fix(notification-outbox): give KPI response a failure shape; log status-query faults

src/ScadaLink.Commons/Messages/Notification/NotificationOutboxQueries.cs

@@ -82,9 +82,13 @@ public record NotificationKpiRequest(
 
 /// <summary>
 /// Central -> Outbox UI: KPI summary for the notification outbox dashboard.
+/// On a repository fault <see cref="Success"/> is <c>false</c>, <see cref="ErrorMessage"/>
+/// carries the cause, and the KPI fields are zeroed/<c>null</c>.
 /// </summary>
 public record NotificationKpiResponse(
     string CorrelationId,
+    bool Success,
+    string? ErrorMessage,
     int QueueDepth,
     int StuckCount,
     int ParkedCount,

src/ScadaLink.NotificationOutbox/NotificationOutboxActor.cs

@@ -298,9 +298,8 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
     {
         var sender = Sender;
         var now = DateTimeOffset.UtcNow;
-        var stuckThreshold = _options.StuckAgeThreshold;
 
-        QueryOutboxAsync(request, now, stuckThreshold).PipeTo(
+        QueryOutboxAsync(request, now).PipeTo(
             sender,
             success: response => response,
             failure: ex => new NotificationOutboxQueryResponse(
@@ -312,7 +311,7 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
     }
 
     private async Task<NotificationOutboxQueryResponse> QueryOutboxAsync(
-        NotificationOutboxQueryRequest request, DateTimeOffset now, TimeSpan stuckThreshold)
+        NotificationOutboxQueryRequest request, DateTimeOffset now)
     {
         var filter = new NotificationOutboxFilter(
             Status: ParseEnum<NotificationStatus>(request.StatusFilter),
@@ -321,7 +320,7 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
             ListName: request.ListNameFilter,
             SubjectKeyword: request.SubjectKeyword,
             StuckOnly: request.StuckOnly,
-            StuckCutoff: request.StuckOnly ? now - stuckThreshold : null,
+            StuckCutoff: request.StuckOnly ? StuckCutoff(now) : null,
             From: request.From,
             To: request.To);
 
@@ -329,7 +328,7 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
         var repository = scope.ServiceProvider.GetRequiredService<INotificationOutboxRepository>();
         var (rows, totalCount) = await repository.QueryAsync(filter, request.PageNumber, request.PageSize);
 
-        var stuckCutoff = now - stuckThreshold;
+        var stuckCutoff = StuckCutoff(now);
         var summaries = rows
             .Select(row => new NotificationSummary(
                 row.NotificationId,
@@ -362,9 +361,17 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
         StatusQueryAsync(query).PipeTo(
             sender,
             success: response => response,
-            failure: _ => new NotificationStatusResponse(
-                query.CorrelationId, Found: false, Status: string.Empty,
-                RetryCount: 0, LastError: null, DeliveredAt: null));
+            failure: ex =>
+            {
+                // NotificationStatusResponse has no error field, so a repository fault is
+                // reported as Found: false — log the fault so a transient DB error is not
+                // silently indistinguishable from a genuinely-missing notification.
+                _logger.LogWarning(
+                    ex, "Status query for notification {NotificationId} failed.", query.NotificationId);
+                return new NotificationStatusResponse(
+                    query.CorrelationId, Found: false, Status: string.Empty,
+                    RetryCount: 0, LastError: null, DeliveredAt: null);
+            });
     }
 
     private async Task<NotificationStatusResponse> StatusQueryAsync(NotificationStatusQuery query)
@@ -482,10 +489,21 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
     {
         var sender = Sender;
         var now = DateTimeOffset.UtcNow;
-        var stuckCutoff = now - _options.StuckAgeThreshold;
+        var stuckCutoff = StuckCutoff(now);
         var deliveredSince = now - _options.DeliveredKpiWindow;
 
-        ComputeKpisAsync(request.CorrelationId, stuckCutoff, deliveredSince).PipeTo(sender);
+        ComputeKpisAsync(request.CorrelationId, stuckCutoff, deliveredSince).PipeTo(
+            sender,
+            success: response => response,
+            failure: ex => new NotificationKpiResponse(
+                request.CorrelationId,
+                Success: false,
+                ErrorMessage: ex.GetBaseException().Message,
+                QueueDepth: 0,
+                StuckCount: 0,
+                ParkedCount: 0,
+                DeliveredLastInterval: 0,
+                OldestPendingAge: null));
     }
 
     private async Task<NotificationKpiResponse> ComputeKpisAsync(
@@ -497,6 +515,8 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
 
         return new NotificationKpiResponse(
             correlationId,
+            Success: true,
+            ErrorMessage: null,
             snapshot.QueueDepth,
             snapshot.StuckCount,
             snapshot.ParkedCount,
@@ -504,6 +524,12 @@ public class NotificationOutboxActor : ReceiveActor, IWithTimers
             snapshot.OldestPendingAge);
     }
 
+    /// <summary>
+    /// The instant before which a still-pending notification counts as stuck — <paramref name="now"/>
+    /// offset back by <see cref="NotificationOutboxOptions.StuckAgeThreshold"/>.
+    /// </summary>
+    private DateTimeOffset StuckCutoff(DateTimeOffset now) => now - _options.StuckAgeThreshold;
+
     /// <summary>
     /// A notification counts as stuck when it is still in a non-terminal status
     /// (<c>Pending</c> or <c>Retrying</c>) and was created before the supplied cutoff.