hub v0.123.0: app_stopped_unhealthy (decision 28); 09 decisions 26-28 recorded
gates / gates (push) Successful in 31s

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS
This commit is contained in:
2026-09-24 11:38:13 +02:00
parent 86c4b9a0d8
commit 99c0709cbe
13 changed files with 109 additions and 4 deletions
+4
View File
@@ -398,6 +398,8 @@ var perAppCooldownEvents = map[string]bool{
// v0.122.0 (R-659): a held app with no whole copy on its box is one app's event with no digest —
// two apps stranded on one night are two alarms, and the second must not be swallowed.
"app_hold_no_whole_copy": true,
// v0.123.0 (decision 28): one app's stop, no digest behind it.
"app_stopped_unhealthy": true,
}
// perAppCustomerCooldownEvents is the CUSTOMER-leg sibling of perAppCooldownEvents (v0.120.0). The
@@ -407,6 +409,8 @@ var perAppCooldownEvents = map[string]bool{
var perAppCustomerCooldownEvents = map[string]bool{
"app_update_undone": true,
"app_update_held": true,
// v0.123.0 (decision 28): two apps stopped on one night are two mails.
"app_stopped_unhealthy": true,
}
// cooldownStackSuffix returns ":"+stack_name when the event's details carry a non-empty `stack_name`
@@ -70,7 +70,8 @@ func TestR389_StackSuffixIsAllowListedAndFailSoft(t *testing.T) {
func TestR389_TheAllowListHasExactlyOneMember(t *testing.T) {
// v0.121.0 widened it again, on purpose (R-636): an OOM storm is one app's event with no digest.
// v0.122.0 once more (R-659): a stranded held app is one app's event with no digest.
want := []string{"app_hold_no_whole_copy", "app_oom_storm", "app_start_failed", "app_update_held", "app_update_undone"}
// v0.123.0 once more (decision 28): an unhealthy stop is one app's event with no digest.
want := []string{"app_hold_no_whole_copy", "app_oom_storm", "app_start_failed", "app_stopped_unhealthy", "app_update_held", "app_update_undone"}
ok := len(perAppCooldownEvents) == len(want)
for _, w := range want {
ok = ok && perAppCooldownEvents[w]
@@ -80,7 +81,7 @@ func TestR389_TheAllowListHasExactlyOneMember(t *testing.T) {
for k := range perAppCooldownEvents {
got = append(got, k)
}
t.Fatalf("perAppCooldownEvents = %v, want exactly [app_hold_no_whole_copy app_oom_storm app_start_failed app_update_held app_update_undone]. Adding a member is the "+
t.Fatalf("perAppCooldownEvents = %v, want exactly [app_hold_no_whole_copy app_oom_storm app_start_failed app_stopped_unhealthy app_update_held app_update_undone]. Adding a member is the "+
"fenced act: the backup family's cooldown is coarse ON PURPOSE (R-97a, R-182) so one full "+
"disk sends one digest, not one mail per app. Read the fence before widening this.", got)
}
+2
View File
@@ -383,6 +383,8 @@ func trimRepeatedUsage(reason, targetPath string) string {
var appNamedMailEvents = map[string]bool{
"app_update_undone": true,
"app_update_held": true,
// v0.123.0 (`09` §3 decision 28): the box stopped an app that kept crashing / ran out of memory.
"app_stopped_unhealthy": true,
}
// stackNameOf reads `stack_name` from an event's details, "" when absent or unreadable.
@@ -0,0 +1,18 @@
SUBJECT: [Felhom] Warning: ?: the app was stopped because it kept crashing
---
Dear Customer,
Your Felhom system sent the following notification:
?: the app was stopped because it kept crashing
Details:
- Server: demo-fixture
- Time: 2026-01-15 10:30
- Level: Warning
- Type: app_stopped_unhealthy
If you have any questions, contact your operator.
Best regards,
Felhom.eu monitoring
@@ -0,0 +1,18 @@
SUBJECT: [Felhom] Figyelmeztetés: ?: az alkalmazást leállítottuk, mert újra és újra összeomlott
---
Kedves Ügyfél!
A Felhom rendszered a következő értesítést küldte:
?: az alkalmazást leállítottuk, mert újra és újra összeomlott
Részletek:
- Szerver: demo-fixture
- Időpont: 2026-01-15 10:30
- Szint: Figyelmeztetés
- Típus: app_stopped_unhealthy
Ha kérdésed van, vedd fel a kapcsolatot az üzemeltetővel.
Üdvözlettel,
Felhom.eu monitoring