5d075f1374
Six adversarial-review findings in the central SQL/ingest layer. F1 (AuditLogRepository.InsertChunkAsync) — the set-based ingest declared each string parameter at its COLUMN width (Actor/Target 256, Action 64, Outcome 16, Category 32, SourceNode 64), so SqlClient truncated an over-long value at bind time and committed the mutilated row — silent, in an append-only store, with no PayloadTruncated flag — while the per-row and reconciliation paths sent the same value in full and let the server reject it with 2628. Bind at the value's own length instead; explicit SqlDbType is kept (it fixes the VALUES constructor's derived column types and datetime2 precision). Design: reject everywhere, truncate nowhere — matching today's per-row behaviour. F2 (SiteCallAuditRepository.UpsertAsync) — the single-statement upsert ran the monotonic UPDATE first and INSERTed only if nothing matched. Two writers racing the first packet of one TrackedOperationId (the cached dual-write and the reconciliation pull carry DIFFERENT lifecycle states) both matched nothing, and the loser then skipped its INSERT or swallowed a 2627 — dropping its Status/RetryCount/HttpStatus/TerminalAtUtc. Legs swapped to `IF NOT EXISTS … INSERT; UPDATE <monotonic>` — still one round trip, and the loser's UPDATE now lands on the winner's row. The duplicate-key catch re-runs the monotonic UPDATE for the same reason. Moved to raw SQL with explicitly-typed parameters so the intricate rank predicate exists in exactly one place (an untyped DateTime would bind as `datetime` and round the freshness tiebreaker). F3 (docs/plans/sql/*.sql) — filtered-index DDL failed with error 1934 under the documented `docker exec … sqlcmd` path, which defaults QUOTED_IDENTIFIER OFF; once IX_Notifications_Delivered exists, QI-OFF DML on Notifications fails too. All four scripts now open with `SET QUOTED_IDENTIFIER ON; SET ANSI_NULLS ON; GO` (own batch, so it is in force when the next batch parses), and the migration convention in Component-ConfigurationDatabase.md documents `sqlcmd -I`. Verified live: the pre-fix script fails 1934 without -I, the fixed one applies. F4 (SiteCallAuditActor) — the off-mailbox reconciliation/purge passes reuse the injected repository, so tests drove one DbContext from the pass and a mailbox handler concurrently. Serialized at the CALL via a private SerializedRepository wrapper applied only by the test constructors, rather than running the pass on-mailbox: production keeps its PipeTo shape untouched, and the existing "a blocked drain does not stall ingest/query/KPI" regression tests stay meaningful (they would have been invalidated by suspending the mailbox). F5 (AuditLogIngestActor) — when the batch failed because the 20 s IngestBudget expired, the per-row fallback reused the same expired token: N instant failures, N counter bumps, zero accepted. The fallback now gets a fresh 5 s budget (inside the 30 s outer Ask), and a blown budget bumps the failure counter ONCE for the batch instead of once per row. F6 (NotificationOutboxRepository.UpdateAsync) — ExecuteUpdate's row count was discarded, so an operator Retry/Discard of a notification the retention purge had already deleted reported success (the pre-ExecuteUpdate code threw DbUpdateConcurrencyException). UpdateAsync now returns whether a row matched; the operator one-shots answer "notification not found" and emit no audit row for the action that did not happen, while the dispatcher logs a warning (its delivery already happened; nothing to retry). GetByIdAsync switched to AsNoTracking since the write is out-of-band. Tests: 5 new SQL-backed regressions (over-long Target rejected on both paths + boundary round-trip; concurrent first-write and already-created-by-another-writer upserts; vanished-row UpdateAsync), a token-identity pin on the ingest fallback, a repository-concurrency detector for the SiteCallAudit passes, and vanished-row operator-path tests. The F1/F2/F4 regressions were each confirmed failing against the pre-fix code. Suites: ConfigurationDatabase 369, AuditLog 378, SiteCallAudit 66, NotificationOutbox 152 — all green, solution builds with 0 warnings.
156 lines
5.8 KiB
C#
156 lines
5.8 KiB
C#
using Akka.Actor;
|
|
using Akka.TestKit.Xunit2;
|
|
using Microsoft.Extensions.DependencyInjection;
|
|
using Microsoft.Extensions.Logging.Abstractions;
|
|
using NSubstitute;
|
|
using ZB.MOM.WW.Audit;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Entities.Notifications;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Services;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Notification;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Types.Audit;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
|
|
using ZB.MOM.WW.ScadaBridge.NotificationOutbox.Delivery;
|
|
|
|
namespace ZB.MOM.WW.ScadaBridge.NotificationOutbox.Tests;
|
|
|
|
/// <summary>
|
|
/// Task 13 (arch-review 04) — verifies that an operator-initiated Retry on a parked
|
|
/// notification emits a <see cref="AuditChannel.Notification"/>/<see cref="AuditKind.NotifyDeliver"/>
|
|
/// audit row with status <see cref="AuditStatus.Submitted"/> and the operator as
|
|
/// <c>Actor</c>, closing the forensic gap (previously the lifecycle read
|
|
/// <c>Parked → Attempted → Delivered</c> with no record of who un-parked it). Also
|
|
/// asserts the audit write is best-effort — a throwing writer never fails the retry.
|
|
/// </summary>
|
|
public class NotificationOutboxActorRetryEmissionTests : TestKit
|
|
{
|
|
private readonly INotificationOutboxRepository _outboxRepository =
|
|
OutboxRepositorySubstitute.Healthy();
|
|
|
|
private readonly RecordingCentralAuditWriter _auditWriter = new();
|
|
|
|
private sealed class RecordingCentralAuditWriter : ICentralAuditWriter
|
|
{
|
|
public List<AuditRowProjection.AuditRowValues> Events { get; } = new();
|
|
public Func<AuditEvent, Task>? OnWrite { get; set; }
|
|
|
|
public Task WriteAsync(AuditEvent evt, CancellationToken ct = default)
|
|
{
|
|
lock (Events)
|
|
{
|
|
Events.Add(evt.AsRow());
|
|
}
|
|
|
|
return OnWrite?.Invoke(evt) ?? Task.CompletedTask;
|
|
}
|
|
}
|
|
|
|
private IServiceProvider BuildServiceProvider()
|
|
{
|
|
var services = new ServiceCollection();
|
|
services.AddScoped(_ => _outboxRepository);
|
|
return services.BuildServiceProvider();
|
|
}
|
|
|
|
private IActorRef CreateActor()
|
|
{
|
|
return Sys.ActorOf(Props.Create(() => new NotificationOutboxActor(
|
|
BuildServiceProvider(),
|
|
new NotificationOutboxOptions { DispatchInterval = TimeSpan.FromHours(1) },
|
|
(ICentralAuditWriter)_auditWriter,
|
|
NullLogger<NotificationOutboxActor>.Instance)));
|
|
}
|
|
|
|
private static Notification MakeParked(Guid? notificationId = null)
|
|
{
|
|
return new Notification(
|
|
(notificationId ?? Guid.NewGuid()).ToString("D"),
|
|
NotificationType.Email,
|
|
"ops-team",
|
|
"Tank overflow",
|
|
"Tank 3 level critical",
|
|
"site-1")
|
|
{
|
|
Status = NotificationStatus.Parked,
|
|
RetryCount = 5,
|
|
CreatedAt = DateTimeOffset.UtcNow,
|
|
};
|
|
}
|
|
|
|
private List<AuditRowProjection.AuditRowValues> EventsByStatus(AuditStatus status)
|
|
{
|
|
lock (_auditWriter.Events)
|
|
{
|
|
return _auditWriter.Events.Where(e => e.Status == status).ToList();
|
|
}
|
|
}
|
|
|
|
[Fact]
|
|
public void Retry_OnParked_Emits_Submitted_NotifyDeliver_AuditRow_With_Operator()
|
|
{
|
|
var notificationId = Guid.NewGuid();
|
|
var notification = MakeParked(notificationId);
|
|
_outboxRepository.GetByIdAsync(notification.NotificationId, Arg.Any<CancellationToken>())
|
|
.Returns(notification);
|
|
var actor = CreateActor();
|
|
|
|
actor.Tell(new RetryNotificationRequest(
|
|
CorrelationId: "test-corr", NotificationId: notification.NotificationId, RequestedBy: "jdoe"));
|
|
|
|
ExpectMsg<RetryNotificationResponse>(r => r.Success);
|
|
AwaitAssert(() =>
|
|
{
|
|
var submitted = EventsByStatus(AuditStatus.Submitted);
|
|
Assert.Single(submitted);
|
|
var evt = submitted[0];
|
|
Assert.Equal(AuditChannel.Notification, evt.Channel);
|
|
Assert.Equal(AuditKind.NotifyDeliver, evt.Kind);
|
|
Assert.Equal("jdoe", evt.Actor);
|
|
Assert.Equal(notificationId, evt.CorrelationId);
|
|
});
|
|
}
|
|
|
|
[Fact]
|
|
public void Discard_OnParked_Emits_Discarded_AuditRow_With_Operator()
|
|
{
|
|
var notification = MakeParked();
|
|
_outboxRepository.GetByIdAsync(notification.NotificationId, Arg.Any<CancellationToken>())
|
|
.Returns(notification);
|
|
var actor = CreateActor();
|
|
|
|
actor.Tell(new DiscardNotificationRequest(
|
|
CorrelationId: "test-corr", NotificationId: notification.NotificationId, RequestedBy: "jdoe"));
|
|
|
|
ExpectMsg<DiscardNotificationResponse>(r => r.Success);
|
|
AwaitAssert(() =>
|
|
{
|
|
var discarded = EventsByStatus(AuditStatus.Discarded);
|
|
Assert.Single(discarded);
|
|
Assert.Equal("jdoe", discarded[0].Actor);
|
|
});
|
|
}
|
|
|
|
[Fact]
|
|
public void Retry_AuditFailure_DoesNotFail_TheRetry()
|
|
{
|
|
// Audit is best-effort: a throwing writer must NOT abort the retry — the
|
|
// row is still flipped back to Pending and the response reports Success.
|
|
var notification = MakeParked();
|
|
_outboxRepository.GetByIdAsync(notification.NotificationId, Arg.Any<CancellationToken>())
|
|
.Returns(notification);
|
|
_auditWriter.OnWrite = _ => throw new InvalidOperationException("audit dead");
|
|
var actor = CreateActor();
|
|
|
|
actor.Tell(new RetryNotificationRequest(
|
|
CorrelationId: "test-corr", NotificationId: notification.NotificationId, RequestedBy: "jdoe"));
|
|
|
|
ExpectMsg<RetryNotificationResponse>(r => r.Success);
|
|
AwaitAssert(() =>
|
|
{
|
|
_outboxRepository.Received(1).UpdateAsync(
|
|
Arg.Is<Notification>(n => n.Status == NotificationStatus.Pending),
|
|
Arg.Any<CancellationToken>());
|
|
});
|
|
}
|
|
}
|