feat(health): CentralAuditWriteFailures + AuditCentralHealthSnapshot (#23 M6)

src/ScadaLink.AuditLog/Central/IAuditCentralHealthSnapshot.cs

@@ -0,0 +1,62 @@
+using ScadaLink.AuditLog.Payload;
+
+namespace ScadaLink.AuditLog.Central;
+
+/// <summary>
+/// Audit Log (#23) M6 Bundle E read-side surface exposing the central-side
+/// audit-health counters: <see cref="CentralAuditWriteFailures"/> (every
+/// repository insert throw from <see cref="CentralAuditWriter"/> /
+/// <see cref="AuditLogIngestActor"/>), <see cref="AuditRedactionFailure"/>
+/// (every payload-filter redactor throw on the central path), and
+/// <see cref="SiteAuditTelemetryStalled"/> (per-site latched state from the
+/// <see cref="SiteAuditTelemetryStalledTracker"/>).
+/// </summary>
+/// <remarks>
+/// <para>
+/// <b>Read-only contract.</b> Implementations expose a point-in-time snapshot
+/// — increments and tracker updates happen through the dedicated counter /
+/// tracker interfaces, not through this surface. Consumers (M7+ central
+/// health pages) read these properties; they never mutate.
+/// </para>
+/// <para>
+/// <b>Why a parallel surface from <see cref="ICentralHealthAggregator"/>.</b>
+/// <see cref="ICentralHealthAggregator"/> aggregates per-site
+/// <c>SiteHealthState</c> reports the SITE emits. The central audit-write
+/// failure / redaction-failure counters originate ON central (no site report
+/// carries them), so they live on a dedicated snapshot rather than being
+/// retro-fitted into a per-site state. The two surfaces will be composed at
+/// the M7 dashboard layer.
+/// </para>
+/// </remarks>
+public interface IAuditCentralHealthSnapshot
+{
+    /// <summary>
+    /// Count of central-side audit-write failures since process start.
+    /// Incremented by every <see cref="CentralAuditWriter"/> /
+    /// <see cref="AuditLogIngestActor"/> repository insert that throws.
+    /// </summary>
+    int CentralAuditWriteFailures { get; }
+
+    /// <summary>
+    /// Count of central-side payload-filter redactor over-redactions since
+    /// process start. Incremented by every header / body / SQL-parameter
+    /// redactor stage that throws (the filter falls back to the
+    /// <c>&lt;redacted: redactor error&gt;</c> marker and never aborts the
+    /// user-facing action). Sites have their own counter
+    /// (<see cref="IAuditRedactionFailureCounter"/>-backed
+    /// <c>SiteHealthReport.AuditRedactionFailure</c>) and the central
+    /// composition root's binding routes ALL central redactor throws
+    /// (CentralAuditWriter + AuditLogIngestActor paths) into this counter.
+    /// </summary>
+    int AuditRedactionFailure { get; }
+
+    /// <summary>
+    /// Per-site latched stalled state: <c>true</c> when the
+    /// <see cref="SiteAuditReconciliationActor"/> has observed two
+    /// consecutive non-draining cycles for that site, <c>false</c> after the
+    /// first draining cycle. Sites absent from the map are interpreted as
+    /// healthy (<c>Stalled=false</c> default). Snapshot is a defensive
+    /// copy — readers must not mutate.
+    /// </summary>
+    IReadOnlyDictionary<string, bool> SiteAuditTelemetryStalled { get; }
+}