Merge branch 'master' into fix/r3-02-stale-good-family

# Conflicts:
#	src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Drivers/DriverHostActor.cs
#	tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/Harness/V3ArtifactSeeder.cs
This commit is contained in:
Joseph Doherty
2026-08-20 11:03:02 -04:00
46 changed files with 5411 additions and 208 deletions
@@ -104,8 +104,6 @@ public static class OtOpcUaTelemetry
Meter.CreateCounter<long>("otopcua.redundancy.service_level_change", unit: "{change}",
description: "OPC UA Server.ServiceLevel transitions emitted by the redundancy state.");
/// <summary>Inbound operations denied by the Primary data-plane gate (archreview 03/S4) —
/// site=write|ack|alarm-emit, reason=secondary|detached|role-unknown.</summary>
/// <summary>Archreview 03/S15 — tag refs a driver left <c>BadNoCommunication</c> after it reconnected:
/// the host marked them Bad on the outage, and the driver never re-published them. Non-zero means a
/// driver that reconnects without a full re-publish (a push driver missing its initial push, or a
@@ -115,10 +113,26 @@ public static class OtOpcUaTelemetry
Meter.CreateCounter<long>("otopcua.driver.comms_latched_refs", unit: "{ref}",
description: "Refs still BadNoCommunication after their driver reconnected (driver, driver_type).");
/// <summary>Inbound operations denied by the Primary data-plane gate (archreview 03/S4) —
/// site=write|ack|alarm-emit, reason=secondary|detached|role-unknown.</summary>
public static readonly Counter<long> PrimaryGateDenied =
Meter.CreateCounter<long>("otopcua.redundancy.primary_gate_denied", unit: "{denial}",
description: "Operations denied by the Primary gate (site=write|ack|alarm-emit, reason=secondary|detached|role-unknown).");
/// <summary>
/// API-key store lookups the 03/S18 bound intervened on (outcome=timeout|cache_hit).
/// </summary>
/// <remarks>
/// One counter with an <c>outcome</c> tag rather than two: <c>timeout</c> is the alarm signal that
/// the ConfigDb is not answering the OPC UA impersonation callback, and <c>cache_hit</c> is the
/// ratio that says whether the TTL is doing anything. A missing <c>cache_hit</c> stream on a busy
/// fused central is how you notice <c>Security:ApiKeys:StoreCacheSeconds</c> was set to 0 by
/// accident. A plain read-through meters neither — the counter names interventions, not traffic.
/// </remarks>
public static readonly Counter<long> ApiKeyStoreBounded =
Meter.CreateCounter<long>("otopcua.opcua.apikey_store.bounded", unit: "{lookup}",
description: "API-key store lookups the bound intervened on (outcome=timeout|cache_hit).");
// ---------------- Convenience helpers ----------------
/// <summary>