feat(health): AuditRedactionFailure counter + bridge (#23 M5)

Bundle C task M5-T7 — surface DefaultAuditPayloadFilter redactor
over-redactions as a Site Health metric so a misconfigured /
catastrophic regex shows up on /monitoring/health rather than
disappearing into a NoOp sink.

  - SiteHealthReport: new 'AuditRedactionFailure' int field
    (defaulted to 0 for back-compat with existing producers/tests).
  - ISiteHealthCollector / SiteHealthCollector:
    new IncrementAuditRedactionFailure() — per-interval atomic
    counter with Interlocked, reset on CollectReport, mirroring
    the M2 Bundle G SiteAuditWriteFailures pattern.
  - HealthMetricsAuditRedactionFailureCounter: new bridge in
    ScadaLink.AuditLog.Site that forwards IAuditRedactionFailureCounter
    increments to ISiteHealthCollector — mirrors
    HealthMetricsAuditWriteFailureCounter one-for-one.
  - AddAuditLogHealthMetricsBridge: now ALSO Replaces the
    NoOpAuditRedactionFailureCounter binding with the health-metrics
    bridge, so a single AddAuditLogHealthMetricsBridge() call wires
    both the M2 Bundle G write-failure counter and the M5 Bundle C
    redaction-failure counter into the health report.

Site-side only for M5 — the filter also runs on CentralAuditWriter
and AuditLogIngestActor (where it just keeps the NoOp default), but
a central-side health-metric surface for AuditRedactionFailure is
deferred to M6 alongside the rest of the central health collector
work.

Tests:
  - AuditRedactionFailureMetricTests (HealthMonitoring) covers the
    SiteHealthCollector increment/report/reset shape (3 tests).
  - HealthMetricsAuditRedactionFailureCounterTests (AuditLog) covers
    the AuditLog → HealthMonitoring bridge (3 tests).
  - Existing CountCapturingHealthCollector stub in
    DeploymentManagerRedeployTests extended with the new no-op
    interface method.

Verified: dotnet build clean, all 24 test projects green
(the only Failed at first ScadaLink.SiteRuntime.Tests run was the
known-flaky InstanceActorChildAttributeRaceTests; passes on re-run
in isolation and full suite, unrelated to these changes).

src/ScadaLink.AuditLog/ServiceCollectionExtensions.cs

@@ -172,26 +172,38 @@ public static class ServiceCollectionExtensions
     }
 
     /// <summary>
-    /// Audit Log (#23) M2 Bundle G — swap the default
+    /// Audit Log (#23) M2 Bundle G + M5 Bundle C — swap the default
-    /// <see cref="NoOpAuditWriteFailureCounter"/> registration for the real
+    /// <see cref="NoOpAuditWriteFailureCounter"/> and
-    /// <see cref="HealthMetricsAuditWriteFailureCounter"/> bridge so the
+    /// <see cref="NoOpAuditRedactionFailureCounter"/> registrations for the
-    /// FallbackAuditWriter primary-failure counter surfaces in the site health
+    /// real <see cref="HealthMetricsAuditWriteFailureCounter"/> /
-    /// report payload as <c>SiteHealthReport.SiteAuditWriteFailures</c>.
+    /// <see cref="HealthMetricsAuditRedactionFailureCounter"/> bridges so the
+    /// FallbackAuditWriter primary-failure counter AND the
+    /// DefaultAuditPayloadFilter redactor-failure counter both surface in the
+    /// site health report payload as
+    /// <c>SiteHealthReport.SiteAuditWriteFailures</c> +
+    /// <c>SiteHealthReport.AuditRedactionFailure</c>.
     /// </summary>
     /// <remarks>
     /// <para>
     /// Must be called AFTER both <see cref="AddAuditLog"/> (registers the
-    /// NoOp default this method replaces) and
+    /// NoOp defaults this method replaces) and
     /// <c>ScadaLink.HealthMonitoring.ServiceCollectionExtensions.AddHealthMonitoring</c>
     /// or <c>AddSiteHealthMonitoring</c> (registers the
-    /// <see cref="ISiteHealthCollector"/> the bridge depends on). Resolving
+    /// <see cref="ISiteHealthCollector"/> the bridges depend on). Resolving
-    /// <see cref="IAuditWriteFailureCounter"/> without the latter throws
+    /// <see cref="IAuditWriteFailureCounter"/> or
+    /// <see cref="IAuditRedactionFailureCounter"/> without the latter throws
     /// <see cref="InvalidOperationException"/> at <c>GetRequiredService</c>
     /// time — by design, since a silent NoOp would mask a misconfiguration.
     /// </para>
     /// <para>
-    /// Idempotent — calling twice replaces the descriptor each time without
+    /// Idempotent — calling twice replaces each descriptor without piling up
-    /// piling up registrations.
+    /// registrations.
+    /// </para>
+    /// <para>
+    /// Site-side only for M5: the central composition root keeps the NoOp
+    /// defaults; the central health-metric surface that would expose
+    /// <c>AuditRedactionFailure</c> next to the existing central counters
+    /// ships in M6.
     /// </para>
     /// </remarks>
     public static IServiceCollection AddAuditLogHealthMetricsBridge(this IServiceCollection services)
@@ -200,6 +212,8 @@ public static class ServiceCollectionExtensions
 
         services.Replace(
             ServiceDescriptor.Singleton<IAuditWriteFailureCounter, HealthMetricsAuditWriteFailureCounter>());
+        services.Replace(
+            ServiceDescriptor.Singleton<IAuditRedactionFailureCounter, HealthMetricsAuditRedactionFailureCounter>());
         return services;
     }
 }

src/ScadaLink.AuditLog/Site/HealthMetricsAuditRedactionFailureCounter.cs

@@ -0,0 +1,48 @@
+using ScadaLink.AuditLog.Payload;
+using ScadaLink.HealthMonitoring;
+
+namespace ScadaLink.AuditLog.Site;
+
+/// <summary>
+/// Audit Log (#23) M5 Bundle C — bridges
+/// <see cref="IAuditRedactionFailureCounter"/> (incremented by
+/// <see cref="DefaultAuditPayloadFilter"/> every time a header / body / SQL
+/// parameter redactor stage throws and the filter has to over-redact the
+/// offending field) into <see cref="ISiteHealthCollector"/> so the count
+/// surfaces in the site health report payload as
+/// <c>SiteHealthReport.AuditRedactionFailure</c>.
+/// </summary>
+/// <remarks>
+/// <para>
+/// Registered by <see cref="ServiceCollectionExtensions.AddAuditLogHealthMetricsBridge"/>;
+/// callers must register <c>AddHealthMonitoring()</c> first so
+/// <see cref="ISiteHealthCollector"/> resolves. The default <see cref="ServiceCollectionExtensions.AddAuditLog"/>
+/// registration keeps <see cref="NoOpAuditRedactionFailureCounter"/> for nodes
+/// where Site Health Monitoring is not wired (the silent-sink contract —
+/// redaction failures must NEVER abort the user-facing action, alog.md §7).
+/// </para>
+/// <para>
+/// Mirrors the M2 Bundle G <see cref="HealthMetricsAuditWriteFailureCounter"/>
+/// shape one-for-one so the two health-metric bridges age together.
+/// </para>
+/// <para>
+/// Site-side only for M5: the redaction filter also runs on the central
+/// writers (CentralAuditWriter + AuditLogIngestActor), but the central
+/// health-metric surface that would expose <c>AuditRedactionFailure</c>
+/// alongside the existing central counters ships in M6. Until then, the
+/// central composition root keeps the NoOp default — the redactions still
+/// happen, they just don't get counted into a health report.
+/// </para>
+/// </remarks>
+public sealed class HealthMetricsAuditRedactionFailureCounter : IAuditRedactionFailureCounter
+{
+    private readonly ISiteHealthCollector _collector;
+
+    public HealthMetricsAuditRedactionFailureCounter(ISiteHealthCollector collector)
+    {
+        _collector = collector ?? throw new ArgumentNullException(nameof(collector));
+    }
+
+    /// <inheritdoc/>
+    public void Increment() => _collector.IncrementAuditRedactionFailure();
+}

src/ScadaLink.Commons/Messages/Health/SiteHealthReport.cs

@@ -25,7 +25,14 @@ public record SiteHealthReport(
     // primary failures (SQLite throws routed to the drop-oldest ring). Surfaces
     // a sustained audit-write outage on /monitoring/health. Defaults to 0 so
     // existing producers / tests that don't construct the field stay valid.
-    int SiteAuditWriteFailures = 0);
+    int SiteAuditWriteFailures = 0,
+    // Audit Log (#23) M5 Bundle C: per-interval count of payload-filter
+    // redactor over-redactions (header / body / SQL parameter stages all
+    // throwing → field replaced with the "<redacted: redactor error>"
+    // marker). Surfaces a misconfigured / catastrophic regex on
+    // /monitoring/health. Defaults to 0 for back-compat with existing
+    // producers and tests that don't construct the field.
+    int AuditRedactionFailure = 0);
 
 /// <summary>
 /// Broadcast wrapper used between central nodes to keep per-node

src/ScadaLink.HealthMonitoring/ISiteHealthCollector.cs

@@ -19,6 +19,15 @@ public interface ISiteHealthCollector
     /// <c>AddAuditLogHealthMetricsBridge()</c>.
     /// </summary>
     void IncrementSiteAuditWriteFailures();
+    /// <summary>
+    /// Audit Log (#23) M5 Bundle C — increment the per-interval count of
+    /// payload-filter redactor over-redactions (header / body / SQL
+    /// parameter stage throws routed to the
+    /// <c>&lt;redacted: redactor error&gt;</c> marker). Bridged from the
+    /// <c>IAuditRedactionFailureCounter</c> binding registered via
+    /// <c>AddAuditLogHealthMetricsBridge()</c>.
+    /// </summary>
+    void IncrementAuditRedactionFailure();
     void UpdateConnectionHealth(string connectionName, ConnectionHealth health);
     void RemoveConnection(string connectionName);
     void UpdateTagResolution(string connectionName, int totalSubscribed, int successfullyResolved);

src/ScadaLink.HealthMonitoring/SiteHealthCollector.cs

@@ -14,6 +14,7 @@ public class SiteHealthCollector : ISiteHealthCollector
     private int _alarmErrorCount;
     private int _deadLetterCount;
     private int _siteAuditWriteFailures;
+    private int _auditRedactionFailures;
     private readonly ConcurrentDictionary<string, ConnectionHealth> _connectionStatuses = new();
     private readonly ConcurrentDictionary<string, TagResolutionStatus> _tagResolutionCounts = new();
     private readonly ConcurrentDictionary<string, string> _connectionEndpoints = new();
@@ -74,6 +75,20 @@ public class SiteHealthCollector : ISiteHealthCollector
         Interlocked.Increment(ref _siteAuditWriteFailures);
     }
 
+    /// <summary>
+    /// Audit Log (#23) M5 Bundle C — increment the per-interval count of
+    /// payload-filter redactor over-redactions (header / body / SQL
+    /// parameter stages routed to the
+    /// <c>&lt;redacted: redactor error&gt;</c> marker). Bridged from the
+    /// <c>IAuditRedactionFailureCounter</c> binding registered via
+    /// <c>AddAuditLogHealthMetricsBridge()</c>; reset every interval together
+    /// with the other per-interval counters.
+    /// </summary>
+    public void IncrementAuditRedactionFailure()
+    {
+        Interlocked.Increment(ref _auditRedactionFailures);
+    }
+
     /// <summary>
     /// Update the health status for a named data connection.
     /// Called by DCL when connection state changes.
@@ -158,6 +173,7 @@ public class SiteHealthCollector : ISiteHealthCollector
         var alarmErrors = Interlocked.Exchange(ref _alarmErrorCount, 0);
         var deadLetters = Interlocked.Exchange(ref _deadLetterCount, 0);
         var siteAuditWriteFailures = Interlocked.Exchange(ref _siteAuditWriteFailures, 0);
+        var auditRedactionFailures = Interlocked.Exchange(ref _auditRedactionFailures, 0);
 
         // Snapshot current connection and tag resolution state
         var connectionStatuses = new Dictionary<string, ConnectionHealth>(_connectionStatuses);
@@ -190,6 +206,7 @@ public class SiteHealthCollector : ISiteHealthCollector
             DataConnectionTagQuality: tagQuality,
             ParkedMessageCount: Interlocked.CompareExchange(ref _parkedMessageCount, 0, 0),
             ClusterNodes: _clusterNodes?.ToList(),
-            SiteAuditWriteFailures: siteAuditWriteFailures);
+            SiteAuditWriteFailures: siteAuditWriteFailures,
+            AuditRedactionFailure: auditRedactionFailures);
     }
 }

tests/ScadaLink.AuditLog.Tests/Site/HealthMetricsAuditRedactionFailureCounterTests.cs

@@ -0,0 +1,49 @@
+using NSubstitute;
+using ScadaLink.AuditLog.Site;
+using ScadaLink.HealthMonitoring;
+
+namespace ScadaLink.AuditLog.Tests.Site;
+
+/// <summary>
+/// Bundle C (M5-T7) — the <see cref="HealthMetricsAuditRedactionFailureCounter"/>
+/// adapter is the production binding for
+/// <see cref="ScadaLink.AuditLog.Payload.IAuditRedactionFailureCounter"/> on
+/// site nodes; it forwards every <see cref="DefaultAuditPayloadFilter"/>
+/// redactor over-redaction event into the shared
+/// <see cref="ISiteHealthCollector"/> so the site health report surfaces the
+/// count as <c>AuditRedactionFailure</c>. Mirrors the M2 Bundle G
+/// HealthMetricsAuditWriteFailureCounter shape one-for-one.
+/// </summary>
+public class HealthMetricsAuditRedactionFailureCounterTests
+{
+    [Fact]
+    public void Increment_Routes_To_Collector_IncrementAuditRedactionFailure()
+    {
+        var collector = Substitute.For<ISiteHealthCollector>();
+        var counter = new HealthMetricsAuditRedactionFailureCounter(collector);
+
+        counter.Increment();
+
+        collector.Received(1).IncrementAuditRedactionFailure();
+    }
+
+    [Fact]
+    public void Increment_Multiple_Calls_Route_To_Collector_Each_Time()
+    {
+        var collector = Substitute.For<ISiteHealthCollector>();
+        var counter = new HealthMetricsAuditRedactionFailureCounter(collector);
+
+        counter.Increment();
+        counter.Increment();
+        counter.Increment();
+
+        collector.Received(3).IncrementAuditRedactionFailure();
+    }
+
+    [Fact]
+    public void Construction_With_Null_Collector_Throws_ArgumentNullException()
+    {
+        Assert.Throws<ArgumentNullException>(
+            () => new HealthMetricsAuditRedactionFailureCounter(null!));
+    }
+}

tests/ScadaLink.HealthMonitoring.Tests/AuditRedactionFailureMetricTests.cs

@@ -0,0 +1,57 @@
+namespace ScadaLink.HealthMonitoring.Tests;
+
+/// <summary>
+/// Bundle C (M5-T7) regression coverage. The Audit Log payload filter
+/// (<c>DefaultAuditPayloadFilter</c>) increments
+/// <c>IAuditRedactionFailureCounter</c> every time a header/body/SQL-param
+/// redactor stage throws and the filter has to over-redact the field with
+/// the <c>&lt;redacted: redactor error&gt;</c> marker. Bundle C bridges that
+/// counter into the Site Health Monitoring report payload as
+/// <c>AuditRedactionFailure</c> so a misconfigured / catastrophic regex
+/// surfaces on /monitoring/health rather than disappearing into a NoOp sink.
+/// Mirrors the Bundle G <c>SiteAuditWriteFailures</c> metric shape — same
+/// per-interval increment-and-reset semantics, same defaults-to-zero
+/// contract.
+/// </summary>
+public class AuditRedactionFailureMetricTests
+{
+    private readonly SiteHealthCollector _collector = new();
+
+    [Fact]
+    public void Increment_Three_Times_Counter_Reports_3()
+    {
+        _collector.IncrementAuditRedactionFailure();
+        _collector.IncrementAuditRedactionFailure();
+        _collector.IncrementAuditRedactionFailure();
+
+        var report = _collector.CollectReport("site-1");
+
+        Assert.Equal(3, report.AuditRedactionFailure);
+    }
+
+    [Fact]
+    public void Report_Payload_Includes_AuditRedactionFailure_AsZeroByDefault()
+    {
+        var report = _collector.CollectReport("site-1");
+
+        Assert.Equal(0, report.AuditRedactionFailure);
+    }
+
+    /// <summary>
+    /// Mirrors the existing per-interval reset semantics for ScriptErrorCount /
+    /// AlarmEvaluationErrorCount / DeadLetterCount / SiteAuditWriteFailures —
+    /// AuditRedactionFailure is an interval count, not a running total.
+    /// </summary>
+    [Fact]
+    public void CollectReport_Resets_AuditRedactionFailure()
+    {
+        _collector.IncrementAuditRedactionFailure();
+        _collector.IncrementAuditRedactionFailure();
+
+        var first = _collector.CollectReport("site-1");
+        Assert.Equal(2, first.AuditRedactionFailure);
+
+        var second = _collector.CollectReport("site-1");
+        Assert.Equal(0, second.AuditRedactionFailure);
+    }
+}

tests/ScadaLink.SiteRuntime.Tests/Actors/DeploymentManagerRedeployTests.cs

@@ -70,6 +70,7 @@ public class DeploymentManagerRedeployTests : TestKit, IDisposable
         public void IncrementAlarmError() { }
         public void IncrementDeadLetter() { }
         public void IncrementSiteAuditWriteFailures() { }
+        public void IncrementAuditRedactionFailure() { }
         public void UpdateConnectionHealth(string connectionName, ConnectionHealth health) { }
         public void RemoveConnection(string connectionName) { }
         public void UpdateTagResolution(string connectionName, int totalSubscribed, int successfullyResolved) { }