USED to declare monitoring (e.g. dns-zone, [dns]→none) may have
+			// open `unmonitored` signals from before the change. They are no
+			// longer a gap, so close them; otherwise they linger forever,
+			// because resolveCoverageSignal only runs from the hasCheck path
+			// and a None() entity never gains a check.
+			if resolveCoverageSignal(ctx, pool, e.id) {
+				resolved++
+				slog.Info("scheduler: type now unmonitorable, resolving stale signal", "entity", e.slug)
+			}
 		case e.hasCheck:
 			if resolveCoverageSignal(ctx, pool, e.id) {
 				resolved++