CB-573: keep health monitoring after failures

bridged/src/test/java/dev/ltms/bridged/health/FleetHealthMonitorTest.java

@@ -1,5 +1,8 @@
 package dev.ltms.bridged.health;
 
+import ch.qos.logback.classic.Logger;
+import ch.qos.logback.classic.spi.ILoggingEvent;
+import ch.qos.logback.core.read.ListAppender;
 import dev.ltms.bridged.herdr.AgentControl;
 import dev.ltms.bridged.herdr.FakeHerdr;
 import dev.ltms.bridged.inject.Injector;
@@ -12,6 +15,7 @@ import dev.ltms.bridged.herdr.WorkspaceControl;
 import dev.ltms.bridged.guard.SubscriptionGuard;
 import dev.ltms.bridged.config.BridgedConfig;
 import org.junit.jupiter.api.Test;
+import org.slf4j.LoggerFactory;
 
 import java.util.Map;
 import java.util.Set;
@@ -38,4 +42,40 @@ class FleetHealthMonitorTest {
         monitor.stop();
         assertEquals(1, herdr.calls.stream().filter(call -> call.method().equals("agent.list")).count());
     }
+
+    @Test void failedTickDoesNotStopTheNextTick() {
+        FakeHerdr herdr = new FakeHerdr().healthy(false);
+        AgentControl agents = new AgentControl(herdr);
+        var scheduler = Executors.newSingleThreadScheduledExecutor();
+        FleetHealthMonitor monitor = new FleetHealthMonitor(agents, java.util.List::of,
+                new MessageService(agents, new Injector(agents), new Rendezvous(), new InMemoryReplyInbox()),
+                scheduler, () -> 1, 60);
+        monitor.tick();
+        herdr.healthy(true);
+        monitor.tick();
+        monitor.stop();
+        assertEquals(2, herdr.calls.stream().filter(call -> call.method().equals("agent.list")).count());
+    }
+
+    @Test void faultTransitionLogsOnlyOnceUntilItChanges() {
+        Logger logger = (Logger) LoggerFactory.getLogger(FleetHealthMonitor.class);
+        ListAppender<ILoggingEvent> appender = new ListAppender<>();
+        appender.start();
+        logger.addAppender(appender);
+        try {
+            FakeHerdr herdr = new FakeHerdr();
+            AgentControl agents = new AgentControl(herdr);
+            var scheduler = Executors.newSingleThreadScheduledExecutor();
+            FleetHealthMonitor monitor = new FleetHealthMonitor(agents, java.util.List::of,
+                    new MessageService(agents, new Injector(agents), new Rendezvous(), new InMemoryReplyInbox()),
+                    scheduler, () -> 1, 60);
+            monitor.reportTransition("term_a", HealthState.TURN_BOUNDARY_LOST);
+            monitor.reportTransition("term_a", HealthState.TURN_BOUNDARY_LOST);
+            monitor.stop();
+            assertEquals(1, appender.list.stream().filter(event -> event.getFormattedMessage()
+                    .contains("member=term_a state=TURN_BOUNDARY_LOST")).count());
+        } finally {
+            logger.detachAppender(appender);
+        }
+    }
 }