feat(site-runtime): tag-subscribe in-flight guard — one outstanding request per connection until TagSubscribeInFlightCeilingMs (Lever 1)

FailedSubscribeResponse_IsRetried and LostSubscribeResponse_IsRetried_AndSuccessStopsRetrying now pin the in-flight ceiling to the retry interval: a lost reply is re-sent only once the outstanding request is presumed lost, by design.

Claude-Session: https://claude.ai/code/session_019ZxXT5sxZs5XrtdwYzJDPV
This commit is contained in:
Joseph Doherty
2026-08-28 14:24:35 -04:00
parent 2f471dd7a1
commit 029d39fca2
2 changed files with 169 additions and 25 deletions
@@ -1290,7 +1290,7 @@ public class InstanceActorTests : TestKit, IDisposable
[Fact]
public void FailedSubscribeResponse_IsRetried()
{
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200 };
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200, TagSubscribeInFlightCeilingMs = 200 };
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
var first = dclProbe.ExpectMsg<SubscribeTagsRequest>();
@@ -1305,7 +1305,8 @@ public class InstanceActorTests : TestKit, IDisposable
[Fact]
public void LostSubscribeResponse_IsRetried_AndSuccessStopsRetrying()
{
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200 };
// Lever 1: a lost reply is re-sent only once the outstanding request is presumed lost (ceiling), by design.
var options = new SiteRuntimeOptions { TagSubscribeRetryIntervalMs = 200, TagSubscribeInFlightCeilingMs = 200 };
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
dclProbe.ExpectMsg<SubscribeTagsRequest>();
@@ -1316,4 +1317,68 @@ public class InstanceActorTests : TestKit, IDisposable
true, null, DateTimeOffset.UtcNow), dclProbe.Ref);
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(600)); // retry timer cancelled
}
// --- Lever 1 (2026-08-28): in-flight guard ---
[Fact]
public void SlowSubscribe_DoesNotStackDuplicates_WhileInFlight()
{
// Retry ticks every 200 ms, but an unanswered request blocks a duplicate for 2 s.
var options = new SiteRuntimeOptions
{
TagSubscribeRetryIntervalMs = 200,
TagSubscribeRetryMaxIntervalMs = 200,
TagSubscribeInFlightCeilingMs = 2000,
};
var (_, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
dclProbe.ExpectMsg<SubscribeTagsRequest>();
// Pre-Lever-1 this window would carry ~4 more requests (one per 200 ms tick).
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(1000));
}
[Fact]
public void SlowSubscribe_ReissuesAfterInFlightCeiling_AndOnlyOnce()
{
var options = new SiteRuntimeOptions
{
TagSubscribeRetryIntervalMs = 200,
TagSubscribeRetryMaxIntervalMs = 200,
TagSubscribeInFlightCeilingMs = 600,
};
var (_, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
var first = dclProbe.ExpectMsg<SubscribeTagsRequest>();
var second = dclProbe.ExpectMsg<SubscribeTagsRequest>(TimeSpan.FromSeconds(3)); // after ceiling
Assert.NotEqual(first.CorrelationId, second.CorrelationId);
Assert.Equal(first.TagPaths, second.TagPaths);
// The new request is itself guarded — no third one inside its ceiling window.
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(400));
}
[Fact]
public void ReplyToSupersededRequest_IsIgnored_AndLatestStillGoverns()
{
var options = new SiteRuntimeOptions
{
TagSubscribeRetryIntervalMs = 200,
TagSubscribeRetryMaxIntervalMs = 200,
TagSubscribeInFlightCeilingMs = 300,
};
var (instance, dclProbe) = CreateInstanceWithDataSourcedAttribute(options);
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.
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
Assert.NotEqual(second.CorrelationId, third.CorrelationId);
// Success for the live id stops everything.
instance.Tell(new SubscribeTagsResponse(third.CorrelationId, third.InstanceUniqueName,
true, null, DateTimeOffset.UtcNow), dclProbe.Ref);
dclProbe.ExpectNoMsg(TimeSpan.FromMilliseconds(800));
}
}