chore(communication): low-severity cleanup — eviction counting, shared ingest timeout, split app heartbeat interval, doc notes

src/ZB.MOM.WW.ScadaBridge.Communication/Actors/CentralCommunicationActor.cs

@@ -137,20 +137,18 @@ public class CentralCommunicationActor : ReceiveActor
 
     /// <summary>
     /// Default Ask timeout for routing audit ingest commands to the
-    /// AuditLogIngestActor proxy — 30 s, matching the value of
-    /// <c>SiteStreamGrpcServer.AuditIngestAskTimeout</c> (that constant is private
-    /// to the gRPC server and not reachable here, so it is declared locally). A
-    /// generous window absorbs a slow MS SQL connection without the round-trip
-    /// surfacing as a failure on a healthy site. When the window is exceeded the
-    /// Ask faults and that fault is piped back to the caller as a
-    /// <see cref="Status.Failure"/> (see <see cref="HandleIngestAuditEvents"/>).
-    /// </summary>
-    private static readonly TimeSpan DefaultAuditIngestAskTimeout = TimeSpan.FromSeconds(30);
-
-    /// <summary>
     /// Effective Ask timeout for audit ingest routing. Defaults to
-    /// <see cref="DefaultAuditIngestAskTimeout"/>; overridable via the constructor
-    /// so tests can exercise the timeout/fault path without waiting 30 s.
+    /// <see cref="Grpc.SiteStreamGrpcServer.AuditIngestAskTimeout"/> (30 s) — the two
+    /// audit-ingest transports (gRPC vs ClusterClient) now share one source of truth
+    /// for the timeout. Overridable via the constructor so tests can exercise the
+    /// timeout/fault path without waiting 30 s. When the window is exceeded the Ask
+    /// faults and that fault is piped back to the caller as a
+    /// <see cref="Status.Failure"/> (see <see cref="HandleIngestAuditEvents"/>).
+    ///
+    /// The gRPC and ClusterClient ingest transports differ in fault semantics (the
+    /// gRPC handler surfaces the fault as an RpcException; here it becomes a piped
+    /// Status.Failure). Consolidating the two ingest transports is a scheduled
+    /// follow-up — see arch review 02, Underdeveloped #1.
     /// </summary>
     private readonly TimeSpan _auditIngestAskTimeout;
 
@@ -166,7 +164,7 @@ public class CentralCommunicationActor : ReceiveActor
     /// <param name="siteClientFactory">Factory used to create per-site ClusterClient actors.</param>
     /// <param name="auditIngestAskTimeout">
     /// Optional override for the audit-ingest Ask timeout; defaults to
-    /// <see cref="DefaultAuditIngestAskTimeout"/> (30 s). Exists only so tests can
+    /// <see cref="Grpc.SiteStreamGrpcServer.AuditIngestAskTimeout"/> (30 s). Exists only so tests can
     /// exercise the timeout/fault path quickly — production always uses the default.
     /// </param>
     public CentralCommunicationActor(
@@ -176,7 +174,7 @@ public class CentralCommunicationActor : ReceiveActor
     {
         _serviceProvider = serviceProvider;
         _siteClientFactory = siteClientFactory;
-        _auditIngestAskTimeout = auditIngestAskTimeout ?? DefaultAuditIngestAskTimeout;
+        _auditIngestAskTimeout = auditIngestAskTimeout ?? Grpc.SiteStreamGrpcServer.AuditIngestAskTimeout;
 
         // Site address cache loaded from database
         Receive<SiteAddressCacheLoaded>(HandleSiteAddressCacheLoaded);

src/ZB.MOM.WW.ScadaBridge.Communication/Actors/SiteCommunicationActor.cs

@@ -434,12 +434,14 @@ public class SiteCommunicationActor : ReceiveActor, IWithTimers
     {
         _log.Info("SiteCommunicationActor started for site {0}", _siteId);
 
-        // Schedule periodic heartbeat to central
+        // Schedule periodic heartbeat to central. Uses the application heartbeat
+        // cadence — distinct from the Akka.Remote transport failure-detector
+        // interval — so the two can be tuned independently.
         Timers.StartPeriodicTimer(
             "heartbeat",
             new SendHeartbeat(),
             TimeSpan.FromSeconds(1), // initial delay
-            _options.TransportHeartbeatInterval);
+            _options.ApplicationHeartbeatInterval);
     }
 
     private void HandleRegisterLocalHandler(RegisterLocalHandler msg)

src/ZB.MOM.WW.ScadaBridge.Communication/Actors/StreamRelayActor.cs

@@ -104,9 +104,13 @@ public class StreamRelayActor : ReceiveActor
 
     private void WriteToChannel(SiteStreamEvent protoEvent)
     {
+        // TryWrite on a DropOldest bounded channel never returns false for a "full"
+        // channel — eviction of the oldest item is what happens instead, and it is
+        // counted by the channel's itemDropped callback (SiteStreamGrpcServer). This
+        // branch therefore guards only a completed/closed channel, not backpressure.
         if (!_channelWriter.TryWrite(protoEvent))
         {
-            _log.Warning("Channel full, dropping event for correlation {0}", _correlationId);
+            _log.Debug("Channel closed, dropping event for correlation {0}", _correlationId);
         }
     }