Adds GetUsageSnapshot/GetModelUsage/GetTaskUsage to WorkerHub (backed by a
shared UsageSnapshotBuilder), a UsageUpdated broadcast fired after every
UsageMonitorService poll cycle, and records the resolved model on each
task_runs row so per-model/per-task usage can be reported from history.
Per-list optional VerifyCommand (list_config.verify_command) runs via
VerifyCommandRunner in the list's working dir right after a successful
merge/continue-merge, before the task is allowed to reach Done. A
non-zero exit or timeout leaves the merge in place but keeps the task
out of Done and reports StatusVerifyFailed with an output excerpt
through MergeResultDto/review_task; no command configured behaves
exactly as before. Merges against the same repo are now serialized
per working dir so a running verify can't be interrupted by a second
merge landing mid-build. Adds the field to the List Settings modal
(en/de localized) and covers success/failure/timeout in
TaskMergeServiceTests + VerifyCommandRunnerTests.
> **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
Replaces the list handler's Start-Sleep + blind get_task poll (Phase 3
of the merge-helper prompt) with a blocking MCP tool that returns as
soon as a task leaves Queued/Running, or times out. Implemented as an
async DB poll (short-lived DbContext, 500ms delay, no held connection)
rather than hooking HubBroadcaster, keeping the existing broadcast
callers untouched. timeoutSeconds is clamped server-side to 170s, under
the list handler's 200s MCP_TOOL_TIMEOUT.
Aggregates ~/.claude/projects/**/*.jsonl assistant messages by date/model/
scope (ClaudeDo worktree-or-sandbox cwd vs Other), deduped by requestId
(falls back to message.id), with a per-file length+mtime cache so repeat
calls skip unchanged files.
Adds Usage/ with ClaudeOAuthUsageClient (reads the access token Claude
Code keeps fresh at ~/.claude/.credentials.json, calls the Anthropic
OAuth usage endpoint, defensively parses buckets/limits), UsageState
(threadsafe last-good-snapshot holder that never regresses on
failure), and UsageMonitorService (BackgroundService polling on the
new usage_poll_interval_seconds config, min 15s, one poll at startup,
warns at most once per distinct error).
- 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.
Nullable filter/patch params across the External/ MCP tool classes (ListTasks,
UpdateTask, AddSubtask, ReviewTask, SetMyDay, SetListConfig/SetTaskConfig,
CreateList/UpdateList) lacked C# default values, so the generated tool schema
marked them required — MCP clients omitting them (the common case) failed.
Gave every such parameter a default value.
Also registered a call-tool filter (ExternalMcpExceptionFilter) on the external
MCP host that translates InvalidOperationException/ArgumentException into
McpException, since the SDK's own catch-all discards ex.Message for any other
exception type and returns a generic "An error occurred invoking 'X'." string.
Added a reflection-based schema test sweeping every [McpServerToolType] class
to guard against reintroducing a required-but-nullable parameter.
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.
Adds InteractiveLaunchSpecService + GetInteractiveLaunchSpec hub method that
prepares a task worktree (session-skills seeding, run env) and returns a
LaunchSpec {cwd,exe,args,env} for a UI-hosted ConPTY terminal. Reuses
ISessionSkillSeeder, TaskRunner.UnionSkillNames, and WindowsTerminalLauncher
resume-arg/resolve logic. Guards mirror ResumeTaskInTerminal; a never-run task
yields a fresh-start spec instead of an error.
Interactive/streaming sessions are persistent claude.exe processes that
wait on stdin and never exit on their own. The only teardown was an
explicit StopInteractiveSession from the UI — there is no client-disconnect
or shutdown sweep — so an abandoned chat (UI closed, navigated away,
crashed) kept its claude.exe (+ conhost) alive for the worker's whole
lifetime. Under a long-running autostart worker these accumulate to dozens
of orphaned child processes.
LiveSessionRegistry now tracks per-session activity (Touch on every output
line and user action) and exposes ReapIdleAsync, which stops sessions idle
past a timeout while skipping any with a turn in flight. IdleSessionReaper
(BackgroundService) sweeps every 5 min; idle timeout defaults to 30 min,
configurable via interactive_idle_timeout_minutes (0 disables).
InteractiveSessionService resolves a task's list working dir + seeded prompt,
spawns a StreamingClaudeSession (claude stream-json in the list dir, model+auto
as before), registers it in LiveSessionRegistry, streams output over TaskMessage,
and broadcasts InteractiveSessionStarted/Ended (an exit watcher fires Ended). The
hub's OpenInteractiveTerminalAsync now starts this in-app session; SendInteractiveMessage
and StopInteractiveSession route to it. The external Windows-Terminal interactive
launch (LaunchInteractiveAsync / InteractiveLaunchContext / OpenInteractiveAsync) is
removed; planning sessions keep their terminal launch.
A running task can call mcp__claudedo_run__AskUser(question) to block (up to 3
min) on a human answer. PendingQuestionRegistry holds the pending question +
TaskCompletionSource; the tool broadcasts TaskQuestionAsked, awaits the answer
(WorkerHub.AnswerTaskQuestion resolves it), and returns it as the tool result —
or a 'proceed on your judgment' fallback on timeout. The run stays Running
throughout (no status/schema change). ClaudeProcess raises MCP_TOOL_TIMEOUT so
the 60s HTTP-MCP cap doesn't kill the wait; the run MCP is now wired for every
task, not just standalone ones. System prompt updated to reconcile 'unattended'.
Add seven best-effort batch variants of the single-entity external MCP
tools: batch_get_tasks, batch_add_tasks, batch_update_task_status,
batch_cancel_tasks, batch_delete_tasks, batch_set_my_day, and
batch_cleanup_task_worktrees. Each loops the existing ExternalMcpService
methods sequentially (scoped DbContext is not thread-safe), returns a
per-item result array so a failing item never aborts the rest, and
rejects empty or over-100-item batches. Merge/review stay single-task.
wt.exe treats ';' as a command/tab delimiter in every argument, with no escape
that survives quoting (microsoft/terminal#13264), so a task description
containing ';' spawned extra terminals on "Run interactively" and planning start.
Route the launch as wt -> powershell -> claude and pass the free-text prompt via
$env:CLAUDEDO_LAUNCH_PROMPT so it never reaches the wt command line; PowerShell
binds the variable as a single argument (embedded quotes escaped for PS 5.1).
Also clarify the launcher, which serves interactive runs too (not just planning):
IPlanningTerminalLauncher -> ITerminalLauncher, WindowsTerminalPlanningLauncher ->
WindowsTerminalLauncher, LaunchStart/Resume -> LaunchPlanning{Start,Resume}Async.
AttachmentMcpTools exposes add_task_attachment (text or base64),
list_task_attachments, and remove_task_attachment on the external MCP
endpoint, so an agent can prepare reference files (plans, scripts) on a task
that will run later. Re-attaching the same name overwrites; add/remove refuse
on a running task.
TaskRunner appends attached files (absolute paths) to the run prompt as the
read-only Reference files section. Task and list deletes now remove the
on-disk attachment dir eagerly, and a startup AttachmentOrphanRecovery sweep
drops any attachments/<taskId>/ whose task no longer exists (covers list
cascade and planning-discard paths).
Hub: GetOnlineInboxState / SetOnlineInboxConfig / SetOnlineInboxAuth /
ClearOnlineInboxAuth. WorkerConfig.SaveOnlineInbox persists only the
online_inbox section. OnlineTokenStore + config registered always so hub
methods work when sync is disabled. IWorkerClient surface + all test fakes
synced. RedirectUri config (default http://localhost:8765/callback).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Headless refresh-token -> access-token exchange via OIDC discovery + token
endpoint. Cached to expiry (60s margin), thread-safe, persists rotated refresh
tokens, graceful null on invalid_grant/network errors. Wired into DI when
online_inbox is enabled. Interactive PKCE login (UI) still pending the
registered redirect URI. 7 tests, stubbed HttpMessageHandler.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Optional, opt-in (online_inbox.enabled, default false → zero network).
Worker-side reconcile loop: pull web-created tasks down as Idle, push the
list catalog and the Idle backlog mirror up. Auth behind IOnlineAuthProvider
(StaticTokenAuthProvider default; ZitadelAuthProvider stubbed for Phase 2).
DPAPI refresh-token store. 35 tests, no real network/Zitadel/Claude.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
BUNDLE — all changes live in src/ClaudeDo.Worker/External/ExternalMcpService.cs only, so this is one worktree / one merge. Do NOT touch run-recording or data-layer code (those are separate tasks). Reuse the existing services behind the UI modals (WorktreesOverviewModalView, DiffModalView, MergeModalView) — do not reimplement git plumbing. Build green after each addition.
Add these MCP tools:
1. g
ClaudeDo-Task: f6bdfb5b-8cbf-4e65-93d4-6c758a160484
Wire ListMcpTools, ConfigMcpTools, RunHistoryMcpTools, AgentMcpTools,
LifecycleMcpTools, and AppSettingsMcpTools into the external MCP
container and expose them via WithTools<>().
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
A LocalSystem Windows service can't see the logged-in user's Claude CLI
authentication, so the worker now runs as the current user via a hidden
per-user logon Scheduled Task with restart-on-failure.
- Worker is WinExe (no console window) with a Serilog rolling file sink and
a single-instance mutex so the logon task, app ensure-running, and Restart
button can't fight over the SignalR port.
- Installer replaces the service steps (register/start/stop) with autostart
task steps, migrates the legacy ClaudeDoWorker service away on update, and
removes the task on uninstall. ServicePage drops the service-account UI.
- UI gains a WorkerLocator; the app ensures the worker is running at startup
and the Restart button kills+relaunches this install's worker process.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Drops TagEntity, TagRepository, and tag wiring across data layer, worker,
and UI. Adds RemoveTags migration to clean up schema.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three behavioral changes around stuck planning subtasks:
- OrphanRecovery no longer clears ParentTaskId. Queued children of a
parent that is not in a planning phase are dequeued (Status: Queued
-> Idle, BlockedByTaskId cleared) but stay attached to the parent so
the historical lineage is preserved.
- DiscardPlanningAsync stops promoting terminal (Done/Failed/Cancelled)
children to top-level for the same reason - they remain ChildTasks of
the (now non-planning) parent.
- New PlanningLineageRecovery hosted service scans
~/.todo-app/planning-sessions/ and re-attaches a single, unambiguous
blocked-by chain to its original planning parent when the
parent_task_id links were lost. Refuses to guess when multiple
candidate chains exist.
UI now exposes ConnectionRestoredEvent on IWorkerClient, fired on first
connect and every reconnect. ListsIslandViewModel refreshes counters
and TasksIslandViewModel reloads the current list - so stale counts no
longer survive a worker restart.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Three coordinated guards close the orphan-creation paths:
- CreateChildAsync refuses when the parent is not in a planning phase.
- DiscardPlanningAsync now returns a structured DiscardPlanningOutcome
and refuses when children are queued or running; callers can opt into
auto-dequeuing queued kids via dequeueQueuedChildren=true. Terminal
children (Done/Failed/Cancelled) are promoted to top-level instead of
becoming orphans when the parent's PlanningPhase is reset.
- OrphanRecovery hosted service clears ParentTaskId on any rows whose
parent is missing or no longer in a planning phase on worker startup,
mirroring the StaleTaskRecovery pattern.
UI surfaces the block reason: a confirm dialog offers to dequeue queued
children and retry; a running-children block is shown as a hard error
asking the user to cancel first.
WorkerClient now negotiates the JsonStringEnumConverter so the
DiscardPlanningResult enum round-trips correctly over SignalR.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Worker now runs `claude --version` before listening; on non-zero exit
it logs critical and exits with code 1. Skippable via env var
CLAUDEDO_SKIP_CLI_PREFLIGHT=1 for environments without the CLI (tests,
dev). Closes verification step 2 / open.md item 3.1.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slice 5 of the worker state consolidation refactor.
OverrideSlotService (new in Worker/Queue/) owns RunNow, ContinueTask,
and the override-slot piece of CancelTask. QueueService keeps the
queue-slot guard for "task is already running" rejection and delegates
to OverrideSlotService for execution; CancelTask tries the override
slot first, then the queue slot. QueueSlotState is extracted to its own
file.
Folder reorg (via git mv to preserve history):
- Worker/Queue/ QueueService, OverrideSlotService, QueueSlotState
(alongside existing waker/picker)
- Worker/Lifecycle/ StaleTaskRecovery, TaskResetService, TaskMergeService
- Worker/Worktrees/ WorktreeMaintenanceService
- Worker/Agents/ AgentFileService, DefaultAgentSeeder
Worker/Services/ folder removed. All consumers updated to the new
namespaces (Program.cs, WorkerHub, ExternalMcpService,
PlanningMergeOrchestrator, all Worker tests).
OverrideSlotService is registered as a DI singleton in both the main
worker app and the external MCP app.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slice 4 of the worker state consolidation refactor. Eliminates the
"queue never picks up planning tasks" bug structurally by routing both
the manager and MCP finalize paths through TaskStateService and
PlanningChainCoordinator.SetupChainAsync, where the auto-wake on enqueue
guarantees the queue picker claims the first child immediately.
- Delete TaskRepository.FinalizePlanningAsync; PlanningSessionManager
now orchestrates via _state.FinalizePlanningAsync + _chain.SetupChainAsync.
- Rename QueueSubtasksSequentiallyAsync to SetupChainAsync (internal);
layout is now Status=Queued + BlockedByTaskId, with auto-attached agent tag.
- OnChildFinishedAsync looks up the successor by BlockedByTaskId, drops
the legacy Waiting status lookup.
- PlanningMcpService.Finalize routes through state+chain; EditableStatuses
drops Waiting and adds Idle; gate uses PlanningPhase==Active.
- TaskStateService.FinalizePlanningAsync clears the planning session token.
- UI: TaskRowViewModel adds BlockedByTaskId; IsQueued/IsWaiting reflect
the new layout; TasksIslandViewModel.RemoveFromQueueAsync clears
BlockedByTaskId on dequeue.
- New regression test PlanningEndToEndTests.FinalizeAsync_FirstChildIs
ClaimedByPicker_WithinDeadline asserts the picker claims the first
child within 200ms with no manual WakeQueue.
Co-Authored-By: Claude Opus 4.7 (1M context) <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>
A second WebApplication runs the external MCP server on its own port (default 47822) so it can expose a different tool set under different auth than the internal /mcp endpoint. Shared singletons (config, broadcaster, queue, db factory) are injected by instance so both apps share runtime state. ExternalMcpAuthMiddleware enforces an optional X-ClaudeDo-Key header; loopback-only trust when no key is configured.
Tools: ListTaskLists, ListTasks, GetTask, AddTask, UpdateTaskStatus, RunTaskNow, CancelTask.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Coordinates Waiting -> Queued transitions between sibling subtasks: when a child finishes Done, the next Waiting sibling is promoted to Queued. WorkerHub.QueuePlanningSubtasksAsync exposes this to the UI; TaskRunner advances the chain on completion. Also tightens the planning-session prompt: planner must use MCP tools, not direct edits.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Wire TasksIslandViewModel to TaskUpdated/WorktreeUpdated/TaskMessage worker
events so rows refresh without a full reload; add ForegroundHelper to permit
wt.exe to take foreground on planning launch; misc UI polish on lists, task
rows and settings modal.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add PlanningMcpContextAccessor (Option A) to read PlanningMcpContext
from HttpContext.Items set by PlanningTokenAuthMiddleware
- Annotate PlanningMcpService with [McpServerToolType]/[McpServerTool]
and remove PlanningMcpContext ctx parameter from all tool methods
- Broadcast TaskUpdated(parentTaskId) via HubBroadcaster after every
mutation in PlanningMcpService
- Refactor PlanningSessionManager to accept IDbContextFactory for
singleton-safe use in DI; keep direct-repo ctor for tests
- Register PlanningSessionManager (singleton), IPlanningTerminalLauncher,
PlanningMcpContextAccessor, PlanningMcpService, and MCP server in
Program.cs; wire PlanningTokenAuthMiddleware and MapMcp("/mcp")
- Update PlanningMcpServiceTests with fake HttpContext accessor and
no-op HubBroadcaster (avoids Moq dependency)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
mika kuns