feat(claude-do): Worker: UsageGate — Queue ab Schwelle pausieren

> **Stand 2026-08-05 (List-Handler):** Der Roadblock aus dem letzten Lauf ist erledigt. Beide Voraussetzungen sind jetzt auf `main` gemerged: die `app_settings`-Schwellen `UsageGateFiveHourPct`/`UsageGateSevenDayPct` (Merge-Commit `b1efcdc`) und `UsageState`/`IUsageClient`/`UsageMonitorService` unter `src/ClaudeDo.Worker/Usage/` (Merge-Commit `b126a21`). Dein Worktree ist frisch von diesem `main`

ClaudeDo-Task: 06a7cc32-6ab7-4758-98f4-bee77149b2bf
This commit is contained in:
mika kuns
2026-08-05 11:10:30 +02:00
parent 334cf1e1d2
commit 8f8c2a65b2
12 changed files with 375 additions and 33 deletions
+2 -2
View File
@@ -21,7 +21,7 @@ Worker/
Report/ — ClaudeHistoryReader, WeekReportPromptBuilder, WeekReportService; interfaces in Report/Interfaces/ Report/ — ClaudeHistoryReader, WeekReportPromptBuilder, WeekReportService; interfaces in Report/Interfaces/
Prime/ — daily-prep ("Prime Claude"): PrimeScheduler (BackgroundService), PrimeRunner (runs the daily prep), DailyPrepPrompt (fixed prompt + CLI args + LogPath() helper), NextDueCalculator, PrimeScheduleSignal; interfaces in Prime/Interfaces/ (IPrimeRunner, IPrimeClock, IPrimeScheduleSignal, IPrimeBroadcaster) Prime/ — daily-prep ("Prime Claude"): PrimeScheduler (BackgroundService), PrimeRunner (runs the daily prep), DailyPrepPrompt (fixed prompt + CLI args + LogPath() helper), NextDueCalculator, PrimeScheduleSignal; interfaces in Prime/Interfaces/ (IPrimeRunner, IPrimeClock, IPrimeScheduleSignal, IPrimeBroadcaster)
Online/ — optional Online Inbox sync: OnlineInboxConfig (config record), Dtos (RemoteList/RemoteTask/MirrorTask), IOnlineInboxApi, OnlineInboxApiClient (typed HttpClient, bearer auth, HTTPS guard), OnlineTokenStore (DPAPI refresh-token store, Windows-only), StaticTokenAuthProvider (default/test IOnlineAuthProvider), ZitadelAuthProvider (OIDC discovery + refresh-token flow), OnlineSyncService (BackgroundService: reconcile loop), OnlineBacklog (Idle-backlog filter/query); interface in Online/Interfaces/ (IOnlineAuthProvider) Online/ — optional Online Inbox sync: OnlineInboxConfig (config record), Dtos (RemoteList/RemoteTask/MirrorTask), IOnlineInboxApi, OnlineInboxApiClient (typed HttpClient, bearer auth, HTTPS guard), OnlineTokenStore (DPAPI refresh-token store, Windows-only), StaticTokenAuthProvider (default/test IOnlineAuthProvider), ZitadelAuthProvider (OIDC discovery + refresh-token flow), OnlineSyncService (BackgroundService: reconcile loop), OnlineBacklog (Idle-backlog filter/query); interface in Online/Interfaces/ (IOnlineAuthProvider)
Usage/ — OAuth usage monitor: UsageModels (UsageBucket/UsageLimitRow/UsageSnapshot), ClaudeOAuthUsageClient (reads the access token Claude Code keeps fresh at `~/.claude/.credentials.json`, calls `GET https://api.anthropic.com/api/oauth/usage`; defensive parsing — missing/null buckets → null, missing `limits` → empty list; never logs the token), UsageState (threadsafe singleton; a failed poll never overwrites the last good snapshot, only sets `LastError`), UsageMonitorService (BackgroundService, polls on `usage_poll_interval_seconds`, one poll at startup, logs a failure at most once per distinct error message), TranscriptUsageReader (aggregates Claude Code transcript token usage from `~/.claude/projects/**/*.jsonl` by date/model/scope (ClaudeDo vs Other), deduped by requestId, with a per-file length+mtime cache); interfaces in Usage/Interfaces/ (IUsageClient, ITranscriptUsageReader) Usage/ — OAuth usage monitor: UsageModels (UsageBucket/UsageLimitRow/UsageSnapshot), ClaudeOAuthUsageClient (reads the access token Claude Code keeps fresh at `~/.claude/.credentials.json`, calls `GET https://api.anthropic.com/api/oauth/usage`; defensive parsing — missing/null buckets → null, missing `limits` → empty list; never logs the token), UsageState (threadsafe singleton; a failed poll never overwrites the last good snapshot, only sets `LastError`), UsageMonitorService (BackgroundService, polls on `usage_poll_interval_seconds`, one poll at startup, logs a failure at most once per distinct error message), TranscriptUsageReader (aggregates Claude Code transcript token usage from `~/.claude/projects/**/*.jsonl` by date/model/scope (ClaudeDo vs Other), deduped by requestId, with a per-file length+mtime cache), UsageGate (reads `UsageState` + `AppSettings.UsageGateFiveHourPct`/`UsageGateSevenDayPct`, returns a `UsageGateDecision(IsBlocked, Reason)`; `Utilization` from `UsageBucket` is already a 0100 percent, compared directly against the threshold with `>=`; threshold `0` = that bucket never gates; fail-open — no snapshot yet, a failed last poll, or a settings-read error all resolve to not-blocked); interfaces in Usage/Interfaces/ (IUsageClient, ITranscriptUsageReader, IUsageGate)
``` ```
Interfaces (e.g. `IQueueWaker`, `IPrimeClock`, `ITaskStateService`) live in an `Interfaces/` subfolder within their area; the namespace stays the area namespace. Interfaces (e.g. `IQueueWaker`, `IPrimeClock`, `ITaskStateService`) live in an `Interfaces/` subfolder within their area; the namespace stays the area namespace.
@@ -30,7 +30,7 @@ Interfaces (e.g. `IQueueWaker`, `IPrimeClock`, `ITaskStateService`) live in an `
- **Program.cs** — loads config, inits schema, registers DI, configures SignalR on `/hub`, binds to `127.0.0.1:47821` - **Program.cs** — loads config, inits schema, registers DI, configures SignalR on `/hub`, binds to `127.0.0.1:47821`
- **TaskStateService** — only component that writes `Status`, `PlanningPhase`, `BlockedByTaskId`. All transitions return a `TransitionResult` (no exceptions on invalid moves). Wakes the queue and broadcasts `TaskUpdated` automatically; advances the planning chain on child terminal transitions. - **TaskStateService** — only component that writes `Status`, `PlanningPhase`, `BlockedByTaskId`. All transitions return a `TransitionResult` (no exceptions on invalid moves). Wakes the queue and broadcasts `TaskUpdated` automatically; advances the planning chain on child terminal transitions.
- **IQueueWaker / IQueuePicker / QueueService** — waker is a singleton `SemaphoreSlim`; picker performs the atomic `Queued → Running` claim filtered by `BlockedByTaskId IS NULL`, `is_manual = 0` and schedule; QueueService is a thin `BackgroundService` that loops on the waker and dispatches via `TaskRunner`. - **IQueueWaker / IQueuePicker / QueueService** — waker is a singleton `SemaphoreSlim`; picker performs the atomic `Queued → Running` claim filtered by `BlockedByTaskId IS NULL`, `is_manual = 0` and schedule; QueueService is a thin `BackgroundService` that loops on the waker and dispatches via `TaskRunner`. On each loop tick, after computing `maxParallel`, it also asks `IUsageGate.EvaluateAsync` — if blocked, the slot-fill loop is skipped entirely for that tick (already-running slots are untouched; `RunNow`/`ContinueTask`/interactive/planning/daily-prep all bypass the queue and are unaffected). A blocked↔free transition is logged/broadcast (`WorkerLog`, Warn on block / Info on resume) exactly once per change, not on every tick; the 30 s backstop timer re-evaluates the gate on its own even with no wake signal, so the queue self-recovers once usage drops back under the threshold.
- **OverrideSlotService** — owns `RunNow` / `ContinueTask`; goes through `TaskStateService.StartRunningAsync` (caller-driven, serialized by slot lock). - **OverrideSlotService** — owns `RunNow` / `ContinueTask`; goes through `TaskStateService.StartRunningAsync` (caller-driven, serialized by slot lock).
- **StaleTaskRecovery** — startup-only service; calls `TaskStateService.RecoverStaleRunningAsync` to flip orphaned `Running` rows to `Failed`. - **StaleTaskRecovery** — startup-only service; calls `TaskStateService.RecoverStaleRunningAsync` to flip orphaned `Running` rows to `Failed`.
- **External/*** — always-on MCP tools for general Claude sessions, scoped to *starting* and *observing* sessions (no worktree/merge, multi-turn, planning, or app-settings writes). Auth via optional `X-ClaudeDo-Key` header. Registered explicitly in `Program.cs`'s external app via `.WithTools<T>()`. Every optional/filter parameter across these tools must carry a C# default value (e.g. `string? status = null`) — the MCP schema only marks a parameter optional when it has one; nullability alone doesn't do it (`ExternalMcpToolSchemaTests` guards this by reflection). `ExternalMcpExceptionFilter.Wrap` is registered as a call-tool filter so `InvalidOperationException`/`ArgumentException` messages survive as `McpException` — otherwise the SDK's own catch-all replaces any non-`McpException` with a generic "An error occurred invoking 'X'." Organized by concern: - **External/*** — always-on MCP tools for general Claude sessions, scoped to *starting* and *observing* sessions (no worktree/merge, multi-turn, planning, or app-settings writes). Auth via optional `X-ClaudeDo-Key` header. Registered explicitly in `Program.cs`'s external app via `.WithTools<T>()`. Every optional/filter parameter across these tools must carry a C# default value (e.g. `string? status = null`) — the MCP schema only marks a parameter optional when it has one; nullability alone doesn't do it (`ExternalMcpToolSchemaTests` guards this by reflection). `ExternalMcpExceptionFilter.Wrap` is registered as a call-tool filter so `InvalidOperationException`/`ArgumentException` messages survive as `McpException` — otherwise the SDK's own catch-all replaces any non-`McpException` with a generic "An error occurred invoking 'X'." Organized by concern:
+1
View File
@@ -206,6 +206,7 @@ builder.Services.AddHttpClient<IUsageClient, ClaudeOAuthUsageClient>(client =>
client.Timeout = TimeSpan.FromSeconds(5); client.Timeout = TimeSpan.FromSeconds(5);
}); });
builder.Services.AddHostedService<UsageMonitorService>(); builder.Services.AddHostedService<UsageMonitorService>();
builder.Services.AddSingleton<IUsageGate, UsageGate>();
// Loopback-only bind. Firewall is irrelevant for 127.0.0.1. // Loopback-only bind. Firewall is irrelevant for 127.0.0.1.
builder.WebHost.UseUrls($"http://127.0.0.1:{cfg.SignalRPort}"); builder.WebHost.UseUrls($"http://127.0.0.1:{cfg.SignalRPort}");
+44 -1
View File
@@ -2,8 +2,11 @@ using ClaudeDo.Data;
using ClaudeDo.Data.Models; using ClaudeDo.Data.Models;
using ClaudeDo.Data.Repositories; using ClaudeDo.Data.Repositories;
using ClaudeDo.Worker.Config; using ClaudeDo.Worker.Config;
using ClaudeDo.Worker.Hub;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.State; using ClaudeDo.Worker.State;
using ClaudeDo.Worker.Usage;
using ClaudeDo.Worker.Usage.Interfaces;
using Microsoft.EntityFrameworkCore; using Microsoft.EntityFrameworkCore;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus; using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
@@ -20,9 +23,13 @@ public sealed class QueueService : BackgroundService
private readonly OverrideSlotService _override; private readonly OverrideSlotService _override;
private readonly ITaskStateService _state; private readonly ITaskStateService _state;
private readonly RunCancellationRegistry _runCancels; private readonly RunCancellationRegistry _runCancels;
private readonly IUsageGate _usageGate;
private readonly UsageState _usageState;
private readonly HubBroadcaster _broadcaster;
private readonly object _lock = new(); private readonly object _lock = new();
private readonly Dictionary<string, QueueSlotState> _queueSlots = new(); private readonly Dictionary<string, QueueSlotState> _queueSlots = new();
private bool _usageGateBlocked;
public QueueService( public QueueService(
IDbContextFactory<ClaudeDoDbContext> dbFactory, IDbContextFactory<ClaudeDoDbContext> dbFactory,
@@ -33,7 +40,10 @@ public sealed class QueueService : BackgroundService
IQueuePicker picker, IQueuePicker picker,
OverrideSlotService overrideSlot, OverrideSlotService overrideSlot,
ITaskStateService state, ITaskStateService state,
RunCancellationRegistry runCancels) RunCancellationRegistry runCancels,
IUsageGate usageGate,
UsageState usageState,
HubBroadcaster broadcaster)
{ {
_dbFactory = dbFactory; _dbFactory = dbFactory;
_runner = runner; _runner = runner;
@@ -44,6 +54,9 @@ public sealed class QueueService : BackgroundService
_override = overrideSlot; _override = overrideSlot;
_state = state; _state = state;
_runCancels = runCancels; _runCancels = runCancels;
_usageGate = usageGate;
_usageState = usageState;
_broadcaster = broadcaster;
} }
public IReadOnlyList<(string slot, string taskId, DateTime startedAt)> GetActive() public IReadOnlyList<(string slot, string taskId, DateTime startedAt)> GetActive()
@@ -113,6 +126,13 @@ public sealed class QueueService : BackgroundService
var maxParallel = await GetMaxParallelAsync(stoppingToken); var maxParallel = await GetMaxParallelAsync(stoppingToken);
var gateDecision = await _usageGate.EvaluateAsync(stoppingToken);
await ReportUsageGateTransitionAsync(gateDecision);
// Only queue refill is gated. Runs already in flight (RunNow, ContinueTask,
// interactive sessions, planning, daily prep) keep going regardless.
if (!gateDecision.IsBlocked)
{
// Fill as many free slots as the limit allows. // Fill as many free slots as the limit allows.
while (!stoppingToken.IsCancellationRequested) while (!stoppingToken.IsCancellationRequested)
{ {
@@ -142,6 +162,7 @@ public sealed class QueueService : BackgroundService
} }
} }
} }
}
catch (OperationCanceledException) when (stoppingToken.IsCancellationRequested) catch (OperationCanceledException) when (stoppingToken.IsCancellationRequested)
{ {
break; break;
@@ -155,6 +176,28 @@ public sealed class QueueService : BackgroundService
_logger.LogInformation("QueueService stopping"); _logger.LogInformation("QueueService stopping");
} }
private async Task ReportUsageGateTransitionAsync(UsageGateDecision decision)
{
if (decision.IsBlocked == _usageGateBlocked) return;
_usageGateBlocked = decision.IsBlocked;
if (decision.IsBlocked)
{
_logger.LogInformation("QueueService: usage gate blocking queue refill ({Reason})", decision.Reason);
await _broadcaster.WorkerLog($"Queue pausiert: {decision.Reason}", WorkerLogLevel.Warn, DateTime.UtcNow);
}
else
{
var snapshot = _usageState.Snapshot;
var message = snapshot?.FiveHour is not null && snapshot.SevenDay is not null
? $"Queue fortgesetzt: 5h {snapshot.FiveHour.Utilization:0}%, 7d {snapshot.SevenDay.Utilization:0}%"
: "Queue fortgesetzt";
_logger.LogInformation("QueueService: usage gate cleared, queue refill resumed");
await _broadcaster.WorkerLog(message, WorkerLogLevel.Info, DateTime.UtcNow);
}
}
private async Task<int> GetMaxParallelAsync(CancellationToken ct) private async Task<int> GetMaxParallelAsync(CancellationToken ct)
{ {
try try
@@ -0,0 +1,6 @@
namespace ClaudeDo.Worker.Usage.Interfaces;
public interface IUsageGate
{
Task<UsageGateDecision> EvaluateAsync(CancellationToken ct = default);
}
+58
View File
@@ -0,0 +1,58 @@
using ClaudeDo.Data;
using ClaudeDo.Data.Repositories;
using ClaudeDo.Worker.Usage.Interfaces;
using Microsoft.EntityFrameworkCore;
namespace ClaudeDo.Worker.Usage;
public sealed record UsageGateDecision(bool IsBlocked, string? Reason);
/// <summary>
/// Gates autonomous queue refill on the 5h/7d Claude usage window. Fail-open: no snapshot yet,
/// a failed last poll, or a settings read error all resolve to "not blocked" — an undocumented
/// or unreachable usage API must never stall automation. Only queue refill is gated; runs already
/// in flight (RunNow, ContinueTask, interactive sessions, planning, daily prep) are untouched.
/// </summary>
public sealed class UsageGate : IUsageGate
{
private readonly IDbContextFactory<ClaudeDoDbContext> _dbFactory;
private readonly UsageState _state;
private readonly ILogger<UsageGate> _logger;
public UsageGate(IDbContextFactory<ClaudeDoDbContext> dbFactory, UsageState state, ILogger<UsageGate> logger)
{
_dbFactory = dbFactory;
_state = state;
_logger = logger;
}
public async Task<UsageGateDecision> EvaluateAsync(CancellationToken ct = default)
{
var snapshot = _state.Snapshot;
if (snapshot is null || _state.LastError is not null)
return new UsageGateDecision(false, null);
int fiveHourPct;
int sevenDayPct;
try
{
using var context = _dbFactory.CreateDbContext();
var settings = await new AppSettingsRepository(context).GetAsync(ct);
fiveHourPct = settings.UsageGateFiveHourPct;
sevenDayPct = settings.UsageGateSevenDayPct;
}
catch (Exception ex)
{
_logger.LogWarning(ex, "UsageGate: failed to read gate thresholds; not blocking");
return new UsageGateDecision(false, null);
}
if (fiveHourPct > 0 && snapshot.FiveHour is not null && snapshot.FiveHour.Utilization >= fiveHourPct)
return new UsageGateDecision(true, $"5h-Limit {snapshot.FiveHour.Utilization:0}% >= {fiveHourPct}%");
if (sevenDayPct > 0 && snapshot.SevenDay is not null && snapshot.SevenDay.Utilization >= sevenDayPct)
return new UsageGateDecision(true, $"7d-Limit {snapshot.SevenDay.Utilization:0}% >= {sevenDayPct}%");
return new UsageGateDecision(false, null);
}
}
@@ -8,6 +8,7 @@ using ClaudeDo.Worker.Planning;
using ClaudeDo.Worker.Queue; using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure; using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using ClaudeDo.Worker.Worktrees; using ClaudeDo.Worker.Worktrees;
using ClaudeDo.Worker.Config; using ClaudeDo.Worker.Config;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
@@ -75,7 +76,8 @@ public sealed class AddSubtaskToolTests : IDisposable
var picker = new ClaudeDo.Worker.Queue.QueuePicker(dbFactory); var picker = new ClaudeDo.Worker.Queue.QueuePicker(dbFactory);
var runCancels = new RunCancellationRegistry(); var runCancels = new RunCancellationRegistry();
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels); var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels);
var queue = new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance, waker, picker, overrideSlot, state, runCancels); var queue = new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance, waker, picker, overrideSlot, state, runCancels,
new FakeUsageGate(), new UsageState(), broadcaster);
var maintenance = new WorktreeMaintenanceService(dbFactory, git, NullLogger<WorktreeMaintenanceService>.Instance); var maintenance = new WorktreeMaintenanceService(dbFactory, git, NullLogger<WorktreeMaintenanceService>.Instance);
var merge = new TaskMergeService(dbFactory, git, broadcaster, state, NullLogger<TaskMergeService>.Instance); var merge = new TaskMergeService(dbFactory, git, broadcaster, state, NullLogger<TaskMergeService>.Instance);
var aggregator = new PlanningAggregator(dbFactory, git, NullLogger<PlanningAggregator>.Instance); var aggregator = new PlanningAggregator(dbFactory, git, NullLogger<PlanningAggregator>.Instance);
+3 -1
View File
@@ -10,6 +10,7 @@ using ClaudeDo.Worker.Planning;
using ClaudeDo.Worker.Queue; using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure; using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using ClaudeDo.Worker.Worktrees; using ClaudeDo.Worker.Worktrees;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus; using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
@@ -96,7 +97,8 @@ public sealed class BatchMcpToolsTests : IDisposable
var runCancels = new RunCancellationRegistry(); var runCancels = new RunCancellationRegistry();
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels); var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels);
return new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance, return new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance,
new QueueWaker(), new QueuePicker(dbFactory), overrideSlot, state, runCancels); new QueueWaker(), new QueuePicker(dbFactory), overrideSlot, state, runCancels,
new FakeUsageGate(), new UsageState(), broadcaster);
} }
[Fact] [Fact]
@@ -10,6 +10,7 @@ using ClaudeDo.Worker.Planning;
using ClaudeDo.Worker.Queue; using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure; using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using ClaudeDo.Worker.Worktrees; using ClaudeDo.Worker.Worktrees;
using Microsoft.AspNetCore.SignalR; using Microsoft.AspNetCore.SignalR;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
@@ -161,7 +162,8 @@ public sealed class ExternalMcpServiceTests : IDisposable
var picker = new ClaudeDo.Worker.Queue.QueuePicker(dbFactory); var picker = new ClaudeDo.Worker.Queue.QueuePicker(dbFactory);
var runCancels = new RunCancellationRegistry(); var runCancels = new RunCancellationRegistry();
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels); var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, runCancels);
return new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance, waker, picker, overrideSlot, state, runCancels); return new QueueService(dbFactory, runner, cfg, NullLogger<QueueService>.Instance, waker, picker, overrideSlot, state, runCancels,
new FakeUsageGate(), new UsageState(), broadcaster);
} }
[Fact] [Fact]
@@ -0,0 +1,11 @@
using ClaudeDo.Worker.Usage;
using ClaudeDo.Worker.Usage.Interfaces;
namespace ClaudeDo.Worker.Tests.Infrastructure;
public sealed class FakeUsageGate : IUsageGate
{
public UsageGateDecision Decision { get; set; } = new(false, null);
public Task<UsageGateDecision> EvaluateAsync(CancellationToken ct = default) => Task.FromResult(Decision);
}
@@ -6,6 +6,7 @@ using ClaudeDo.Worker.Hub;
using ClaudeDo.Worker.Queue; using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure; using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus; using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
@@ -59,7 +60,8 @@ public sealed class QueueServiceSlotGuardTests : IDisposable
_waker = new QueueWaker(); _waker = new QueueWaker();
var picker = new QueuePicker(dbFactory); var picker = new QueuePicker(dbFactory);
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, built.RunCancels); var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, built.RunCancels);
var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance, _waker, picker, overrideSlot, state, built.RunCancels); var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance, _waker, picker, overrideSlot, state, built.RunCancels,
new FakeUsageGate(), new UsageState(), broadcaster);
return (service, fake); return (service, fake);
} }
@@ -7,6 +7,7 @@ using ClaudeDo.Worker.Hub;
using ClaudeDo.Worker.Queue; using ClaudeDo.Worker.Queue;
using ClaudeDo.Worker.Runner; using ClaudeDo.Worker.Runner;
using ClaudeDo.Worker.Tests.Infrastructure; using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using Microsoft.Extensions.Logging.Abstractions; using Microsoft.Extensions.Logging.Abstractions;
using TaskStatus = ClaudeDo.Data.Models.TaskStatus; using TaskStatus = ClaudeDo.Data.Models.TaskStatus;
@@ -44,12 +45,16 @@ public sealed class QueueServiceTests : IDisposable
} }
private QueueWaker _waker = null!; private QueueWaker _waker = null!;
private FakeUsageGate _usageGate = null!;
private CapturingHubContext _hubContext = null!;
private (QueueService service, FakeClaudeProcess fakeProcess) CreateService( private (QueueService service, FakeClaudeProcess fakeProcess) CreateService(
Func<string, string, IReadOnlyList<string>, Func<string, Task>, CancellationToken, Task<RunResult>>? handler = null) Func<string, string, IReadOnlyList<string>, Func<string, Task>, CancellationToken, Task<RunResult>>? handler = null,
FakeUsageGate? usageGate = null)
{ {
var fake = new FakeClaudeProcess(handler); var fake = new FakeClaudeProcess(handler);
var broadcaster = new HubBroadcaster(new CapturingHubContext()); _hubContext = new CapturingHubContext();
var broadcaster = new HubBroadcaster(_hubContext);
var dbFactory = _db.CreateFactory(); var dbFactory = _db.CreateFactory();
var wtManager = new WorktreeManager(new GitService(), dbFactory, _cfg, NullLogger<WorktreeManager>.Instance); var wtManager = new WorktreeManager(new GitService(), dbFactory, _cfg, NullLogger<WorktreeManager>.Instance);
var argsBuilder = new ClaudeArgsBuilder(); var argsBuilder = new ClaudeArgsBuilder();
@@ -60,7 +65,9 @@ public sealed class QueueServiceTests : IDisposable
_waker = new QueueWaker(); _waker = new QueueWaker();
var picker = new QueuePicker(dbFactory); var picker = new QueuePicker(dbFactory);
var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, built.RunCancels); var overrideSlot = new OverrideSlotService(dbFactory, runner, NullLogger<OverrideSlotService>.Instance, built.RunCancels);
var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance, _waker, picker, overrideSlot, state, built.RunCancels); _usageGate = usageGate ?? new FakeUsageGate();
var service = new QueueService(dbFactory, runner, _cfg, NullLogger<QueueService>.Instance, _waker, picker, overrideSlot, state, built.RunCancels,
_usageGate, new UsageState(), broadcaster);
return (service, fake); return (service, fake);
} }
@@ -342,4 +349,107 @@ public sealed class QueueServiceTests : IDisposable
tcs.SetResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" }); tcs.SetResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" });
} }
[Fact]
public async Task Blocked_UsageGate_Skips_Queue_Refill()
{
var listId = await SeedListAsync();
await SeedQueuedTask(listId);
var gate = new FakeUsageGate { Decision = new UsageGateDecision(true, "5h-Limit 90% >= 80%") };
var (service, fake) = CreateService(
(_, _, _, _, _) => Task.FromResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" }), gate);
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
_waker.Wake();
await Task.Delay(200);
cts.Cancel();
Assert.Equal(0, fake.CallCount);
}
[Fact]
public async Task UsageGate_Clearing_Resumes_QueueRefill_OnNextTick()
{
var listId = await SeedListAsync();
await SeedQueuedTask(listId);
var gate = new FakeUsageGate { Decision = new UsageGateDecision(true, "5h-Limit 90% >= 80%") };
var done = new TaskCompletionSource();
var (service, fake) = CreateService((_, _, _, _, _) =>
{
done.TrySetResult();
return Task.FromResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" });
}, gate);
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
_waker.Wake();
await Task.Delay(150);
Assert.Equal(0, fake.CallCount);
// Clear the gate; the 50ms backstop timer in this test's config picks it up.
gate.Decision = new UsageGateDecision(false, null);
await done.Task.WaitAsync(TimeSpan.FromSeconds(5));
cts.Cancel();
Assert.Equal(1, fake.CallCount);
}
[Fact]
public async Task Blocked_UsageGate_Does_Not_Cancel_AlreadyRunning_Slot()
{
var listId = await SeedListAsync();
await SeedQueuedTask(listId);
var running = new TaskCompletionSource();
var cancelled = false;
var gate = new FakeUsageGate();
var (service, _) = CreateService(async (_, _, _, _, ct) =>
{
running.SetResult();
try
{
await Task.Delay(Timeout.Infinite, ct);
}
catch (OperationCanceledException)
{
cancelled = true;
throw;
}
return new RunResult { ExitCode = 0, ResultMarkdown = "ok" };
}, gate);
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
_waker.Wake();
await running.Task.WaitAsync(TimeSpan.FromSeconds(5));
// Block after the slot is already running — several backstop ticks pass.
gate.Decision = new UsageGateDecision(true, "5h-Limit 90% >= 80%");
await Task.Delay(200);
Assert.False(cancelled);
cts.Cancel();
}
[Fact]
public async Task UsageGate_TransitionLogging_FiresOncePerChange()
{
var gate = new FakeUsageGate { Decision = new UsageGateDecision(true, "5h-Limit 90% >= 80%") };
var (service, _) = CreateService(
(_, _, _, _, _) => Task.FromResult(new RunResult { ExitCode = 0, ResultMarkdown = "ok" }), gate);
using var cts = new CancellationTokenSource();
await service.StartAsync(cts.Token);
// Several backstop ticks (50ms interval) all observe the same blocked state.
await Task.Delay(200);
cts.Cancel();
var warnCalls = _hubContext.Proxy.Calls
.Count(c => c.Method == "WorkerLog" && (WorkerLogLevel)c.Args[1]! == WorkerLogLevel.Warn);
Assert.Equal(1, warnCalls);
}
} }
@@ -0,0 +1,105 @@
using ClaudeDo.Data.Repositories;
using ClaudeDo.Worker.Tests.Infrastructure;
using ClaudeDo.Worker.Usage;
using Microsoft.Extensions.Logging.Abstractions;
namespace ClaudeDo.Worker.Tests.Usage;
public sealed class UsageGateTests : IDisposable
{
private readonly DbFixture _db = new();
public void Dispose() => _db.Dispose();
private async Task SetThresholdsAsync(int fiveHourPct, int sevenDayPct)
{
using var ctx = _db.CreateContext();
var repo = new AppSettingsRepository(ctx);
var settings = await repo.GetAsync();
settings.UsageGateFiveHourPct = fiveHourPct;
settings.UsageGateSevenDayPct = sevenDayPct;
await repo.UpdateAsync(settings);
}
private UsageGate CreateGate(UsageState state) =>
new(_db.CreateFactory(), state, NullLogger<UsageGate>.Instance);
private static UsageState StateWithSnapshot(double fiveHourPct, double sevenDayPct)
{
var state = new UsageState();
state.ReportSuccess(new UsageSnapshot(
new UsageBucket(fiveHourPct, null),
new UsageBucket(sevenDayPct, null),
Array.Empty<UsageLimitRow>(),
DateTime.UtcNow));
return state;
}
[Fact]
public async Task BothUnderThreshold_NotBlocked()
{
await SetThresholdsAsync(80, 90);
var decision = await CreateGate(StateWithSnapshot(50, 60)).EvaluateAsync();
Assert.False(decision.IsBlocked);
}
[Fact]
public async Task FiveHourAtOrOverThreshold_Blocked()
{
await SetThresholdsAsync(80, 90);
var decision = await CreateGate(StateWithSnapshot(85, 60)).EvaluateAsync();
Assert.True(decision.IsBlocked);
Assert.Contains("5h", decision.Reason);
}
[Fact]
public async Task SevenDayAtOrOverThreshold_Blocked()
{
await SetThresholdsAsync(80, 90);
var decision = await CreateGate(StateWithSnapshot(50, 95)).EvaluateAsync();
Assert.True(decision.IsBlocked);
Assert.Contains("7d", decision.Reason);
}
[Fact]
public async Task ExactlyOnThreshold_Blocked()
{
await SetThresholdsAsync(80, 90);
var decision = await CreateGate(StateWithSnapshot(80, 60)).EvaluateAsync();
Assert.True(decision.IsBlocked);
}
[Fact]
public async Task ThresholdZero_ThatBucketNeverGates()
{
await SetThresholdsAsync(0, 90);
var decision = await CreateGate(StateWithSnapshot(100, 60)).EvaluateAsync();
Assert.False(decision.IsBlocked);
}
[Fact]
public async Task BothThresholdsZero_AlwaysFree()
{
await SetThresholdsAsync(0, 0);
var decision = await CreateGate(StateWithSnapshot(100, 100)).EvaluateAsync();
Assert.False(decision.IsBlocked);
}
[Fact]
public async Task NoSnapshotYet_FailsOpen()
{
await SetThresholdsAsync(80, 90);
var decision = await CreateGate(new UsageState()).EvaluateAsync();
Assert.False(decision.IsBlocked);
}
[Fact]
public async Task LastPollFailed_FailsOpen()
{
await SetThresholdsAsync(80, 90);
var state = StateWithSnapshot(95, 95);
state.ReportFailure("boom", DateTime.UtcNow);
var decision = await CreateGate(state).EvaluateAsync();
Assert.False(decision.IsBlocked);
}
}