feat(core): PollGroupEngine v2 — failure backoff + caller-token-filtered OCE exit (CONV-1/STAB-8; STAB-14-class engine guard)

src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/PollGroupEngine.cs

@@ -35,6 +35,7 @@ public sealed class PollGroupEngine : IAsyncDisposable
     private readonly Action<ISubscriptionHandle, string, DataValueSnapshot> _onChange;
     private readonly Action<Exception>? _onError;
     private readonly TimeSpan _minInterval;
+    private readonly TimeSpan? _backoffCap;
     private readonly ConcurrentDictionary<long, SubscriptionState> _subscriptions = new();
     private long _nextId;
 
@@ -52,11 +53,17 @@ public sealed class PollGroupEngine : IAsyncDisposable
     ///     internal contract-violation throw) so the owning driver can route the failure to its
     ///     health surface. Defensive: an <c>onError</c> handler that
     ///     itself throws is silently absorbed so a buggy forwarder cannot crash the poll loop.</param>
+    /// <param name="backoffCap">Optional cap enabling capped-exponential failure backoff
+    ///     (05/STAB-8). When supplied, sustained reader failures stretch the retry cadence
+    ///     (interval, 2×, 4×, … saturating at this cap) instead of hammering a dead device every
+    ///     tick; a successful poll resets to the base interval. <c>null</c> (default) keeps the
+    ///     byte-identical fixed-interval cadence for consumers that have not opted in.</param>
     public PollGroupEngine(
         Func<IReadOnlyList<string>, CancellationToken, Task<IReadOnlyList<DataValueSnapshot>>> reader,
         Action<ISubscriptionHandle, string, DataValueSnapshot> onChange,
         TimeSpan? minInterval = null,
-        Action<Exception>? onError = null)
+        Action<Exception>? onError = null,
+        TimeSpan? backoffCap = null)
     {
         ArgumentNullException.ThrowIfNull(reader);
         ArgumentNullException.ThrowIfNull(onChange);
@@ -64,6 +71,7 @@ public sealed class PollGroupEngine : IAsyncDisposable
         _onChange = onChange;
         _onError = onError;
         _minInterval = minInterval ?? DefaultMinInterval;
+        _backoffCap = backoffCap;
     }
 
     /// <summary>Register a new polled subscription and start its background loop.</summary>
@@ -116,31 +124,54 @@ public sealed class PollGroupEngine : IAsyncDisposable
 
     private async Task PollLoopAsync(SubscriptionState state, CancellationToken ct)
     {
+        var consecutiveFailures = 0;
+
         // Initial-data push: every subscribed tag fires once at subscribe time regardless of
         // whether it has changed, satisfying OPC UA Part 4 initial-value semantics.
-        try { await PollOnceAsync(state, forceRaise: true, ct).ConfigureAwait(false); }
-        catch (OperationCanceledException) { return; }
+        try
+        {
+            await PollOnceAsync(state, forceRaise: true, ct).ConfigureAwait(false);
+            consecutiveFailures = 0;
+        }
+        // Only a teardown OCE (the loop's OWN token) exits the loop. A reader that throws OCE with
+        // the loop token un-cancelled — a driver-internal timeout CTS (the STAB-14/STAB-15 class) —
+        // must NOT tear the loop down: it falls through to the generic handler, is reported, and the
+        // loop retries with backoff. This is the guard that makes the S7 fork migration safe.
+        catch (OperationCanceledException) when (ct.IsCancellationRequested) { return; }
         catch (Exception ex) when (!IsFatal(ex))
         {
             // first-read error tolerated — loop continues; forward to driver health surface.
+            consecutiveFailures++;
             ReportError(ex);
         }
 
         while (!ct.IsCancellationRequested)
         {
-            try { await Task.Delay(state.Interval, ct).ConfigureAwait(false); }
+            // Fixed cadence by default; when a backoff cap is configured, sustained failures
+            // stretch the delay (capped exponential) and a success snaps it back to Interval.
+            var delay = _backoffCap is null
+                ? state.Interval
+                : ConnectionBackoff.ComputeDelay(state.Interval, consecutiveFailures, _backoffCap.Value);
+            try { await Task.Delay(delay, ct).ConfigureAwait(false); }
             catch (OperationCanceledException) { return; }
             // Defensive: the CTS may be disposed by Unsubscribe/DisposeAsync between the
             // cancellation check above and the Task.Delay touching the token. Treat that race
             // as a normal cancellation rather than a fatal exception.
             catch (ObjectDisposedException) { return; }
 
-            try { await PollOnceAsync(state, forceRaise: false, ct).ConfigureAwait(false); }
-            catch (OperationCanceledException) { return; }
+            try
+            {
+                await PollOnceAsync(state, forceRaise: false, ct).ConfigureAwait(false);
+                consecutiveFailures = 0;
+            }
+            // Only teardown (the loop token) exits; a reader OCE with ct un-cancelled backs off
+            // like any other failure instead of killing the loop (STAB-14 engine guard).
+            catch (OperationCanceledException) when (ct.IsCancellationRequested) { return; }
             catch (Exception ex) when (!IsFatal(ex))
             {
-                // transient poll error — loop continues, driver health surface logs it
-                // via the supplied onError callback.
+                // transient poll error — loop continues (with backoff when configured); driver
+                // health surface logs it via the supplied onError callback.
+                consecutiveFailures++;
                 ReportError(ex);
             }
         }