fix(cluster): record RoleLeaderChanged leader from the event, not the lagging state snapshot (#590)

ClusterRoleInfo resolved the leader address through Cluster.State.Members, which is
published asynchronously; a miss stored null permanently, so RoleLeader(role) stayed null
(flaky test timed out under load: 6/10 failing with CPU contention, 0/20 after). Only the
address is ever read, so store it directly. Adds a deterministic unit test (fails without
the fix) and InternalsVisibleTo for the Cluster.Tests project.

Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe

src/Core/ZB.MOM.WW.OtOpcUa.Cluster/ClusterRoleInfo.cs

@@ -37,7 +37,7 @@ public sealed class ClusterRoleInfo : IClusterRoleInfo, IDisposable
     // RoleLeaderChanged event landed last would silently overwrite the other's leader — turning two
     // real, independent facts Akka tracks separately into one, wrong, merged one. Pinned by
     // ClusterRoleInfoRoleLeaderCaseTests.RoleLeaderChanged_for_driver_then_Driver_keeps_distinct_entries.
-    private readonly Dictionary<string, Member?> _roleLeaders = new(StringComparer.Ordinal);
+    private readonly Dictionary<string, Akka.Actor.Address?> _roleLeaders = new(StringComparer.Ordinal);
     private readonly Dictionary<string, HashSet<Member>> _membersByRole = new(StringComparer.OrdinalIgnoreCase);
     private IActorRef? _subscriber;
 
@@ -113,7 +113,7 @@ public sealed class ClusterRoleInfo : IClusterRoleInfo, IDisposable
         lock (_lock)
         {
             return _roleLeaders.TryGetValue(role, out var leader) && leader is not null
-                ? ToNodeId(leader.Address)
+                ? ToNodeId(leader)
                 : (CommonsNodeId?)null;
         }
     }
@@ -137,9 +137,7 @@ public sealed class ClusterRoleInfo : IClusterRoleInfo, IDisposable
             foreach (var role in snapshot.Members.SelectMany(m => m.Roles).Distinct())
             {
                 var leaderAddr = snapshot.RoleLeader(role);
-                _roleLeaders[role] = leaderAddr is not null
-                    ? snapshot.Members.FirstOrDefault(m => m.Address == leaderAddr)
-                    : null;
+                _roleLeaders[role] = leaderAddr;
             }
         }
     }
@@ -179,17 +177,17 @@ public sealed class ClusterRoleInfo : IClusterRoleInfo, IDisposable
 
         lock (_lock)
         {
-            _roleLeaders.TryGetValue(evt.Role, out var prevMember);
-            if (prevMember is not null)
-                previous = ToNodeId(prevMember.Address);
+            _roleLeaders.TryGetValue(evt.Role, out var prevLeader);
+            if (prevLeader is not null)
+                previous = ToNodeId(prevLeader);
 
-            var nextMember = evt.Leader is null
-                ? null
-                : _cluster.State.Members.FirstOrDefault(m => m.Address == evt.Leader);
-
-            _roleLeaders[evt.Role] = nextMember;
-            if (nextMember is not null)
-                next = ToNodeId(nextMember.Address);
+            // Record the event's own address. The leader used to be resolved by looking the address up
+            // in Cluster.State.Members, but that snapshot is published asynchronously and can lag the
+            // event: a miss stored null and nothing re-ran, so RoleLeader(role) stayed null for good
+            // (Gitea #590). Only the address is ever read, so no Member lookup is needed.
+            _roleLeaders[evt.Role] = evt.Leader;
+            if (evt.Leader is not null)
+                next = ToNodeId(evt.Leader);
 
             raise = !Nullable.Equals(previous, next);
         }

src/Core/ZB.MOM.WW.OtOpcUa.Cluster/ZB.MOM.WW.OtOpcUa.Cluster.csproj

@@ -5,6 +5,10 @@
         <TreatWarningsAsErrors>true</TreatWarningsAsErrors>
     </PropertyGroup>
 
+    <ItemGroup>
+        <InternalsVisibleTo Include="ZB.MOM.WW.OtOpcUa.Cluster.Tests"/>
+    </ItemGroup>
+
     <ItemGroup>
         <PackageReference Include="Akka.Hosting"/>
         <PackageReference Include="Akka.Cluster"/>