fix(audit-log): explicit long CommandTimeout on partition-switch and per-channel purge maintenance paths

src/ZB.MOM.WW.ScadaBridge.Commons/Interfaces/Repositories/IAuditLogRepository.cs

@@ -83,9 +83,17 @@ public interface IAuditLogRepository
     /// </para>
     /// </remarks>
     /// <param name="monthBoundary">Lower-bound datetime of the monthly partition to switch out.</param>
+    /// <param name="commandTimeout">
+    /// Optional per-command timeout for the maintenance SQL (the row-count sample plus the
+    /// drop-and-rebuild dance). When null the provider default applies. The purge actor passes
+    /// <see cref="ZB.MOM.WW.ScadaBridge.AuditLog.Central.AuditLogPurgeOptions.ResolvedMaintenanceCommandTimeout"/>
+    /// (default 30 min) because the ~30s ADO.NET default can abort the switch mid-dance on a large
+    /// or contended partition, leaving the table without <c>UX_AuditLog_EventId</c> until the next
+    /// tick recovers (arch-review 04, S2).
+    /// </param>
     /// <param name="ct">Cancellation token.</param>
     /// <returns>A task that resolves to the approximate number of rows discarded by the partition switch.</returns>
-    Task<long> SwitchOutPartitionAsync(DateTime monthBoundary, CancellationToken ct = default);
+    Task<long> SwitchOutPartitionAsync(DateTime monthBoundary, TimeSpan? commandTimeout = null, CancellationToken ct = default);
 
     /// <summary>
     /// Per-channel retention override purge. Deletes <c>AuditLog</c> rows for a
@@ -115,12 +123,20 @@ public interface IAuditLogRepository
     /// <param name="channel">Canonical channel name (the <c>Category</c> column value, e.g. <c>ApiOutbound</c>).</param>
     /// <param name="threshold">Rows with <c>OccurredAtUtc</c> strictly older than this UTC datetime are deleted.</param>
     /// <param name="batchSize">Maximum rows deleted per batch; must be &gt; 0.</param>
+    /// <param name="commandTimeout">
+    /// Optional per-batch <c>DELETE TOP</c> command timeout. When null the provider default applies.
+    /// The purge actor passes the same
+    /// <see cref="ZB.MOM.WW.ScadaBridge.AuditLog.Central.AuditLogPurgeOptions.ResolvedMaintenanceCommandTimeout"/>
+    /// it uses for the partition switch so a large single batch under lock contention is not aborted
+    /// by the ~30s ADO.NET default (arch-review 04, S2).
+    /// </param>
     /// <param name="ct">Cancellation token.</param>
     /// <returns>A task that resolves to the total number of rows deleted across all batches.</returns>
     Task<long> PurgeChannelOlderThanAsync(
         string channel,
         DateTime threshold,
         int batchSize,
+        TimeSpan? commandTimeout = null,
         CancellationToken ct = default);
 
     /// <summary>