fix(audit): maintenance-login roll-forward/backfill, archive orphan cleanup, head-export health (ScadaBridge#113 #114 #115)

#113: AuditLogPartitionMaintenance (monthly SPLIT RANGE) and the backfill-source-node endpoint now use the AuditLog:MaintenanceConnectionString login when set (unset = unchanged). Migration AuditMaintenanceGrants gives scadabridge_audit_purger ALTER ANY DATASPACE and column-level UPDATE (SourceNode). #114: archive cleanup deletes the writer's own *.tmp files and manifest-less data files older than 24 h inside {Directory}/{YYYY} (DeletedOrphan, dry-run aware). #115: head-export failures bump scadabridge.audit.chain_head_export.failures and Degrade the /health/ready entry audit-chain-head-export (failing or stale > 2 intervals). Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
2026-11-09 23:47:47 -05:00
parent b95ee5a658
commit 533414a16d
19 changed files with 2943 additions and 16 deletions
@@ -50,7 +50,8 @@ public sealed class AuditChainHeadExportServiceTests
        new DateTime(2026, month, 1, 0, 0, 0, DateTimeKind.Utc), seq, Enumerable.Repeat((byte)seq, 32).ToArray(),
        null, null, rows, 0, new DateTime(2026, month, 2, 0, 0, 0, DateTimeKind.Utc));

-    private static (AuditChainHeadExportService Service, FakeStore Store, RecordingSink Sink) Create(bool exportUnchanged = false)
+    private static (AuditChainHeadExportService Service, FakeStore Store, RecordingSink Sink) Create(
+        bool exportUnchanged = false, AuditChainHeadExportStatus? status = null, TimeProvider? time = null)
    {
        var store = new FakeStore();
        var sink = new RecordingSink();
@@ -62,7 +63,7 @@ public sealed class AuditChainHeadExportServiceTests
        });
        var service = new AuditChainHeadExportService(
            services.BuildServiceProvider().GetRequiredService<IServiceScopeFactory>(),
-            options, sink, "central-a", NullLogger<AuditChainHeadExportService>.Instance);
+            options, sink, "central-a", NullLogger<AuditChainHeadExportService>.Instance, time, status);
        return (service, store, sink);
    }

@@ -120,6 +121,48 @@ public sealed class AuditChainHeadExportServiceTests
        Assert.Equal(10, Assert.Single(Assert.Single(sink.Writes)).LastSeq);
    }

+    /// <summary>
+    /// ScadaBridge#115: a failed tick bumps the failure counter metric and the status
+    /// (consecutive + total + last error); the next success clears the consecutive count.
+    /// </summary>
+    /// <returns>A task that represents the asynchronous operation.</returns>
+    [Fact]
+    public async Task FailedTick_RecordsMetricAndStatus_SuccessResetsConsecutive()
+    {
+        var status = new AuditChainHeadExportStatus();
+        var (service, store, sink) = Create(status: status);
+        store.Heads.Add(Head(4, 10, 10));
+        long measured = 0;
+        using var listener = new System.Diagnostics.Metrics.MeterListener();
+        listener.InstrumentPublished = (i, l) =>
+        {
+            if (i.Name == "scadabridge.audit.chain_head_export.failures")
+            {
+                l.EnableMeasurementEvents(i);
+            }
+        };
+        listener.SetMeasurementEventCallback<long>((_, v, _, _) => Interlocked.Add(ref measured, v));
+        listener.Start();
+
+        sink.Fail = true;
+        await service.TickAsync(default);
+        await service.TickAsync(default);
+
+        Assert.Equal(2, Interlocked.Read(ref measured));
+        Assert.Equal(2, status.ConsecutiveFailures);
+        Assert.Equal(2, status.TotalFailures);
+        Assert.Equal("share offline", status.LastError);
+        Assert.Null(status.LastSuccessUtc);
+
+        sink.Fail = false;
+        await service.TickAsync(default);
+
+        Assert.Equal(0, status.ConsecutiveFailures);
+        Assert.Equal(2, status.TotalFailures);
+        Assert.NotNull(status.LastSuccessUtc);
+        Assert.Equal(2, Interlocked.Read(ref measured));
+    }
+
    /// <summary>The validator ignores a disabled export and checks each sink's settings when enabled.</summary>
    /// <param name="configure">Which settings to apply.</param>
    /// <param name="expectedError">A fragment of the expected failure, or null when valid.</param>