Files
ClaudeDo/tests/ClaudeDo.Worker.Tests/Services/QueueServiceSlotGuardTests.cs
Mika Kuns 8823265e5a refactor(worker/state): introduce TaskStateService and route mutations through it
Slice 2 of the worker state consolidation refactor (spec sections 2 and 8).

Adds Worker/State/ITaskStateService + TaskStateService as the single component
that mutates Status, PlanningPhase, and BlockedByTaskId. Each transition is one
atomic ExecuteUpdate with a WHERE filter on the expected source status, so
parallel claims are TOCTOU-free. Side effects (queue wake on -> Queued, hub
TaskUpdated broadcast, chain advance + parent completion on terminal child)
are owned by the service so callers no longer need to remember them.

Migrated callers (mechanical, behavior preserved):
- TaskRunner: HandleSuccess/HandleFailure/MarkFailed/RunAsync/ContinueAsync
- StaleTaskRecovery: bulk recover stale Running tasks
- TaskResetService: status flip (worktree cleanup stays in service)
- PlanningSessionManager.StartAsync: status flip via state, token write via repo
- PlanningChainCoordinator.OnChildFinishedAsync: routes the next-sibling write
  through state.UnblockAsync (Slice 4 finishes the rewrite)
- ExternalMcpService.UpdateTaskStatus: Queued case via state.EnqueueAsync

Repo Mark*Async helpers (MarkRunning/MarkDone/MarkFailed/FlipAllRunningToFailed)
are now internal; ClaudeDo.Data grants InternalsVisibleTo to ClaudeDo.Worker
and ClaudeDo.Worker.Tests for the existing repo-level tests.

DI: TaskStateService is registered as Singleton in both the main app and the
external-MCP app; the queue-wake delegate captures sp -> QueueService.WakeQueue
to break the TaskStateService -> QueueService -> TaskRunner -> TaskStateService
construction cycle. PlanningChainCoordinator takes Func<ITaskStateService> for
the same reason; Slice 3 will replace both with IQueueWaker.

Tests: TaskStateServiceTests covers happy + reject for every transition, the
parallel StartRunningAsync claim race, child-terminal chain advancement, and
stale recovery. Existing service/repo tests are updated to construct the new
state-service via a TaskStateServiceBuilder helper. Pre-existing constructor
drift in QueueService/ExternalMcp/PlanningHub tests is patched to keep the
test project building (the surrounding test logic is otherwise untouched).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 11:31:57 +02:00

147 lines
5.3 KiB
C#

using ClaudeDo.Data;
using ClaudeDo.Data.Models;
using ClaudeDo.Data.Repositories;
using ClaudeDo.Worker.Config;
using ClaudeDo.Worker.Hub;
using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Services;
using ClaudeDo.Worker.Tests.Infrastructure;
using Microsoft.AspNetCore.SignalR;
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 TagRepository _tagRepo;
private readonly WorkerConfig _cfg;
private readonly string _tempDir;
public QueueServiceSlotGuardTests()
{
_ctx = _db.CreateContext();
_taskRepo = new TaskRepository(_ctx);
_listRepo = new ListRepository(_ctx);
_tagRepo = new TagRepository(_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 (QueueService service, FakeClaudeProcess fakeProcess) CreateService(
Func<string, string, string, Func<string, Task>, CancellationToken, Task<RunResult>>? handler = null)
{
var fake = new FakeClaudeProcess(handler);
var broadcaster = new HubBroadcaster(new FakeHubContext());
var dbFactory = _db.CreateFactory();
var wtManager = new WorktreeManager(new ClaudeDo.Data.Git.GitService(), dbFactory, _cfg, NullLogger<WorktreeManager>.Instance);
var argsBuilder = new ClaudeArgsBuilder();
var runner = new TaskRunner(fake, dbFactory, broadcaster, wtManager, argsBuilder, _cfg,
NullLogger<TaskRunner>.Instance, TaskStateServiceBuilder.Build(dbFactory).State);
var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance);
return (service, fake);
}
private async Task<string> SeedListWithAgentTagAsync()
{
var listId = Guid.NewGuid().ToString();
await _listRepo.AddAsync(new ListEntity { Id = listId, Name = "Test", CreatedAt = DateTime.UtcNow });
var tags = await _tagRepo.GetAllAsync();
var agentTag = tags.First(t => t.Name == "agent");
await _listRepo.AddTagAsync(listId, agentTag.Id);
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 SeedListWithAgentTagAsync();
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);
service.WakeQueue();
// 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 SeedListWithAgentTagAsync();
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);
service.WakeQueue();
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();
}
}