feat(config): add ClusterNode.MaintenanceMode — the hatch the live gate proved missing

Phase 1 gate step 4 failed: setting Enabled = 0 to take a node out of service
returns 422 ClusterEnabledNodeCountMismatch, because
DraftValidator.ValidateClusterTopology requires the enabled-node count to equal
ServerCluster.NodeCount. On a Warm/Hot pair — every cluster on the rig, and
every cluster in the target topology — Enabled can therefore never be the
maintenance hatch. The plan called step 4 "the check that makes step 3
acceptable to ship", so Task 3's behaviour change was not shippable as it stood:
a node down for maintenance would block every deployment to its cluster.

The two rules were each reasonable and contradictory together — the validator
reads Enabled as "part of the declared topology", Phase 1 additionally read it
as "expect an ack". Split the meanings rather than weaken either rule:

  Enabled          part of the declared topology  (validator, untouched)
  MaintenanceMode  expected to participate now    (coordinator + reconciler)

Rejected alternatives: counting configured rather than enabled nodes (drops the
guard against booting a pair into InvalidTopology); downgrading the rule to a
warning (weakens a deploy gate for everyone); shipping with no hatch.

Sabotage: dropping !n.MaintenanceMode from the coordinator query turns the new
test red. It also asserts both nodes remain Enabled, so the fix cannot quietly
regress to disabling the row after all.

Configuration.Tests 95/95, ControlPlane.Tests 101/101, solution builds clean.

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

src/Server/ZB.MOM.WW.OtOpcUa.ControlPlane/Fleet/ClusterNodeAddressReconciler.cs

@@ -75,21 +75,22 @@ public static class ClusterNodeAddressReconciler
     ///     them would report a mismatch for correct configuration.
     /// </param>
     /// <param name="rows">Every <c>ClusterNode</c> row, enabled or not.</param>
-    /// <param name="enabledNodeIds">
-    ///     The subset of <paramref name="rows"/> that is enabled. Disabled rows are deliberately
-    ///     still matched against membership (a disabled row for a running node is worth knowing) but
-    ///     never reported as <see cref="AddressMismatchKind.EnabledRowNotInCluster"/> — being absent
-    ///     is the whole point of disabling one.
+    /// <param name="expectedPresentNodeIds">
+    ///     The subset of <paramref name="rows"/> that should currently be in the cluster: enabled and
+    ///     not in maintenance. Excluded rows are deliberately still matched against membership (a
+    ///     disabled row for a running node is worth knowing) but never reported as
+    ///     <see cref="AddressMismatchKind.EnabledRowNotInCluster"/> — being absent is the whole point
+    ///     of disabling one or putting it in maintenance.
     /// </param>
     /// <returns>Every disagreement found, ordered by node id for stable logging.</returns>
     public static IReadOnlyList<ClusterNodeAddressMismatch> Reconcile(
         IReadOnlyCollection<(string Host, int Port)> observedDriverMembers,
         IReadOnlyCollection<ClusterNodeAddress> rows,
-        IReadOnlyCollection<string> enabledNodeIds)
+        IReadOnlyCollection<string> expectedPresentNodeIds)
     {
         var byNodeId = new Dictionary<string, ClusterNodeAddress>(StringComparer.OrdinalIgnoreCase);
         foreach (var row in rows) byNodeId[row.NodeId] = row;
-        var enabled = new HashSet<string>(enabledNodeIds, StringComparer.OrdinalIgnoreCase);
+        var expectedPresent = new HashSet<string>(expectedPresentNodeIds, StringComparer.OrdinalIgnoreCase);
 
         var findings = new List<ClusterNodeAddressMismatch>();
         var seen = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
@@ -121,12 +122,12 @@ public static class ClusterNodeAddressReconciler
 
         foreach (var row in rows)
         {
-            if (seen.Contains(row.NodeId) || !enabled.Contains(row.NodeId)) continue;
+            if (seen.Contains(row.NodeId) || !expectedPresent.Contains(row.NodeId)) continue;
             findings.Add(new ClusterNodeAddressMismatch(
                 AddressMismatchKind.EnabledRowNotInCluster, row.NodeId,
                 $"enabled ClusterNode row {row.NodeId} has no matching driver member; the next " +
                 "deployment will fail at the apply deadline waiting for it. Start the node, or set " +
-                "ClusterNode.Enabled = 0 while it is down for maintenance"));
+                "ClusterNode.MaintenanceMode = 1 while it is down for maintenance"));
         }
 
         return findings

src/Server/ZB.MOM.WW.OtOpcUa.ControlPlane/Fleet/ClusterNodeAddressReconcilerActor.cs

@@ -89,8 +89,11 @@ public sealed class ClusterNodeAddressReconcilerActor : ReceiveActor, IWithTimer
             rows = db.ClusterNodes.AsNoTracking()
                 .Select(n => new ClusterNodeAddress(n.NodeId, n.Host, n.AkkaPort))
                 .ToList();
+            // Same predicate the coordinator's expected-ack set uses — a node the deploy path will
+            // not wait for must not be reported as missing either, or the maintenance hatch trades a
+            // failed deployment for a permanent warning.
             enabled = db.ClusterNodes.AsNoTracking()
-                .Where(n => n.Enabled).Select(n => n.NodeId).ToList();
+                .Where(n => n.Enabled && !n.MaintenanceMode).Select(n => n.NodeId).ToList();
         }
         catch (Exception ex)
         {