feat(telemetry): deploy-failure, S&F activity, script-run and DCL-transition instruments (ScadaBridge#81)

Adds four instruments on the already-allow-listed ZB.MOM.WW.ScadaBridge meter: scadabridge.deployments.failed{reason}, scadabridge.store_and_forward.activity{action,category}, scadabridge.site.script.runs{outcome} + scadabridge.site.script.duration{outcome} (ms), scadabridge.site.data_connections.transitions{state}. Queue depth, DCL connection state and deploy-applied already existed. No new Meter, so ZbTelemetryOptions.Meters needs no change. Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
2026-11-09 14:17:53 -05:00
parent 7892c622cf
commit 5ef27fd9a3
8 changed files with 301 additions and 0 deletions
@@ -0,0 +1,98 @@
+using System.Diagnostics.Metrics;
+using ZB.MOM.WW.ScadaBridge.Commons.Observability;
+using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
+
+namespace ZB.MOM.WW.ScadaBridge.Commons.Tests.Observability;
+
+/// <summary>
+/// ScadaBridge#81: the instruments added beyond the first set. Each is observed through a
+/// <see cref="MeterListener"/> filtered to the emitting (test) thread, because the meter is
+/// process-global and other tests emit on it concurrently.
+/// </summary>
+public sealed class ExtendedInstrumentTests
+{
+    private static List<(long Value, Dictionary<string, object?> Tags)> Capture(string instrument, Action act)
+    {
+        var tid = Environment.CurrentManagedThreadId;
+        var got = new List<(long, Dictionary<string, object?>)>();
+        using var listener = new MeterListener
+        {
+            InstrumentPublished = (i, l) =>
+            {
+                if (i.Meter.Name == ScadaBridgeTelemetry.MeterName && i.Name == instrument)
+                    l.EnableMeasurementEvents(i);
+            }
+        };
+        listener.SetMeasurementEventCallback<long>((_, m, tags, _) =>
+        {
+            if (Environment.CurrentManagedThreadId != tid) return;
+            var d = new Dictionary<string, object?>();
+            foreach (var t in tags) d[t.Key] = t.Value;
+            got.Add((m, d));
+        });
+        listener.Start();
+        act();
+        return got;
+    }
+
+    /// <summary>A state change emits one transition tagged with the new state; repeating the same state emits none.</summary>
+    [Fact]
+    public void DataConnectionTransitions_EmitOnlyOnRealStateChange()
+    {
+        var name = "xfer-" + Guid.NewGuid().ToString("N");
+        try
+        {
+            var got = Capture("scadabridge.site.data_connections.transitions", () =>
+            {
+                ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connecting);
+                ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);
+                ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Connected);
+                ScadaBridgeTelemetry.RecordDataConnectionState(name, ConnectionHealth.Disconnected);
+            });
+
+            Assert.Equal(
+                new object?[] { "Connecting", "Connected", "Disconnected" },
+                got.Select(g => g.Tags["state"]).ToArray());
+        }
+        finally { ScadaBridgeTelemetry.RemoveDataConnection(name); }
+    }
+
+    /// <summary>Store-and-forward activity is counted by action and category.</summary>
+    [Fact]
+    public void StoreAndForwardActivity_IsCountedByActionAndCategory()
+    {
+        var got = Capture("scadabridge.store_and_forward.activity",
+            () => ScadaBridgeTelemetry.RecordStoreAndForwardActivity("Parked", "ExternalSystem"));
+
+        var m = Assert.Single(got);
+        Assert.Equal(1, m.Value);
+        Assert.Equal("Parked", m.Tags["action"]);
+        Assert.Equal("ExternalSystem", m.Tags["category"]);
+    }
+
+    /// <summary>Deployment failures are counted by reason.</summary>
+    [Fact]
+    public void DeploymentsFailed_IsCountedByReason()
+    {
+        var got = Capture("scadabridge.deployments.failed",
+            () => ScadaBridgeTelemetry.RecordDeploymentFailed("timeout"));
+
+        var m = Assert.Single(got);
+        Assert.Equal("timeout", m.Tags["reason"]);
+    }
+
+    /// <summary>A script run emits both the run counter and the duration histogram, clamping negatives.</summary>
+    [Fact]
+    public void ScriptRun_EmitsCounterAndDuration()
+    {
+        var runs = Capture("scadabridge.site.script.runs",
+            () => ScadaBridgeTelemetry.RecordScriptRun("failed", 5));
+        Assert.Equal("failed", Assert.Single(runs).Tags["outcome"]);
+
+        var durations = Capture("scadabridge.site.script.duration",
+            () => ScadaBridgeTelemetry.RecordScriptRun("completed", -3));
+        var d = Assert.Single(durations);
+        Assert.Equal(0, d.Value);
+        Assert.Equal("completed", d.Tags["outcome"]);
+    }
+}