fix(mesh): break Phase 6 boot-crash — cluster-redundancy singleton scope must not resolve IClusterRoleInfo eagerly

Phase 6 wired the re-homed redundancy singleton in Program.cs as
`WithOtOpcUaClusterRedundancySingleton(sp.GetRequiredService<IClusterRoleInfo>())`
inside the AddAkka configurator lambda. That lambda runs WHILE the ActorSystem is
being built, but ClusterRoleInfo depends on the ActorSystem (it is a live
Cluster.State view) — so resolving it there recurses into ActorSystem construction
and every node dies at boot with StackOverflowException. It compiles cleanly (a
runtime DI cycle) and RedundancyStateSingletonRehomeTests passed a hand-built
FakeClusterRoleInfo straight into the extension, mocking around the composition-root
line that overflows. The docker-dev live gate caught it on first boot.

Derive the singleton's cluster-role scope from AkkaClusterOptions (pure config, no
ActorSystem) instead: BuildClusterRedundancySingletonOptions / the extension now take
AkkaClusterOptions and compute Role = Roles.FirstOrDefault(IsClusterRole) ?? driver —
identical to ClusterRoleInfo.ClusterRole, which derives from the same config. Program.cs
passes IOptions<AkkaClusterOptions>.Value, which has no ActorSystem dependency.

Live-verified: rebuilt image boots with zero stack-overflow lines, cluster singletons
form per mesh. 5/5 rehome tests pass; Host builds clean.

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

src/Server/ZB.MOM.WW.OtOpcUa.ControlPlane/ServiceCollectionExtensions.cs

@@ -189,9 +189,9 @@ public static class ServiceCollectionExtensions
     /// Primary and publishing <c>redundancy-state</c> on its own mesh's DistributedPubSub.
     /// </remarks>
     public static AkkaConfigurationBuilder WithOtOpcUaClusterRedundancySingleton(
-        this AkkaConfigurationBuilder builder, IClusterRoleInfo roleInfo)
+        this AkkaConfigurationBuilder builder, AkkaClusterOptions clusterOptions)
     {
-        var singletonOptions = BuildClusterRedundancySingletonOptions(roleInfo);
+        var singletonOptions = BuildClusterRedundancySingletonOptions(clusterOptions);
 
         builder.WithSingleton<RedundancyStateActorKey>(
             RedundancyStateSingletonName,
@@ -216,13 +216,23 @@ public static class ServiceCollectionExtensions
     /// (b) on a genuinely split 2-node mesh the <c>driver</c> role is already pair-local — the mesh IS
     /// the pair. So the fallback is correct in both worlds and costs no availability.
     /// </remarks>
-    /// <param name="roleInfo">The local node's cluster-role view.</param>
+    /// <param name="clusterOptions">The node's own cluster configuration (roles), read without the
+    /// ActorSystem so this is safe to call inside the Akka configurator lambda.</param>
     /// <returns>Singleton options scoped to the node's cluster role, or the <c>driver</c> role.</returns>
-    public static ClusterSingletonOptions BuildClusterRedundancySingletonOptions(IClusterRoleInfo roleInfo)
+    public static ClusterSingletonOptions BuildClusterRedundancySingletonOptions(AkkaClusterOptions clusterOptions)
     {
-        ArgumentNullException.ThrowIfNull(roleInfo);
+        ArgumentNullException.ThrowIfNull(clusterOptions);
 
-        return new ClusterSingletonOptions { Role = roleInfo.ClusterRole ?? RoleParser.Driver };
+        // Derive the cluster-{ClusterId} scope from the node's OWN configured roles — NOT from
+        // IClusterRoleInfo. IClusterRoleInfo's implementation depends on the ActorSystem (it is a live
+        // Cluster.State view), and this runs inside the AddAkka configurator lambda WHILE the
+        // ActorSystem is being built; resolving IClusterRoleInfo there recurses back into ActorSystem
+        // construction and stack-overflows the host at boot (the Phase 6 live gate caught exactly this
+        // on the fused central node). AkkaClusterOptions is pure configuration, available before the
+        // cluster forms — the same source ClusterRoleInfo.ClusterRole itself derives from — so the
+        // scope is identical. First cluster role wins, in configuration order (matching ClusterRoleInfo).
+        var clusterRole = clusterOptions.Roles.FirstOrDefault(RoleParser.IsClusterRole);
+        return new ClusterSingletonOptions { Role = clusterRole ?? RoleParser.Driver };
     }
 }
 

src/Server/ZB.MOM.WW.OtOpcUa.Host/Program.cs

@@ -2,6 +2,7 @@ using Akka.Actor;
 using Akka.Hosting;
 using Microsoft.AspNetCore.Server.Kestrel.Core;
 using Microsoft.Extensions.DependencyInjection.Extensions;
+using Microsoft.Extensions.Options;
 using Serilog;
 using ZB.MOM.WW.LocalDb.Replication;
 using Serilog.Events;
@@ -380,9 +381,12 @@ builder.Services.AddAkka("otopcua", (ab, sp) =>
         // back to the driver role for legacy single-mesh / not-yet-migrated nodes (already pair-local
         // on a split mesh, since the mesh IS the pair). Runs on the fused central node too (it is
         // hasDriver), where it scopes to cluster-MAIN — exactly one redundancy singleton per node,
-        // since the admin branch above no longer registers one. IClusterRoleInfo is registered by
+        // since the admin branch above no longer registers one. Pass AkkaClusterOptions (pure config),
-        // AddOtOpcUaCluster and resolved lazily here.
+        // NOT IClusterRoleInfo: this lambda runs WHILE the ActorSystem is being built, and
-        ab.WithOtOpcUaClusterRedundancySingleton(sp.GetRequiredService<IClusterRoleInfo>());
+        // IClusterRoleInfo depends on the ActorSystem — resolving it here recurses into ActorSystem
+        // construction and stack-overflows the host at boot. The singleton scope only needs the node's
+        // configured cluster role, which AkkaClusterOptions carries.
+        ab.WithOtOpcUaClusterRedundancySingleton(sp.GetRequiredService<IOptions<AkkaClusterOptions>>().Value);
     }
 });
 

tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests/RedundancyStateSingletonRehomeTests.cs

@@ -36,7 +36,7 @@ public sealed class RedundancyStateSingletonRehomeTests
     public void Options_scope_the_singleton_to_the_nodes_cluster_role()
     {
         var options = ServiceCollectionExtensions.BuildClusterRedundancySingletonOptions(
-            new FakeClusterRoleInfo(clusterRole: "cluster-SITE-A", clusterId: "SITE-A"));
+            new AkkaClusterOptions { Roles = new[] { "driver", "cluster-SITE-A" } });
 
         options.Role.ShouldBe("cluster-SITE-A");
     }
@@ -51,7 +51,7 @@ public sealed class RedundancyStateSingletonRehomeTests
     public void Missing_cluster_role_falls_back_to_the_driver_role()
     {
         var options = ServiceCollectionExtensions.BuildClusterRedundancySingletonOptions(
-            new FakeClusterRoleInfo(clusterRole: null, clusterId: null));
+            new AkkaClusterOptions { Roles = new[] { "admin", "driver" } });
 
         options.Role.ShouldBe(RoleParser.Driver);
     }
@@ -83,7 +83,7 @@ public sealed class RedundancyStateSingletonRehomeTests
         var registry = await BootAndGetRegistryAsync(
             roles: new[] { "driver", "cluster-SITE-A" },
             configure: ab => ab.WithOtOpcUaClusterRedundancySingleton(
-                new FakeClusterRoleInfo(clusterRole: "cluster-SITE-A", clusterId: "SITE-A")));
+                new AkkaClusterOptions { Roles = new[] { "driver", "cluster-SITE-A" } }));
 
         registry.TryGet<RedundancyStateActorKey>(out _).ShouldBeTrue(
             "every driver node hosts its own mesh's redundancy singleton (Phase 6)");
@@ -102,7 +102,7 @@ public sealed class RedundancyStateSingletonRehomeTests
         var registry = await BootAndGetRegistryAsync(
             roles: new[] { "driver" },
             configure: ab => ab.WithOtOpcUaClusterRedundancySingleton(
-                new FakeClusterRoleInfo(clusterRole: null, clusterId: null)));
+                new AkkaClusterOptions { Roles = new[] { "driver" } }));
 
         registry.TryGet<RedundancyStateActorKey>(out _).ShouldBeTrue(
             "a driver node with no cluster role falls back to the driver role and still boots + registers");