Files
lmxopcua/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Pages/Alerts.razor
T
Joseph Doherty 8ebc712eff feat(v3-batch4-wp4): multi-notifier native alarms (single ReportEvent → raw + equipment notifiers) + teardown symmetry
Materialize each native alarm ONCE at the raw tag (ConditionId = RawPath, Raw
realm); wire the single condition as an SDK event notifier of each referencing
equipment's UNS folder so one ReportEvent fans to every root without
re-reporting per root (which would break Server-object dedup + Part 9 ack
correlation).

- New sink method WireAlarmNotifiers(alarmNodeId, alarmRealm,
  notifierFolderNodeIds, notifierFolderRealm) on IOpcUaAddressSpaceSink,
  forwarded through DeferredAddressSpaceSink + SdkAddressSpaceSink +
  NullOpcUaAddressSpaceSink (the forwarding-trap guard); auto-covered by the
  DeferredSinkForwardingReflectionTests realm + forwarding guards + a
  hand-written forward test.
- OtOpcUaNodeManager: the normative AddNotifier(isInverse) pair + idempotent
  EnsureFolderIsEventNotifier per equipment folder; tracked per condition in
  _alarmNotifierWiring. Teardown symmetry: RemoveNotifier(bidirectional:true) on
  RebuildAddressSpace, RemoveAlarmConditionNode, and RemoveEquipmentSubtree so no
  inverse-notifier entry leaks across redeploys.
- AddressSpaceApplier.MaterialiseRawSubtree wires notifiers for each native alarm
  tag, resolving its ReferencingEquipmentPaths (Area/Line/Equipment) to the
  EquipmentId folder NodeIds via BuildEquipmentIdByFolderPath.
- AlarmTransitionEvent gains ReferencingEquipmentPaths (empty default); /alerts
  renders the referencing-equipment list as display metadata.
- Un-skipped + rewrote the native-alarm dark tests
  (DriverHostActorNativeAlarmTests x6, DriverHostActorNativeAlarmAckRoutingTests
  x1) for the v3 raw-condition model; new NodeManagerMultiNotifierAlarmTests
  proves multi-notifier wiring + teardown symmetry (no leaked duplicates after a
  re-trip) + applier wiring test.

Claude-Session: https://claude.ai/code/session_01LVneM3eh1UtJxEisFXgmox
2026-07-16 12:07:11 -04:00

315 lines
16 KiB
Plaintext

@page "/alerts"
@* Live alarm tail via SignalR. Subscribes to /hubs/alerts and shows the most-recent
AlarmTransitionEvent entries published by ScriptedAlarmActor (Runtime/ScriptedAlarms)
and the AB CIP ALMD bridge. *@
@attribute [Authorize(Policy = AdminUiPolicies.AuthenticatedRead)]
@rendermode RenderMode.InteractiveServer
@using ZB.MOM.WW.OtOpcUa.AdminUI.Hubs
@using ZB.MOM.WW.OtOpcUa.Commons.Interfaces
@using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin
@using ZB.MOM.WW.OtOpcUa.Commons.Messages.Alerts
@inject IInProcessBroadcaster<AlarmTransitionEvent> Alarms
@inject AuthenticationStateProvider AuthState
@inject IAuthorizationService AuthorizationService
@inject IAdminOperationsClient AdminOps
@implements IAsyncDisposable
<div class="d-flex justify-content-between align-items-center mb-3">
<h4 class="mb-0">Alerts</h4>
<div class="d-flex align-items-center gap-2">
<span class="conn-pill" data-state="@(_connected ? "connected" : "disconnected")">
<span class="dot"></span><span>@(_connected ? "live" : "disconnected")</span>
</span>
<button class="btn btn-sm btn-outline-secondary" @onclick="ClearAsync">Clear</button>
</div>
</div>
<section class="panel notice rise" style="animation-delay:.02s">
Live alarm transitions from the cluster's <span class="mono">alerts</span> DPS topic. Shows
the most-recent @Capacity entries since the page opened; reload for a fresh window. Sources:
ScriptedAlarmActor, native driver alarm bridges (AB CIP ALMD, Galaxy where wired).
</section>
@if (_rows.Count == 0)
{
<section class="panel notice rise mt-3" style="animation-delay:.08s">
No alarms in the current window. The table will populate as soon as a
ScriptedAlarmActor or driver alarm bridge publishes a transition.
</section>
}
else
{
<section class="panel rise mt-3" style="animation-delay:.08s">
<div class="panel-head">Recent transitions (@_rows.Count)</div>
<div class="table-wrap">
<table class="data-table">
<thead>
<tr>
<th>Time</th>
<th>Alarm</th>
<th>Equipment</th>
<th>Kind</th>
<th class="num">Severity</th>
<th>User</th>
<th>Message</th>
@if (_canOperate)
{
<th>Actions</th>
}
</tr>
</thead>
<tbody>
@foreach (var e in _rows)
{
<tr>
<td><span class="mono small">@e.TimestampUtc.ToString("HH:mm:ss.fff")</span></td>
<td><span class="mono">@e.AlarmId</span><div class="text-muted small">@e.AlarmName</div></td>
<td>
<span class="mono small">@e.EquipmentPath</span>
@* v3 Batch 4 (multi-notifier native alarms): one condition row carries the list
of referencing equipment (Area/Line/Equipment) as display metadata. Shown only
when the producer populated it (native alarms whose raw tag ≥1 equipment
references); scripted alarms + unreferenced native alarms leave it empty. *@
@if (e.ReferencingEquipmentPaths is { Count: > 0 } refs)
{
<div class="text-muted small" title="Referencing equipment">
@foreach (var p in refs)
{
<span class="chip chip-idle" style="font-size:0.72rem; margin:1px">@p</span>
}
</div>
}
</td>
<td><span class="chip @KindChipClass(e.TransitionKind)">@e.TransitionKind</span></td>
<td class="num">@e.Severity</td>
<td>@e.User</td>
<td>@e.Message</td>
@if (_canOperate)
{
@* DriverOperator-gated Acknowledge / Shelve / Unshelve. Each routes through
the AdminOperationsActor singleton, which republishes onto the cluster
'alarm-commands' topic; the owning node applies it (ownership filter). *@
<td>
<div class="d-flex gap-1 align-items-center">
<button type="button"
class="btn btn-sm btn-outline-secondary"
disabled="@_busyAlarmId.Equals(e.AlarmId)"
@onclick="() => AcknowledgeAsync(e.AlarmId)"
title="Acknowledge this alarm">Ack</button>
<button type="button"
class="btn btn-sm btn-outline-secondary"
disabled="@_busyAlarmId.Equals(e.AlarmId)"
@onclick="() => ShelveAsync(e.AlarmId, ShelveKind.OneShot)"
title="Shelve this alarm until it next clears">Shelve</button>
<input type="number" min="1" class="form-control form-control-sm" style="width:4.5rem"
disabled="@_busyAlarmId.Equals(e.AlarmId)"
@bind:get="GetShelveMinutes(e.AlarmId)" @bind:set="m => SetShelveMinutes(e.AlarmId, m)"
title="Timed-shelve duration in minutes" />
<button type="button"
class="btn btn-sm btn-outline-secondary"
disabled="@_busyAlarmId.Equals(e.AlarmId)"
@onclick="() => ShelveTimedAsync(e.AlarmId)"
title="Shelve this alarm for the chosen number of minutes">Shelve (timed)</button>
<button type="button"
class="btn btn-sm btn-outline-secondary"
disabled="@_busyAlarmId.Equals(e.AlarmId)"
@onclick="() => ShelveAsync(e.AlarmId, ShelveKind.Unshelve)"
title="Remove an existing shelve">Unshelve</button>
</div>
@if (_opResultAlarmId.Equals(e.AlarmId) && _opResultMessage is not null)
{
<span class="chip @(_opResultOk ? "chip-ok" : "chip-bad")" style="font-size:0.8rem">@_opResultMessage</span>
}
</td>
}
</tr>
}
</tbody>
</table>
</div>
</section>
}
@code {
private const int Capacity = 200;
private readonly List<AlarmTransitionEvent> _rows = new();
private bool _connected;
// Authorization — DriverOperator gates the per-row Ack/Shelve/Unshelve controls.
private bool _canOperate;
// Per-row action state. Only one alarm action is in flight at a time; the busy/result
// fields are keyed by AlarmId so the spinner + result chip attach to the right row.
private string _busyAlarmId = "";
private string _opResultAlarmId = "";
private string? _opResultMessage;
private bool _opResultOk;
// Auto-clear timer for the per-row result chip (mirrors DriverStatusPanel): the chip is set in
// ShowOpResult and cleared 8 s later so it doesn't persist until the next action.
private System.Threading.Timer? _opResultClearTimer;
private object? _opResultClearToken;
// Per-row timed-shelve duration (minutes). Keyed by AlarmId so each row's number input is
// independent — binding every row to one shared field would couple all the inputs together.
private const int DefaultShelveMinutes = 5;
private readonly Dictionary<string, int> _shelveMinutes = new();
private int GetShelveMinutes(string alarmId) =>
_shelveMinutes.TryGetValue(alarmId, out var m) ? m : DefaultShelveMinutes;
private void SetShelveMinutes(string alarmId, int minutes) =>
_shelveMinutes[alarmId] = minutes < 1 ? 1 : minutes;
protected override async Task OnInitializedAsync()
{
// Live alarm tail straight from the in-process broadcaster (fed by AlertSignalRBridge off the
// 'alerts' DPS topic). A Blazor Server component can't self-connect a SignalR HubConnection
// behind a reverse proxy — see IInProcessBroadcaster — so we subscribe in-process instead.
// Subscribe to the health signal BEFORE reading IsConnected so a state change between the
// read and the subscribe can't be missed (TOCTOU) — mirrors DriverStatusPanel's
// SnapshotChanged-then-TryGet ordering.
Alarms.ConnectionStateChanged += OnConnectionStateChanged;
Alarms.Received += OnAlarm;
_connected = Alarms.IsConnected;
// Check DriverOperator authorization so the per-row action controls only render for
// permitted users. The username is re-read at click time (GetCurrentUserNameAsync) so a
// mid-session token refresh lands in the published command + audit accurately.
var auth = await AuthState.GetAuthenticationStateAsync();
var authResult = await AuthorizationService.AuthorizeAsync(auth.User, null, AdminUiPolicies.DriverOperator);
_canOperate = authResult.Succeeded;
}
private async Task AcknowledgeAsync(string alarmId)
{
_busyAlarmId = alarmId;
_opResultMessage = null;
StateHasChanged();
try
{
var user = await GetCurrentUserNameAsync();
using var cts = new System.Threading.CancellationTokenSource(TimeSpan.FromSeconds(15));
var result = await AdminOps.AcknowledgeAlarmAsync(
alarmId, user, comment: null, cts.Token);
ShowOpResult(alarmId, result.Ok, result.Ok ? "Ack sent" : (result.Message ?? "Failed"));
}
catch (Exception ex)
{
ShowOpResult(alarmId, false, ex.Message.Length > 60 ? ex.Message[..60] + "…" : ex.Message);
}
finally
{
_busyAlarmId = "";
StateHasChanged();
}
}
// Thin wrapper for the per-row "Shelve (timed)" button: shelves until now + the row's chosen
// minutes. OneShot/Unshelve call ShelveAsync directly with the default null unshelve-at.
private Task ShelveTimedAsync(string alarmId) =>
ShelveAsync(alarmId, ShelveKind.Timed, DateTime.UtcNow.AddMinutes(GetShelveMinutes(alarmId)));
private async Task ShelveAsync(string alarmId, ShelveKind kind, DateTime? unshelveAtUtc = null)
{
_busyAlarmId = alarmId;
_opResultMessage = null;
StateHasChanged();
try
{
var user = await GetCurrentUserNameAsync();
using var cts = new System.Threading.CancellationTokenSource(TimeSpan.FromSeconds(15));
var result = await AdminOps.ShelveAlarmAsync(
alarmId, user, kind, unshelveAtUtc: unshelveAtUtc, comment: null, cts.Token);
var verb = kind == ShelveKind.Unshelve ? "Unshelve" : "Shelve";
ShowOpResult(alarmId, result.Ok, result.Ok ? $"{verb} sent" : (result.Message ?? "Failed"));
}
catch (Exception ex)
{
ShowOpResult(alarmId, false, ex.Message.Length > 60 ? ex.Message[..60] + "…" : ex.Message);
}
finally
{
_busyAlarmId = "";
StateHasChanged();
}
}
/// <summary>
/// Re-reads the AuthenticationState at call time so the operator name forwarded to the
/// command + audit reflects the current claims-principal (survives token refresh during a
/// long-lived circuit). Returns "unknown" if no Name claim is present.
/// </summary>
private async Task<string> GetCurrentUserNameAsync()
{
var auth = await AuthState.GetAuthenticationStateAsync();
return auth.User.Identity?.Name
?? auth.User.FindFirst(System.Security.Claims.ClaimTypes.NameIdentifier)?.Value
?? "unknown";
}
private void ShowOpResult(string alarmId, bool ok, string message)
{
_opResultAlarmId = alarmId;
_opResultOk = ok;
_opResultMessage = message;
StateHasChanged();
// Auto-clear the result chip after 8 s (mirrors DriverStatusPanel). System.Threading.Timer
// is used (not System.Timers.Timer) so DisposeAsync can drain any in-flight callback.
var token = _opResultClearToken = new object();
_opResultClearTimer?.Dispose();
_opResultClearTimer = new System.Threading.Timer(_ =>
InvokeAsync(() =>
{
// Ignore a stale fire: a newer action superseded this timer's chip. (Timer.Dispose does
// not drain an already-queued callback, so without this a stale timer could clear a
// freshly-set result from a different row.)
if (!ReferenceEquals(_opResultClearToken, token)) return;
_opResultMessage = null;
_opResultAlarmId = "";
StateHasChanged();
}),
null, TimeSpan.FromSeconds(8), Timeout.InfiniteTimeSpan);
}
private void OnAlarm(AlarmTransitionEvent evt) =>
// Marshal both the mutation and the re-render onto the circuit sync context so this can't
// race ClearAsync (which runs there) over the shared _rows list.
InvokeAsync(() =>
{
_rows.Insert(0, evt);
if (_rows.Count > Capacity) _rows.RemoveAt(_rows.Count - 1);
StateHasChanged();
});
// Raised by the broadcaster (on the bridge actor's thread) whenever the upstream DPS
// subscription's health flips. Marshal onto the circuit sync context like OnAlarm so the live
// pill re-renders safely.
private void OnConnectionStateChanged(bool connected) =>
InvokeAsync(() => { _connected = connected; StateHasChanged(); });
private async Task ClearAsync()
{
_rows.Clear();
await InvokeAsync(StateHasChanged);
}
private static string KindChipClass(string kind) => kind switch
{
"Activated" => "chip-alert",
"Cleared" => "chip-ok",
"Acknowledged" or "Confirmed" => "chip-caution",
"Shelved" or "Disabled" => "chip-idle",
_ => "chip-idle",
};
public async ValueTask DisposeAsync()
{
// Unsubscribe BOTH broadcaster events first so the singleton can't invoke a handler on a
// disposed component, then drain the auto-clear timer (its async dispose awaits any in-flight
// callback so it can't call StateHasChanged on a gone component).
Alarms.ConnectionStateChanged -= OnConnectionStateChanged;
Alarms.Received -= OnAlarm;
if (_opResultClearTimer is not null) await _opResultClearTimer.DisposeAsync();
}
}