Merge #597/#599: real UnshelveTime, commented re-ack reports, native ack refused off-Primary, /alerts ack-path test; surgically-added raw nodes announced, equipment-with-references removal keeps references severed; Backing* parity guard

Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe
This commit is contained in:
Joseph Doherty
2026-10-08 07:12:59 -04:00
16 changed files with 873 additions and 89 deletions
@@ -44,6 +44,7 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
private readonly ActorRegistry _actorRegistry;
private readonly ILoggerFactory _loggerFactory;
private readonly ILogger<OtOpcUaServerHostedService> _logger;
private readonly IDriverPrimaryRoleSource? _primaryRoleSource;
private OpcUaApplicationHost? _appHost;
private OtOpcUaSdkServer? _server;
@@ -88,6 +89,11 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
/// <param name="time">The shared clock — the one instance the authorizer and the API-key store bound
/// also read. Its <c>CreateTimer</c> arms the revalidation tick.</param>
/// <param name="loggerFactory">The logger factory for creating loggers.</param>
/// <param name="primaryRoleSource">Gitea #597 — the data-plane Primary verdict <c>DriverHostActor</c>
/// publishes on every redundancy snapshot (the same one its native-ack route and device-write gates apply).
/// Wired onto the node manager so a native-condition Acknowledge on a non-Primary node is refused rather than
/// applied and then reverted. Optional: a node with no driver role registers none, and null means "allow" —
/// the single-node posture <c>UnmanagedDriverPrimaryRoleSource</c> also answers with.</param>
public OtOpcUaServerHostedService(
IOptions<OpcUaApplicationHostOptions> options,
DeferredAddressSpaceSink deferredSink,
@@ -101,7 +107,8 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
DataPlaneAuthorizer? dataPlaneAuthorizer,
IOptions<AclOptions> aclOptions,
TimeProvider time,
ILoggerFactory loggerFactory)
ILoggerFactory loggerFactory,
IDriverPrimaryRoleSource? primaryRoleSource = null)
{
ArgumentNullException.ThrowIfNull(aclOptions);
ArgumentNullException.ThrowIfNull(time);
@@ -123,6 +130,7 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
_actorSystemAccessor = actorSystemAccessor;
_actorRegistry = actorRegistry;
_loggerFactory = loggerFactory;
_primaryRoleSource = primaryRoleSource;
_logger = loggerFactory.CreateLogger<OtOpcUaServerHostedService>();
}
@@ -225,6 +233,21 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
}
});
// Gitea #597: a native ack is accepted only on the Primary. The verdict is the one DriverHostActor
// publishes and gates the route above on, so a Secondary refuses (BadInvalidState) instead of applying an
// ack the driver will never see and then reverting it. A volatile property read — safe under the SDK Lock.
if (_primaryRoleSource is { } primaryRoleSource)
{
_server.SetNativeAlarmAckPrimaryGate(() => primaryRoleSource.ShouldActAsPrimary);
}
else
{
// Every driver node registers one (AddOtOpcUaRuntime), so this is a wiring regression, not a mode:
// say so rather than let a Secondary silently go back to accepting acks it will revert.
_logger.LogWarning(
"OtOpcUaServerHostedService: no IDriverPrimaryRoleSource registered — native-alarm acknowledges are accepted on every node regardless of redundancy role");
}
// Wire the reverse-path inbound operator-write gateway: a client write to a writable equipment-tag
// node that passes the node manager's WriteOperate gate routes the write to the owning driver child
// (RouteNodeWrite → NodeWriteResult) via the local DriverHostActor. The node manager calls the
@@ -345,6 +368,7 @@ public sealed class OtOpcUaServerHostedService : IHostedService, IAsyncDisposabl
_server?.SetNodeWriteGateway(null);
// Clear the native-alarm-ack router so a late ack doesn't Tell a stopping DriverHostActor.
_server?.SetNativeAlarmAckRouter(null);
_server?.SetNativeAlarmAckPrimaryGate(null);
// Restore the Null historian so a late HistoryRead doesn't hit a disposed read client.
_server?.SetHistorianDataSource(null);
// Restore the empty authority so a late session activation cannot authorize against a stopping node.