ci(#606): Gitea-compatible trx upload + deterministic fixes for the CI-load test flakes

- v2-ci.yml: upload-artifact@v4 -> @v3 + continue-on-error (act_runner reports as GHES and
  v4 refuses GHES, failing every run); runner-capacity diagnostic step; AKKA_TEST_TIMEFACTOR=3
  on the test step.
- Runtime/ControlPlane harnesses: akka.test.timefactor from AKKA_TEST_TIMEFACTOR
  (TestTimeFactor), single-expect-default 15s; ControlPlane gains PresenceBudget.
- Leaked spinner threads: the infinite-loop timeout tests (Calculation, Host.IntegrationTests
  RoslynVirtualTagEvaluator, 3x Core.Scripting) pinned a core for the rest of the test process
  (abandoned, never stopped). Now a bounded 5 s wall-clock spin; outer compile-inclusive bound 30 s.
- Real test races fixed: ScriptedAlarmEngine push-during-drain (Inactive is also the start
  state + persist-before-update => wait for the Cleared save); DriverReconnectE2e (both nodes
  host the driver; Created[] is last-writer-wins and ForceReconnect is a no-op while
  Connecting); ControlPlaneStarterOrder (lost-race heal waited for a 60 s refresh tick).
- Fixed sleeps -> poll-for-condition: ReconnectSupervisor LastError, Modbus deadband steps
  (wait for observed reads), Modbus dispose hygiene precondition, FOCAS probe-loop log.
- Short presence budgets -> PresenceBudget in the Runtime/ControlPlane tests seen failing on
  Gitea; Calculation Settle 10 -> 30 s. No assertion removed, nothing skipped.
- infra/README.md §10 CI; stale TreatWarningsAsErrors comment in Directory.Build.props.

Claude-Session: https://claude.ai/code/session_01Ef2ozxS7QPanGT8uoATbTe
This commit is contained in:
Joseph Doherty
2026-10-08 19:44:31 -04:00
parent 8801631739
commit 55ae230fa4
36 changed files with 449 additions and 128 deletions
@@ -75,7 +75,7 @@ public sealed class DriverHostActorBootFromCacheTests : RuntimeActorTestBase
opcUaPublishActor: publishProbe.Ref,
deploymentArtifactCache: new StubArtifactCache(cached)));
var rebuild = publishProbe.ExpectMsg<OpcUaPublishActor.RebuildAddressSpace>(TimeSpan.FromSeconds(5));
var rebuild = publishProbe.ExpectMsg<OpcUaPublishActor.RebuildAddressSpace>(PresenceBudget);
rebuild.Artifact.ShouldNotBeNull();
rebuild.Artifact.ShouldBe(blob);
}
@@ -226,7 +226,7 @@ public sealed class DriverHostActorBootFromCacheTests : RuntimeActorTestBase
// The point: the restore path wrote the served artifact back into the cache.
AwaitAssert(
() => cache.Stores.ShouldBe(1),
duration: TimeSpan.FromSeconds(5));
duration: PresenceBudget);
cache.LastStoredDeploymentId.ShouldBe(deploymentId.ToString());
}
@@ -241,10 +241,10 @@ public sealed class DriverHostActorBootFromCacheTests : RuntimeActorTestBase
actor.Tell(new GetDiagnostics(CorrelationId.NewId()), probe.Ref);
probe.ExpectMsg<NodeDiagnosticsSnapshot>(TimeSpan.FromSeconds(2));
},
duration: TimeSpan.FromSeconds(5));
duration: PresenceBudget);
actor.Tell(new GetDiagnostics(CorrelationId.NewId()), probe.Ref);
return probe.ExpectMsg<NodeDiagnosticsSnapshot>(TimeSpan.FromSeconds(5));
return probe.ExpectMsg<NodeDiagnosticsSnapshot>(PresenceBudget);
}
/// <summary>A syntactically valid artifact with no driver instances.</summary>