feat(health): additive script-scheduler stats on ISiteHealthCollector + SiteHealthReport (S2/UA5)

src/ZB.MOM.WW.ScadaBridge.Commons/Messages/Health/SiteHealthReport.cs

@@ -54,7 +54,26 @@ public record SiteHealthReport(
     // signal surfaces a forgotten site's stale backlog (count alone hides age).
     // Additive-only trailing member — defaults to null for producers / tests that
     // don't populate it.
-    double? OldestParkedMessageAgeSeconds = null);
+    double? OldestParkedMessageAgeSeconds = null)
+{
+    // Script-execution-scheduler gauges (S2/UA5), surfaced additively as init
+    // properties (rather than positional parameters) so the constructor signature
+    // is untouched. Point-in-time, refreshed on the site by ScriptSchedulerStatsReporter;
+    // safe defaults for producers / tests that don't populate them.
+
+    /// <summary>Script tasks waiting to run on the dedicated script-execution scheduler.</summary>
+    public int ScriptQueueDepth { get; init; }
+
+    /// <summary>Script-execution worker threads currently running a script body.</summary>
+    public int ScriptBusyThreads { get; init; }
+
+    /// <summary>
+    /// Age (seconds) of the oldest in-flight script across the scheduler's worker
+    /// threads, or null when the pool is idle. A large value with all threads busy
+    /// indicates a stuck/blocked script holding a dedicated thread.
+    /// </summary>
+    public double? ScriptOldestBusyAgeSeconds { get; init; }
+}
 
 /// <summary>
 /// Broadcast wrapper used between central nodes to keep per-node

src/ZB.MOM.WW.ScadaBridge.HealthMonitoring/ISiteHealthCollector.cs

@@ -141,6 +141,24 @@ public interface ISiteHealthCollector
         // SiteHealthCollector overrides this with the Interlocked.Exchange store.
     }
 
+    /// <summary>
+    /// Replace the latest script-execution-scheduler gauges (queue depth, busy
+    /// thread count, and age in seconds of the oldest in-flight script) used by
+    /// the next <see cref="CollectReport"/> call. Refreshed periodically by the
+    /// <c>ScriptSchedulerStatsReporter</c> hosted service. Point-in-time: the
+    /// values are NOT reset on <see cref="CollectReport"/>. S2/UA5 — surfaces a
+    /// saturated or stuck script-execution pool on the site health report.
+    /// Default interface implementation is a no-op so existing test fakes continue
+    /// to compile without per-fake updates.
+    /// </summary>
+    /// <param name="queueDepth">Script tasks waiting to run.</param>
+    /// <param name="busyThreads">Worker threads currently executing a script.</param>
+    /// <param name="oldestBusyAgeSeconds">Age (seconds) of the oldest in-flight script, or <c>null</c> when idle.</param>
+    void SetScriptSchedulerStats(int queueDepth, int busyThreads, double? oldestBusyAgeSeconds)
+    {
+        // Default no-op so test fakes do not need to be updated.
+    }
+
     /// <summary>
     /// Sets the hostname of this node.
     /// </summary>

src/ZB.MOM.WW.ScadaBridge.HealthMonitoring/SiteHealthCollector.cs

@@ -29,6 +29,12 @@ public class SiteHealthCollector : ISiteHealthCollector
     // be read/written atomically via Interlocked (double? is neither atomic nor
     // volatile-able). NaN is the "no parked rows" sentinel (ages are always >= 0).
     private long _oldestParkedAgeBits = BitConverter.DoubleToInt64Bits(double.NaN);
+    // Script-execution-scheduler gauges (S2/UA5), point-in-time, refreshed by the
+    // ScriptSchedulerStatsReporter. Oldest-busy age stored as double bits like the
+    // parked-age above; NaN = idle (no in-flight script).
+    private int _scriptQueueDepth;
+    private int _scriptBusyThreads;
+    private long _scriptOldestBusyAgeBits = BitConverter.DoubleToInt64Bits(double.NaN);
     private volatile string _nodeHostname = "";
     private volatile IReadOnlyList<Commons.Messages.Health.NodeStatus>? _clusterNodes;
     private volatile bool _isActiveNode;
@@ -141,6 +147,22 @@ public class SiteHealthCollector : ISiteHealthCollector
         return double.IsNaN(value) ? null : value;
     }
 
+    /// <inheritdoc />
+    public void SetScriptSchedulerStats(int queueDepth, int busyThreads, double? oldestBusyAgeSeconds)
+    {
+        Interlocked.Exchange(ref _scriptQueueDepth, queueDepth);
+        Interlocked.Exchange(ref _scriptBusyThreads, busyThreads);
+        Interlocked.Exchange(ref _scriptOldestBusyAgeBits,
+            BitConverter.DoubleToInt64Bits(oldestBusyAgeSeconds ?? double.NaN));
+    }
+
+    /// <summary>Reads the atomically-stored oldest-busy script age, mapping the NaN sentinel back to null.</summary>
+    private double? ReadScriptOldestBusyAgeSeconds()
+    {
+        var value = BitConverter.Int64BitsToDouble(Interlocked.Read(ref _scriptOldestBusyAgeBits));
+        return double.IsNaN(value) ? null : value;
+    }
+
     /// <inheritdoc />
     public void SetNodeHostname(string hostname) => _nodeHostname = hostname;
 
@@ -233,6 +255,11 @@ public class SiteHealthCollector : ISiteHealthCollector
             AuditRedactionFailure: auditRedactionFailures,
             SiteAuditBacklog: _siteAuditBacklog,
             SiteEventLogWriteFailures: Interlocked.Read(ref _siteEventLogWriteFailures),
-            OldestParkedMessageAgeSeconds: ReadOldestParkedAgeSeconds());
+            OldestParkedMessageAgeSeconds: ReadOldestParkedAgeSeconds())
+        {
+            ScriptQueueDepth = Interlocked.CompareExchange(ref _scriptQueueDepth, 0, 0),
+            ScriptBusyThreads = Interlocked.CompareExchange(ref _scriptBusyThreads, 0, 0),
+            ScriptOldestBusyAgeSeconds = ReadScriptOldestBusyAgeSeconds()
+        };
     }
 }

tests/ZB.MOM.WW.ScadaBridge.HealthMonitoring.Tests/SiteHealthCollectorTests.cs

@@ -38,6 +38,25 @@ public class SiteHealthCollectorTests
         Assert.Equal(2, report.AlarmEvaluationErrorCount);
     }
 
+    [Fact]
+    public void CollectReport_CarriesScriptSchedulerStats()
+    {
+        _collector.SetScriptSchedulerStats(queueDepth: 7, busyThreads: 3, oldestBusyAgeSeconds: 42.5);
+        var report = _collector.CollectReport("site-1");
+        Assert.Equal(7, report.ScriptQueueDepth);
+        Assert.Equal(3, report.ScriptBusyThreads);
+        Assert.Equal(42.5, report.ScriptOldestBusyAgeSeconds);
+    }
+
+    [Fact]
+    public void CollectReport_ScriptSchedulerStats_DefaultToZeroAndNull()
+    {
+        var report = _collector.CollectReport("site-1");
+        Assert.Equal(0, report.ScriptQueueDepth);
+        Assert.Equal(0, report.ScriptBusyThreads);
+        Assert.Null(report.ScriptOldestBusyAgeSeconds);
+    }
+
     [Fact]
     public void IncrementDeadLetter_AccumulatesBetweenReports()
     {