feat(mesh): route deploy, driver-control and alarm commands through the mesh router
Phase 2 Task 7. The five central->node publish sites -- ConfigPublishCoordinator's deploy dispatch, and AdminOperationsActor's restart, reconnect, acknowledge and shelve -- now hand a MeshCommand to the transport router instead of telling the DistributedPubSub mediator directly. Neither actor knows which transport is in force any more. _meshRouter is NULLABLE with a mediator fallback, and that is deliberate: about a dozen existing coordinator and admin-operations tests construct these actors without a router, and they must keep exercising the real DPS path rather than a silently-disabled one. The fallback is not a permanent seam -- Phase 6 deletes it with the DPS branch and the single mesh. Wiring note: the comm actor's WithActors block moved ABOVE the singleton registrations so both singletons can resolve it with registry.Get, which is the ordering-by-registration idiom AdminOperationsActor already uses for the coordinator. An earlier version used ActorSelection.ResolveOne().GetAwaiter() .GetResult() inside the props factory -- that blocks inside actor construction and races the very spawn it waits for. Sabotage-verified by inverting the branch so the mediator always wins: all six new tests go red, including the fallback test (which proves it is asserting the mediator path rather than passing by accident). Suites after: ControlPlane 118/118, Runtime 450/450, Host.IntegrationTests 196/202 -- sole failure AbCip_Green_AgainstSim, the fixture baseline that fails on master too. Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
This commit is contained in:
Joseph Doherty
@@ -4,6 +4,7 @@ using Akka.Event;
|
||||
using Microsoft.EntityFrameworkCore;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Deploy;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Mesh;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Types;
|
||||
using ZB.MOM.WW.OtOpcUa.Configuration;
|
||||
@@ -26,6 +27,13 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
private readonly IActorRef _coordinator;
|
||||
private readonly IReadOnlyDictionary<string, IDriverProbe> _probesByType;
|
||||
private readonly TagConfigValidationMode _tagConfigValidationMode;
|
||||
|
||||
/// <summary>
|
||||
/// Where central→node commands are handed off (per-cluster mesh Phase 2), or
|
||||
/// <see langword="null"/> to publish on the mediator directly.
|
||||
/// </summary>
|
||||
private readonly IActorRef? _meshRouter;
|
||||
|
||||
private readonly ILoggingAdapter _log = Context.GetLogger();
|
||||
|
||||
/// <summary>Creates actor props for the admin operations actor.</summary>
|
||||
@@ -33,29 +41,38 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
/// <param name="coordinator">Reference to the deployment coordinator actor.</param>
|
||||
/// <param name="probes">Driver probes registered in DI; keyed by DriverType (case-insensitive).</param>
|
||||
/// <param name="tagConfigValidationMode">Deploy-gate TagConfig strictness mode (Warn default | Error opt-in).</param>
|
||||
/// <param name="meshRouter">
|
||||
/// Central comm actor commands are handed to, or <see langword="null"/> to publish on the
|
||||
/// DistributedPubSub mediator directly (the pre-Phase-2 behaviour).
|
||||
/// </param>
|
||||
/// <returns>Props configured to create an AdminOperationsActor.</returns>
|
||||
public static Props Props(
|
||||
IDbContextFactory<OtOpcUaConfigDbContext> dbFactory,
|
||||
IActorRef coordinator,
|
||||
IEnumerable<IDriverProbe> probes,
|
||||
TagConfigValidationMode tagConfigValidationMode = TagConfigValidationMode.Warn) =>
|
||||
Akka.Actor.Props.Create(() => new AdminOperationsActor(dbFactory, coordinator, probes, tagConfigValidationMode));
|
||||
TagConfigValidationMode tagConfigValidationMode = TagConfigValidationMode.Warn,
|
||||
IActorRef? meshRouter = null) =>
|
||||
Akka.Actor.Props.Create(() =>
|
||||
new AdminOperationsActor(dbFactory, coordinator, probes, tagConfigValidationMode, meshRouter));
|
||||
|
||||
/// <summary>Initializes a new instance of the AdminOperationsActor.</summary>
|
||||
/// <param name="dbFactory">Factory for creating config database contexts.</param>
|
||||
/// <param name="coordinator">Reference to the deployment coordinator actor.</param>
|
||||
/// <param name="probes">Driver probes registered in DI; keyed by DriverType (case-insensitive).</param>
|
||||
/// <param name="tagConfigValidationMode">Deploy-gate TagConfig strictness mode (Warn default | Error opt-in).</param>
|
||||
/// <param name="meshRouter">Central comm actor, or <see langword="null"/> for the mediator.</param>
|
||||
public AdminOperationsActor(
|
||||
IDbContextFactory<OtOpcUaConfigDbContext> dbFactory,
|
||||
IActorRef coordinator,
|
||||
IEnumerable<IDriverProbe> probes,
|
||||
TagConfigValidationMode tagConfigValidationMode = TagConfigValidationMode.Warn)
|
||||
TagConfigValidationMode tagConfigValidationMode = TagConfigValidationMode.Warn,
|
||||
IActorRef? meshRouter = null)
|
||||
{
|
||||
_dbFactory = dbFactory;
|
||||
_coordinator = coordinator;
|
||||
_probesByType = probes.ToDictionary(p => p.DriverType, StringComparer.OrdinalIgnoreCase);
|
||||
_tagConfigValidationMode = tagConfigValidationMode;
|
||||
_meshRouter = meshRouter;
|
||||
|
||||
ReceiveAsync<StartDeployment>(HandleStartDeploymentAsync);
|
||||
ReceiveAsync<TestDriverConnect>(HandleTestDriverConnectAsync);
|
||||
@@ -65,6 +82,23 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
Receive<ShelveAlarmCommand>(HandleShelveAlarm);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Hands a central→node command to the mesh transport router, or publishes it directly when
|
||||
/// no router is wired.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// The fallback keeps ~12 existing tests (and any node wired before per-cluster mesh Phase 2)
|
||||
/// on exactly the pre-Phase-2 behaviour. It is not a permanent seam: Phase 6 deletes it along
|
||||
/// with the DistributedPubSub branch and the single mesh.
|
||||
/// </remarks>
|
||||
/// <param name="topic">The legacy DistributedPubSub topic.</param>
|
||||
/// <param name="message">The command.</param>
|
||||
private void Dispatch(string topic, object message)
|
||||
{
|
||||
if (_meshRouter is not null) _meshRouter.Tell(new MeshCommand(topic, message));
|
||||
else DistributedPubSub.Get(Context.System).Mediator.Tell(new Publish(topic, message));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// AdminUI Acknowledge path. Maps the control-plane command to a
|
||||
/// <see cref="AlarmCommand"/> (<c>Operation = "Acknowledge"</c>) and publishes it onto the
|
||||
@@ -85,7 +119,7 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
Comment: msg.Comment,
|
||||
UnshelveAtUtc: null);
|
||||
|
||||
DistributedPubSub.Get(Context.System).Mediator.Tell(new Publish(AlarmCommandsTopic.Name, alarmCmd));
|
||||
Dispatch(AlarmCommandsTopic.Name, alarmCmd);
|
||||
|
||||
_log.Info("AdminOps: Acknowledge published for alarm {AlarmId} by {User}", msg.AlarmId, msg.User);
|
||||
replyTo.Tell(new AcknowledgeAlarmResult(true, null, msg.CorrelationId));
|
||||
@@ -132,7 +166,7 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
Comment: msg.Comment,
|
||||
UnshelveAtUtc: unshelveAt);
|
||||
|
||||
DistributedPubSub.Get(Context.System).Mediator.Tell(new Publish(AlarmCommandsTopic.Name, alarmCmd));
|
||||
Dispatch(AlarmCommandsTopic.Name, alarmCmd);
|
||||
|
||||
_log.Info("AdminOps: {Operation} published for alarm {AlarmId} by {User}", operation, msg.AlarmId, msg.User);
|
||||
replyTo.Tell(new ShelveAlarmResult(true, null, msg.CorrelationId));
|
||||
@@ -394,7 +428,7 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
{
|
||||
// Broadcast to every DriverHostActor on every node via the driver-control DPS topic.
|
||||
// Only the host that owns the instance will act; others ignore it (id not found in _children).
|
||||
DistributedPubSub.Get(Context.System).Mediator.Tell(new Publish(DriverControlTopic.Name, msg));
|
||||
Dispatch(DriverControlTopic.Name, msg);
|
||||
|
||||
await using var db = await _dbFactory.CreateDbContextAsync();
|
||||
db.ConfigEdits.Add(new ConfigEdit
|
||||
@@ -424,7 +458,7 @@ public sealed class AdminOperationsActor : ReceiveActor
|
||||
try
|
||||
{
|
||||
// Broadcast to every DriverHostActor; only the one owning the instance reacts.
|
||||
DistributedPubSub.Get(Context.System).Mediator.Tell(new Publish(DriverControlTopic.Name, msg));
|
||||
Dispatch(DriverControlTopic.Name, msg);
|
||||
|
||||
await using var db = await _dbFactory.CreateDbContextAsync();
|
||||
db.ConfigEdits.Add(new ConfigEdit
|
||||
|
||||
Reference in New Issue
Block a user