feat(comm): ack site health reports end-to-end (SiteHealthReportAck, additive contract)

This commit is contained in:
Joseph Doherty
2026-07-08 16:09:08 -04:00
parent f7b9d342e4
commit 17af376a8e
4 changed files with 105 additions and 3 deletions
@@ -0,0 +1,10 @@
namespace ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
/// <summary>
/// Acknowledgement for a <see cref="SiteHealthReport"/> forwarded site→central.
/// Review 01 [Medium]: the transport was fire-and-forget, so the sender's
/// interval-counter restore logic could never observe a loss. The ack makes
/// delivery observable end-to-end (central processed the report).
/// </summary>
public sealed record SiteHealthReportAck(
string SiteId, long SequenceNumber, bool Accepted, string? Error = null);
@@ -394,6 +394,15 @@ public class CentralCommunicationActor : ReceiveActor
{
// No-op in non-clustered hosts (TestKit).
}
// Ack the site so its AkkaHealthReportTransport Ask completes and the
// report-loss counter-restore path can observe delivery (review 01
// [Medium]). Guarded so the peer-replica path (SiteHealthReportReplica,
// which arrives without an Ask sender) never dead-letters an ack.
if (!Sender.IsNobody())
{
Sender.Tell(new SiteHealthReportAck(report.SiteId, report.SequenceNumber, Accepted: true));
}
}
/// <summary>
@@ -390,11 +390,28 @@ public class SiteCommunicationActor : ReceiveActor, IWithTimers
// Internal: send heartbeat tick
Receive<SendHeartbeat>(_ => SendHeartbeatToCentral());
// Internal: forward health report to central
// Internal: forward health report to central. The original Sender (the
// AkkaHealthReportTransport's Ask) is forwarded as the ClusterClient.Send
// sender so the central SiteHealthReportAck routes straight back to the
// waiting Ask — making report delivery observable end-to-end (review 01
// [Medium]). Mirrors the NotificationSubmit ack pattern above.
Receive<SiteHealthReport>(msg =>
{
_centralClient?.Tell(
new ClusterClient.Send("/user/central-communication", msg), Self);
if (_centralClient == null)
{
// No ClusterClient registered yet. A non-accepted ack makes the
// sender's counter-restore path treat this tick as a loss.
_log.Warning(
"Cannot forward SiteHealthReport #{0} — no central ClusterClient registered",
msg.SequenceNumber);
Sender.Tell(new SiteHealthReportAck(
msg.SiteId, msg.SequenceNumber, Accepted: false,
Error: "Central ClusterClient not registered"));
return;
}
_centralClient.Tell(
new ClusterClient.Send("/user/central-communication", msg), Sender);
});
}
@@ -0,0 +1,66 @@
using Akka.Actor;
using Akka.TestKit.Xunit2;
using Microsoft.Extensions.DependencyInjection;
using NSubstitute;
using ZB.MOM.WW.ScadaBridge.Commons.Entities.Sites;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
using ZB.MOM.WW.ScadaBridge.Commons.Types;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
using ZB.MOM.WW.ScadaBridge.Communication.Actors;
using ZB.MOM.WW.ScadaBridge.HealthMonitoring;
namespace ZB.MOM.WW.ScadaBridge.Communication.Tests;
/// <summary>
/// Review 01 [Medium]: site→central health reports were fire-and-forget, so a lost
/// report was invisible to the sender. These tests pin the new end-to-end ack:
/// the site actor replies not-accepted when it has no central ClusterClient, and the
/// central actor processes + acks a report it receives.
/// </summary>
public class HealthReportAckTests : TestKit
{
private readonly CommunicationOptions _options = new();
private static SiteHealthReport SampleReport(long seq, string siteId = "site-a") =>
new(siteId, seq, DateTimeOffset.UtcNow,
new Dictionary<string, ConnectionHealth>(),
new Dictionary<string, TagResolutionStatus>(),
0, 0, new Dictionary<string, int>(), 0, 0, 0, 0);
[Fact]
public void SiteCommunicationActor_NoCentralClient_RepliesNotAccepted()
{
var dmProbe = CreateTestProbe();
var siteComm = Sys.ActorOf(Props.Create(() =>
new SiteCommunicationActor("site-a", _options, dmProbe.Ref)));
// No RegisterCentralClient sent => _centralClient is null.
siteComm.Tell(SampleReport(seq: 7));
var ack = ExpectMsg<SiteHealthReportAck>();
Assert.False(ack.Accepted);
Assert.Equal(7, ack.SequenceNumber);
Assert.Equal("site-a", ack.SiteId);
}
[Fact]
public void CentralCommunicationActor_OnReport_ProcessesAndAcks()
{
var mockRepo = Substitute.For<ISiteRepository>();
mockRepo.GetAllSitesAsync(Arg.Any<CancellationToken>()).Returns(new List<Site>());
var aggregator = Substitute.For<ICentralHealthAggregator>();
var services = new ServiceCollection();
services.AddScoped(_ => mockRepo);
services.AddSingleton(aggregator);
var sp = services.BuildServiceProvider();
var siteClientFactory = Substitute.For<ISiteClientFactory>();
var actor = Sys.ActorOf(Props.Create(() => new CentralCommunicationActor(sp, siteClientFactory)));
actor.Tell(SampleReport(seq: 3));
var ack = ExpectMsg<SiteHealthReportAck>();
Assert.True(ack.Accepted);
Assert.Equal(3, ack.SequenceNumber);
AwaitAssert(() => aggregator.Received().ProcessReport(Arg.Is<SiteHealthReport>(r => r.SequenceNumber == 3)));
}
}