Files
ClaudeDo/tests/ClaudeDo.Worker.Tests/Services/QueueServiceSlotGuardTests.cs
T
mika kuns 07dd75700d feat(worker): Toggle "Continue on session limit reset" für Usage-Limit-Abbrüche
Klassifiziert einen echten Usage-Limit-Abbruch als eigene FailureReason
"usage_limit" (TaskRunner.ClassifyFailureReason: nur bei terminal_reason
"api_error" plus einem Limit-Muster im gerenderten Fehlertext, nicht an
Status==Failed allein). Neuer Toggle AutoContinueOnUsageLimit (app_settings,
Default aus) unter Settings → General → "Usage limit stop":

- UsageLimitAutoContinueCoordinator feuert pro Task genau einmal ContinueTask
  über OverrideSlotService, sobald das 5h-Fenster (UsageState.Snapshot.FiveHour
  .ResetsAt) tatsächlich zurückgesetzt ist; ein persistenter Marker
  (TaskEntity.UsageLimitAutoContinuedAt) verhindert einen zweiten Anlauf bei
  einem erneuten Limit-Treffer.
- QueueService schedult zusätzlich einen exakten Wake-Timer auf den
  Reset-Zeitpunkt, statt nur auf den 30s-Backstop zu warten.
- Fail-open durchgängig: kein Snapshot/keine Reset-Zeit → kein Timer, kein
  Continue, kein Throw. Toggle aus ändert das heutige Verhalten nicht.

Migration AddUsageLimitAutoContinue fügt beide Spalten hinzu; die von
`dotnet ef migrations add` mitgescaffoldete leere UpdateData auf app_settings
(columns/values: []) erzeugte ungültiges SQL ("near WHERE") und wurde entfernt
— TaskNumberMigrationTests deckte das über den vollen Migrate()-Pfad auf.
2026-08-21 18:43:02 +02:00

152 lines
5.7 KiB
C#

using ClaudeDo.Data;
using ClaudeDo.Data.Models;
using ClaudeDo.Data.Repositories;
using ClaudeDo.Worker.Config;
using ClaudeDo.Worker.Hub;
using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using Microsoft.Extensions.Logging.Abstractions;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
namespace ClaudeDo.Worker.Tests.Services;
public sealed class QueueServiceSlotGuardTests : IDisposable
{
private readonly DbFixture _db = new();
private readonly ClaudeDoDbContext _ctx;
private readonly TaskRepository _taskRepo;
private readonly ListRepository _listRepo;
private readonly WorkerConfig _cfg;
private readonly string _tempDir;
public QueueServiceSlotGuardTests()
{
_ctx = _db.CreateContext();
_taskRepo = new TaskRepository(_ctx);
_listRepo = new ListRepository(_ctx);
_tempDir = Path.Combine(Path.GetTempPath(), $"claudedo_slotguard_{Guid.NewGuid():N}");
Directory.CreateDirectory(_tempDir);
_cfg = new WorkerConfig
{
SandboxRoot = Path.Combine(_tempDir, "sandbox"),
LogRoot = Path.Combine(_tempDir, "logs"),
QueueBackstopIntervalMs = 50,
};
}
public void Dispose()
{
_ctx.Dispose();
_db.Dispose();
try { Directory.Delete(_tempDir, true); } catch { }
}
private QueueWaker _waker = null!;
private (QueueService service, FakeClaudeProcess fakeProcess) CreateService(
Func<string, string, IReadOnlyList<string>, Func<string, Task>, CancellationToken, Task<RunResult>>? handler = null)
{
var fake = new FakeClaudeProcess(handler);
var broadcaster = new HubBroadcaster(new CapturingHubContext());
var dbFactory = _db.CreateFactory();
var wtManager = new WorktreeManager(new ClaudeDo.Data.Git.GitService(), dbFactory, _cfg, NullLogger<WorktreeManager>.Instance);
var argsBuilder = new ClaudeArgsBuilder();
var built = TaskStateServiceBuilder.Build(dbFactory);
var state = built.State;
var runner = new TaskRunner(fake, dbFactory, broadcaster, wtManager, argsBuilder, _cfg,
NullLogger<TaskRunner>.Instance, state, new TaskRunTokenRegistry(), new AttachmentStore(), new FakeSessionSkillSeeder(), new FakeTranscriptUsageReader());
_waker = new QueueWaker();
var picker = new QueuePicker(dbFactory);
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, built.RunCancels);
var usageState = new UsageState();
var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance, _waker, picker, overrideSlot, state, built.RunCancels,
new FakeUsageGate(), usageState, broadcaster,
new UsageLimitAutoContinueCoordinator(dbFactory, usageState, overrideSlot, broadcaster, NullLogger<UsageLimitAutoContinueCoordinator>.Instance));
return (service, fake);
}
private async Task<string> SeedListAsync()
{
var listId = Guid.NewGuid().ToString();
await _listRepo.AddAsync(new ListEntity { Id = listId, Name = "Test", CreatedAt = DateTime.UtcNow });
return listId;
}
private async Task<TaskEntity> SeedQueuedTaskAsync(string listId)
{
var task = new TaskEntity
{
Id = Guid.NewGuid().ToString(),
ListId = listId,
Title = "Guard test task",
Description = "Test",
Status = TaskStatus.Queued,
CreatedAt = DateTime.UtcNow,
};
await _taskRepo.AddAsync(task);
return task;
}
[Fact]
public async Task RunNow_Throws_When_Task_Already_Running_In_Queue_Slot()
{
var listId = await SeedListAsync();
var task = await SeedQueuedTaskAsync(listId);
// Gate keeps the queue slot occupied indefinitely.
var tcs = new TaskCompletionSource<RunResult>();
var queuePickedUp = new TaskCompletionSource();
var (service, _) = CreateService(async (_, _, _, _, ct) =>
{
queuePickedUp.TrySetResult();
return await tcs.Task;
});
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
_waker.Wake();
// Wait until the queue slot has actually picked up the task.
await queuePickedUp.Task.WaitAsync(TimeSpan.FromSeconds(5));
// Now the same taskId is in the queue slot — RunNow must reject it.
var ex = await Assert.ThrowsAsync<InvalidOperationException>(() => service.RunNow(task.Id));
Assert.Contains("already running", ex.Message);
tcs.SetResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" });
cts.Cancel();
}
[Fact]
public async Task ContinueTask_Throws_When_Task_Already_Running_In_Queue_Slot()
{
var listId = await SeedListAsync();
var task = await SeedQueuedTaskAsync(listId);
var tcs = new TaskCompletionSource<RunResult>();
var queuePickedUp = new TaskCompletionSource();
var (service, _) = CreateService(async (_, _, _, _, ct) =>
{
queuePickedUp.TrySetResult();
return await tcs.Task;
});
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
_waker.Wake();
await queuePickedUp.Task.WaitAsync(TimeSpan.FromSeconds(5));
var ex = await Assert.ThrowsAsync<InvalidOperationException>(() =>
service.ContinueTask(task.Id, "follow-up"));
Assert.Contains("already running", ex.Message);
tcs.SetResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" });
cts.Cancel();
}
}