Files
felhom.eu/hub/internal/notify/recovery_unit_dispatch_test.go
T
admin f21e7caed1
gates / gates (push) Successful in 7s
hub v0.90.1 — the digest's per-app lines stop repeating the filesystem figures (R-182)
Found by reading the first REAL digest, not by design. Every app row ended with
the same usage clause the mail already prints once on its own Filesystem line.
On a two-app box that is untidy; down a list of a dozen it is the same forty
characters twelve times, pushing the part that DIFFERS off a phone screen at
07:00 — the only moment this mail has to work.

The reserve's refusal message is authored for a single-app alert where naming
the filesystem is right, so the message is unchanged; the digest trims the
duplicate when rendering. trimRepeatedUsage removes ONLY an exact
"— <target path>:" suffix, so an unrelated reason is untouched and a reason that
is nothing but the usage clause is left alone rather than emptied.

Also updates TestRecoveryUnitCaptureFailed_NeverReachesTheCustomer, which
required the OPERATOR to be emailed a per-app capture failure. That was correct
when the event was the only signal and is wrong now that it is the record and
the digest is the notification. Its customer-safety claim is unchanged and is
why the test still exists; the operator assertion is inverted with the reasoning
written in place, and R-158's guarantee is shown to have MOVED, not weakened.
2026-08-03 13:54:02 +02:00

143 lines
6.6 KiB
Go

package notify
import (
"io"
"log"
"strings"
"testing"
)
func discardLogger() *log.Logger { return log.New(io.Discard, "", 0) }
// R-158 / R-167 Scenario G — the two new signals of decision D-c sit on OPPOSITE sides of the
// operator/customer line, and each is tested through the real dispatch path rather than by reading
// the register.
//
// D-c's rule, restated: a customer can free space, delete files or add a drive, so a FILL WARNING is
// theirs. A customer can do nothing about a recovery-unit capture failure, so it is not.
// The operator half. Run under the BREAKING configuration — the customer has the event explicitly
// enabled and has an email address — because that is the only configuration in which a missing
// operatorOnlyEvents entry is visible. This is the v0.78.0 defect, demonstrated rather than argued.
func TestRecoveryUnitCaptureFailed_NeverReachesTheCustomer(t *testing.T) {
st := opOnlyStore(t)
if err := st.SaveNotificationPrefs("c1", "customer@example.com",
[]string{"recovery_unit_capture_failed", "backup_failed"}, 6); err != nil {
t.Fatalf("SaveNotificationPrefs: %v", err)
}
rec := &sentTo{}
d := opOnlyDispatcher(t, st, rec)
d.ProcessEvent("c1", "recovery_unit_capture_failed", "error",
`Recovery unit capture FAILED for "immich" — the app has no fresh local (Tier-1) backup`,
`{"app":"immich","used_percent":100,"space_known":true}`, "controller")
for _, to := range rec.to {
if to == "customer@example.com" {
t.Fatalf("a customer was emailed the OPERATOR-ONLY recovery_unit_capture_failed (%s) — "+
"enabled_events must not be able to opt in to a failure they cannot act on", to)
}
}
// R-182 CHANGED WHAT THIS ASSERTS, DELIBERATELY, AND THE OLD ASSERTION IS WORTH KEEPING IN VIEW.
//
// Until 2026-08-03 this test required the OPERATOR to be e-mailed here, on the grounds that "the
// alert is the whole point of R-158". That was right when this event was the only signal, and it
// is wrong now: measured, nine of these arrived at the hub and two were mailed, because the
// operator cooldown key carries no app identifier — so as an alarm it told the operator about one
// app and threw the rest away.
//
// The type is now RECORD-ONLY: written down every time, never mailed. R-158's guarantee — the
// operator learns WHICH app failed and WHY — is not weakened, it MOVED: the per-run digest
// `backup_run_failures` carries every failed app in one mail, and is pinned by
// backup_run_digest_test.go. The customer safety claim below is untouched and is the reason this
// test still exists.
for _, to := range rec.to {
if to == "operator@felhom.eu" {
t.Fatal("the operator was e-mailed a PER-APP capture failure — this type is the record " +
"now, not the alarm. One mail per failing app on a full disk is a dozen mails, which " +
"is the volume problem the operator ruled against; the digest is the notification")
}
}
// The RECORD must exist, always. It is what makes the digest trustworthy: if the digest is ever
// lost, delayed or suppressed, the failures are still individually written down. An absent row is
// equally consistent with "correctly not mailed" and "the dispatcher never ran" — the positive
// observable is the row itself (standing rule 3).
logs, err := st.GetRecentNotifications("c1", 20)
if err != nil {
t.Fatalf("GetRecentNotifications: %v", err)
}
found := false
for _, l := range logs {
if l.EventType == "recovery_unit_capture_failed" && l.Status == "recorded" &&
strings.Contains(l.ErrorMessage, "record-only") {
found = true
}
}
if !found {
t.Fatalf("the per-app failure left no 'recorded' row — a failure that is neither mailed nor "+
"written down is exactly the 2026-08-03 defect, rebuilt; got %d row(s)", len(logs))
}
}
// The customer half. The fill warning MUST be delivered, and it must render the controller's own
// Hungarian text — which names the drive and the free space — rather than a generic template or the
// raw English.
func TestDiskFillWarning_ReachesTheCustomerInHungarianWithItsNumbers(t *testing.T) {
st := opOnlyStore(t)
if err := st.SaveNotificationPrefs("c1", "customer@example.com", []string{"disk_warning"}, 6); err != nil {
t.Fatal(err)
}
// The exact shape the controller sends from v0.191.0.
const hun = `A(z) „Fotók" tároló 87%-osan megtelt — 4,2 GB szabad hely maradt. ` +
`Szabadíts fel helyet (törölj felesleges fájlokat, vagy csatlakoztass új meghajtót), ` +
`különben a biztonsági mentések hamarosan meghiúsulnak.`
var bodies []string
d := NewDispatcher(st, "test-key", "from@felhom.eu", "operator@felhom.eu", true, discardLogger())
d.sendEmailFn = func(to, subject, body string, headers map[string]string) error {
if to == "customer@example.com" {
bodies = append(bodies, subject+"\n"+body)
}
return nil
}
d.ProcessEvent("c1", "disk_warning", "warning", hun,
`{"label":"Fotók","used_percent":87,"avail_gb":4.2}`, "controller")
if len(bodies) == 0 {
t.Fatal("the customer was NOT warned that a disk is filling — this is the customer half of " +
"decision D-c, and nothing reached them")
}
got := strings.Join(bodies, "\n")
// The controller's dynamic text must survive. A customerMessages entry for disk_warning would
// OVERRIDE it (templates.go prefers the entry) and discard the drive name and the free space,
// leaving the customer with "A lemezterület 90% felett van" and nothing to act on — which is
// exactly why v0.191.0 removes those two entries.
if !strings.Contains(got, "Fotók") {
t.Fatalf("the customer email does not name the drive — a generic customerMessages entry has "+
"discarded the controller's dynamic text (templates.go priority). Got:\n%s", got)
}
if !strings.Contains(got, "4,2 GB") {
t.Fatalf("the customer email does not carry the free-space figure. Got:\n%s", got)
}
if !strings.Contains(got, "Szabadíts fel helyet") {
t.Fatalf("the customer email does not tell the customer what to DO. Got:\n%s", got)
}
}
// The generic entries must STAY REMOVED. A well-meaning re-add would silently re-break the test
// above's guarantee for every future reader — this pins the deletion itself.
func TestDiskFillTypesHaveNoGenericCustomerMessage(t *testing.T) {
for _, et := range []string{"disk_warning", "disk_critical"} {
if msg, ok := customerMessages[et]; ok {
t.Fatalf("customerMessages[%q] = %q — a static entry OVERRIDES the controller's dynamic "+
"Hungarian text (FormatCustomerEmail prefers the entry), discarding the drive name "+
"and the free-space figure the customer needs. Same reason offbox_enlarge_blocked "+
"and disk_health_degraded deliberately have none", et, msg)
}
}
}