fix(communication): resolve Communication-004..008 — Resume supervision, gRPC option wiring, address-load logging, sync dispose, flap detection

src/ScadaLink.Communication/Grpc/SiteStreamGrpcServer.cs

@@ -3,6 +3,7 @@ using System.Threading.Channels;
 using Akka.Actor;
 using Grpc.Core;
 using Microsoft.Extensions.Logging;
+using Microsoft.Extensions.Options;
 using GrpcStatus = Grpc.Core.Status;
 
 namespace ScadaLink.Communication.Grpc;
@@ -19,6 +20,7 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
     private readonly ILogger<SiteStreamGrpcServer> _logger;
     private readonly ConcurrentDictionary<string, StreamEntry> _activeStreams = new();
     private readonly int _maxConcurrentStreams;
+    private readonly TimeSpan _maxStreamLifetime;
     private volatile bool _ready;
     private long _actorCounter;
 
@@ -26,10 +28,36 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
         ISiteStreamSubscriber streamSubscriber,
         ILogger<SiteStreamGrpcServer> logger,
         int maxConcurrentStreams = 100)
+        : this(streamSubscriber, logger, maxConcurrentStreams, TimeSpan.FromHours(4))
+    {
+    }
+
+    /// <summary>
+    /// DI constructor — binds <see cref="CommunicationOptions.GrpcMaxConcurrentStreams"/>
+    /// and <see cref="CommunicationOptions.GrpcMaxStreamLifetime"/> so the documented
+    /// concurrency limit and the 4-hour zombie-stream session timeout are honoured
+    /// rather than hard-coded.
+    /// </summary>
+    public SiteStreamGrpcServer(
+        ISiteStreamSubscriber streamSubscriber,
+        ILogger<SiteStreamGrpcServer> logger,
+        IOptions<CommunicationOptions> options)
+        : this(streamSubscriber, logger,
+            options.Value.GrpcMaxConcurrentStreams,
+            options.Value.GrpcMaxStreamLifetime)
+    {
+    }
+
+    private SiteStreamGrpcServer(
+        ISiteStreamSubscriber streamSubscriber,
+        ILogger<SiteStreamGrpcServer> logger,
+        int maxConcurrentStreams,
+        TimeSpan maxStreamLifetime)
     {
         _streamSubscriber = streamSubscriber;
         _logger = logger;
         _maxConcurrentStreams = maxConcurrentStreams;
+        _maxStreamLifetime = maxStreamLifetime;
     }
 
     /// <summary>
@@ -49,6 +77,12 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
     /// </summary>
     public int ActiveStreamCount => _activeStreams.Count;
 
+    /// <summary>Effective max concurrent stream limit. Exposed for tests.</summary>
+    internal int MaxConcurrentStreams => _maxConcurrentStreams;
+
+    /// <summary>Effective per-stream session lifetime. Exposed for tests.</summary>
+    internal TimeSpan MaxStreamLifetime => _maxStreamLifetime;
+
     public override async Task SubscribeInstance(
         InstanceStreamRequest request,
         IServerStreamWriter<SiteStreamEvent> responseStream,
@@ -69,6 +103,11 @@ public class SiteStreamGrpcServer : SiteStreamService.SiteStreamServiceBase
             throw new RpcException(new GrpcStatus(StatusCode.ResourceExhausted, "Max concurrent streams reached"));
 
         using var streamCts = CancellationTokenSource.CreateLinkedTokenSource(context.CancellationToken);
+        // Session timeout (design doc "gRPC Connection Keepalive": 4-hour third layer
+        // of dead-client detection) — forces a long-lived zombie stream to terminate
+        // even if keepalive PINGs never detect the loss.
+        if (_maxStreamLifetime > TimeSpan.Zero && _maxStreamLifetime != Timeout.InfiniteTimeSpan)
+            streamCts.CancelAfter(_maxStreamLifetime);
         var entry = new StreamEntry(streamCts);
         _activeStreams[request.CorrelationId] = entry;