Instrument the historian plugin with runtime query health counters and read-only cluster failover so operators can detect silent query degradation and keep serving history when a single cluster node goes down

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/ZB.MOM.WW.LmxOpcUa.Host/Historian/HistorianHealthSnapshot.cs

@@ -0,0 +1,97 @@
+using System;
+using System.Collections.Generic;
+
+namespace ZB.MOM.WW.LmxOpcUa.Host.Historian
+{
+    /// <summary>
+    ///     Point-in-time runtime health of the historian plugin, surfaced to the status dashboard
+    ///     and health check service. Fills the gap between the load-time plugin status
+    ///     (<see cref="HistorianPluginLoader.LastOutcome"/>) and actual query behavior so operators
+    ///     can detect silent query degradation.
+    /// </summary>
+    public sealed class HistorianHealthSnapshot
+    {
+        /// <summary>
+        ///     Gets or sets the total number of historian read operations attempted since startup
+        ///     across all read paths (raw, aggregate, at-time, events).
+        /// </summary>
+        public long TotalQueries { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the total number of read operations that completed without an exception
+        ///     being caught by the plugin's error handler. Includes empty result sets as successes —
+        ///     the counter reflects "the SDK call returned" not "the SDK call returned data".
+        /// </summary>
+        public long TotalSuccesses { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the total number of read operations that raised an exception. Each failure
+        ///     also resets and closes the underlying SDK connection via the existing reconnect path.
+        /// </summary>
+        public long TotalFailures { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the number of consecutive failures since the last success. Latches until
+        ///     a successful query clears it. The health check service uses this as a degradation signal.
+        /// </summary>
+        public int ConsecutiveFailures { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the UTC timestamp of the last successful read, or <see langword="null"/>
+        ///     when no query has succeeded since startup.
+        /// </summary>
+        public DateTime? LastSuccessTime { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the UTC timestamp of the last failure, or <see langword="null"/> when no
+        ///     query has failed since startup.
+        /// </summary>
+        public DateTime? LastFailureTime { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the exception message from the most recent failure. Cleared on the next
+        ///     successful query.
+        /// </summary>
+        public string? LastError { get; set; }
+
+        /// <summary>
+        ///     Gets or sets a value indicating whether the plugin currently holds an open SDK
+        ///     connection for the process (historical values) path.
+        /// </summary>
+        public bool ProcessConnectionOpen { get; set; }
+
+        /// <summary>
+        ///     Gets or sets a value indicating whether the plugin currently holds an open SDK
+        ///     connection for the event (alarm history) path.
+        /// </summary>
+        public bool EventConnectionOpen { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the node the plugin is currently connected to for the process path,
+        ///     or <see langword="null"/> when no connection is open.
+        /// </summary>
+        public string? ActiveProcessNode { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the node the plugin is currently connected to for the event path,
+        ///     or <see langword="null"/> when no event connection is open.
+        /// </summary>
+        public string? ActiveEventNode { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the total number of configured historian cluster nodes. A value of 1
+        ///     reflects a legacy single-node deployment.
+        /// </summary>
+        public int NodeCount { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the number of configured nodes that are currently healthy (not in cooldown).
+        /// </summary>
+        public int HealthyNodeCount { get; set; }
+
+        /// <summary>
+        ///     Gets or sets the per-node cluster state in configuration order.
+        /// </summary>
+        public List<HistorianClusterNodeState> Nodes { get; set; } = new();
+    }
+}