fix(alarms): native-alarm re-statements no longer duplicate history or hide acked alarms (#656)
- AlarmTransitionKind.ActiveAcknowledged (appended): active AND acked applied as ONE projection. Galaxy ActiveAcked snapshot entries and OpcUaClient inactive->(active,acked) use it; the projector writes 'Activated' only if not already active, 'Acknowledged' only if not acked. - AlarmEventArgs.IsRestatement (optional, default false): set only by Galaxy snapshot entries and OpcUaClient first sight. A flagged Retrigger on an Active+unacked condition with the same message and severity, or a flagged Clear on an inactive condition, writes no /alerts row. - NativeAlarmProjector reports the history rows per transition; ForwardNativeAlarm writes one row per entry. Unflagged sources (FOCAS/MTConnect/AbCip, live Galaxy) are unchanged. - Tests: projector rules each with a must-write control; OpcUaClient transition table; Galaxy feed/driver mapping; Galaxy + OpcUaClient end-to-end through DriverHostActor. Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe
This commit is contained in:
Joseph Doherty
@@ -1877,49 +1877,74 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers, IWithUnboundedS
|
||||
foreach (var n in nodeIds)
|
||||
{
|
||||
var nodeId = n.NodeId;
|
||||
var snapshot = _nativeAlarmProjector.Project(nodeId, msg.Args, out var restatement);
|
||||
var snapshot = _nativeAlarmProjector.Project(nodeId, msg.Args, out IReadOnlyList<AlarmTransitionKind> historyKinds);
|
||||
_opcUaPublishActor.Tell(new ZB.MOM.WW.OtOpcUa.Runtime.OpcUa.OpcUaPublishActor.AlarmStateUpdate(
|
||||
nodeId, snapshot, msg.Args.SourceTimestampUtc, n.Realm));
|
||||
|
||||
// Only the Primary publishes the cluster-wide alerts transition (see the gate above). A re-statement
|
||||
// (Gitea #647 review: a Raise on an already-active condition, sent by a driver a deploy respawned) is
|
||||
// not a transition — the condition was already Active, so a second "Activated" row would be a duplicate.
|
||||
if (!serviceAlertsAsPrimary || restatement) continue;
|
||||
// Only the Primary publishes the cluster-wide alerts transition (see the gate above). The projector
|
||||
// decides WHICH rows the transition warrants: none for a re-statement (Gitea #647 review: a Raise on an
|
||||
// already-active condition from a respawned driver; #656: a flagged snapshot/first-sight Retrigger or
|
||||
// Clear that changes nothing the condition shows), and up to two for an ActiveAcknowledged (#656:
|
||||
// "Activated" only if it was not already active, "Acknowledged" only if it was not already acked).
|
||||
if (!serviceAlertsAsPrimary) continue;
|
||||
|
||||
var meta = _alarmMetaByNodeId.TryGetValue(nodeId, out var m)
|
||||
? m : (EquipmentId: nodeId, Name: nodeId, AlarmType: "AlarmCondition", HistorizeToAveva: (bool?)null,
|
||||
ReferencingEquipmentPaths: (IReadOnlyList<string>)Array.Empty<string>());
|
||||
var alertEvent = new AlarmTransitionEvent(
|
||||
AlarmId: nodeId,
|
||||
EquipmentPath: meta.EquipmentId,
|
||||
AlarmName: meta.Name,
|
||||
TransitionKind: ToEventKind(msg.Args.Kind),
|
||||
// The projector mapped the four-bucket AlarmSeverity onto the OPC UA 1..1000 scale already;
|
||||
// reuse its ushort so the condition node + the alerts row agree on severity.
|
||||
Severity: snapshot.Severity,
|
||||
Message: msg.Args.Message,
|
||||
// Native transitions are device-driven; an operator comment only rides along on an
|
||||
// acknowledge from the upstream alarm system. "device" marks a non-operator origin.
|
||||
User: msg.Args.OperatorComment is null ? string.Empty : "device",
|
||||
TimestampUtc: msg.Args.SourceTimestampUtc,
|
||||
AlarmTypeName: meta.AlarmType,
|
||||
Comment: msg.Args.OperatorComment,
|
||||
// Per-condition opt-out parsed from TagConfig.alarm.historizeToAveva (bool?, null ⇒ absent ⇒
|
||||
// historize). The HistorianAdapterActor gate (historizeToAveva is not false) historizes null +
|
||||
// true and suppresses the durable AVEVA row only on an explicit false — the same posture as the
|
||||
// scripted-alarm opt-out. null here rides through unchanged (the gate treats it as default-on).
|
||||
HistorizeToAveva: meta.HistorizeToAveva,
|
||||
// WP4: the Area/Line/Equipment UNS paths that reference this raw condition — the /alerts row
|
||||
// renders them as the equipment list (empty for a raw condition no equipment references yet).
|
||||
ReferencingEquipmentPaths: meta.ReferencingEquipmentPaths);
|
||||
_mediator.Tell(new Publish(ScriptedAlarmHostActor.AlertsTopic, alertEvent));
|
||||
// Phase 5: fan the same transition into the node-local live-telemetry hub (no-op until a gRPC
|
||||
// client subscribes). The DPS publish above is unchanged — a strictly additive tap, riding the
|
||||
// same Primary gate (only reached when serviceAlertsAsPrimary).
|
||||
_telemetryHub?.Emit(new TelemetryItem.Alarm(alertEvent));
|
||||
foreach (var historyKind in historyKinds)
|
||||
PublishNativeAlertRow(msg.Args, nodeId, snapshot, meta, historyKind);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Publish one native-alarm <c>alerts</c> row (DPS + the node-local telemetry hub). Primary-gated by the caller.
|
||||
/// </summary>
|
||||
/// <param name="args">The native transition.</param>
|
||||
/// <param name="nodeId">The condition node id.</param>
|
||||
/// <param name="snapshot">The projected snapshot (its severity is the row's).</param>
|
||||
/// <param name="meta">The condition's authored metadata.</param>
|
||||
/// <param name="historyKind">The row's transition kind (one of the projector's history kinds).</param>
|
||||
private void PublishNativeAlertRow(
|
||||
AlarmEventArgs args, string nodeId, AlarmConditionSnapshot snapshot,
|
||||
(string EquipmentId, string Name, string AlarmType, bool? HistorizeToAveva, IReadOnlyList<string> ReferencingEquipmentPaths) meta,
|
||||
AlarmTransitionKind historyKind)
|
||||
{
|
||||
// #656: an ActiveAcknowledged expands to "Activated" + "Acknowledged". The operator comment/user belong to
|
||||
// the acknowledgement, and the activation happened at the original raise time when the source knows it.
|
||||
var expandedActivation = args.Kind == AlarmTransitionKind.ActiveAcknowledged
|
||||
&& historyKind != AlarmTransitionKind.Acknowledge;
|
||||
var comment = expandedActivation ? null : args.OperatorComment;
|
||||
var timestamp = expandedActivation ? args.OriginalRaiseTimestampUtc ?? args.SourceTimestampUtc : args.SourceTimestampUtc;
|
||||
var alertEvent = new AlarmTransitionEvent(
|
||||
AlarmId: nodeId,
|
||||
EquipmentPath: meta.EquipmentId,
|
||||
AlarmName: meta.Name,
|
||||
TransitionKind: ToEventKind(historyKind),
|
||||
// The projector mapped the four-bucket AlarmSeverity onto the OPC UA 1..1000 scale already;
|
||||
// reuse its ushort so the condition node + the alerts row agree on severity.
|
||||
Severity: snapshot.Severity,
|
||||
Message: args.Message,
|
||||
// Native transitions are device-driven; an operator comment only rides along on an
|
||||
// acknowledge from the upstream alarm system. "device" marks a non-operator origin.
|
||||
User: comment is null ? string.Empty : "device",
|
||||
TimestampUtc: timestamp,
|
||||
AlarmTypeName: meta.AlarmType,
|
||||
Comment: comment,
|
||||
// Per-condition opt-out parsed from TagConfig.alarm.historizeToAveva (bool?, null ⇒ absent ⇒
|
||||
// historize). The HistorianAdapterActor gate (historizeToAveva is not false) historizes null +
|
||||
// true and suppresses the durable AVEVA row only on an explicit false — the same posture as the
|
||||
// scripted-alarm opt-out. null here rides through unchanged (the gate treats it as default-on).
|
||||
HistorizeToAveva: meta.HistorizeToAveva,
|
||||
// WP4: the Area/Line/Equipment UNS paths that reference this raw condition — the /alerts row
|
||||
// renders them as the equipment list (empty for a raw condition no equipment references yet).
|
||||
ReferencingEquipmentPaths: meta.ReferencingEquipmentPaths);
|
||||
_mediator.Tell(new Publish(ScriptedAlarmHostActor.AlertsTopic, alertEvent));
|
||||
// Phase 5: fan the same transition into the node-local live-telemetry hub (no-op until a gRPC
|
||||
// client subscribes). The DPS publish above is unchanged — a strictly additive tap, riding the
|
||||
// same Primary gate (only reached when serviceAlertsAsPrimary).
|
||||
_telemetryHub?.Emit(new TelemetryItem.Alarm(alertEvent));
|
||||
}
|
||||
|
||||
/// <summary>Maps a native <see cref="AlarmTransitionKind"/> onto the canonical alarm event-kind
|
||||
/// vocabulary scripted alarms emit (the <c>EmissionKind</c> names) so a native row renders with the
|
||||
/// correct chip on the <c>/alerts</c> page and historizes into the same <c>EventKind</c> column as
|
||||
@@ -1930,6 +1955,8 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers, IWithUnboundedS
|
||||
AlarmTransitionKind.Raise or AlarmTransitionKind.Retrigger => "Activated",
|
||||
AlarmTransitionKind.Clear => "Cleared",
|
||||
AlarmTransitionKind.Acknowledge => "Acknowledged",
|
||||
// #656: never reached in practice — the projector expands ActiveAcknowledged into Raise + Acknowledge rows.
|
||||
AlarmTransitionKind.ActiveAcknowledged => "Acknowledged",
|
||||
_ => "Activated",
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user