releases/ClaudeDo
2
0
Fork 0
Code Issues 1 Pull Requests 2 Actions Packages Projects Releases 25 Wiki Activity

fix(worker): Usage-Limit-Auto-Continue verbrennt nicht mehr alle Kandidaten außer dem ersten

Browse Source 
OverrideSlotService hält genau einen Slot, und ein Usage-Limit stoppt
naturgemäß alle laufenden Tasks gleichzeitig — "mehr Kandidaten als
Kapazität" ist also der Normalfall. Der Coordinator stempelte
UsageLimitAutoContinuedAt aber VOR dem ContinueTask (der Marker ist die
Dedupe-Guard), sodass Kandidat 2..n den Marker bekamen, deren
ContinueTask mit "override slot busy" in den catch flog und sie danach
dauerhaft aus GetUsageLimitAutoContinueCandidatesAsync ausgeschlossen
waren — ein Continue, der nie lief.

- Vorab-Check auf CurrentSlot: bei belegtem Slot bricht der Tick ab,
  statt die restlichen Kandidaten zu verbrennen.
- Neuer TaskRepository.ReleaseUsageLimitAutoContinueClaimAsync gibt den
  Claim zurück, wenn ContinueTask wirft; danach return, der 30s-Backstop
  holt den Rest im nächsten Tick.
- Regressionstest mit zwei Kandidaten, deterministisch über eine
  TaskCompletionSource im FakeClaudeProcess (StartInSlot setzt _slot
  synchron unter dem Lock, bevor die Arbeit startet).
This commit is contained in:
mika kuns
2026-08-24 09:05:20 +02:00
parent 55bfb765e6
commit 3dfae30fff
3 changed files with 106 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ClaudeDo.Worker.Tests/Queue/UsageLimitAutoContinueCoordinatorTests.cs
+68 -10
View File
@@ -7,6 +7,7 @@ using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using Microsoft.EntityFrameworkCore;
using Microsoft.Extensions.Logging.Abstractions;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
@@ -29,12 +30,13 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
public void Dispose() { _db.Dispose(); try { Directory.Delete(_tempDir, true); } catch { } }
private (UsageLimitAutoContinueCoordinator Coordinator, UsageState UsageState, FakeClaudeProcess Process) BuildCoordinator()
private (UsageLimitAutoContinueCoordinator Coordinator, UsageState UsageState, FakeClaudeProcess Process, OverrideSlotService Slot) BuildCoordinator(
Func<string, string, IReadOnlyList<string>, Func<string, Task>, CancellationToken, Task<RunResult>>? handler = null)
{
var dbFactory = _db.CreateFactory();
var state = TaskStateServiceBuilder.Build(dbFactory).State;
var wt = new WorktreeManager(new ClaudeDo.Data.Git.GitService(), dbFactory, _cfg, NullLogger<WorktreeManager>.Instance);
var fake = new FakeClaudeProcess();
var fake = new FakeClaudeProcess(handler);
var runner = new TaskRunner(fake, dbFactory, new HubBroadcaster(new CapturingHubContext()), wt,
new ClaudeArgsBuilder(), _cfg, NullLogger<TaskRunner>.Instance, state, new TaskRunTokenRegistry(),
new AttachmentStore(), new FakeSessionSkillSeeder(), new FakeTranscriptUsageReader());
@@ -44,9 +46,12 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
var coordinator = new UsageLimitAutoContinueCoordinator(
dbFactory, usageState, overrideSlot,
new HubBroadcaster(new CapturingHubContext()), NullLogger<UsageLimitAutoContinueCoordinator>.Instance);
return (coordinator, usageState, fake);
return (coordinator, usageState, fake, overrideSlot);
}
// Raw inserts bypass TaskNumberAllocator, so hand out distinct Numbers — tasks.number is unique.
private int _nextNumber = 1;
private async Task<string> SeedUsageLimitTaskAsync(bool withSessionId = true)
{
var listId = Guid.NewGuid().ToString();
@@ -56,7 +61,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
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.Failed,
Id = taskId, ListId = listId, Title = "T", Status = TaskStatus.Failed, Number = _nextNumber++,
FailureReason = "usage_limit", CreatedAt = DateTime.UtcNow, FinishedAt = DateTime.UtcNow,
});
if (withSessionId)
@@ -95,7 +100,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
[Fact]
public async Task Toggle_Off_Never_Schedules_Or_Continues()
{
var (coordinator, usageState, fake) = BuildCoordinator();
var (coordinator, usageState, fake, _) = BuildCoordinator();
var taskId = await SeedUsageLimitTaskAsync();
usageState.ReportSuccess(new UsageSnapshot(
new UsageBucket(85, DateTimeOffset.UtcNow.AddSeconds(-1)), null, Array.Empty<UsageLimitRow>(), DateTime.UtcNow));
@@ -114,7 +119,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
[Fact]
public async Task Toggle_On_No_Snapshot_Yet_Schedules_Nothing_And_Does_Not_Crash()
{
var (coordinator, _, fake) = BuildCoordinator();
var (coordinator, _, fake, _) = BuildCoordinator();
await SeedUsageLimitTaskAsync();
await EnableToggleAsync();
@@ -128,7 +133,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
[Fact]
public async Task Toggle_On_Reset_In_Future_Schedules_Wake_But_Does_Not_Continue_Yet()
{
var (coordinator, usageState, fake) = BuildCoordinator();
var (coordinator, usageState, fake, _) = BuildCoordinator();
await SeedUsageLimitTaskAsync();
await EnableToggleAsync();
var resetsAt = DateTimeOffset.UtcNow.AddMinutes(5);
@@ -146,7 +151,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
[Fact]
public async Task Toggle_On_Reset_Already_Passed_Continues_Exactly_Once()
{
var (coordinator, usageState, fake) = BuildCoordinator();
var (coordinator, usageState, fake, _) = BuildCoordinator();
var taskId = await SeedUsageLimitTaskAsync();
await EnableToggleAsync();
usageState.ReportSuccess(new UsageSnapshot(
@@ -164,10 +169,63 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
Assert.Equal(1, fake.CallCount);
}
/// A usage limit stops every running task at once, so "more candidates than override slots"
/// is the normal case, not an edge case. The claim has to be taken before the run starts
/// (it is the dedupe guard), so a candidate that never got a slot must not keep it — the
/// candidate query filters on that marker and would exclude the task forever.
[Fact]
public async Task Busy_Override_Slot_Leaves_The_Other_Candidate_For_A_Later_Tick()
{
var gate = new TaskCompletionSource();
var (coordinator, usageState, fake, slot) = BuildCoordinator(async (_, _, _, _, _) =>
{
await gate.Task;
return new RunResult { ExitCode = 0, ResultMarkdown = "ok" };
});
await SeedUsageLimitTaskAsync();
await SeedUsageLimitTaskAsync();
await EnableToggleAsync();
usageState.ReportSuccess(new UsageSnapshot(
new UsageBucket(85, DateTimeOffset.UtcNow.AddSeconds(-1)), null, Array.Empty<UsageLimitRow>(), DateTime.UtcNow));
// Tick 1 — the first candidate takes the single slot and holds it on the gate.
await coordinator.RunAsync(default);
Assert.Equal(1, await CountClaimedAsync());
// Tick 2 while that slot is still busy — the second candidate must stay unclaimed.
await coordinator.RunAsync(default);
Assert.Equal(1, await CountClaimedAsync());
// Let the first run finish, freeing the slot.
await PollAsync(() => fake.CallCount >= 1);
gate.SetResult();
await PollAsync(() => slot.CurrentSlot is null);
// Tick 3 — the leftover candidate finally gets its turn.
await coordinator.RunAsync(default);
await PollAsync(() => fake.CallCount >= 2);
Assert.Equal(2, fake.CallCount);
Assert.Equal(2, await CountClaimedAsync());
}
private async Task<int> CountClaimedAsync()
{
using var ctx = _db.CreateContext();
return await ctx.Tasks.CountAsync(t => t.UsageLimitAutoContinuedAt != null);
}
private static async Task PollAsync(Func<bool> condition)
{
var deadline = DateTime.UtcNow.AddSeconds(10);
while (DateTime.UtcNow < deadline && !condition())
await Task.Delay(25);
Assert.True(condition(), "condition did not become true within 10s");
}
[Fact]
public async Task Missing_Reset_Time_Never_Continues_And_Never_Throws()
{
var (coordinator, usageState, fake) = BuildCoordinator();
var (coordinator, usageState, fake, _) = BuildCoordinator();
await SeedUsageLimitTaskAsync();
await EnableToggleAsync();
// A snapshot exists, but this bucket has no reset time — fail open.
@@ -185,7 +243,7 @@ public sealed class UsageLimitAutoContinueCoordinatorTests : IDisposable
[Fact]
public async Task Non_UsageLimit_Failure_Is_Never_Touched()
{
var (coordinator, usageState, fake) = BuildCoordinator();
var (coordinator, usageState, fake, _) = BuildCoordinator();
var listId = Guid.NewGuid().ToString();
var taskId = Guid.NewGuid().ToString();
using (var ctx = _db.CreateContext())