fix(auditlog): reconciliation abandons only row-intrinsic failures and only when a sibling row inserted (review 2026-10-21 follow-up M1)

tests/ZB.MOM.WW.ScadaBridge.AuditLog.Tests/Central/SiteAuditReconciliationActorTests.cs

@@ -5,6 +5,7 @@ using Microsoft.Extensions.DependencyInjection;
 using Microsoft.Extensions.Logging.Abstractions;
 using Microsoft.Extensions.Options;
 using ZB.MOM.WW.ScadaBridge.AuditLog.Central;
+using ZB.MOM.WW.ScadaBridge.AuditLog.Tests.TestSupport;
 using ZB.MOM.WW.Audit;
 using ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.Entities;
 using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
@@ -254,13 +255,29 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
         /// <summary>Gets the audit events recorded by this stub.</summary>
         public List<AuditEvent> Inserted { get; } = new();
         private readonly HashSet<Guid> _seen = new();
+        private readonly Guid _poisonId;
+        private readonly Guid _healthyId;
+
+        /// <summary>Initializes the stub.</summary>
+        /// <param name="poisonId">The row that fails with a row-intrinsic (permanent) SQL error.</param>
+        /// <param name="healthyId">The one non-synthetic row that inserts; every other row fails transiently.</param>
+        public AlwaysFailUnlessSyntheticRepo(Guid poisonId, Guid healthyId)
+        {
+            _poisonId = poisonId;
+            _healthyId = healthyId;
+        }
 
         /// <inheritdoc />
         public Task InsertIfNotExistsAsync(AuditEvent evt, CancellationToken ct = default)
         {
-            if (!evt.Action.EndsWith(".ReconciliationAbandoned", StringComparison.Ordinal))
+            if (evt.EventId == _poisonId)
             {
-                throw new InvalidOperationException("simulated permanent insert failure");
+                throw SqlExceptionFactory.Create(8152);
+            }
+            if (evt.EventId != _healthyId
+                && !evt.Action.EndsWith(".ReconciliationAbandoned", StringComparison.Ordinal))
+            {
+                throw new TimeoutException("simulated transient insert failure");
             }
             if (_seen.Add(evt.EventId))
             {
@@ -900,12 +917,15 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
         // Five pulls each returning the same poison row so its per-EventId attempt
         // counter reaches MaxPermanentInsertAttempts (5); afterwards the scripted
         // client returns empty and the actor settles.
+        // A healthy sibling (earlier timestamp) rides every page: it proves the database
+        // accepts writes, which is what lets the poison row be abandoned at all (follow-up M1).
+        // The poison fault is a ROW-intrinsic SQL error (8152 string truncation).
+        var healthy = NewEvent(siteId, poisonTime.AddSeconds(-1));
         var responses = Enumerable.Range(0, 5)
-            .Select(_ => new PullAuditEventsResponse(new[] { poison }, MoreAvailable: false))
+            .Select(_ => new PullAuditEventsResponse(new[] { healthy, poison }, MoreAvailable: false))
             .ToArray();
         var client = new ScriptedPullClient().Script(siteId, responses);
-        var repo = new PoisonInsertRepo(
-            poison.EventId, new InvalidOperationException("poison row will never insert"));
+        var repo = new PoisonInsertRepo(poison.EventId, SqlExceptionFactory.Create(8152));
 
         var actor = CreateActor(sites, client, repo, FastTickOptions());
 
@@ -965,6 +985,9 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
         var siteId = "siteReabandon";
         var poisonTime = new DateTime(2026, 5, 20, 10, 5, 0, DateTimeKind.Utc);
         var poison = NewEvent(siteId, poisonTime);
+        // A row that always inserts rides every page so the poison row is abandonable
+        // (an all-rows-failing page is a database problem and never abandons — follow-up M1).
+        var healthy = NewEvent(siteId, poisonTime.AddSeconds(-1));
 
         // 10 scripted responses: enough for exactly two 5-attempt abandon
         // cycles of the poison row (the cursor never advances between them,
@@ -974,12 +997,12 @@ public class SiteAuditReconciliationActorTests : TestKit, IClassFixture<MsSqlMig
         // row count is bounded and deterministic.
         var responses = Enumerable.Range(0, 10)
             .Select(i => new PullAuditEventsResponse(
-                new[] { poison, NewEvent(siteId, poisonTime.AddSeconds(i + 1)) },
+                new[] { healthy, poison, NewEvent(siteId, poisonTime.AddSeconds(i + 1)) },
                 MoreAvailable: false))
             .ToArray();
         var client = new ScriptedPullClient().Script(siteId, responses);
         var sites = new StaticEnumerator(new SiteEntry(siteId, "http://x:8083"));
-        var repo = new AlwaysFailUnlessSyntheticRepo();
+        var repo = new AlwaysFailUnlessSyntheticRepo(poison.EventId, healthy.EventId);
 
         var actor = CreateActor(sites, client, repo, FastTickOptions());