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).
StreamingClaudeSession.RemoveQueuedAsync drops the first occurrence of a queued
message from _pending and re-broadcasts the updated queue. Wired through
InteractiveSessionService + WorkerHub.RemoveQueuedInteractiveMessage +
IWorkerClient.RemoveQueuedInteractiveMessageAsync. Removal by text (first match)
is robust to a turn flushing mid-click. Fakes + ILiveSession impls updated.
StreamingClaudeSession raises onQueueChanged (pending snapshot) and onUserMessageSent
(on delivery, incl. the seeded first prompt); InteractiveSessionService forwards these
as InteractiveQueueChanged/InteractiveMessageSent broadcasts. Lets the UI show queued
messages above the input and move a message into the transcript only when actually
delivered to Claude. Client events + fakes updated.
StreamingClaudeSession now buffers a mid-turn user message in a FIFO queue and
flushes one when the turn's result arrives (no implicit interrupt). InterruptAsync
only writes the control_request (no-op when idle); the resulting turn-end then
flushes any queued message. New InteractiveSessionService.InterruptAsync +
WorkerHub.InterruptInteractiveSession + IWorkerClient.InterruptInteractiveSessionAsync.
Adds SendInteractiveMessageAsync/StopInteractiveSessionAsync and the
InteractiveSessionStarted/Ended events to IWorkerClient + WorkerClient
(UI-thread dispatch mirroring TaskQuestionAsked). Updates the IWorkerClient
fakes in both test projects.
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.
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.
TaskMonitorViewModel surfaces a pending AskUser question (TaskQuestionAsked /
TaskQuestionResolved events) with an AnswerDraft + SubmitAnswerCommand that calls
the new IWorkerClient.AnswerTaskQuestionAsync; MonitorPaneView shows an accent
question banner with an input box above the terminal. Pending question is cleared
on answer/resolve/finish and re-hydrated on attach via GetPendingQuestionAsync.
en/de localization for missionControl.question.*; test fakes updated.
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.
OnlineSyncService is registered once at startup; toggling the feature off
in Settings persisted the flag but never stopped the running loop, so it
kept polling and failing OIDC discovery every cycle. Guard TickAsync on
the shared config's Enabled flag so disabling takes effect live.
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).
GetConflictsAsync/GetMergeConflicts (+ MergeConflicts/ConflictFileContent/ConflictFileDto/ConflictHunkDto DTOs and the now-orphaned GitService.ShowStageAsync) were superseded by the segment-based GetMergeConflictDocuments path and had no production callers. Removes the IWorkerClient member, both test fakes, the lingering test, and updates the Worker/Ui/Data CLAUDE.md surface notes.
Replace the whole-file conflict model with line-level hunks, the
foundation for the full in-app merge editor.
- ConflictMarkerParser: parses git conflict markers (incl. diff3 base)
into ordered stable/conflict MergeSegments; exact round-trip + Compose
- GitService.MergeNoFfAsync passes -c merge.conflictStyle=diff3 so the
working tree carries the merge base in conflict markers
- TaskMergeService.GetConflictDocumentsAsync: reads each conflicted file,
parses into segments, flags binary files
- hub GetMergeConflictDocuments + DTOs (MergeConflictDocumentsDto/
ConflictDocumentDto/MergeSegmentDto), IWorkerClient + both fakes
- tests: 8 parser unit tests + a real-git integration test asserting
line-level hunks with a diff3 base
ZitadelAuthProvider cached the access token in memory and only re-read the
refresh token when the cache expired. Re-signing as a different user saved a
new refresh token but the worker kept serving the previous user's cached
access token until it expired — so sync (and ownerId stamping) continued under
the old identity.
Track the refresh token that minted the cached token and invalidate the cache
when the stored refresh token changes (user switch or sign-out). Switching
users now takes effect on the next sync without a worker restart.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Plumb a per-resource owner (Zitadel sub) through the sync contract without
enforcing isolation client-side — the server stays the authority.
- Dtos: add optional ownerId to RemoteList/RemoteTask/MirrorTask
- JwtClaims: decode the sub claim from the access token (never throws)
- OnlineSyncService: stamp ownerId on pushed lists + mirror; defensively skip
pulled tasks owned by a different user (unowned tasks still sync, so
single-user behavior is unchanged)
- docs: contract documents ownerId + multi-user readiness
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The Online API now requires the "user" project role (claim
urn:zitadel:iam:org:project:roles) instead of an ALLOWED_USER_IDS allowlist.
- IOnlineAuthProvider: add GetAccessTokenAsync(forceRefresh) overload
- ZitadelAuthProvider: forceRefresh drops the cached token and re-runs the
refresh-token grant to mint a fresh, role-bearing token
- OnlineInboxApiClient: on 401, force-refresh and retry once; if still 401,
throw a clear "missing 'user' role" error
- OnlineSyncService: surface the 401 at Error level (no longer silent)
- UI: ZitadelTokenInspector decodes the access token after login and warns
early when the "user" role is absent (fail-open); shown in settings
- docs: online-inbox-api-contract reflects role-based access (no allowlist)
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
The API base URL is https://claudedo.kuns.dev/api — leading-slash request
paths discarded the /api segment. Use relative paths so they nest under the
base. Tests now use a /api/ base to guard the regression.
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>
The picker claims Queued->Running atomically before dispatch; the new
StartRunningAsync guard then rejected every queue-dispatched run. Add
alreadyClaimed to RunAsync/ContinueAsync (queue passes true, override
slot keeps the guard) and align the routing tests.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
OverrideSlotService dispatches RunAsync before calling StartRunningAsync,
so a preflight failure (list not found, worktree setup) can reach MarkFailed
while the task is still Queued. The guard is intentional, not dead code.
- Add comment in FailAsync explaining the OverrideSlotService preflight gap
- Add FailAsync_FromQueued_TransitionsToFailed test
- Update CLAUDE.md transition table with the precise rationale
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Kontext: Auf der Hub/Client-Ebene existieren zwei fast gleichnamige Methodenpaare mit unterschiedlicher Semantik: ContinueMerge/AbortMerge (Single-Task-Konflikt-Resolver, Layer C) vs. ContinuePlanningMerge/AbortPlanningMerge (Unit-Merge eines Parents mit Kindern). Verwechslungsgefahr.
Änderungen (NUR die Hub/Client/UI-Ebene umbenennen):
1. src/ClaudeDo.Worker/Hub/WorkerHub.cs: ContinueMerge → Con
ClaudeDo-Task: 5f2e0f88-d4c9-490b-95a7-46244465dbb6
PlanningMergeOrchestrator._states is in-memory. A worker restart during a
conflict pause left the list repo mid-merge with no recovery path: both
ContinuePlanningMerge and AbortPlanningMerge threw "no in-progress merge",
and re-Approving failed on the IsMidMergeAsync guard.
AbortAsync now falls through to a stateless path when no _states entry exists:
it looks up the parent's list WorkingDir and, if the repo is mid-merge, runs
git merge --abort there directly, then broadcasts PlanningMergeAborted.
Parent remains WaitingForReview — the next Approve restarts the unit merge
(already-Merged child worktrees are skipped as before).
ContinueAsync error message now points to AbortPlanningMerge as the recovery
action. StartAsync mid-merge guard also carries an actionable hint.
Tests: AbortAsync stateless + mid-merge (restart recovery), AbortAsync
stateless + clean repo (clear error).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Befund (bestätigt): src/ClaudeDo.Worker/Runner/TaskRunner.cs:101 (RunAsync) und :211 (ContinueAsync) ignorieren das TransitionResult von _state.StartRunningAsync. Race-Szenario: Der QueuePicker claimt Queued→Running atomar; ruft der Override-Pfad (RunNow) kurz danach RunAsync für denselben Task auf, schlägt StartRunningAsync fehl (0 rows affected), der Runner startet Claude aber trotzdem → derselb
ClaudeDo-Task: 44f86be2-7f3d-462e-98b3-eb94c0174eea
Add 16 missing members to IWorkerClient (IsReconnecting, WorkerLogReceivedEvent,
PrimeFired, LastApproveTarget, Refresh/RestoreDefaultAgents, UpdateAppSettings,
prime schedule CRUD, UpdateList/UpdateListConfig, all worktree ops).
Switch all production consumers off the concrete WorkerClient type; only
Program.cs/App host still resolves the concrete registration.
Update StubWorkerClient and FakeWorkerClient to satisfy the expanded interface.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replaces the direct EF Status write in PlanningMergeOrchestrator with
_state.ApproveReviewAsync, enforcing the TaskStateService invariant as
sole owner of Status writes. Handles the improvement-parent path where
TaskMergeService already approved the parent's own worktree during the
drain (status == Done on entry → still success). If the parent was
concurrently cancelled, the transition guard rejects the approve,
PlanningCompleted is not broadcast, and the cancelled status is
preserved. ApproveReviewAsync now also sets FinishedAt.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 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>
AddTask, planning CreateChildTask, and SuggestImprovement now accept an
optional alias-validated model (haiku/sonnet/opus; blank = inherit) so the
model is chosen at creation time instead of a follow-up set_task_config call.
The planning, system, and improvement prompts instruct Claude to pick the
cheapest capable model (haiku < sonnet < opus).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
- UnifiedDiffParser detects added/deleted/renamed/binary files; diff
modal shows a file list, binary/empty placeholders, and can diff a
merged task by commit range after its worktree is gone
- DetailsIslandViewModel flags children needing attention (failed,
cancelled, awaiting review, or with roadblocks) on the parent
- GitService gains worktree head-commit/range support; planning chain,
merge orchestration, and session manager tweaks with updated tests
- refresh app/installer/worker icons
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Add WaitingForChildren to the CancelAsync guard so a parent waiting on its
children can be cancelled.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Approve & Merge is now the only review+merge entry. For a parent with
children it drives the unit merge via the worker (conflicts still surface
through the existing PlanningMergeConflict dialog); the separate Merge All
Subtasks button, MergeAllCommand, CanMergeAll plumbing, and the dead
MergeAllPlanningAsync client method are removed. Combined-diff preview and
conflict continue/abort are kept.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
ApproveReview routes a parent that has children through
PlanningMergeOrchestrator (merge parent + each Done child, set parent Done,
conflict continue/abort) instead of the parent-only ApproveAndMergeAsync.
Childless tasks are unchanged. Removes the now-redundant MergeAllPlanning hub
method (UI rewiring follows separately).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
A finalized planning parent now joins the unified parent lifecycle:
WaitingForChildren while its child chain runs (or WaitingForReview directly
if it has no children), advancing to review like an improvement parent.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Collapse TryCompleteParentAsync (planning -> Done) and
TryAdvanceImprovementParentAsync (improvement -> WaitingForReview) into one
TryAdvanceParentAsync that surfaces any WaitingForChildren parent for review
once all children are terminal. Planning parents no longer auto-complete.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
merge_task only flipped the worktree to Merged; it never transitioned the task
status. With allowWaitingForReview this left a merged task stuck in
WaitingForReview. Approve it to Done on a successful merge (a Done task is
already terminal). Mirrors the ApproveAndMergeAsync review flow.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
