Merge CB-562: the readiness gate says why it gave up (PR #33)
CI / build (push) Successful in 1m1s
CI / contract (push) Successful in 1m14s

When the injector's readiness grace expired it cleared the queue and logged
nothing. The failure then surfaced elsewhere as a turn-stall, which names the
wrong cause. Diagnosing CB-560 cost two live spawns and a wrong first
hypothesis for exactly this reason: the logs said "session marked failed" and
"failed send via turn-stall fallback", and neither says the message was never
typed into the pane at all.

The expiry now logs the target, the number of messages being failed, the grace
in polls and seconds, and the real cause in plain words.

The grace in seconds is derived, not written down twice: Bridged's own
INJECT_POLL_MILLIS is deleted and Injector.POLL_INTERVAL_MILLIS is the single
source, passed to every StatusPoller. A cadence change can no longer leave a
log line confidently stating the wrong duration.

Behaviour is unchanged. This is the first structured health event in the
daemon, and the foundation the fleet-health work will build on.
This commit is contained in:
Dai Ha
2026-08-15 04:21:29 +02:00
3 changed files with 54 additions and 4 deletions
@@ -70,9 +70,6 @@ public final class Bridged {
private static final Logger log = LoggerFactory.getLogger(Bridged.class);
/** How often the injector samples a busy worker's status while it has queued work. */
private static final long INJECT_POLL_MILLIS = 250;
/** CB-504: how long to wait at startup for herdr's socket before serving degraded. */
private static final long HERDR_WAIT_SECONDS = 30;
private static final long HERDR_WAIT_POLL_MILLIS = 500;
@@ -290,7 +287,7 @@ public final class Bridged {
};
Injector injector = new Injector(agents, turnListener, deliverableTo(presence, leads),
presence::forget);
StatusPoller poller = new StatusPoller(agents, injector, INJECT_POLL_MILLIS);
StatusPoller poller = new StatusPoller(agents, injector, Injector.POLL_INTERVAL_MILLIS);
poller.start();
// CB-307: reply inbox. A broker: block (with a uri) selects the AMQP-backed durable adapter;
@@ -78,6 +78,15 @@ public final class Injector {
*/
private static final int READINESS_GRACE_POLLS = 240;
/**
* The single source for the injector poll cadence — how often the {@link StatusPoller} drives
* {@link #onStatus} at. {@code Bridged} passes this to every {@link StatusPoller} it constructs,
* and this class reads it to state the readiness grace in seconds on the CB-562 expiry log
* instead of hardcoding "60s". One constant, so a cadence change cannot silently desync a log
* that claims a grace duration.
*/
public static final long POLL_INTERVAL_MILLIS = 250;
private final AgentControl agents;
private final TurnListener turnListener;
private final Predicate<String> ready; // CB-113: a target is deliverable only when available
@@ -264,6 +273,11 @@ public final class Injector {
// fail every queued message and release the target (CB-114) instead of
// polling it indefinitely with the caller's future never completing.
notReady = new ArrayList<>(t.queue);
log.warn("readiness grace for {} expired after {} polls ({}s): target never "
+ "became deliverable, so failing {} queued message(s) that never "
+ "reached its pane",
target, READINESS_GRACE_POLLS,
READINESS_GRACE_POLLS * POLL_INTERVAL_MILLIS / 1000, notReady.size());
t.queue.clear();
t.notReadySincePoll = 0;
}
@@ -1,10 +1,15 @@
package dev.ltms.bridged.inject;
import ch.qos.logback.classic.Level;
import ch.qos.logback.classic.LoggerContext;
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.AgentStatus;
import dev.ltms.bridged.herdr.FakeHerdr;
import dev.ltms.bridged.herdr.HerdrException;
import org.junit.jupiter.api.Test;
import org.slf4j.LoggerFactory;
import java.util.ArrayList;
import java.util.List;
@@ -369,6 +374,40 @@ class InjectorTest {
assertTrue(inj.activeTargets().isEmpty(), "the target is reclaimed, not polled forever");
}
@Test
void readinessGraceExpiryIsLogged() {
// CB-562: the grace-expiry path used to clear the queue silently, so a message that never
// reached the worker's pane surfaced elsewhere as an unrelated turn-stall failure. Assert the
// expiry now names the real cause. (ListAppender capture pattern mirrors AuditLogTest.)
LoggerContext ctx = (LoggerContext) LoggerFactory.getILoggerFactory();
ch.qos.logback.classic.Logger injectorLog =
(ch.qos.logback.classic.Logger) LoggerFactory.getLogger(Injector.class);
ListAppender<ILoggingEvent> appender = new ListAppender<>();
appender.setContext(ctx);
appender.start();
injectorLog.addAppender(appender);
injectorLog.setLevel(Level.WARN);
try {
Injector inj = new Injector(new AgentControl(herdr), TurnListener.NOOP, _ -> false, _ -> {
});
inj.enqueue(T, "task");
for (int i = 0; i < READINESS_SAMPLES; i++) inj.onStatus(T, AgentStatus.IDLE);
String warn = appender.list.stream()
.filter(e -> e.getLevel().equals(Level.WARN))
.map(ILoggingEvent::getFormattedMessage)
.findFirst()
.orElse("no grace-expiry WARN logged");
assertTrue(warn.contains(T), "the log names the target terminal: " + warn);
assertTrue(warn.contains("never reached"), "the log names the real cause: " + warn);
assertTrue(warn.contains("1 queued message"),
"the log carries the failed message count: " + warn);
} finally {
injectorLog.detachAppender(appender);
}
}
@Test
void aWorkerThatBecomesReadyWithinTheGraceIsDeliveredNormally() {
// The readiness grace must not fail a worker that is merely slow to boot: once it becomes