fix(GWC-33): unregister terminal worker queue gauge

2026-08-25 10:56:23 -04:00
parent f2090fe1b5
commit b0156c685e
2 changed files with 49 additions and 3 deletions
@@ -1147,6 +1147,41 @@ public sealed class WorkerClientTests
        Assert.Equal(0, metrics.GetSnapshot().WorkerEventQueueDepth);
    }

+    /// <summary>
+    ///     GWC-33: a faulted client can remain retained for diagnostics, but its abandoned event
+    ///     backlog must stop contributing to the gateway-wide queue-depth gauge as soon as the
+    ///     client enters a terminal state rather than waiting for disposal.
+    /// </summary>
+    /// <returns>A task that represents the asynchronous operation.</returns>
+    [Fact]
+    public async Task WorkerEventQueueDepthGauge_WhenClientFaults_StopsCountingRetainedClient()
+    {
+        using GatewayMetrics metrics = new();
+        await using PipePair pipePair = await PipePair.CreateAsync();
+        await using WorkerClient client = CreateClient(
+            pipePair,
+            new WorkerClientOptions
+            {
+                EventChannelCapacity = 4,
+                EventChannelFullModeTimeout = TimeSpan.FromMinutes(5),
+                HeartbeatGrace = TimeSpan.FromSeconds(30),
+                HeartbeatCheckInterval = TimeSpan.FromSeconds(30),
+            },
+            metrics: metrics);
+        await CompleteHandshakeAsync(client, pipePair);
+
+        await pipePair.WriteAsync(CreateEventEnvelope(sequence: 1, MxEventFamily.OnDataChange));
+        await WaitUntilAsync(
+            () => metrics.GetSnapshot().WorkerEventQueueDepth == 1,
+            TestTimeout);
+
+        await pipePair.WriteAsync(CreateWorkerFaultEnvelope("scripted retained-client fault"));
+        await WaitUntilAsync(() => client.State == WorkerClientState.Faulted, TestTimeout);
+
+        Assert.Equal(WorkerClientState.Faulted, client.State);
+        Assert.Equal(0, metrics.GetSnapshot().WorkerEventQueueDepth);
+    }
+
    private static WorkerClient CreateClient(
        PipePair pipePair,
        WorkerClientOptions? options = null,