fix(communication): cancel-only CTS replacement, deferred channel disposal, single-endpoint debug stream (arch-review 2026-08-19 P3-1 + P3-2 + P3-3)

src/ZB.MOM.WW.ScadaBridge.Communication/Grpc/SiteStreamGrpcClientFactory.cs

@@ -120,7 +120,7 @@ public class SiteStreamGrpcClientFactory : IAsyncDisposable, IDisposable
         foreach (var key in _clients.Keys.Where(k => k.Site == siteIdentifier).ToList())
         {
             if (_clients.TryRemove(key, out var client))
-                await client.DisposeAsync();
+                await DisposeClientAsync(client, key);
         }
 
         // Drop the cached preshared key too, so a site removed and re-added under the same
@@ -129,16 +129,39 @@ public class SiteStreamGrpcClientFactory : IAsyncDisposable, IDisposable
     }
 
     /// <summary>
-    /// Asynchronously disposes all cached clients and clears the cache.
+    /// Asynchronously disposes all cached clients and clears the cache. Each client's disposal
+    /// is fault-isolated: one throwing client must not abort the loop and strand every later
+    /// client's channel undisposed (arch-review 2026-08-19 P3-1).
     /// </summary>
     /// <returns>A value task that completes when all clients have been disposed.</returns>
     public async ValueTask DisposeAsync()
     {
-        foreach (var client in _clients.Values)
+        foreach (var entry in _clients)
+        {
+            await DisposeClientAsync(entry.Value, entry.Key);
+        }
+        _clients.Clear();
+    }
+
+    /// <summary>
+    /// Disposes one client, logging and swallowing any failure so the caller's disposal loop
+    /// continues to the remaining clients.
+    /// </summary>
+    /// <param name="client">The client to dispose.</param>
+    /// <param name="key">Cache key of the client, for diagnostics.</param>
+    /// <returns>A task that completes when the client has been disposed (or its failure logged).</returns>
+    private async Task DisposeClientAsync(SiteStreamGrpcClient client, (string Site, string Endpoint) key)
+    {
+        try
         {
             await client.DisposeAsync();
         }
-        _clients.Clear();
+        catch (Exception ex)
+        {
+            _loggerFactory.CreateLogger<SiteStreamGrpcClientFactory>().LogWarning(
+                ex, "Disposing the site stream gRPC client for site {SiteId} endpoint {Endpoint} failed",
+                key.Site, key.Endpoint);
+        }
     }
 
     /// <summary>
@@ -147,12 +170,22 @@ public class SiteStreamGrpcClientFactory : IAsyncDisposable, IDisposable
     /// a stall/deadlock risk during host shutdown). Each
     /// <see cref="SiteStreamGrpcClient"/> releases all of its resources
     /// synchronously, so we dispose them directly with no async path.
+    /// Fault-isolated per client, exactly as <see cref="DisposeAsync"/> is.
     /// </summary>
     public void Dispose()
     {
-        foreach (var client in _clients.Values)
+        foreach (var entry in _clients)
         {
-            client.Dispose();
+            try
+            {
+                entry.Value.Dispose();
+            }
+            catch (Exception ex)
+            {
+                _loggerFactory.CreateLogger<SiteStreamGrpcClientFactory>().LogWarning(
+                    ex, "Disposing the site stream gRPC client for site {SiteId} endpoint {Endpoint} failed",
+                    entry.Key.Site, entry.Key.Endpoint);
+            }
         }
         _clients.Clear();
     }