perf(comms): alarms-only seed, capped buffers, at-least-once audit pull

src/ZB.MOM.WW.ScadaBridge.Communication/SiteAlarmLiveCacheService.cs

@@ -132,7 +132,7 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
     public bool IsLive(int siteId)
     {
         lock (_lock)
-            return _sites.TryGetValue(siteId, out var entry) && entry.HasPublished;
+            return _sites.TryGetValue(siteId, out var entry) && entry.HasPublished && entry.StreamLive;
     }
 
     // ── Subscriber teardown ─────────────────────────────────────────────────────
@@ -213,8 +213,8 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
 
             Func<CancellationToken, Task<IReadOnlyList<AlarmStateChanged>>> seedFn =
                 ct => FanOutSnapshotsAsync(entry.SiteId, ct);
-            Action<IReadOnlyList<AlarmStateChanged>> publish =
-                snapshot => OnPublish(entry, snapshot);
+            Action<IReadOnlyList<AlarmStateChanged>, bool> publish =
+                (snapshot, streamLive) => OnPublish(entry, snapshot, streamLive);
 
             lock (_lock)
             {
@@ -236,7 +236,8 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
                     _options.LiveAlarmCacheReconcileInterval,
                     _options.LiveAlarmCachePublishCoalesce,
                     TimeSpan.FromSeconds(5),    // reconnect delay — former ReconnectDelay static default
-                    TimeSpan.FromSeconds(60))); // stability window — former StabilityWindow static default
+                    TimeSpan.FromSeconds(60),   // stability window — former StabilityWindow static default
+                    _options.LiveAlarmCacheReconcileJitterFraction));
 
                 entry.Actor = system.ActorOf(props, $"site-alarm-aggregator-{entry.SiteId}-{Guid.NewGuid():N}");
 
@@ -378,7 +379,12 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
         await gate.WaitAsync(ct);
         try
         {
-            var request = new DebugSnapshotRequest(instanceUniqueName, Guid.NewGuid().ToString("N"));
+            // Alarms-only (WP2.3): this fan-out discards snapshot.AttributeValues, so
+            // asking the site to build and ship them is pure wire waste. The flag is
+            // additive on the wire; a pre-WP2.3 site ignores it and returns the full
+            // snapshot, which this loop reads exactly as before.
+            var request = new DebugSnapshotRequest(
+                instanceUniqueName, Guid.NewGuid().ToString("N"), AlarmsOnly: true);
             var snapshot = await _communicationService.RequestDebugSnapshotAsync(siteIdentifier, request, ct);
             if (snapshot.InstanceNotFound)
                 return;
@@ -402,7 +408,7 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
 
     // ── Publish (actor thread → viewers) ────────────────────────────────────────
 
-    private void OnPublish(SiteEntry entry, IReadOnlyList<AlarmStateChanged> snapshot)
+    private void OnPublish(SiteEntry entry, IReadOnlyList<AlarmStateChanged> snapshot, bool streamLive)
     {
         Subscription[] subscribers;
         lock (_lock)
@@ -410,6 +416,10 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
             // Store the fresh immutable snapshot (readers get it lock-free-ish via GetCurrentAlarms).
             entry.Current = snapshot;
             entry.HasPublished = true;
+            // Liveness is the STREAM's, not the cache's: a completed or given-up stream must
+            // stop reporting live between reopen ticks, or the page grafts a freezing snapshot
+            // over fresh poll data (WP2.3 carried residual).
+            entry.StreamLive = streamLive;
             subscribers = entry.Subscribers.ToArray();
         }
 
@@ -462,6 +472,7 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
 
             entry.Actor = null;
             entry.HasPublished = false;
+            entry.StreamLive = false;
             entry.Current = Empty;
 
             if (entry.Subscribers.Count > 0 && !entry.Starting)
@@ -498,6 +509,13 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
         /// <summary>True once the aggregator has seeded and published at least once.</summary>
         public bool HasPublished { get; set; }
 
+        /// <summary>
+        /// Liveness of the aggregator's site-wide gRPC stream as of the last publish. Both
+        /// this and <see cref="HasPublished"/> must hold for <c>IsLive</c>: a published cache
+        /// behind a dead stream is stale, not live.
+        /// </summary>
+        public bool StreamLive { get; set; }
+
         public Timer? LingerTimer { get; set; }
         public int LingerVersion { get; set; }