fix(redundancy): key redundancy-state snapshot by canonical host:port NodeId (was host-only — broke ServiceLevel + scripted-alarm emit gate)

2026-06-11 09:56:17 -04:00
parent 23a4a0093b
commit e241332a24
2 changed files with 37 additions and 1 deletions
@@ -42,4 +42,30 @@ public sealed class RedundancyStateActorTests : ControlPlaneActorTestBase
        // After debounce settles, no more events are fired by a quiescent cluster.
        probe.ExpectNoMsg(TimeSpan.FromMilliseconds(500));
    }
+
+    /// <summary>
+    /// Regression guard: the snapshot node id MUST be the canonical <c>host:port</c> form (matching
+    /// ClusterRoleInfo.LocalNode/ToNodeId), or every consumer's
+    /// <c>n.NodeId == _localNode.Value</c> match fails and no node ever learns its role.
+    /// </summary>
+    [Fact]
+    public void ToNodeId_uses_canonical_host_and_port()
+    {
+        var nodeId = RedundancyStateActor.ToNodeId(
+            new Address("akka.tcp", "otopcua", "central-2", 4053));
+
+        nodeId.Value.ShouldBe("central-2:4053");
+    }
+
+    /// <summary>
+    /// Documents the host-less/port-less fallback (<c>:0</c>). Such members are skipped by
+    /// BuildSnapshot's guard, but the helper must still format deterministically.
+    /// </summary>
+    [Fact]
+    public void ToNodeId_handles_missing_port()
+    {
+        var nodeId = RedundancyStateActor.ToNodeId(new Address("akka.tcp", "otopcua"));
+
+        nodeId.Value.ShouldBe(":0");
+    }
 }