fix(site-runtime): ConnectionQualityChanged(Good) only resets the tag-subscribe backoff while it is stretched — a flapping connection can no longer defer the retry it was meant to hasten

Review finding on ab08ecd3: each Good re-armed the watchdog from 'now', so Goods arriving faster than the floor starved the retry. Pinned by FlappingGood_DoesNotDeferTheRetry (12 Goods over 1.2 s; naive re-arm measured 1.43 s, guarded ~0.3 s). Claude-Session: https://claude.ai/code/session_019ZxXT5sxZs5XrtdwYzJDPV
2026-08-28 14:57:30 -04:00
parent 150c3f60d8
commit 0589486f4e
2 changed files with 42 additions and 1 deletions
@@ -1442,6 +1442,43 @@ public class InstanceActorTests : TestKit, IDisposable

    // --- Lever 1 (2026-08-28): Good quality resets the backoff ---

+    [Fact]
+    public void FlappingGood_DoesNotDeferTheRetry()
+    {
+        // A burst of Good events faster than the floor must not keep re-arming the watchdog
+        // from "now" — after the first reset the interval is at the floor and later Goods are
+        // no-ops, so the retry still lands within one floor interval of the first Good.
+        var options = new SiteRuntimeOptions
+        {
+            TagSubscribeRetryIntervalMs = 300,
+            TagSubscribeRetryMaxIntervalMs = 5000,
+            TagSubscribeInFlightCeilingMs = 60_000,
+        };
+        var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
+
+        var req = dclProbe.ExpectMsg<SubscribeTagsRequest>();
+        for (var i = 0; i < 3; i++)
+        {
+            instance.Tell(new SubscribeTagsResponse(req.CorrelationId, req.InstanceUniqueName,
+                false, "busy", DateTimeOffset.UtcNow), dclProbe.Ref);
+            req = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(5));
+        }
+        instance.Tell(new SubscribeTagsResponse(req.CorrelationId, req.InstanceUniqueName,
+            false, "busy", DateTimeOffset.UtcNow), dclProbe.Ref);
+
+        var sw = System.Diagnostics.Stopwatch.StartNew();
+        // Twelve Goods over ~1.2 s — a naive re-arm-from-now on each would push the tick to ≥1.5 s.
+        for (var i = 0; i < 12; i++)
+        {
+            instance.Tell(new ConnectionQualityChanged("conn-1", QualityCode.Good, DateTimeOffset.UtcNow));
+            Thread.Sleep(100);
+        }
+
+        // The probe already holds the retry (it landed ~300 ms after the first Good) by the time the burst ends.
+        dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(2));
+        Assert.True(sw.Elapsed < TimeSpan.FromMilliseconds(1400), $"retry took {sw.Elapsed} — flapping Good deferred it");
+    }
+
    [Fact]
    public void ConnectionBackToGood_ResetsBackoff_AndRetriesPromptly()
    {