package notify import ( "io" "log" "sync" "testing" "time" ) // Operator ruling 2026-09-15 (decision A) — "box is down" mail is not swallowed by the quiet hour. // BIGNIGHT F9: a node_stale 39 minutes after F8's node_stale was suppressed by the 1-hour cooldown. // // RED-PROOF (run 2026-09-15, recorded in REPORT.md): with operatorCooldownFor returning the hour for // every type (the pre-ruling behaviour), the 39-minute node_stale was suppressed and this failed at // "node_stale 39 min after the previous one was suppressed". func TestOperatorCooldown_NodeLivenessBypassesQuietHour(t *testing.T) { st := newDispStore(t) d := NewDispatcher(st, "test-key", "from@felhom.eu", "op@felhom.eu", true, log.New(io.Discard, "", 0)) var mu sync.Mutex sent := 0 d.sendEmailFn = func(string, string, string, map[string]string) error { mu.Lock() defer mu.Unlock() sent++ return nil } count := func() int { mu.Lock(); defer mu.Unlock(); return sent } // The previous node_stale mail went 39 minutes ago. d.mu.Lock() d.opCooldowns["c1:host_stale"] = time.Now().Add(-39 * time.Minute) d.opCooldowns["c1:node_stale"] = time.Now().Add(-39 * time.Minute) d.opCooldowns["c1:app_start_failed"] = time.Now().Add(-39 * time.Minute) d.mu.Unlock() d.processOperator("c1", "node_stale", "warning", "box stale", "{}", "hub") if count() != 1 { t.Fatalf("node_stale 39 min after the previous one was suppressed (sent=%d) — the BIGNIGHT F9 silence", count()) } // A flap 1 minute later is deduped. d.processOperator("c1", "node_stale", "warning", "box stale again", "{}", "hub") if count() != 1 { t.Fatalf("node_stale 1 min after a sent one was mailed again (sent=%d) — the 5-minute dedupe is gone", count()) } // Ruling 2: the same for a HOST-plane mail, 39 minutes after the last one. d.processOperator("c1", "host_stale", "warning", "host stale", "{}", "hub") if count() != 2 { t.Fatalf("host_stale 39 min after the previous one was suppressed (sent=%d) — ruling 2 (R-529)", count()) } // The design is unchanged for every other type: still the hour. d.processOperator("c1", "app_start_failed", "warning", "app down", "{}", "hub") if count() != 2 { t.Fatalf("a non-liveness type lost its 1-hour cooldown (sent=%d)", count()) } for _, et := range []string{"node_down", "node_recovered"} { if operatorCooldownFor(et) != nodeLivenessDedupeWindow { t.Fatalf("%s is not in the ruling's bypass", et) } } // Ruling 2 (2026-09-16, R-529): the host-plane siblings joined the bypass. for _, et := range []string{"host_stale", "host_down", "host_recovered"} { if operatorCooldownFor(et) != nodeLivenessDedupeWindow { t.Fatalf("%s must bypass the quiet hour too (operator ruling 2026-09-16)", et) } } // A type in neither ruling keeps the hour — the design is narrowed, not removed. if operatorCooldownFor("storage_disconnected") != operatorCooldown { t.Fatal("an unrelated type lost its 1-hour cooldown") } }