feat(alarms): condition Quality tracks source connectivity (#477)
v2-ci / build (pull_request) Successful in 4m49s
v2-ci / unit-tests (pull_request) Failing after 3h11m25s

Part 9 ConditionType.Quality was never assigned; default(StatusCode)==Good
so every native + scripted condition reported Good unconditionally — a
comms-lost device still showed a healthy, inactive, Good condition (a
wrong-VALUE bug, distinct from the null-value #473/#475). Clients (and HMIs
bucketing on IsGood) could not tell "genuinely inactive" from "lost contact".

Layer 1 — make Quality a real, plumbed field:
- AlarmConditionSnapshot gains OpcUaQuality Quality (default Good).
- MaterialiseAlarmCondition sets it (native BadWaitingForInitialData, scripted Good).
- WriteAlarmCondition projects snapshot.Quality; the delta-gate gains a Quality
  member so a quality-bucket change fires a Part 9 event.

Layer 2 — drive native quality from driver connectivity (a comms-lost driver
emits no alarm transitions, and an alarm-bearing raw tag has no value variable,
so quality can't come from either existing channel):
- DriverInstanceActor Tells parent ConnectivityChanged on Connected/Reconnecting.
- DriverHostActor fans it to every native condition the driver owns as
  OpcUaPublishActor.AlarmQualityUpdate (Good on connect, Bad on disconnect).
- New dedicated IOpcUaAddressSpaceSink.WriteAlarmQuality sets ONLY Quality and
  fires only on a bucket change — never touches Active/Acked/Retain (an active
  alarm that loses comms stays active). Not a full-snapshot re-projection, so it
  can't clobber severity/message and works for a never-fired condition.
  Forwarded through DeferredAddressSpaceSink (F10b trap; auto-verified by the
  reflection forwarding guard). Ungated by redundancy role; no /alerts row.

Scripted conditions stay Good; worst-of-input quality deferred to #478 (Layer 3).

Tests: node-level (materialise/project/no-clobber/unknown-node no-op),
NativeAlarmProjector, DriverInstanceActor connectivity emission, DriverHostActor
fan-out, OpcUaPublishActor routing, and the wire-level guard
(Condition_event_Quality_tracks_source_connectivity_on_the_wire) — RED-verified
against a simulated pre-fix always-Good server. Existing DriverInstanceActor
parent probes ignore the new ConnectivityChanged.

Docs: docs/AlarmTracking.md §"Condition source-data Quality (#477)";
design doc docs/plans/2026-07-17-alarm-condition-quality-477-design.md.
This commit is contained in:
Joseph Doherty
2026-07-17 15:10:04 -04:00
parent f6a3c31b60
commit db751d12a5
30 changed files with 752 additions and 7 deletions
@@ -119,6 +119,7 @@ public sealed class OpcUaPublishActorApplyFailureTests : RuntimeActorTestBase
private sealed class ThrowOnRebuildSink : IOpcUaAddressSpaceSink
{
public void WriteValue(string nodeId, object? value, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) { }
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
@@ -133,6 +134,7 @@ public sealed class OpcUaPublishActorApplyFailureTests : RuntimeActorTestBase
private sealed class NoopSink : IOpcUaAddressSpaceSink
{
public void WriteValue(string nodeId, object? value, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) { }
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
@@ -443,6 +443,7 @@ public sealed class OpcUaPublishActorRebuildTests : RuntimeActorTestBase
/// <param name="alarmNodeId">The alarm node ID.</param>
/// <param name="state">The full condition state snapshot.</param>
/// <param name="ts">The timestamp of the state change.</param>
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime ts, AddressSpaceRealm realm = AddressSpaceRealm.Uns)
=> Calls.Enqueue($"WA:{alarmNodeId}");
/// <summary>Records a materialise-alarm-condition call.</summary>
@@ -76,6 +76,26 @@ public sealed class OpcUaPublishActorTests : RuntimeActorTestBase
}, duration: TimeSpan.FromMilliseconds(500));
}
/// <summary>#477 — AlarmQualityUpdate routes to sink.WriteAlarmQuality with the quality + realm.</summary>
[Fact]
public void AlarmQualityUpdate_routes_to_sink_WriteAlarmQuality()
{
var sink = new RecordingSink();
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink));
actor.Tell(new OpcUaPublishActor.AlarmQualityUpdate(
"Plant/Modbus/dev1/temp_hi", OpcUaQuality.Bad, DateTime.UtcNow, Realm: AddressSpaceRealm.Raw));
AwaitAssert(() =>
{
sink.AlarmQualityQueue.Count.ShouldBe(1);
sink.AlarmQualityQueue.TryPeek(out var q).ShouldBeTrue();
q.AlarmNodeId.ShouldBe("Plant/Modbus/dev1/temp_hi");
q.Quality.ShouldBe(OpcUaQuality.Bad);
q.Realm.ShouldBe(AddressSpaceRealm.Raw);
}, duration: TimeSpan.FromMilliseconds(500));
}
/// <summary>Builds a test <see cref="AlarmConditionSnapshot"/> with sensible defaults so each test
/// only specifies the fields it cares about.</summary>
private static AlarmConditionSnapshot Snapshot(
@@ -577,6 +597,8 @@ public sealed class OpcUaPublishActorTests : RuntimeActorTestBase
public ConcurrentQueue<(string NodeId, object? Value, OpcUaQuality Quality, DateTime Ts)> ValueQueue { get; } = new();
/// <summary>Gets the queue of recorded alarm condition updates.</summary>
public ConcurrentQueue<(string AlarmNodeId, AlarmConditionSnapshot State, DateTime Ts)> AlarmQueue { get; } = new();
/// <summary>Gets the queue of recorded alarm-quality annotations (#477).</summary>
public ConcurrentQueue<(string AlarmNodeId, OpcUaQuality Quality, DateTime Ts, AddressSpaceRealm Realm)> AlarmQualityQueue { get; } = new();
/// <summary>Count of rebuild calls.</summary>
public int RebuildCalls;
/// <summary>Gets the queue of recorded EnsureFolder calls.</summary>
@@ -616,6 +638,10 @@ public sealed class OpcUaPublishActorTests : RuntimeActorTestBase
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime ts, AddressSpaceRealm realm = AddressSpaceRealm.Uns) =>
AlarmQueue.Enqueue((alarmNodeId, state, ts));
/// <summary>Records an alarm-quality annotation (#477).</summary>
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime ts, AddressSpaceRealm realm = AddressSpaceRealm.Uns) =>
AlarmQualityQueue.Enqueue((alarmNodeId, quality, ts, realm));
/// <summary>Materialises an alarm condition (no-op in test).</summary>
/// <param name="alarmNodeId">The alarm node ID.</param>
/// <param name="equipmentNodeId">The equipment folder node ID.</param>