lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/Drivers/DriverHostActorScriptedAlarmRestartTests.cs

using System.Text.Json;
using Akka.Actor;
using Serilog;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.Engines;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
using ZB.MOM.WW.OtOpcUa.Commons.Types;
using ZB.MOM.WW.OtOpcUa.Configuration.Entities;
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
using ZB.MOM.WW.OtOpcUa.Core.ScriptedAlarms;
using ZB.MOM.WW.OtOpcUa.Core.Scripting;
using ZB.MOM.WW.OtOpcUa.Runtime.Drivers;
using ZB.MOM.WW.OtOpcUa.Runtime.OpcUa;
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;
using ZB.MOM.WW.OtOpcUa.Runtime.VirtualTags;

namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.Drivers;

/// <summary>
///     Review I-2: under the factory Props a supervision restart of the scripted-alarm host builds a fresh, EMPTY
///     engine. Nothing re-sent <c>ApplyScriptedAlarms</c>, so until the next deploy the host had no mux interest
///     (inputs stopped) and its ownership filter dropped every operator ack/shelve as "not owned". The host now
///     tells its parent <see cref="ScriptedAlarms.ScriptedAlarmHostActor.ScriptedAlarmHostRestarted"/> from <c>PostRestart</c>,
///     and <see cref="DriverHostActor"/> re-sends the last plans it applied. This test never re-applies by hand.
/// </summary>
public sealed class DriverHostActorScriptedAlarmRestartTests : RuntimeActorTestBase
{
    private static readonly NodeId TestNode = NodeId.Parse("driver-alarmhost-restart-test");
    private static readonly RevisionHash RevA = RevisionHash.Parse(new string('d', 64));
    private static readonly TimeSpan Timeout = TimeSpan.FromSeconds(30);

    private static DeploymentId SeedAlarmDeployment(Microsoft.EntityFrameworkCore.IDbContextFactory<ZB.MOM.WW.OtOpcUa.Configuration.OtOpcUaConfigDbContext> db)
    {
        var artifact = JsonSerializer.SerializeToUtf8Bytes(new
        {
            ScriptedAlarms = new[]
            {
                new
                {
                    ScriptedAlarmId = "alm-1", EquipmentId = "eq-1", Name = "HighTemp", AlarmType = "AlarmCondition",
                    Severity = 800, MessageTemplate = "hot", PredicateScriptId = "s-1",
                    HistorizeToAveva = false, Retain = true, Enabled = true,
                },
            },
            Scripts = new[] { new { ScriptId = "s-1", SourceCode = "return (int)ctx.GetTag(\"M.T\").Value > 90;" } },
        });
        var id = DeploymentId.NewId();
        using var ctx = db.CreateDbContext();
        ctx.Deployments.Add(new Deployment
        {
            DeploymentId = id.Value, RevisionHash = RevA.Value, Status = DeploymentStatus.Sealed,
            CreatedBy = "test", SealedAtUtc = DateTime.UtcNow, ArtifactBlob = artifact,
        });
        ctx.SaveChanges();
        return id;
    }

    [Fact]
    public void After_a_supervision_restart_the_alarm_host_is_re_applied_and_inputs_and_acks_work_again()
    {
        var db = NewInMemoryDbFactory();
        var deploymentId = SeedAlarmDeployment(db);
        var publish = this.CreateCleanOutcomePublishProbe();
        var mux = CreateTestProbe();
        var coordinator = CreateTestProbe();
        var host = Sys.ActorOf(DriverHostActor.Props(
            db, TestNode, coordinator.Ref,
            localRoles: new HashSet<string> { "driver" },
            dependencyMux: mux.Ref,
            opcUaPublishActor: publish.Ref,
            virtualTagEvaluator: NullVirtualTagEvaluator.Instance,
            virtualTagHostOverride: CreateTestProbe().Ref,
            scriptRootLogger: new ScriptRootLogger(new LoggerConfiguration().CreateLogger()),
            alarmStateStore: new InMemoryAlarmStateStore()));
        V3ArtifactSeeder.Dispatch(host, coordinator, deploymentId, RevA);

        var first = mux.FishForMessage<DependencyMuxActor.RegisterInterest>(r => r.TagRefs.Contains("M.T"), Timeout, cancellationToken: TestContext.Current.CancellationToken);
        var alarmHost = first.Subscriber;

        // The crash: a batch item with a null TagId makes the upstream Push throw (the documented unguarded
        // path), so supervision restarts the alarm host. NO manual re-apply follows.
        alarmHost.Tell(new VirtualTagActor.DependencyValueBatch(new[]
        {
            new VirtualTagActor.DependencyValueChanged(null!, 1, DateTime.UtcNow),
        }));
        mux.FishForMessage<DependencyMuxActor.UnregisterInterest>(u => u.Subscriber.Equals(alarmHost), Timeout, cancellationToken: TestContext.Current.CancellationToken);

        // The parent re-applies on the restart signal: interest is registered again by the new incarnation.
        mux.FishForMessage<DependencyMuxActor.RegisterInterest>(r => r.TagRefs.Contains("M.T"), Timeout, cancellationToken: TestContext.Current.CancellationToken);

        // Inputs work: a dependency push activates the alarm.
        alarmHost.Tell(new VirtualTagActor.DependencyValueChanged("M.T", 99, DateTime.UtcNow));
        publish.FishForMessage<OpcUaPublishActor.AlarmStateUpdate>(
            m => m.AlarmNodeId == "alm-1" && m.State.Active && !m.State.Acknowledged, Timeout, cancellationToken: TestContext.Current.CancellationToken);

        // Acks work: the restarted engine owns alm-1 again, so the command is not filtered out as unowned.
        alarmHost.Tell(new AlarmCommand(AlarmId: "alm-1", Operation: "Acknowledge", User: "alice", Comment: null, UnshelveAtUtc: null));
        publish.FishForMessage<OpcUaPublishActor.AlarmStateUpdate>(
            m => m.AlarmNodeId == "alm-1" && m.State.Acknowledged, Timeout, cancellationToken: TestContext.Current.CancellationToken)
            .State.Acknowledged.ShouldBeTrue();
    }
}