fix(worker): honor RunCancellationRegistry.Register's return value at both dispatch sites
Register(taskId, cts) already refuses (and logs) a double-registration, but both call sites discarded the bool and dispatched anyway under an unregistered CTS. If the loser then unregistered the winner's CTS during its own cleanup, TryCancel could silently no-op against a live process. - OverrideSlotService.StartInSlot now fails RunNow/ContinueTask loudly (throws) when it loses the registration race instead of registering over — or silently proceeding despite losing to — the queue picker. - QueueService's picker loop retries registration briefly (the loser's own claim-attempt-then-unregister resolves fast) before dispatching; if registration never resolves it marks the already-claimed row Failed instead of running it unregistered. - RunCancellationRegistry.Unregister already had compare-and-remove semantics (TryRemove(KeyValuePair)), so a loser's cleanup could not have removed the winner's CTS once registration correctly failed. Added regression tests exercising the real registry through both dispatch paths: RunNow losing the registration race throws without disturbing the winner, the picker's retry succeeds and TryCancel reaches the live run when the loser unregisters in time, and the picker fails the task instead of running unregistered when it never does.
This commit is contained in:
@@ -31,7 +31,7 @@ public sealed class OverrideSlotServiceTests : IDisposable
|
||||
|
||||
public void Dispose() { _db.Dispose(); try { Directory.Delete(_tempDir, true); } catch { } }
|
||||
|
||||
private OverrideSlotService BuildService()
|
||||
private OverrideSlotService BuildService(RunCancellationRegistry? runCancels = null)
|
||||
{
|
||||
var dbFactory = _db.CreateFactory();
|
||||
var state = TaskStateServiceBuilder.Build(dbFactory).State;
|
||||
@@ -39,7 +39,7 @@ public sealed class OverrideSlotServiceTests : IDisposable
|
||||
var runner = new TaskRunner(new FakeClaudeProcess(), dbFactory, new HubBroadcaster(new CapturingHubContext()), wt,
|
||||
new ClaudeArgsBuilder(), _cfg, NullLogger<TaskRunner>.Instance, state, new TaskRunTokenRegistry(),
|
||||
new AttachmentStore(), new FakeSessionSkillSeeder(), new FakeTranscriptUsageReader());
|
||||
var runCancels = new RunCancellationRegistry(NullLogger<RunCancellationRegistry>.Instance);
|
||||
runCancels ??= new RunCancellationRegistry(NullLogger<RunCancellationRegistry>.Instance);
|
||||
return new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels);
|
||||
}
|
||||
|
||||
@@ -86,4 +86,41 @@ public sealed class OverrideSlotServiceTests : IDisposable
|
||||
// background, so this only asserts the precheck doesn't reject a claimable task.
|
||||
await service.RunNow(taskId);
|
||||
}
|
||||
|
||||
// Regression for the RunCancellationRegistry.Register-return double-dispatch bug: the
|
||||
// queue picker's atomic Queued->Running claim can land between RunNow's DB precheck and
|
||||
// its registry registration. If the queue side already holds the registration, RunNow
|
||||
// must fail loudly instead of silently registering over it (or being ignored and then
|
||||
// unregistering the winner's CTS during its own cleanup).
|
||||
[Fact]
|
||||
public async Task RunNow_LosesRegistrationRaceToQueue_ThrowsAndLeavesWinnersCtsUntouched()
|
||||
{
|
||||
string listId = Guid.NewGuid().ToString(), taskId = Guid.NewGuid().ToString();
|
||||
using (var ctx = _db.CreateContext())
|
||||
{
|
||||
ctx.Lists.Add(new ListEntity { Id = listId, Name = "L", CreatedAt = DateTime.UtcNow });
|
||||
ctx.Tasks.Add(new TaskEntity
|
||||
{
|
||||
Id = taskId, ListId = listId, Title = "T", Status = TaskStatus.Queued,
|
||||
CreatedAt = DateTime.UtcNow,
|
||||
});
|
||||
await ctx.SaveChangesAsync();
|
||||
}
|
||||
|
||||
var runCancels = new RunCancellationRegistry(NullLogger<RunCancellationRegistry>.Instance);
|
||||
var service = BuildService(runCancels);
|
||||
|
||||
// Simulate the queue picker having already won the registration race for this task id.
|
||||
using var winnerCts = new CancellationTokenSource();
|
||||
Assert.True(runCancels.Register(taskId, winnerCts));
|
||||
|
||||
var ex = await Assert.ThrowsAsync<InvalidOperationException>(() => service.RunNow(taskId));
|
||||
Assert.Contains("lost the double-dispatch race", ex.Message);
|
||||
Assert.Null(service.CurrentSlot);
|
||||
|
||||
// The loser must not have cancelled or displaced the winner's registration.
|
||||
Assert.False(winnerCts.IsCancellationRequested);
|
||||
Assert.True(runCancels.TryCancel(taskId));
|
||||
Assert.True(winnerCts.IsCancellationRequested);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user