fix(sitestream): deathwatch resets live-cache liveness on aggregator termination (plan R2-07 T10)

2026-07-13 11:01:54 -04:00
parent 76ef97f729
commit 5b16429635
4 changed files with 97 additions and 2 deletions
@@ -302,4 +302,40 @@ public class SiteAlarmLiveCacheServiceTests : TestKit
        AwaitCondition(() => service.IsLive(3), TimeSpan.FromSeconds(5));
        Assert.True(factory.GetOrCreateCount >= 1); // a client was created for the single endpoint
    }
+
+    // ── R2 T10: deathwatch un-sticks IsLive on aggregator death (N6) ──
+
+    [Fact]
+    public async Task Aggregator_Death_Resets_IsLive_And_Clears_The_Snapshot()
+    {
+        var service = CreateService(TimeSpan.FromMinutes(5), out _);
+        using var sub = service.Subscribe(SiteId, () => { });
+        AwaitAssert(() => Assert.True(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+
+        // Kill the aggregator out from under the service (crash-death, NOT a linger stop).
+        var aggregator = await Sys.ActorSelection($"/user/site-alarm-aggregator-{SiteId}-*")
+            .ResolveOne(TimeSpan.FromSeconds(5));
+        Sys.Stop(aggregator);
+
+        AwaitAssert(() =>
+        {
+            Assert.False(service.IsLive(SiteId));          // sticky no more (R2 N6)
+            Assert.Empty(service.GetCurrentAlarms(SiteId)); // frozen snapshot never grafted
+        }, TimeSpan.FromSeconds(10));
+    }
+
+    [Fact]
+    public void Linger_Stop_Does_Not_Resurrect_The_Aggregator()
+    {
+        // Last viewer leaves, linger fires, entry removed: the deathwatch on the
+        // deliberately-stopped actor must be a no-op (entry gone), not a restart.
+        var service = CreateService(TimeSpan.FromMilliseconds(50), out var factory);
+        var sub = service.Subscribe(SiteId, () => { });
+        AwaitAssert(() => Assert.True(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+        sub.Dispose();
+        AwaitAssert(() => Assert.False(service.IsLive(SiteId)), TimeSpan.FromSeconds(10));
+        var startsAfterStop = factory.GetOrCreateCount;
+        Thread.Sleep(300);
+        Assert.Equal(startsAfterStop, factory.GetOrCreateCount); // no self-heal restart fired
+    }
 }