TaskRunner.RunAsync created the worktree (PrepareRunDirectoryAsync)
before claiming Running via StartRunningAsync. RunNow dispatches by
task id with no atomic claim of their own, so a Queued task racing
the queue picker's atomic SQL claim could hit WorktreeManager's
branch-collision self-heal, which force-removes and recreates the
winner's live worktree mid-run.
Move the claim before any resource creation and bail out immediately
when it's rejected. OverrideSlotService.RunNow also fast-rejects a
task already Running in the DB (defense in depth). RunCancellationRegistry
now refuses (and logs) a double registration instead of silently
overwriting the first CTS, so a losing dispatch's cleanup can no
longer unregister the winner's cancellation token.
task_runs.tokens_in only ever held the API's uncached "input_tokens" field
(off by a factor of ~400,000 on a resumed session), and tokens_out summed
only the last result event instead of the whole session. TaskRunner now
reads each run's cache-read/cache-write/input/output totals from the
session transcript via a new ITranscriptUsageReader.ReadSessionTotalsAsync,
storing the delta against prior runs on the same session so a --resume
doesn't double-count. New task_runs.cache_read_tokens/cache_write_tokens
columns; the Session tab now shows the raw total (what actually counts
against the 5h/7d usage limit) with a breakdown tooltip.
> **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
- CancelAsync now signals the running Claude process of the cancelled task and
its cascaded children via the new RunCancellationRegistry (queue + override
slots register their CTS there) instead of only flipping DB state.
- external MCP review_task 'approve' now mirrors the hub's ApproveReview:
unit merge for parents, ApproveAndMergeAsync for childless tasks, optional
targetBranch; ReviewTaskResult carries mergeStatus/conflicts.
The embedded ConPTY terminal replaced the in-app streaming interactive session, so
delete the dead stack: StreamingClaudeSession, InteractiveSessionService,
ProcessClaudeStreamTransport, IClaudeStreamTransport, ILiveSession, LiveSessionRegistry,
IdleSessionReaper (+ WorkerConfig.InteractiveIdleTimeoutMinutes), the WorkerHub
interactive methods + HubBroadcaster events, IWorkerClient interactive members, the
TaskMonitorViewModel composer + SessionTerminalView composer markup, and the old
'Run interactively' entry. AskUser/PendingQuestionRegistry, the autonomous path,
planning, ResumeTaskInTerminal, and all ConPTY code are kept. Localization pruned.
StreamingClaudeSession drives claude --input-format stream-json over a kept-
open stdin: sends user messages, interrupts the in-flight turn via the verified
control_request protocol, and tracks turn state from result events (treating an
interrupt-aborted error_during_execution result as turn-ended). IClaudeStreamTransport
abstracts the process I/O so it is unit-tested with a fake (no real claude).
LiveSessionRegistry maps taskId -> live session for the hub to route into.
Backs the upcoming in-app interactive sessions; autonomous task execution untouched.
- Extract FakeClaudeProcess to Infrastructure/FakeClaudeProcess.cs (was
defined inline in QueueServiceTests #region); all consumers updated
- Replace duplicate FakeHubContext/FakeHubClients/FakeClientProxy
(QueueServiceTests) with existing CapturingHubContext from Infrastructure
across all 7 affected files; Planning's file-local FakeHubContext kept
- Rename SeedListWithAgentTag → SeedListAsync (return Task<string>, drop
unused agentTagId tuple element) and SeedListWithAgentTagAsync → SeedListAsync
- PrimeRunnerTests keeps its private nested FakeClaudeProcess: constructor
API (delay/exitCode/lines/result params) differs from the shared one and
replacement would require rewriting every test in that file
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Slice 3 of the worker state and queue consolidation refactor.
- Add IQueueWaker / QueueWaker (singleton holding the wake semaphore).
- Add IQueuePicker / QueuePicker; raw SQL UPDATE...RETURNING moves out of
TaskRepository.GetNextQueuedAgentTaskAsync (deleted) and now also filters
on blocked_by_task_id IS NULL and writes started_at on claim.
- TaskStateService takes IQueueWaker directly; the Func<QueueService>
indirection is gone. State transitions to Queued auto-wake the dispatcher.
- QueueService waits via the shared waker and dispatches via the picker.
- Drop explicit _queue.WakeQueue() calls in WorkerHub.QueuePlanningSubtasksAsync
and ExternalMcpService.AddTask. The hub WakeQueue endpoint stays for
diagnostics, delegating to _waker.Wake().
- Migrate tests; pre-existing flaky AppSettings/ExternalMcp tests untouched.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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>
Update constructor calls (6-arg), seed AppSettings with sibling strategy,
git-init working dirs via GitRepoFixture.InitRepoWithInitialCommit, and
replace McpConfigPath assertions with worktree-path / .mcp.json checks.
Also fixes PlanningHubTests which had the same 3-arg constructor.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Add PlanningSessionFiles, PlanningSessionStartContext/ResumeContext DTOs,
PlanningSessionManager.StartAsync (file scaffolding + status transition),
and integration tests. Also fix migration discovery by adding [DbContext]
attribute to all migration classes and switch DbFixture to EnsureCreated.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Worker and App Program.cs: replace SqliteConnectionFactory+SchemaInitializer
with AddDbContextFactory<ClaudeDoDbContext> + Database.Migrate(). Repos
changed from AddSingleton to AddScoped.
All singleton services (QueueService, StaleTaskRecovery, WorktreeManager,
TaskRunner) and singleton ViewModels (MainWindowViewModel, TaskDetailViewModel,
TaskListViewModel, TaskEditorViewModel) now take IDbContextFactory<ClaudeDoDbContext>
and create short-lived contexts per operation.
Test infrastructure: DbFixture now uses EF migrations instead of SchemaInitializer;
all test classes create contexts via DbFixture.CreateContext().
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
GitService (in ClaudeDo.Data so the UI can reuse it) wraps the git CLI:
IsGitRepo, RevParseHead, WorktreeAdd/Remove, HasChanges, AddAll, Commit
(multi-line via -F -), DiffStat, BranchDelete, MergeFfOnly. Throws with
stderr on failure.
WorktreeManager owns the per-task lifecycle: validate working_dir is a
git repo (throws if not, no DB row written), create the worktree at
<repo>/../.claudedo-worktrees/<slug>/<id>/ (or central root per config),
insert the worktrees row. CommitIfChangedAsync skips when there are no
changes, otherwise commits and updates head_commit + diff_stat.
CommitMessageBuilder produces "{type}({list-slug}): {title<=60}" with a
blank-line-separated description (truncated to 400) and a permanent
"ClaudeDo-Task: <id>" trailer. Slug normalises whitespace + strips
non-alphanumerics. Newlines hard-coded to \n so git on Windows doesn't
choke on \r\n.
TaskRunner branches on list.WorkingDir: worktree path runs Claude in the
worktree, commits on success, broadcasts WorktreeUpdated; failure leaves
the worktree row active for inspection. Sandbox path unchanged.
Tests: 38 pass (12 new). GitRepoFixture spins up a real temp repo with a
seed commit; tests skip gracefully if `git` isn't on PATH.
CommitMessageBuilder fully unit-tested. WorktreeManager covers create,
no-change skip, real-commit, and non-repo failure.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Data: TagRepository, ListRepository, TaskRepository (incl. queue selection via
effective agent tag + scheduled_for filter), WorktreeRepository. All CRUD via
parameterized SqliteCommand; enums roundtrip as lowercase strings matching the
schema CHECK constraints.
Worker: StaleTaskRecovery IHostedService flips running -> failed on startup and
marks the result column with a [stale] reason. All four repositories registered
as singletons.
Tests: DbFixture with temp-file SQLite + schema bootstrap, covering
TaskRepository (queue pick via list-tag and task-tag, schedule filter,
transitions, stale flip), ListRepository CRUD + junctions, and
StaleTaskRecovery. 14 tests pass.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
mika kuns