Files
lmxopcua/src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/IAlarmSource.cs
T
Joseph Doherty 48a80b5962 fix(alarms): atomic InactiveUnacknowledged + flagged Clear/Acknowledge first sight for OpcUaClient (#657)
After an OpcUaClient respawn an upstream inactive+unacked condition went out as
Retrigger+Clear (duplicate Activated+Cleared rows, Active flicker), and a
first-sight inactive+acked one as Unspecified (an Activated row for an inactive
alarm; a retained-Active host condition never cleared).

- New AlarmTransitionKind.InactiveUnacknowledged: one projection, rows only for
  what changed (Activated+Cleared from acked, Cleared from active+unacked, none
  when already inactive+unacked).
- OpcUaClient uses it for moves into inactive+unacked; first sight of an
  inactive condition is InactiveUnacknowledged or Clear+Acknowledge, flagged.
- Projector: a flagged Acknowledge on an already-acked condition writes no row.
- E2E tests through DriverHostActor.ForwardNativeAlarm (red-proven).

Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe
2026-10-09 06:08:39 -04:00

160 lines
9.9 KiB
C#

namespace ZB.MOM.WW.OtOpcUa.Core.Abstractions;
/// <summary>
/// Driver capability for alarm events. Optional — only drivers whose backends expose
/// alarm conditions implement this. Currently: Galaxy (MxAccess alarms), FOCAS
/// (CNC alarms), OPC UA Client (A&amp;C events from upstream server), MTConnect
/// (CONDITION data items, Gitea #626).
/// </summary>
public interface IAlarmSource
{
/// <summary>
/// Subscribe to alarm events for a node-set (typically: a folder or equipment subtree).
/// The driver fires <see cref="OnAlarmEvent"/> for every alarm transition.
/// </summary>
/// <param name="sourceNodeIds">The driver node IDs to subscribe to.</param>
/// <param name="cancellationToken">Cancellation token for the operation.</param>
/// <returns>A handle identifying the created subscription.</returns>
Task<IAlarmSubscriptionHandle> SubscribeAlarmsAsync(
IReadOnlyList<string> sourceNodeIds,
CancellationToken cancellationToken);
/// <summary>Cancel an alarm subscription returned by <see cref="SubscribeAlarmsAsync"/>.</summary>
/// <param name="handle">The subscription handle returned from <see cref="SubscribeAlarmsAsync"/>.</param>
/// <param name="cancellationToken">Cancellation token for the operation.</param>
/// <returns>A task that represents the asynchronous operation.</returns>
Task UnsubscribeAlarmsAsync(IAlarmSubscriptionHandle handle, CancellationToken cancellationToken);
/// <summary>Acknowledge one or more active alarms by source node ID + condition ID.</summary>
/// <param name="acknowledgements">The batch of alarm acknowledgement requests.</param>
/// <param name="cancellationToken">Cancellation token for the operation.</param>
/// <returns>A task that represents the asynchronous operation.</returns>
Task AcknowledgeAsync(
IReadOnlyList<AlarmAcknowledgeRequest> acknowledgements,
CancellationToken cancellationToken);
/// <summary>Server-pushed alarm transition (raise / clear / change).</summary>
event EventHandler<AlarmEventArgs>? OnAlarmEvent;
}
/// <summary>Opaque alarm-subscription identity returned by <see cref="IAlarmSource.SubscribeAlarmsAsync"/>.</summary>
public interface IAlarmSubscriptionHandle
{
/// <summary>Driver-internal subscription identifier (for diagnostics + post-mortem).</summary>
string DiagnosticId { get; }
}
/// <summary>One alarm acknowledgement in a batch.</summary>
/// <param name="SourceNodeId">Driver-side identifier for the alarm source.</param>
/// <param name="ConditionId">Stable id correlating raise / ack / clear of the same condition.</param>
/// <param name="Comment">Operator-supplied comment forwarded to the upstream alarm system.</param>
/// <param name="OperatorUser">Authenticated principal performing the ack; null on the raw/non-OPC-UA path.</param>
public sealed record AlarmAcknowledgeRequest(
string SourceNodeId,
string ConditionId,
string? Comment,
string? OperatorUser = null);
/// <summary>Event payload for <see cref="IAlarmSource.OnAlarmEvent"/>.</summary>
/// <param name="SubscriptionHandle">Subscription this event belongs to.</param>
/// <param name="SourceNodeId">Driver-side identifier for the alarm source.</param>
/// <param name="ConditionId">Stable id correlating raise / ack / clear of the same condition.</param>
/// <param name="AlarmType">Driver-defined alarm type name (e.g. AnalogLimitAlarm.HiHi).</param>
/// <param name="Message">Human-readable alarm description.</param>
/// <param name="Severity">Four-bucket severity ladder.</param>
/// <param name="SourceTimestampUtc">When this transition occurred.</param>
/// <param name="OperatorComment">
/// Operator-supplied comment recorded by the upstream alarm system on Acknowledge
/// transitions. Null on raise / clear, or when the upstream path can't surface
/// the comment (the Galaxy sub-attribute fallback path collapses comments into a
/// single string write — null on that path; the driver-native gateway path
/// populates this).
/// </param>
/// <param name="OriginalRaiseTimestampUtc">
/// When the alarm originally entered the active state. Preserved across
/// Acknowledge transitions so OPC UA Part 9 conditions keep the original raise
/// time in <c>Time</c>. Null when the upstream path doesn't surface it.
/// </param>
/// <param name="AlarmCategory">
/// Upstream alarm taxonomy bucket (e.g. <c>Process</c> / <c>Safety</c> /
/// <c>Diagnostics</c>). Maps to OPC UA <c>ConditionClassName</c> downstream when
/// a class mapping is configured. Null when the upstream path doesn't carry it.
/// </param>
/// <param name="Kind">
/// The alarm transition kind (raise / acknowledge / clear / retrigger). Lets a
/// consumer derive OPC UA Part 9 active/ack state without inferring it from
/// other fields. <see cref="AlarmTransitionKind.Unspecified"/> when the upstream
/// path doesn't surface a distinct kind.
/// </param>
/// <param name="OpcUaSeverity">
/// Optional exact OPC UA severity (1..1000) for a source whose own scale is finer than the four
/// <see cref="AlarmSeverity"/> buckets (Gitea #626: MTConnect Warning = 500, Fault = 800). When set it
/// supersedes the bucket on the projected Part 9 condition (clamped to 1..1000); <c>null</c> — every
/// pre-#626 source — keeps the bucket mapping. <see cref="Severity"/> must still carry the nearest
/// bucket for consumers that only read the bucket.
/// </param>
/// <param name="QualityStatusCode">
/// Optional status code of the condition's SOURCE data (Part 9 <c>ConditionType.Quality</c>), for a
/// source that can report "no value for this condition" per alarm rather than per connection (Gitea
/// #626: MTConnect <c>Unavailable</c>). <c>null</c> keeps the pre-#626 behaviour (projected Good;
/// driver-wide comms loss is annotated separately by the host). An event whose <see cref="Kind"/> is
/// <see cref="AlarmTransitionKind.Unspecified"/> and which carries a quality is a
/// <b>quality-only annotation</b> (<see cref="IsQualityOnly"/>): the host updates (via its Quality-only node path) the condition's
/// Quality without touching its Active/Acked state and publishes no <c>alerts</c> row for it.
/// </param>
/// <param name="IsRestatement">
/// Gitea #656 — true when the source is RE-STATING upstream's current state rather than reporting a transition it
/// watched happen: a reconnect snapshot entry (Galaxy) or the first event for a condition after a driver start or
/// deploy respawn (OpcUaClient). It governs <b>history only, never node state</b>: the host still projects the
/// state, but writes no <c>alerts</c> row when the re-statement changes nothing the condition shows (a Retrigger on
/// an Active+unacked condition with the same message and severity; a Clear on an already-inactive condition; an
/// Acknowledge on an already-acknowledged condition) — or
/// when a flagged <see cref="AlarmTransitionKind.Unspecified"/> update moves the message/severity of an
/// already-active condition (node updated, one condition event, active/acked kept, no row). AbCip ALMA sets the
/// flag for the last shape (the governing limit changed, no new occurrence). OpcUaClient (Gitea #657) re-states a
/// first-seen inactive+acked condition as a flagged Clear then a flagged Acknowledge, so a host already showing
/// that writes nothing and a host retaining it Active gets a real "Cleared". <c>false</c> (the default, every source that does not
/// opt in) keeps every transition's row.
/// </param>
public sealed record AlarmEventArgs(
IAlarmSubscriptionHandle SubscriptionHandle,
string SourceNodeId,
string ConditionId,
string AlarmType,
string Message,
AlarmSeverity Severity,
DateTime SourceTimestampUtc,
string? OperatorComment = null,
DateTime? OriginalRaiseTimestampUtc = null,
string? AlarmCategory = null,
AlarmTransitionKind Kind = AlarmTransitionKind.Unspecified,
int? OpcUaSeverity = null,
uint? QualityStatusCode = null,
bool IsRestatement = false)
{
/// <summary>
/// True when this event only re-annotates the condition's source-data quality — a
/// <see cref="QualityStatusCode"/> with an <see cref="AlarmTransitionKind.Unspecified"/> kind. No
/// alarm-state change happened, so the host must not publish it as an alarm transition.
/// </summary>
public bool IsQualityOnly => Kind == AlarmTransitionKind.Unspecified && QualityStatusCode is not null;
}
/// <summary>Mirrors the <c>NodePermissions</c> alarm-severity enum in <c>docs/v2/acl-design.md</c>.</summary>
public enum AlarmSeverity { Low, Medium, High, Critical }
/// <summary>
/// Kind of alarm state change carried by <see cref="AlarmEventArgs.Kind"/>, letting a
/// consumer derive OPC UA Part 9 active/ack state. Mirrors the driver-side
/// transition-kind enums (e.g. Galaxy's <c>GalaxyAlarmTransitionKind</c>).
/// <see cref="ActiveAcknowledged"/> (Gitea #656) means "the condition is active AND acknowledged", applied by the
/// host as ONE projection — never Raise-then-Acknowledge, which would show clients an Active+unacked intermediate.
/// <see cref="InactiveUnacknowledged"/> (Gitea #657) is its mirror: "the condition is inactive AND unacknowledged"
/// (it went active and cleared unacknowledged), applied as ONE projection — never Raise-then-Clear, which showed
/// clients the condition Active again for an instant. The host writes rows only for what actually changed:
/// "Activated" + "Cleared" when the condition was acknowledged (a new occurrence must have happened), "Cleared"
/// alone when it was Active+unacked, none when it already showed inactive+unacked.
/// Members are append-only: their numeric values must not move.
/// </summary>
public enum AlarmTransitionKind { Unspecified = 0, Raise, Acknowledge, Clear, Retrigger, ActiveAcknowledged, InactiveUnacknowledged }