fix(abcip): a refused probe tag proves the device reachable (no blackout)

H10: the probe loop recorded EVERY exception - including the controller answering NotFound for a typo'd or download-deleted Probe.ProbeTagPath - as a Forward-Open failure. At a 5 s tick against a 30 s backoff cap ShouldAttempt was never true again, so every cold or evicted data tag on a reachable device read BadCommunicationError indefinitely and the host showed Stopped. The probe now decides the backoff verdict and the host state separately: - a device refusal (thrown or as a status word) is backoff success + host Running + one Warning per device naming the probe tag; an initialised probe runtime is kept so its lease is not re-opened every tick; - a malformed probe tag name (AbCipTagConfigurationException) never reached the device: no backoff signal, no host transition, one Warning; - a genuine transport failure is unchanged (backoff failure, host Stopped). Refs #737 Claude-Session: https://claude.ai/code/session_01Ub9hGmYLQvn9XETzw7CMsT
2026-10-22 14:17:03 -04:00
parent f087f01d2b
commit 22d4680e7b
2 changed files with 145 additions and 11 deletions
@@ -0,0 +1,86 @@
+using Microsoft.Extensions.Logging;
+using Shouldly;
+using Xunit;
+using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
+using ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport;
+using CapturingLogger = ZB.MOM.WW.OtOpcUa.Driver.AbCip.Tests.AbCipLoggingTests.CapturingLogger<ZB.MOM.WW.OtOpcUa.Driver.AbCip.AbCipDriver>;
+
+namespace ZB.MOM.WW.OtOpcUa.Driver.AbCip.Tests;
+
+/// <summary>
+///     Review 07 H10: a typo'd (or download-deleted) <c>Probe.ProbeTagPath</c> used to record a Forward-Open
+///     FAILURE every probe tick, so the device's backoff window never closed and every cold / evicted data tag read
+///     <c>BadCommunicationError</c> forever — a permanent device blackout that a restart did not cure. The controller
+///     ANSWERED, so the probe now counts it as reachable: backoff success, host Running, one config Warning.
+/// </summary>
+[Trait("Category", "Unit")]
+public sealed class AbCipProbeRefusalTests
+{
+    private const string Device = "ab://10.0.0.5/1,0";
+
+    private static (AbCipDriver Driver, CapturingLogger Logger) Build(Exception probeFault)
+    {
+        var logger = new CapturingLogger();
+        var factory = new FakeAbCipTagFactory
+        {
+            Customise = p => p.TagName == "ProbeTagTypo"
+                ? new FakeAbCipTag(p) { ThrowOnInitialize = true, Exception = probeFault }
+                : new FakeAbCipTag(p) { Value = 7 },
+        };
+        var drv = new AbCipDriver(new AbCipDriverOptions
+        {
+            Devices = [new AbCipDeviceOptions(Device)],
+            RawTags = AbCipRawTags.From(new AbCipTagDefinition("Speed", Device, "Motor1.Speed", AbCipDataType.DInt)),
+            Probe = new AbCipProbeOptions
+            {
+                Enabled = true,
+                ProbeTagPath = "ProbeTagTypo",
+                Interval = TimeSpan.FromMilliseconds(10),
+                Timeout = TimeSpan.FromMilliseconds(100),
+            },
+        }, "abcip-probe-refusal", factory, logger: logger);
+        return (drv, logger);
+    }
+
+    private static async Task WaitUntilAsync(Func<bool> condition)
+    {
+        var deadline = DateTime.UtcNow.AddSeconds(5);
+        while (!condition())
+        {
+            if (DateTime.UtcNow > deadline) throw new TimeoutException("condition never met");
+            await Task.Delay(5);
+        }
+    }
+
+    /// <summary>A NotFound probe tag leaves the device reachable: data tags still connect, host is Running, warned once.</summary>
+    [Fact]
+    public async Task A_missing_probe_tag_does_not_black_out_the_device()
+    {
+        var (drv, logger) = Build(new AbTransportException(AbStatus.NotFound, "NotFound"));
+        await drv.InitializeAsync("{}", CancellationToken.None);
+        await WaitUntilAsync(() => drv.GetHostStatuses().Single().State == HostState.Running);
+        await Task.Delay(100); // many probe ticks
+
+        var r = await drv.ReadAsync(["Speed"], CancellationToken.None);
+
+        r[0].StatusCode.ShouldBe(AbCipStatusMapper.Good); // a cold create, NOT throttled
+        r[0].Value.ShouldBe(7);
+        drv.GetHostStatuses().Single().State.ShouldBe(HostState.Running);
+        logger.Entries.Count(e => e.Level == LogLevel.Warning && e.Message.Contains("ProbeTagTypo")).ShouldBe(1);
+        await drv.DisposeAsync();
+    }
+
+    /// <summary>Positive control: a probe that genuinely cannot connect still stops the host and throttles cold creates.</summary>
+    [Fact]
+    public async Task An_unreachable_device_still_stops_the_host_and_throttles()
+    {
+        var (drv, _) = Build(new AbTransportException(AbStatus.Timeout, "Timeout"));
+        await drv.InitializeAsync("{}", CancellationToken.None);
+        await WaitUntilAsync(() => drv.GetHostStatuses().Single().State == HostState.Stopped);
+
+        var r = await drv.ReadAsync(["Speed"], CancellationToken.None);
+
+        r[0].StatusCode.ShouldBe(AbCipStatusMapper.BadCommunicationError); // throttled by the open window
+        await drv.DisposeAsync();
+    }
+}