fix(scheduler): derive entity health from all its checks, not the last one

host:strong logged 226 health.changed events in one hour, oscillating
down/healthy while the host was fine throughout. host:hubris did it 126 times.

runCheck wrote entity_status.health on every check completion, so an entity's
health was simply whichever of its checks finished most recently. A host with
six checks reported whichever facet happened to be sampled last, and one
failing probe alternating with five passing ones flapped forever. resolveSignal
forced "healthy" too, a second path by which one passing probe erased another
probe's genuine failure.

On this fleet the trigger is a known false positive: the scheduler's network
vantage point cannot ICMP host:strong, so its ping check fails while every
ssh-script check succeeds. Under last-writer-wins that single probe declared
the whole host down, twice a minute.

Each check now records its own verdict (check_defs.last_health, migration 027)
and the entity's health is the worst across its enabled checks. A failing probe
now degrades the entity honestly and *stably*, without erasing what the other
five report, and health.changed fires only when that aggregate actually moves.
Checks that have never run are ignored rather than counted as unknown, so
adding a check cannot drag a known-good entity down before it has a verdict.

Also declares service:oikos in the seed. The previous commit re-pointed the mcp
ingress at it, but the entity only ever existed in the production database — so
a fresh seed (a new install, or a DR restore) failed on an unresolvable edge.
Caught by seeding an empty database rather than a copy of prod, which is the
only way that class of bug shows up.

Co-Authored-By: Claude <noreply@anthropic.com>

internal/db/queries/operations.sql

@@ -68,7 +68,21 @@ WHERE cd.enabled = true
        OR cd.last_run_at <= now() - make_interval(secs => cd.interval_s));
 
 -- name: MarkCheckRun :exec
-UPDATE check_defs SET last_run_at = now() WHERE entity_id = $1;
+UPDATE check_defs SET last_run_at = now(), last_health = $2 WHERE entity_id = $1;
+
+-- name: WorstHealthForTarget :one
+-- An entity is as healthy as its unhealthiest check. Checks that have not run
+-- yet (last_health IS NULL) are ignored rather than counted as unknown, so a
+-- newly added check does not drag a known-good entity down before it has
+-- produced a verdict.
+SELECT COALESCE(
+  (SELECT last_health FROM check_defs
+   WHERE enabled AND target_id = $1 AND last_health IS NOT NULL
+   ORDER BY CASE last_health
+     WHEN 'down' THEN 0 WHEN 'degraded' THEN 1 WHEN 'stale' THEN 2
+     WHEN 'unknown' THEN 3 ELSE 4 END
+   LIMIT 1),
+  'unknown')::text AS health;
 
 -- name: GetCheckDef :one
 SELECT * FROM check_defs WHERE entity_id = $1;

internal/db/sqlcgen/models.go

@@ -114,6 +114,8 @@ type CheckDef struct {
 	UpdatedAt  time.Time
 	// When this check last executed. NULL = never, due immediately. Compared against interval_s to decide due-ness.
 	LastRunAt *time.Time
+	// This check's own most recent verdict (healthy/degraded/down/unknown). entity_status.health is the worst of these across the target's enabled checks.
+	LastHealth *string
 }
 
 type Classification struct {
@@ -255,6 +257,20 @@ type KnowledgeEntity struct {
 	UpdatedAt   time.Time
 	ContentHash *string
 	Search      interface{}
+	EditedBy    string
+	DeletedAt   *time.Time
+}
+
+type KnowledgeRevision struct {
+	ID        int64
+	EntityID  uuid.UUID
+	Title     string
+	Content   string
+	Source    *string
+	Tags      []string
+	EditedBy  string
+	VersionAt time.Time
+	RevisedAt time.Time
 }
 
 type Ledger struct {

internal/db/sqlcgen/operations.sql.go

@@ -51,7 +51,7 @@ func (q *Queries) GetAutonomySetting(ctx context.Context, key string) (string, e
 }
 
 const getCheckDef = `-- name: GetCheckDef :one
-SELECT entity_id, target_id, target_type, kind, config, interval_s, timeout_s, zone, enabled, updated_at, last_run_at FROM check_defs WHERE entity_id = $1
+SELECT entity_id, target_id, target_type, kind, config, interval_s, timeout_s, zone, enabled, updated_at, last_run_at, last_health FROM check_defs WHERE entity_id = $1
 `
 
 func (q *Queries) GetCheckDef(ctx context.Context, entityID uuid.UUID) (CheckDef, error) {
@@ -69,6 +69,7 @@ func (q *Queries) GetCheckDef(ctx context.Context, entityID uuid.UUID) (CheckDef
 		&i.Enabled,
 		&i.UpdatedAt,
 		&i.LastRunAt,
+		&i.LastHealth,
 	)
 	return i, err
 }
@@ -1133,11 +1134,16 @@ func (q *Queries) ListSkills(ctx context.Context, status *string) ([]Skill, erro
 }
 
 const markCheckRun = `-- name: MarkCheckRun :exec
-UPDATE check_defs SET last_run_at = now() WHERE entity_id = $1
+UPDATE check_defs SET last_run_at = now(), last_health = $2 WHERE entity_id = $1
 `
 
-func (q *Queries) MarkCheckRun(ctx context.Context, entityID uuid.UUID) error {
+type MarkCheckRunParams struct {
-	_, err := q.db.Exec(ctx, markCheckRun, entityID)
+	EntityID   uuid.UUID
+	LastHealth *string
+}
+
+func (q *Queries) MarkCheckRun(ctx context.Context, arg MarkCheckRunParams) error {
+	_, err := q.db.Exec(ctx, markCheckRun, arg.EntityID, arg.LastHealth)
 	return err
 }
 
@@ -1462,3 +1468,25 @@ func (q *Queries) UpsertSignal(ctx context.Context, arg UpsertSignalParams) (Sig
 	)
 	return i, err
 }
+
+const worstHealthForTarget = `-- name: WorstHealthForTarget :one
+SELECT COALESCE(
+  (SELECT last_health FROM check_defs
+   WHERE enabled AND target_id = $1 AND last_health IS NOT NULL
+   ORDER BY CASE last_health
+     WHEN 'down' THEN 0 WHEN 'degraded' THEN 1 WHEN 'stale' THEN 2
+     WHEN 'unknown' THEN 3 ELSE 4 END
+   LIMIT 1),
+  'unknown')::text AS health
+`
+
+// An entity is as healthy as its unhealthiest check. Checks that have not run
+// yet (last_health IS NULL) are ignored rather than counted as unknown, so a
+// newly added check does not drag a known-good entity down before it has
+// produced a verdict.
+func (q *Queries) WorstHealthForTarget(ctx context.Context, targetID *uuid.UUID) (string, error) {
+	row := q.db.QueryRow(ctx, worstHealthForTarget, targetID)
+	var health string
+	err := row.Scan(&health)
+	return health, err
+}

internal/scheduler/scheduler.go

@@ -115,8 +115,16 @@ func runCheck(ctx context.Context, pool *db.Pool, cd sqlcgen.ListEnabledCheckDef
 
 	// Stamp the run before processing the result: due-ness must advance even
 	// when a check fails, or a permanently failing check would be re-run on
-	// every pass instead of at its declared interval.
+	// every pass instead of at its declared interval. last_health records THIS
-	if err := q.MarkCheckRun(ctx, cd.EntityID); err != nil {
+	// check's own verdict, which is what makes the aggregation below possible.
+	checkHealth := result.health
+	if checkHealth == "" {
+		checkHealth = "healthy"
+	}
+	if err := q.MarkCheckRun(ctx, sqlcgen.MarkCheckRunParams{
+		EntityID:   cd.EntityID,
+		LastHealth: &checkHealth,
+	}); err != nil {
 		slog.Error("scheduler: mark check run", "entity", cd.EntitySlug, "error", err)
 	}
 
@@ -150,16 +158,12 @@ func runCheck(ctx context.Context, pool *db.Pool, cd sqlcgen.ListEnabledCheckDef
 
 	if result.signalKind == "" || result.health == "healthy" {
 		resolveSignal(ctx, pool, cd.EntityID, targetID, cd.EntitySlug)
-		_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
+		// NOT unconditionally "healthy": this check passing says nothing about
-			EntityID:    targetID,
+		// the entity's other checks. Writing healthy here is what let one
-			Health:      "healthy",
+		// passing probe erase a genuine failure reported by another — and,
-			LastCheckAt: &[]time.Time{time.Now()}[0],
+		// alternating with a failing probe, produced 226 health flips an hour
-			Details:     []byte(`{}`),
+		// on a host that was fine throughout.
-		})
+		applyAggregateHealth(ctx, pool, q, targetID, cd.EntitySlug, prevHealth)
-		if prevHealth != "" && prevHealth != "healthy" {
-			emitSchedulerEvent(ctx, pool, "health.changed", targetID, "info",
-				map[string]any{"slug": cd.EntitySlug, "from": prevHealth, "to": "healthy"})
-		}
 		return
 	}
 
@@ -180,22 +184,52 @@ func runCheck(ctx context.Context, pool *db.Pool, cd sqlcgen.ListEnabledCheckDef
 		return
 	}
 
-	_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
-		EntityID:    targetID,
-		Health:      result.health,
-		LastCheckAt: &[]time.Time{time.Now()}[0],
-		Details:     []byte(`{}`),
-	})
 	_ = sig
 
 	if prevHealth == "" || prevHealth == "healthy" {
 		emitSchedulerEvent(ctx, pool, "signal.raised", targetID, severity,
 			map[string]any{"slug": cd.EntitySlug, "kind": result.signalKind, "evidence": result.evidence})
 	}
-	if prevHealth != result.health {
+	applyAggregateHealth(ctx, pool, q, targetID, cd.EntitySlug, prevHealth)
-		emitSchedulerEvent(ctx, pool, "health.changed", targetID, severity,
+}
-			map[string]any{"slug": cd.EntitySlug, "from": prevHealth, "to": result.health})
+
+// applyAggregateHealth sets the target's health to the worst verdict across
+// all of its enabled checks, and emits health.changed only when that aggregate
+// actually moves.
+//
+// Health is a property of the entity, but each check only ever observes one
+// facet of it — reachability, disk, a systemd unit. Letting whichever check
+// finished last overwrite the entity's health meant a host with six checks
+// reported whichever facet was sampled most recently, so one failing probe and
+// five passing ones oscillated forever instead of settling on "degraded".
+func applyAggregateHealth(ctx context.Context, pool *db.Pool, q *sqlcgen.Queries,
+	targetID uuid.UUID, checkSlug, prevHealth string) {
+
+	health, err := q.WorstHealthForTarget(ctx, &targetID)
+	if err != nil {
+		slog.Error("scheduler: aggregate health", "entity", checkSlug, "error", err)
+		return
 	}
+
+	_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
+		EntityID:    targetID,
+		Health:      health,
+		LastCheckAt: &[]time.Time{time.Now()}[0],
+		Details:     []byte(`{}`),
+	})
+
+	if prevHealth == health {
+		return
+	}
+	severity := "info"
+	switch health {
+	case "down":
+		severity = "critical"
+	case "degraded", "stale":
+		severity = "warning"
+	}
+	emitSchedulerEvent(ctx, pool, "health.changed", targetID, severity,
+		map[string]any{"slug": checkSlug, "from": prevHealth, "to": health})
 }
 
 // currentHealth reads the last recorded health for an entity, or "" if none.
@@ -217,7 +251,6 @@ func emitSchedulerEvent(ctx context.Context, pool *db.Pool, eventType string, en
 // checkID matches how signals are keyed (UpsertSignal uses the check's own
 // entity id); targetID is the observed entity whose status this affects.
 func resolveSignal(ctx context.Context, pool *db.Pool, checkID, targetID uuid.UUID, slug string) {
-	q := sqlcgen.New(pool)
 	// Check if there's an open signal on this entity
 	tag, err := pool.Exec(ctx, `UPDATE signals SET state = 'resolved', updated_at = now()
 		WHERE entity_id = $1 AND state = 'raised'`, checkID)
@@ -227,14 +260,12 @@ func resolveSignal(ctx context.Context, pool *db.Pool, checkID, targetID uuid.UU
 	if tag.RowsAffected() > 0 {
 		emitSchedulerEvent(ctx, pool, "signal.resolved", targetID, "info",
 			map[string]any{"slug": slug})
+		slog.Info("scheduler: signal resolved", "entity", slug)
 	}
-	_ = q.UpsertEntityStatus(ctx, sqlcgen.UpsertEntityStatusParams{
+	// Deliberately does NOT write health. Resolving THIS check's signal says
-		EntityID:    targetID,
+	// nothing about the target's other checks; the caller re-derives health
-		Health:      "healthy",
+	// from all of them. Forcing "healthy" here was a second path by which one
-		LastCheckAt: &[]time.Time{time.Now()}[0],
+	// passing probe erased another probe's genuine failure.
-		Details:     []byte(`{}`),
-	})
-	slog.Info("scheduler: signal resolved", "entity", slug)
 }
 
 // checkResult bundles the outcome of a single check execution.

migrations/027_check_last_health.up.sql

@@ -0,0 +1,28 @@
+-- 027_check_last_health.up.sql
+-- Aggregate an entity's health across its checks instead of last-writer-wins.
+--
+-- runCheck wrote entity_status.health on every check completion, so an
+-- entity's health was simply whichever of its checks finished most recently.
+-- host:hubris has 6 checks, host:strong 6 — one failing probe alternating with
+-- five passing ones produced a permanent flap: 226 health.changed events for
+-- host:strong in a single hour, oscillating down/healthy, while the host was
+-- fine the whole time.
+--
+-- On this fleet the trigger is a known false positive: the scheduler's network
+-- vantage point cannot ICMP host:strong, so its ping check fails while every
+-- ssh-script check succeeds. Under last-writer-wins that one probe was enough
+-- to declare the whole host down, twice a minute.
+--
+-- Storing each check's own verdict lets entity health be derived as the worst
+-- current result across that entity's enabled checks — so a single failing
+-- probe degrades the entity honestly without erasing what the other five say,
+-- and a passing probe cannot mask a genuine failure elsewhere.
+
+ALTER TABLE check_defs ADD COLUMN IF NOT EXISTS last_health TEXT;
+
+COMMENT ON COLUMN check_defs.last_health IS 'This check''s own most recent verdict (healthy/degraded/down/unknown). entity_status.health is the worst of these across the target''s enabled checks.';
+
+-- The aggregation reads every enabled check for one target on each completion.
+CREATE INDEX IF NOT EXISTS idx_check_defs_target_health
+  ON check_defs (target_id)
+  WHERE enabled AND target_id IS NOT NULL;

seeds/inventory.yaml

@@ -270,6 +270,15 @@ entities:
      attributes: {url: "https://teddy.hubris.network",
                   doc_page: knowledge/wiki/containers/131-teddycloud.md,
                   risk_notes: "no forward-auth gate — reachable by anyone on LAN/mesh"}}
+  # The Go control plane itself: api/scheduler/notifier/web on the mac-mini,
+  # and what mcp.hubris.network fronts since the cutover. It existed in the
+  # database (created outside the seed) but was never declared here, so a
+  # fresh seed could not resolve the routes-to edge below.
+  - {slug: "service:oikos", type: service, name: oikos,
+     attributes: {url: "https://oikos.hubris.network",
+                  host: "ws:mac-mini",
+                  ports: {api: 8090, web: 8091, nomos_gateway: 8092},
+                  note: "homelab automation platform — api/scheduler/notifier/web on mac-mini docker compose (project name oikos)"}}
   - {slug: "service:homelab-mcp", type: service, name: homelab_mcp,
      attributes: {port: 9810, systemd_unit: homelab-mcp,
                   endpoint: "https://mcp.hubris.network/mcp",
@@ -451,6 +460,7 @@ relationships:
   # fronts the Go api. Nomos recorded this correctly on 2026-07-12; the seed
   # was the stale one, and re-asserting the old edge alongside it is what made
   # ingress:mcp a cardinality violation.
+  - {source: "ws:mac-mini", target: "service:oikos", type: provides}
   - {source: "ingress:mcp.hubris.network", target: "service:oikos", type: routes-to}
   - {source: "ingress:secrets.hubris.network", target: "service:secrets-issuance", type: routes-to}
   - {source: "ingress:house.hubris.network", target: "service:house", type: routes-to}