fix(mesh-phase5): telemetry service — graceful client-disconnect + null-safe required-string mapping

Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW

src/Server/ZB.MOM.WW.OtOpcUa.Host/Grpc/TelemetryProtoMapNode.cs

@@ -67,17 +67,21 @@ public static class TelemetryProtoMapNode
 
     private static AlarmTransition MapAlarm(AlarmTransitionEvent e)
     {
+        // Required (non-optional) proto string setters throw ArgumentNullException on null, and the
+        // domain records carry no runtime null guard (nullable-ref annotations are compile-time only).
+        // Coalesce every required string to "" so a stray null can never throw out of the pump and kill
+        // the stream. The `optional` fields below keep their null-vs-"" presence guards.
         var msg = new AlarmTransition
         {
-            AlarmId = e.AlarmId,
-            EquipmentPath = e.EquipmentPath,
-            AlarmName = e.AlarmName,
-            TransitionKind = e.TransitionKind,
+            AlarmId = e.AlarmId ?? "",
+            EquipmentPath = e.EquipmentPath ?? "",
+            AlarmName = e.AlarmName ?? "",
+            TransitionKind = e.TransitionKind ?? "",
             Severity = e.Severity,
-            Message = e.Message,
-            User = e.User,
+            Message = e.Message ?? "",
+            User = e.User ?? "",
             TimestampUtc = ToUtcTimestamp(e.TimestampUtc),
-            AlarmTypeName = e.AlarmTypeName,
+            AlarmTypeName = e.AlarmTypeName ?? "",
         };
 
         if (e.Comment is not null)
@@ -93,9 +97,9 @@ public static class TelemetryProtoMapNode
     {
         var msg = new ScriptLog
         {
-            ScriptId = e.ScriptId,
-            Level = e.Level,
-            Message = e.Message,
+            ScriptId = e.ScriptId ?? "",
+            Level = e.Level ?? "",
+            Message = e.Message ?? "",
             TimestampUtc = ToUtcTimestamp(e.TimestampUtc),
         };
 
@@ -113,9 +117,9 @@ public static class TelemetryProtoMapNode
     {
         var msg = new DriverHealth
         {
-            ClusterId = e.ClusterId,
-            DriverInstanceId = e.DriverInstanceId,
-            State = e.State,
+            ClusterId = e.ClusterId ?? "",
+            DriverInstanceId = e.DriverInstanceId ?? "",
+            State = e.State ?? "",
             ErrorCount5Min = e.ErrorCount5Min,
             PublishedUtc = ToUtcTimestamp(e.PublishedUtc),
         };
@@ -132,8 +136,8 @@ public static class TelemetryProtoMapNode
     {
         var msg = new DriverResilienceStatus
         {
-            DriverInstanceId = e.DriverInstanceId,
-            HostName = e.HostName,
+            DriverInstanceId = e.DriverInstanceId ?? "",
+            HostName = e.HostName ?? "",
             BreakerOpen = e.BreakerOpen,
             ConsecutiveFailures = e.ConsecutiveFailures,
             CurrentInFlight = e.CurrentInFlight,

src/Server/ZB.MOM.WW.OtOpcUa.Host/Grpc/TelemetryStreamGrpcService.cs

@@ -103,6 +103,15 @@ public sealed class TelemetryStreamGrpcService : GeneratedServiceBase
                 // Normal termination: the client disconnected (context token) or the max-lifetime cap
                 // fired (linked token). Neither is an error — swallow and let the stream close cleanly.
             }
+            catch (Exception ex) when (ex is IOException or RpcException)
+            {
+                // Routine mid-stream disconnect: central's TelemetryStreamClient reconnects on ANY
+                // non-Cancelled error, so a broken pipe / connection-reset here is expected churn, not a
+                // fault. Swallow at Debug so grpc-dotnet doesn't log it at Error on every reconnect.
+                // (A genuinely unexpected exception still escapes to surface as an error.)
+                _log.LogDebug(
+                    ex, "Telemetry client disconnected mid-stream (correlationId={CorrelationId})", correlationId);
+            }
 
             _log.LogDebug("Telemetry stream closed (correlationId={CorrelationId})", correlationId);
         }