feat(site-runtime): tag-subscribe failure reply frees the in-flight slot, backs off (×2 ±20%, capped) and Success resets to floor (Lever 1)

Also from the Task 3 review: FailedSubscribeResponse_IsRetried guards the failure path again (large ceiling); HandleSubscribeTagsResponse reads state instead of get-or-create; SubscribeToDcl prunes stale retry state on re-entry; doc comments refreshed.

Claude-Session: https://claude.ai/code/session_019ZxXT5sxZs5XrtdwYzJDPV
This commit is contained in:
Joseph Doherty
2026-08-28 14:36:22 -04:00
parent 029d39fca2
commit b6b401c879
2 changed files with 95 additions and 10 deletions
@@ -1290,7 +1290,7 @@ public class InstanceActorTests : TestKit, IDisposable
[Fact]
public void FailedSubscribeResponse_IsRetried()
{
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200, TagSubscribeInFlightCeilingMs = 200 };
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200, TagSubscribeInFlightCeilingMs = 60_000 };
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
var first = dclProbe.ExpectMsg<SubscribeTagsRequest>();
@@ -1370,7 +1370,8 @@ public class InstanceActorTests : TestKit, IDisposable
var first = dclProbe.ExpectMsg<SubscribeTagsRequest>();
var second = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(3));
// A late Success for the FIRST id must not cancel the watchdog guarding the SECOND.
// A late Success for the FIRST id is dropped at the pending-map check (its id was
// removed at the ceiling); the watchdog guarding the SECOND is untouched.
instance.Tell(new SubscribeTagsResponse(first.CorrelationId, first.InstanceUniqueName,
true, null, DateTimeOffset.UtcNow), dclProbe.Ref);
var third = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(3)); // second eventually re-sent
@@ -1381,4 +1382,60 @@ public class InstanceActorTests : TestKit, IDisposable
true, null, DateTimeOffset.UtcNow), dclProbe.Ref);
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(800));
}
// --- Lever 1 (2026-08-28): backoff on failure, reset on success ---
[Fact]
public void RepeatedFailures_BackOff_AndSuccessResetsToFloor()
{
// Floor 200 ms, max 800 ms. Jitter is ±20 % so bound the assertions, don't pin them.
var options = new SiteRuntimeOptions
{
TagSubscribeRetryIntervalMs = 200,
TagSubscribeRetryMaxIntervalMs = 800,
TagSubscribeInFlightCeilingMs = 60_000, // guard never expires; only replies drive retries
};
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
var req = dclProbe.ExpectMsg<SubscribeTagsRequest>();
var gaps = new List<TimeSpan>();
for (var i = 0; i < 3; i++)
{
instance.Tell(new SubscribeTagsResponse(req.CorrelationId, req.InstanceUniqueName,
false, "gateway busy", DateTimeOffset.UtcNow), dclProbe.Ref);
var sw = System.Diagnostics.Stopwatch.StartNew();
req = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(5));
gaps.Add(sw.Elapsed);
}
// Expected nominal gaps: 400, 800(cap), 800(cap) — each ±20 % jitter and scheduler slack.
Assert.InRange(gaps[0].TotalMilliseconds, 300, 560);
Assert.InRange(gaps[1].TotalMilliseconds, 600, 1100);
Assert.InRange(gaps[2].TotalMilliseconds, 600, 1100);
// Success resets: no further request follows a confirmed subscription.
instance.Tell(new SubscribeTagsResponse(req.CorrelationId, req.InstanceUniqueName,
true, null, DateTimeOffset.UtcNow), dclProbe.Ref);
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(1200));
}
[Fact]
public void FailureReply_ReissuesEvenThoughGuardHasNotExpired()
{
var options = new SiteRuntimeOptions
{
TagSubscribeRetryIntervalMs = 200,
TagSubscribeRetryMaxIntervalMs = 200,
TagSubscribeInFlightCeilingMs = 60_000,
};
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
var first = dclProbe.ExpectMsg<SubscribeTagsRequest>();
instance.Tell(new SubscribeTagsResponse(first.CorrelationId, first.InstanceUniqueName,
false, "Unknown connection: conn-1", DateTimeOffset.UtcNow), dclProbe.Ref);
// A definite failure clears the in-flight slot, so the watchdog re-sends.
var retry = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(3));
Assert.NotEqual(first.CorrelationId, retry.CorrelationId);
}
}