IBaseDirtyChecker, IInteractiveLaunchSpecService and the LaunchSpec wrapper
had one implementation and one caller each; ProcessRunnerAdapter existed only
to give a static class an interface, and InstallArtifactLocator used
inheritance for two constructor arguments. The external MCP container now
shares its singletons through a Share<T> helper instead of 17 near-identical
registrations.
WorkerHub and IWorkerClient each carried their own copy of every record and
had already drifted — MergePreviewDto lost its verify fields on the client
side, two records disagreed on their name. They now live in Data/Wire.cs and
reach both sides via a <Using> item, so a hub signature change is a compile
error instead of a silently dropped JSON field.
Nine interfaces had exactly one implementation and no test double — they existed
only to be named twice in a DI registration: IFindingsStore, IFindingsStoreLocator,
IPrimeScheduleSignal, IRefineRunner, IWeekReportService, IMergeCoordinator,
IMissionControlPane, IOnlineLoginService, ITaskListFilter. Consumers now depend on
the concrete type; the DTO records that shared those files moved next to their
implementation. IInteractiveLaunchSpecService stays — it carries 54 lines of
contract documentation, which is not ceremony.
IMergeCoordinator in particular had a redundant null object: MergeCoordinator with
a null Handler already no-ops, and every test used the real class with Handler set.
Filtering/ collapses from 8 files to 1. ITaskListFilter and TaskListFilterBase were
a double abstraction over four predicates, with MatchesAsContext => false declared
in both. SmartFlagFilter also compiled its expression twice (its own _flag plus the
inherited Matches cache) — it now uses the cache.
StaticTokenAuthProvider was in src but production uses ZitadelAuthProvider; it is
a test double, so it moves to the test project. Its own test goes away with it.
The modal deliberately shows only a slice of the analytics; this hands off
to TokenTracker's own local dashboard for the rest. The worker starts
`tokentracker serve` on demand and returns the URL, the UI opens the browser.
Three things the spawn has to get right: port 7680 is not free on Windows
(Delivery Optimization holds [::]:7680) and serve does not fall back, so we
scan 7680-7689 with a dual-stack bind probe; --no-open because the CLI would
open the browser before the server answers; and the child is a cmd.exe shim,
so shutdown kills the process tree. --no-sync keeps our no-cloud-sync rule.
ListsIslandViewModel.OpenInExplorer, MergeSectionViewModel.OpenWorktree,
WorktreesOverviewModalViewModel.OpenInExplorer, AboutModalViewModel.OpenPath and
TasksIslandViewModel.OpenTaskWorktree each reimplemented "open this path in the
shell" with their own existence check, launch mechanism and error handling.
Replace all five with the new ShellOpen.Path helper and route failures through
the existing ErrorReported -> footer-strip convention instead of bare catch {}.
ListsIslandViewModel and SettingsModalViewModel each re-implemented "does
this list have a linked WorkingDir" with different whitespace handling.
RepoLinkage.IsLinked/IsLinkedInDb is now the single definition; both
callers derive from it, closing the whitespace-only WorkingDir gap where
the Settings modal disagreed with the ListsIsland banner.
Both viewmodels carried byte-identical copies of the reset-countdown
formatter. Moved it to UsageTimeFormat.FormatRemaining and pointed
both call sites at it; locale keys and output unchanged.
Klassifiziert einen echten Usage-Limit-Abbruch als eigene FailureReason
"usage_limit" (TaskRunner.ClassifyFailureReason: nur bei terminal_reason
"api_error" plus einem Limit-Muster im gerenderten Fehlertext, nicht an
Status==Failed allein). Neuer Toggle AutoContinueOnUsageLimit (app_settings,
Default aus) unter Settings → General → "Usage limit stop":
- UsageLimitAutoContinueCoordinator feuert pro Task genau einmal ContinueTask
über OverrideSlotService, sobald das 5h-Fenster (UsageState.Snapshot.FiveHour
.ResetsAt) tatsächlich zurückgesetzt ist; ein persistenter Marker
(TaskEntity.UsageLimitAutoContinuedAt) verhindert einen zweiten Anlauf bei
einem erneuten Limit-Treffer.
- QueueService schedult zusätzlich einen exakten Wake-Timer auf den
Reset-Zeitpunkt, statt nur auf den 30s-Backstop zu warten.
- Fail-open durchgängig: kein Snapshot/keine Reset-Zeit → kein Timer, kein
Continue, kein Throw. Toggle aus ändert das heutige Verhalten nicht.
Migration AddUsageLimitAutoContinue fügt beide Spalten hinzu; die von
`dotnet ef migrations add` mitgescaffoldete leere UpdateData auf app_settings
(columns/values: []) erzeugte ungültiges SQL ("near WHERE") und wurde entfernt
— TaskNumberMigrationTests deckte das über den vollen Migrate()-Pfad auf.
Neither the initial nor the handoff kickoff ever told a list-handler
session its own handler task id, so handoff_list_handler(taskId, ...)
was unrenderable -- the handoff chain broke exactly where it was needed
(#200/#201 on 2026-08-21).
Add {handlerTaskId} to both MergeHelperInitialDefault and
MergeHelperHandoffDefault, thread a handlerTaskId parameter through
BuildForMergeHelperAsync (interface, WorkerHub.GetMergeHelperLaunchSpec,
IWorkerClient/WorkerClient, and the MissionControlViewModel call site,
which already had the id from CreateMergeHelperTaskAsync but never
passed it on), and render it in BuildForMergeHelperHandoffAsync from the
taskId parameter it already receives.
RenderTemplate leaves unknown/missing tokens untouched, so a
user-edited override without the new token still renders fine -- no
forced migration for override users.
The task-list done toggle (both islands) and RemoveFromQueue wrote TaskEntity.Status
directly via EF, bypassing TaskStateService: no TaskUpdated broadcast, no guard against
a concurrent picker claim (lost update), and no status-based filter. Added guarded
MarkDoneAsync/UnmarkDoneAsync/DequeueToIdleAsync transitions plus matching hub methods
(SetTaskDone/UnsetTaskDone/DequeueTask) and IWorkerClient wrappers; the three UI call
sites now route through the hub with optimistic-then-revert row updates and
ErrorReported on failure. RemoveFromQueueAsync dequeues each queued child individually
through the same guarded path instead of cascading via a raw EF update.
Also closes two hub guard gaps: UpdateListConfig's delete branch now preserves a list's
SerializeOnFileOverlap flag instead of dropping it, and SubmitTaskForReview's Idle/Failed
status gate now runs before either mutation branch so a Done/Cancelled task can't get
committed or stamped and then rejected.
A child merge that came back blocked/verify_failed/untracked_collision during a
parent/children unit merge used to vanish: DrainAsync only logged it server-side,
PlanningMergeAborted carried no reason, and ApproveReview/review_task always
reported StatusMerged for a task with children regardless of the real outcome,
so a failed unit merge left the parent stuck with no visible error.
- PlanningMergeOrchestrator.StartAsync/ContinueAsync/DrainAsync now return a
PlanningMergeResult(Status, Reason) instead of void, and PlanningMergeAborted
carries that reason to the UI.
- WorkerHub.ApproveReview and ExternalMcpService.ReviewTask's approve branch
propagate the real status/reason for a parent with children instead of
hardcoding "merged" (or masking a non-conflict failure as "conflict").
- StartAsync now requires the parent to already be WaitingForReview for
improvement parents too, not just planning ones, so a stale caller can no
longer trigger a partial child merge.
- HasActiveMerge now also covers the window between the last child merging and
FinalizeParentDoneAsync completing, closing a gap where a concurrent Cancel
could race the parent's own approve-to-Done transition.
- IslandsShellViewModel.OnPlanningMergeAborted flashes the reason via
FlashFooterError instead of only clearing the external-merge banner.
Its job (surfacing the DetailsIsland.BindAsync churn) is done; leave the
InvokeTimedAsync wrappers and Island Record call sites in place as a
chokepoint for next time, but stop writing by default. Shared now only
writes when CLAUDEDO_OP_TIMING=1 is set; the constructor keeps enabled=true
so both TestSetup redirects and OperationTimingTests are unaffected.
DetailsIsland.BindAsync churn (~1900 binds/day, 91-96% cancelled) was not a
UI reactivity bug: OperationTiming.Shared is a static singleton hardcoded to
~/.todo-app/logs/operation-timing.ndjson, and Ui.Tests/Worker.Tests both
construct real DetailsIslandViewModel/TasksIslandViewModel instances that
call Shared.Record directly. Every dotnet test run appended 50-100 lines
straight into the live app's log — pid-burst analysis showed 13 distinct
test-run pids in the ":?" bucket (tests never pass a source) plus a
no-suffix bucket with no pid field at all (pre-dating the pid-per-line
feature). Real user-driven binds that day: 4.
Made Shared settable and added a [ModuleInitializer]-based TestSetup in
both test projects that redirects it to a per-process temp file before any
test runs.
Merge/verify phases now broadcast over a generic (opKey, phase, current,
total) Hub event instead of a merge-specific one, so future producers
(worktree cleanup, startup recovery, planning integration) can reuse it.
IWorkerClient.MergeProgressEvent stays as a thin forwarder for existing
consumers (elapsed seconds riding in the generic "current" slot).
Three causes behind the stuck indicator:
- OperationStatus.End did not retire the generation, so tick work posted
while the dispatcher was blocked drained afterwards and set
ShowIndicator back to true on a finished operation.
- The startup update check ran in Task.Run; OperationStatus writes its
observable properties on the calling thread, so the final
ShowIndicator=false never reached the binding.
- OperationIndicator overwrote its own DataContext from the Status
property, which re-targeted the call-site binding. It now scopes the
DataContext to an inner panel and collapses itself when Status is
null; every call site switched from DataContext= to Status=.
Also gates the footer connection pill in the command body instead of
CanExecute (a disabled command greyed out the ONLINE chip), and extends
OperationTiming: pid per line, 4 MB rollover, fast successes dropped
(failures always kept), and DetailsIsland.BindAsync now carries the
selection trigger via TasksIslandViewModel.SelectFrom.
Vorgaben: `docs/superpowers/plans/2026-08-11-operation-feedback.md`, Gruppe A, Entwurf A3. P0-1 ist gemergt: `src/ClaudeDo.Ui/Services/OperationStatus.cs` + `src/ClaudeDo.Ui/Views/Controls/OperationIndicator.axaml`.
SCOPE-ÄNDERUNG (Nutzer, 2026-08-12): OnlineInbox Sign-In/Sign-Out ist AUS DEM SCOPE GENOMMEN — vorerst unwichtig. `ViewModels/Modals/Settings/OnlineInboxSettingsViewModel.cs` und die
ClaudeDo-Task: 2356806f-f16e-4652-b615-4562e95c3a65
Foundation for long-running-operation feedback (P0-1). OperationStatus tracks
IsRunning/ShowIndicator(300ms grace)/Elapsed/IsStalled(60s since last Report)
via an injectable TimeProvider, no static timer. OperationIndicator binds a
status to the shared spinner style. Pre-provisions ops.* locale keys for
groups A and C; no ViewModel wired up yet.
Two chokepoints per P0-2: WorkerClient.InvokeTimedAsync(<T>) wraps all 63
_hub.InvokeAsync call sites (plus TryInvokeAsync), and Stopwatch blocks
around the Island VMs' bulk DB load/write paths (list load, task list load,
reorders, batch delete, reconcile tick, count refresh). Single-row reads
stay untouched per the plan's rule of thumb. No display, no behavior change.
The merge commit message was hand-rolled per caller ("Merge task: <title>",
"Merge <branch>", "Merge subtask") and ignored the task's commit type. Every
caller now passes a blank message and TaskMergeService fills in
CommitMessageBuilder.BuildMerge -> {commitType}(list-slug): merge <title> plus the
ClaudeDo-Task trailer; the merge modal prefills it from GetMergeTargets.
A merge whose list has a verify command holds the MergeTask call for minutes (5m46s
on this repo), during which the modal only disabled its button - no spinner, no
message, so a landed merge looked like a dead app. TaskMergeService now broadcasts
MergeProgress(taskId, phase, elapsedSeconds) for the merging and verifying phases
(re-reported every 30s) plus a WorkerLog line when verify starts; the modal shows a
spinner and the localized phase.
HandoffRequested now carries nextPhase end to end (IWorkerClient ->
WorkerClient -> MissionControlViewModel -> GetMergeHelperHandoffLaunchSpecAsync),
and the outgoing tile is left open on handoff instead of being closed --
lookups that need the active pane for a task now use LastOrDefault since a
handler task's ConPtySessions can hold more than one pane.
Queuing (update_task_status, batch_update_task_status) and run_task_now
now surface a non-blocking baseDirty warning (separate modified/untracked
counts) when the list's working dir has uncommitted changes at enqueue
time, since a new worktree forks from the commit tip and silently misses
them. BaseDirtyChecker caches per working dir for a few seconds so a
batch queue over many tasks in one list only shells out to git once. The
UI surfaces the same warning via the footer error strip on queue actions.
DeleteTaskAsync had no IsConnected guard, unlike every other worker-dependent
command in DetailsIslandViewModel, so an offline delete was a silent no-op.
WorkerClient.DeleteTaskAsync also only caught HubException, letting the
InvalidOperationException thrown by an inactive hub connection escape into
the unobserved command task and vanish.
Gate DeleteTaskCommand behind CanDeleteTask (Task != null && IsConnected),
re-evaluate it on connection-state changes, widen WorkerClient to catch the
connection-inactive case too, and wrap the ViewModel's call in try/catch as
a second line of defense against a race between the guard and the call.
StartAsync awaited the static launch-gate semaphore with no timeout, so one
hung launch (slow disk, AV scanning claude.exe, a Porta.Pty/ConPTY hiccup)
blocked every subsequent pane open behind it indefinitely, including Retry.
Extracted the wait into WaitForLaunchGateAsync with a 30s timeout that
throws TimeoutException before the try/finally (never releasing a gate it
didn't acquire); the exception flows through StartCoreAsync's existing
catch into StartError, so the pane shows an error + Retry instead of
hanging. StartError renders ex.Message directly (no locale key involved),
so no locale changes were needed.
PtyTerminalSession.StartAsync itself needs a real TerminalControl and stays
impractical to unit-test directly, so tests target the extracted
WaitForLaunchGateAsync helper against a plain SemaphoreSlim: timeout throws,
timeout never acquires the gate, and success still acquires it.
RepoScanner.Scan() only guarded reparse points on subdirectories found
during recursion, so a configured import root that is itself a junction
walked straight through onto other drives. Apply the same
FileAttributes.ReparsePoint check to the root before scanning.
RepoImportModalViewModel.ScanAndAdd ran the full 5-level recursive scan
synchronously on the UI thread; pointing the folder picker at a broad
directory froze the app. Offload RepoScanner.Scan to Task.Run per folder
and apply results back on the UI thread.
Add a RepoScannerTests case that creates a real junction (mklink /J) at
the scan root and asserts Scan returns empty.
Two sessions starting back-to-back could interleave SetEnvironmentVariable
calls before either LaunchProcess() forks, leaking one task's env (e.g.
CLAUDEDO_PLANNING_TOKEN) into another's claude process. Serialize the
set-env + LaunchProcess critical section behind a static SemaphoreSlim in
PtyTerminalSession.
OpenConPtySessionAsync/OpenPlanningConPtySessionAsync ran their TaskId
dedupe check before an awaited DB title lookup, and OpenMergeHelperConPtySessionAsync
awaited task creation before any dedupe was possible - rapid double-invocation
could open two panes or mint two host tasks. Claim the key synchronously at
method entry, before any await, and release it in a finally.
Deleting a child from the details pane hard-deleted straight from the UI
process via TaskRepository, bypassing TaskStateService.TryAdvanceParentAsync
entirely. Deleting the last child of a WaitingForChildren parent that way
left it wedged forever. WorkerHub.DeleteTask now mirrors the MCP delete_task
tool (running-task guard, FK-friendly error, advance-parent call), and the
UI goes through it.
TryAdvanceParentAsync also short-circuited when zero children remained,
treating "no children left" as "nothing to evaluate" instead of "all done" -
removed the early return so an empty child list (vacuously) counts as all
terminal.
RepoScanner.Scan now recurses into subdirectories (max depth 5) instead
of only checking the immediate children of the chosen folder. A found
repo (.git as dir or file) is added without descending further; the
selected folder itself is checked too. Skips node_modules/bin/obj/.git/
.vs/packages and reparse points (junctions/symlinks). Per-directory
IOException/UnauthorizedAccessException no longer aborts the whole scan.
TerminalView kills its child process on any logical-tree detach unless
BeginReparent() suppressed it, and RebuildOverviewGrid() detaches every
existing pane whenever one is added - so opening a second interactive
session killed the first. Focus-mode tab switches had the same defect.
PtyTerminalSession now puts the control in permanent reparent mode after
launch (teardown stays explicit via ConPtyPaneViewModel.Dispose -> Kill),
and the new ConPtyPaneHost reparents each pane's single long-lived view
across grid rebuilds and tab switches instead of letting the DataTemplate
instantiate a dead replacement.
review_task/continue_merge on a planning parent always leaves conflicts in
the tree, and the UI auto-opened the resolver on every PlanningMergeConflict
broadcast regardless of who started the merge -- so a running Claude session
resolving a unit-merge conflict could race a human editing the same shared
checkout in a resolver window neither of them asked for.
PlanningMergeOrchestrator.StartAsync now takes an externallyDriven flag (set
by ExternalMcpService's MCP-driven review_task path, left false for the UI's
ApproveReview) that rides along on the PlanningMergeConflict broadcast. The
UI only auto-opens the resolver when it's false; otherwise it shows a
persistent banner with a manual "Open resolver" button, cleared on
PlanningMergeAborted/PlanningCompleted. A new GetActiveExternalConflictsAsync
query (checked against GitService.IsMidMergeAsync rather than the in-memory
flag alone) lets the UI resync the banner on reconnect instead of trusting a
one-shot broadcast that isn't replayed after a restart.
The childless single-task conflict path was checked and needed no change --
it only broadcasts the generic TaskUpdated, never PlanningMergeConflict.
Stamps ClaudeDo.Worker's build with its exact git SHA (SourceRevisionId ->
InformationalVersion) and exposes it via a new GetWorkerBuildInfo hub call.
For the currently selected list, the shell compares that SHA against the
list's git HEAD (GitService.IsAncestorAsync) and shows a persistent footer
banner -- never auto-clearing, never shown on an unrelated repo or when the
ancestry can't be determined -- so "verified against a merge" claims aren't
silently made against a stale process. No auto-restart; the banner just
offers the existing RestartWorkerCommand.
## Befund (am Code verifiziert 2026-08-06)
`AppSettingsEntity.RepoImportFolders` (`src/ClaudeDo.Data/Models/AppSettingsEntity.cs:26`, JSON-Array als TEXT) ist **nicht** Teil des `AppSettingsDto` in `src/ClaudeDo.Worker/Hub/WorkerHub.cs:32-49` und wird weder von `GetAppSettings` (~:375-393) noch von `UpdateAppSettings` (~:396-424) transportiert.
Stattdessen liest und schreibt die Ui das Feld dire
ClaudeDo-Task: 64fbe15d-ae7e-4d81-b8c1-045baa7e3c87
The merge-helper ("Let Claude handle it") system prompt now calls a new
handoff_list_handler MCP tool once every surviving task is enhanced,
instead of continuing into Phases 3-5 in the same session -- avoiding
paying for Phases 0-2's dedupe/rewrite context on every polling round of
the run/review/merge phases.
The tool broadcasts HandoffRequested; Mission Control opens a second
ConPTY tile for the SAME handler task id (no new task, HandlerBaseCommit
untouched) running a fresh handoff brief that starts at Phase 3. The
original tile stays open. Adds PromptKind.MergeHelperHandoff,
InteractiveLaunchSpecService.BuildForMergeHelperHandoffAsync, and the
GetMergeHelperHandoffLaunchSpec hub method.
The usage monitor polled the undocumented OAuth usage endpoint every 60s and
earned 429s. It now polls every 5 min while any task is Running and every
15 min while idle (usage_poll_interval_active_seconds / _idle_seconds, both
clamped to >= 60; the old single usage_poll_interval_seconds key is gone).
A 429 comes back as UsageRateLimitedException carrying Retry-After and adds
exponential backoff on top, capped at 30 min and never shorter than the normal
cadence; the strike count resets on the first success. The schedule arithmetic
is the pure static UsagePollSchedule.NextDelay.
Since the idle cadence is slow on purpose, WorkerHub.RefreshUsage drives
UsageMonitorService.RefreshNowAsync behind a Refresh now button in the Usage
Monitor modal: an out-of-band poll that pushes the loop's next-due time out so
no double poll follows, with a 10s cooldown so click-spam can't earn a 429.
Staleness now measures against the slower (idle) interval so an idle worker
isn't flagged stale just for not polling.
## Kontext: Limits sind Fenster, nicht Summen
Die Runs laufen ueber das Claude-Abo. Limits greifen pro 5h-Fenster und pro 7 Tage. Nicht die Wochensumme tut weh, sondern dass ein Agent-Burst ein Fenster leerraeumt, in dem Mika selbst interaktiv arbeiten will.
## Messgrundlage (alle Transcripts unter ~/.claude/projects)
Agent-Runs sind ueber die ganze Historie nur **18,4 %** des Account-Verbrauch
ClaudeDo-Task: 87105f5e-c4f4-4af4-ae60-89cd2e153e3c
Runaway sessions were the single biggest cost driver: model_presets was
never persisted (stayed code-only), default_max_turns shipped at 100, and
ResolveMaxTurns had no upper bound, so a task/list override could run
hundreds of turns unchecked.
- TaskRunner.ResolveMaxTurns now clamps the resolved value to
AppSettings.MaxTurnsCeiling (new column, default 80) and logs a warning
with task id / requested / effective value when it clamps.
- default_max_turns default lowered from 100 to 40 (entity, EF config,
and the seeded row via the new AddMaxTurnsCeiling migration).
- AppSettingsRepository.GetAsync backfills model_presets with the
shipping defaults on first read instead of leaving the column null.
- Settings > General's per-model preset table and the task/list agent
editor now show a hint when a set max-turns value exceeds the ceiling.
Adds a Usage Monitor modal (Worker menu + wired to the footer/Mission-Control
usage pill's Open command): dynamic gauges built from UsageSnapshotDto.Limits
with gate-threshold marks, a stale/blocked-gate band, and Models/Tasks tabs
backed by GetModelUsageAsync/GetTaskUsageAsync over a 7d/30d/custom range.
mika kuns