fix(r2-01): RED connect-timeout regression tests T1+T3 (task 1)

archreview/plans/R2-01-s7-fault-hardening-plan.md.tasks.json

@@ -10,7 +10,7 @@
     {
       "id": 1,
       "subject": "RED: connect-timeout regression tests T1+T3 (read/write degrade instead of throwing OCE) — must FAIL at f6eaa267",
-      "status": "pending",
+      "status": "completed",
       "blockedBy": [0]
     },
     {

tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.S7.Tests/S7DriverReconnectTests.cs

@@ -133,6 +133,56 @@ public sealed class S7DriverReconnectTests
         drv.GetHealth().State.ShouldBe(DriverState.Healthy);
     }
 
+    // ---- STAB-14: connect-timeout must degrade, not escape as OCE ----
+
+    /// <summary>
+    ///     T1 (STAB-14 regression). When the reopen HANGS and is cut by the internal
+    ///     <c>CancelAfter(_options.Timeout)</c> (the unreachable-host outage — SYNs dropped, not
+    ///     refused), the read batch must degrade to a communication error with Degraded health,
+    ///     NOT throw the timeout-born <see cref="TaskCanceledException"/> up to the caller.
+    ///     Before the fix the OCE escaped <see cref="S7Driver.ReadAsync"/>.
+    /// </summary>
+    [Fact]
+    public async Task Read_degrades_batch_on_connect_timeout_instead_of_throwing()
+    {
+        var factory = new FakeS7PlcFactory();
+        using var drv = new S7Driver(Options(), "s7-read-timeout", factory);
+        await drv.InitializeAsync("{}", TestContext.Current.CancellationToken);
+
+        // Drop connection #1 so the next read reopens; every subsequent open hangs until the
+        // internal connect-timeout CTS fires.
+        factory.Created[0].NextReadThrows = new PlcException(ErrorCode.ConnectionError, "dropped");
+        await drv.ReadAsync(["W0"], TestContext.Current.CancellationToken); // marks dead
+        factory.OpenHangsUntilCancelledCount = int.MaxValue;
+
+        // Must NOT throw — the connect timeout degrades the batch.
+        var timedOut = await drv.ReadAsync(["W0"], TestContext.Current.CancellationToken);
+        timedOut[0].StatusCode.ShouldNotBe(0u);
+        drv.GetHealth().State.ShouldBe(DriverState.Degraded);
+    }
+
+    /// <summary>
+    ///     T3 (STAB-14 regression). The same connect-timeout degrade through
+    ///     <see cref="S7Driver.WriteAsync"/> — <c>EnsureConnectedAsync</c> is called before the
+    ///     per-item loop, so a hanging reopen must degrade the whole write batch, not throw OCE.
+    /// </summary>
+    [Fact]
+    public async Task Write_degrades_batch_on_connect_timeout_instead_of_throwing()
+    {
+        var factory = new FakeS7PlcFactory();
+        using var drv = new S7Driver(Options(), "s7-write-timeout", factory);
+        await drv.InitializeAsync("{}", TestContext.Current.CancellationToken);
+
+        factory.Created[0].NextReadThrows = new PlcException(ErrorCode.ConnectionError, "dropped");
+        await drv.ReadAsync(["W0"], TestContext.Current.CancellationToken); // marks dead
+        factory.OpenHangsUntilCancelledCount = int.MaxValue;
+
+        var timedOut = await drv.WriteAsync(
+            [new WriteRequest("W0", (ushort)1)], TestContext.Current.CancellationToken);
+        timedOut[0].StatusCode.ShouldNotBe(0u);
+        drv.GetHealth().State.ShouldBe(DriverState.Degraded);
+    }
+
     // ---- fakes ----
 
     private sealed class FakeS7PlcFactory : IS7PlcFactory