CB-553: enforce maxLoad on explicit-profile spawns #27

Closed
agent wants to merge 1 commits from worker/cb-553-maxload-explicit-spawn-305ee3-6 into main
2 changed files with 90 additions and 1 deletions
@@ -9,6 +9,7 @@ import dev.ltms.bridged.peer.PeerUnreachableException;
import dev.ltms.bridged.peer.SpawnRequest;
import dev.ltms.bridged.placement.PlacementCandidate;
import dev.ltms.bridged.placement.PlacementContext;
import dev.ltms.bridged.placement.PlacementException;
import dev.ltms.bridged.placement.PlacementPolicies;
import dev.ltms.bridged.placement.PlacementPolicy;
import org.slf4j.Logger;
@@ -139,8 +140,12 @@ public final class CompositePeerLauncher implements PeerLauncher {
public PeerHandle spawn(SpawnRequest req) {
String requestedProfile = req.profileName();
if (requestedProfile != null && !requestedProfile.isBlank()) {
// An explicit profile bypasses the policy entirely.
// An explicit profile bypasses the placement policy, but not the capacity cap: maxLoad
// is documented as an unconditional limit on this profile (BridgedConfig.Worker), and
// the charter makes explicit-profile spawns the normal path — so skipping the check
// here would leave the cap dead config in real operation.
HerdrPeerLauncher d = route(requestedProfile);
enforceMaxLoad(requestedProfile);
PeerHandle handle = d.spawn(req);
spawnedBy.put(handle.id(), d);
return handle;
@@ -190,6 +195,42 @@ public final class CompositePeerLauncher implements PeerLauncher {
+ " candidate(s): " + String.join(", ", unreachable));
}
/**
* Refuse an explicit-profile spawn when the profile is at its {@code maxLoad} cap.
*
* <p>maxLoad is a documented, unconditional capacity limit (see {@code BridgedConfig.Worker#maxLoad}),
* and the charter makes explicit-profile spawns the normal path — so enforcing it only in placement
* ({@link dev.ltms.bridged.placement.PlacementPolicyUtil}) would leave the cap dead config on every
* call that names a profile. Same rule as placement: {@code live >= cap} is at capacity.
*
* <p>Deliberately no fallback to another profile: the caller named {@code profile} for a cost/model
* reason, and silently re-routing a paid-tier (subscription) request elsewhere is worse than
* refusing it. A caller that wants placement should omit the profile and let the policy pick.
*
* <p>Known TOCTOU limitation — documented, not fixed. {@link #liveCount} is read outside any lock and
* {@code SessionManager} registers a session only after {@code launcher.spawn} returns, so two
* genuinely concurrent spawns can both pass this check. The race already exists on the placement
* path. Closing it needs slot reservation in the registry; serializing spawn here would block on
* the readiness gate and is a far worse trade.
*
* @param profile the profile the caller explicitly named
* @throws PlacementException when the profile is at capacity
*/
private void enforceMaxLoad(String profile) {
// Absent config, or a config whose maxLoad normalized to null (non-positive ⇒ unlimited at
// load), means no cap — never cap what wasn't configured.
BridgedConfig.Worker cfg = profileConfigs.get(profile);
Integer cap = (cfg == null) ? null : cfg.maxLoad();
if (cap == null) {
return;
}
int live = liveCount.apply(profile);
if (live >= cap) {
throw new PlacementException("worker profile '" + profile + "' is at maxLoad: " + live
+ " live >= " + cap + " cap; refusing spawn — no fallback to another profile");
}
}
/** Build the candidate list from the configured profiles, in definition order. */
private List<PlacementCandidate> candidates() {
List<PlacementCandidate> out = new ArrayList<>();
@@ -378,6 +378,54 @@ class CompositePeerLauncherTest {
assertEquals(1, adapter.spawnCount("b"));
}
@Test
void explicitSpawnAtMaxLoadThrowsPlacementExceptionNamingProfileLiveAndCap() {
FakeHerdr herdr = new FakeHerdr();
Map<String, BridgedConfig.Worker> profiles = ordered(
"a", stubWorker("a", 1.0f, 2),
"b", stubWorker("b"));
StubLauncher adapter = new StubLauncher("claude", herdr, profiles, "a", Set.of());
CompositePeerLauncher composite = new CompositePeerLauncher(
List.of(adapter), "a", profiles, PlacementPolicies.fixed(), name -> "a".equals(name) ? 2 : 0);
PlacementException e = assertThrows(PlacementException.class,
() -> composite.spawn(new SpawnRequest("a", null, null)));
assertTrue(e.getMessage().contains("'a'"), "message names the profile: " + e.getMessage());
assertTrue(e.getMessage().contains("2 live"), "message names the live count: " + e.getMessage());
assertTrue(e.getMessage().contains("2 cap"), "message names the cap: " + e.getMessage());
assertEquals(0, adapter.spawnCount("a"), "at cap, the spawn is refused before any delegation");
}
@Test
void explicitSpawnUnderMaxLoadStillSucceeds() {
FakeHerdr herdr = new FakeHerdr();
Map<String, BridgedConfig.Worker> profiles = ordered(
"a", stubWorker("a", 1.0f, 2),
"b", stubWorker("b"));
StubLauncher adapter = new StubLauncher("claude", herdr, profiles, "a", Set.of());
CompositePeerLauncher composite = new CompositePeerLauncher(
List.of(adapter), "a", profiles, PlacementPolicies.fixed(), name -> "a".equals(name) ? 1 : 0);
PeerHandle h = composite.spawn(new SpawnRequest("a", null, null));
assertEquals("a", h.profile(), "a profile under its cap accepts an explicit spawn");
assertEquals(1, adapter.spawnCount("a"), "the under-cap spawn is delegated");
}
@Test
void explicitSpawnWithNullMaxLoadIsNeverCapped() {
FakeHerdr herdr = new FakeHerdr();
Map<String, BridgedConfig.Worker> profiles = ordered(
"a", stubWorker("a", 1.0f, null),
"b", stubWorker("b"));
StubLauncher adapter = new StubLauncher("claude", herdr, profiles, "a", Set.of());
// A deliberately absurd live count: an unset maxLoad means unlimited, so it must never refuse.
CompositePeerLauncher composite = new CompositePeerLauncher(
List.of(adapter), "a", profiles, PlacementPolicies.fixed(), name -> 1000);
PeerHandle h = composite.spawn(new SpawnRequest("a", null, null));
assertEquals("a", h.profile(), "a profile with no maxLoad is never capped, however many live workers");
}
@Test
void emptyCandidateSetThrowsClearException() {
FakeHerdr herdr = new FakeHerdr();