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
@@ -1063,6 +1063,45 @@ public class DeploymentServiceTests : TestKit
        Assert.Equal(1, Interlocked.Read(ref applied));
    }

+    /// <summary>Verifies a faulted deployment emits the deployments failed counter tagged reason=error (ScadaBridge#81).</summary>
+    /// <returns>A task that represents the asynchronous operation.</returns>
+    [Fact]
+    public async Task DeployInstanceAsync_Fault_EmitsDeploymentsFailedCounter()
+    {
+        var instance = new Instance("FailMetricInst") { Id = 1, SiteId = 1, State = InstanceState.NotDeployed };
+        _repo.GetInstanceByIdAsync(1).Returns(instance);
+        var config = new FlattenedConfiguration { InstanceUniqueName = "FailMetricInst" };
+        _pipeline.FlattenAndValidateAsync(1, Arg.Any<CancellationToken>())
+            .Returns(Result<FlatteningPipelineResult>.Success(
+                new FlatteningPipelineResult(config, "sha256:abc", ValidationResult.Success())));
+
+        var reasons = new System.Collections.Concurrent.ConcurrentQueue<string?>();
+        using var listener = new MeterListener
+        {
+            InstrumentPublished = (instrument, l) =>
+            {
+                if (instrument.Meter.Name == ScadaBridgeTelemetry.MeterName
+                    && instrument.Name == "scadabridge.deployments.failed")
+                {
+                    l.EnableMeasurementEvents(instrument);
+                }
+            }
+        };
+        listener.SetMeasurementEventCallback<long>((_, _, tags, _) =>
+        {
+            foreach (var t in tags)
+                if (t.Key == "reason") reasons.Enqueue(t.Value as string);
+        });
+        listener.Start();
+
+        // _comms has no actor set -> non-timeout fault -> MarkDeploymentFailedAsync.
+        var result = await _service.DeployInstanceAsync(1, "admin");
+        listener.Dispose();
+
+        Assert.True(result.IsFailure);
+        Assert.Contains("error", reasons);
+    }
+
    /// <summary>Verifies that deploy instance async reconciled does not emit deployments applied counter.</summary>
    /// <returns>A task that represents the asynchronous operation.</returns>
    [Fact]