fix(cluster): AkkaClusterOptions.Roles is the EffectiveRoles instance, not a second derivation

archreview/plans/R3-04-one-role-authority-plan.md.tasks.json

@@ -11,7 +11,7 @@
     {
       "id": "T2",
       "subject": "AddOtOpcUaCluster post-configures AkkaClusterOptions.Roles from the registered EffectiveRoles instance (structural identity, no second derivation)",
-      "status": "pending",
+      "status": "completed",
       "blockedBy": [
         "T1"
       ]

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

@@ -6,6 +6,7 @@ using Akka.Logger.Serilog;
 using Akka.Remote.Hosting;
 using Microsoft.Extensions.Configuration;
 using Microsoft.Extensions.DependencyInjection;
+using Microsoft.Extensions.DependencyInjection.Extensions;
 using Microsoft.Extensions.Options;
 using ZB.MOM.WW.Configuration;
 using ZB.MOM.WW.OtOpcUa.Commons.Interfaces;
@@ -34,21 +35,31 @@ public static class ServiceCollectionExtensions
         services.AddValidatedOptions<AkkaClusterOptions, AkkaClusterOptionsValidator>(
             configuration, AkkaClusterOptions.SectionName);
 
-        // Gitea #532: apply the OTOPCUA_ROLES fallback the Roles property has always DOCUMENTED, in the
+        // R3-04 (structural identity, choice 3): EffectiveRoles is resolved ONCE and registered as a
-        // one place every consumer reads through. Before this, a node configured only through the env
+        // singleton, off the SAME IConfiguration this call received — not off a DI-resolved
-        // var — the knob that drives all of Program.cs's role wiring — bound an EMPTY Roles array and so
+        // IConfiguration, which a plain ServiceCollection (as opposed to a WebApplicationBuilder) never
-        // joined the cluster role-less: invisible to RoleLeader/MembersWithRole, ineligible for every
+        // registers. Every consumer (Program.cs's hasAdmin/hasDriver, the four role-scoped validators,
-        // role-scoped singleton, and un-deployable ("no driver-role nodes are Up") with nothing in its
+        // AkkaClusterOptions.Roles below) therefore reads the exact same instance, so there is no second
-        // own logs to say so. Doing it here rather than at each call site means BuildClusterOptions
+        // derivation left to disagree with — the boot-guard OVERALL asked for is this identity, not a
-        // (Akka's own member roles), ClusterRoleInfo, the ControlPlane singleton scope and
+        // runtime assert (see EffectiveRoles + AkkaClusterOptionsValidator's post-overlay guard).
-        // ConfigDbApiKeyStore's ClusterId all see the same answer.
+        // TryAddSingleton keeps this usable from a harness that registers its own EffectiveRoles first.
+        services.TryAddSingleton(_ => EffectiveRoles.Resolve(configuration));
+
+        // Gitea #532 (superseded by R3-04): apply the OTOPCUA_ROLES fallback the Roles property has
+        // always DOCUMENTED, in the one place every consumer reads through. Before this, a node
+        // configured only through the env var — the knob that drives all of Program.cs's role wiring —
+        // bound an EMPTY Roles array and so joined the cluster role-less: invisible to
+        // RoleLeader/MembersWithRole, ineligible for every role-scoped singleton, and un-deployable
+        // ("no driver-role nodes are Up") with nothing in its own logs to say so. Doing it here rather
+        // than at each call site means BuildClusterOptions (Akka's own member roles), ClusterRoleInfo,
+        // the ControlPlane singleton scope and ConfigDbApiKeyStore's ClusterId all see the same answer.
         //
         // PostConfigure, not a bind trick: it runs after the section binds and before ValidateOnStart,
-        // so the validators below see the effective list. An unknown role in the env var throws out of
+        // so the validators below see the effective list. Now consumes the registered EffectiveRoles
-        // RoleParser.Parse — the same throw Program.cs already takes on the same value, so an invalid
+        // instance rather than re-deriving from options.Roles + the environment — options.Roles becomes
-        // env var cannot reach here on the production path in the first place.
+        // BY CONSTRUCTION the same list Program.cs's hasAdmin/hasDriver are computed from.
-        services.PostConfigure<AkkaClusterOptions>(
+        services.AddOptions<AkkaClusterOptions>().PostConfigure<EffectiveRoles>(
-            options => options.Roles = RoleParser.ResolveEffectiveRoles(options.Roles));
+            (options, roles) => options.Roles = [.. roles.Gossiped]);
 
         // Per-cluster mesh Phase 2: which transport carries central→node commands. Validated at
         // startup for the same reason the cluster options are — a contact point that cannot resolve

tests/Core/ZB.MOM.WW.OtOpcUa.Cluster.Tests/AkkaClusterOptionsRoleFallbackTests.cs

@@ -94,4 +94,34 @@ public class AkkaClusterOptionsRoleFallbackTests
             RoleParser.ClusterIdFromRoles(Bind().Roles).ShouldBe("site-a");
         }
     }
+
+    /// <summary>
+    ///     R3-04 (structural identity, choice 3): <c>AkkaClusterOptions.Roles</c> is not a SECOND
+    ///     derivation of the role rule — it is the registered <see cref="EffectiveRoles"/> instance's
+    ///     <see cref="EffectiveRoles.Gossiped"/> list, verbatim. A mixed-case configured role proves
+    ///     both the normalization (plain lowered, cluster suffix preserved) and the identity: the two
+    ///     views can never disagree because there is only one derivation.
+    /// </summary>
+    [Fact]
+    public void Bound_options_Roles_IS_the_registered_EffectiveRoles_Gossiped_list()
+    {
+        var configuration = new ConfigurationBuilder()
+            .AddInMemoryCollection(new Dictionary<string, string?>
+            {
+                ["Cluster:Roles:0"] = "Driver",
+                ["Cluster:Roles:1"] = "Cluster-SITE-A",
+            })
+            .Build();
+
+        var services = new ServiceCollection();
+        services.AddLogging();
+        services.AddOtOpcUaCluster(configuration);
+        var provider = services.BuildServiceProvider();
+
+        var bound = provider.GetRequiredService<IOptions<AkkaClusterOptions>>().Value;
+        var effectiveRoles = provider.GetRequiredService<EffectiveRoles>();
+
+        bound.Roles.ShouldBe(new[] { "driver", "cluster-SITE-A" });
+        bound.Roles.ShouldBe(effectiveRoles.Gossiped);
+    }
 }