R-1270 (P2): a restore whose app does not reach running in time is never a success — every restore path returns ErrRestoreNotStarted, the household reads that the data is back but the app has not started yet, one operator alarm; the data stays, the undo copy is kept, a late start turns the record into a success and releases the copy. Red-proved. Commit only.

2026-10-25 09:33:26 +01:00
parent 02daebe9c5
commit b680db85cb
18 changed files with 405 additions and 23 deletions
@@ -143,14 +143,15 @@ func (m *Manager) RestoreApp(stackName, snapshotID string) error {
 		m.logger.Printf("[WARN] RESTORE could not restart %s after restore: %v", stackName, err)
 	}

-	// Verify app started successfully
-	if err := m.waitForHealthy(stackName, healthTimeout); err != nil {
-		m.logger.Printf("[WARN] [backup] Restore completed but app health check failed: %v", err)
-	}
+	// Verify app started successfully — R-1270: a timeout is not a success.
+	healthErr := m.waitForHealthy(stackName, healthTimeout)

 	if dataErr != nil {
 		return fmt.Errorf("restore of %s completed with data errors: %w", stackName, dataErr)
 	}
+	if healthErr != nil {
+		return m.restoreNotStarted(stackName, "volume-only restore", healthErr, nil)
+	}
 	m.logger.Printf("[INFO] RESTORE completed: stack=%s", stackName)
 	return nil
 }