"Let Claude handle it" now creates one ClaudeDo task per run to host the
ConPTY session (Idle/IsManual, never queued) instead of an untracked
ad-hoc tile, so the run has a real title, diff, and review outcome.
Since the handler merges its own changes straight into the list's
working dir, the task never gets a WorktreeEntity; its review range
lives as new HandlerBaseCommit/HandlerHeadCommit columns on TaskEntity
instead, reusing the existing commit-range diff machinery and keeping
it out of the worktrees overview entirely.
Two context-menu entries opened a Claude session for the same task via different
mechanisms (embedded ConPTY vs. an external wt terminal). Drop the external-terminal
path entirely, including its worker hub method, launcher plumbing, and localization
keys, since the embedded ConPTY session already covers every case it did.
A full model id like claude-sonnet-4-6 in list_config.model never matched any
ModelPresets row (only bare aliases did), so every run under it landed on the
hardcoded 30-turn/DefaultLevel fallback instead of the sonnet preset row -
this is what killed two autonomous tasks at the 30-turn limit.
ModelRegistry.TryNormalizeAlias (non-throwing: exact match, then substring
match against a full model id) lets ModelPresets.For resolve a full model id
to its alias's preset row. For a model that still doesn't resolve, the
hardcoded 30 is replaced by a caller-supplied fallbackMaxTurns, and TaskRunner
now passes AppSettings.DefaultMaxTurns there - so that setting has a real
effect instead of being dead, matching the direction already noted in
docs/open.md.
## Problem
Die "Let Claude handle it"-Session (List-Handler) startet mit `--permission-mode default` und fragt
dadurch bei jedem Tool-Aufruf nach Bestätigung. Sie soll autonom durchlaufen können — der User
überwacht die ConPTY-Kachel, statt jede Aktion einzeln freizugeben.
## Ist-Zustand
`src/ClaudeDo.Worker/Runner/InteractiveLaunchSpecService.cs`, `BuildForMergeHelperAsync`
(Zeile ~183-249). Die
ClaudeDo-Task: 50a6027eba294dde8b18e4082dfc1e9b
ClaudeDo never passed --effort, so every session inherited whatever effortLevel
the user's Claude Code config happened to carry. Settings -> General now holds one
row per model alias (haiku medium/20, sonnet high/30, opus high/40, fable high/25)
supplying the global effort and turn defaults; list- and task-level max-turns
overrides still win, and the agent editor's inherited badge follows the model.
--effort is applied to autonomous runs and to every ConPTY spec (task session,
planning start/resume, ad-hoc, list handler). The model itself is deliberately not
forced on interactive sessions. The single global 'Max turns' field is replaced by
the table, and 'fable' joins ModelRegistry.Aliases.
The migration also adds the is_manual columns used by the next commit.
Planning start/resume opened an external Windows Terminal (wt) window.
Route them through the embedded ConPTY Command Center pane instead, matching
the existing interactive-session UX (no external window).
- Extract bare planning arg builders (BuildPlanningStartArgs/ResumeArgs) from
WindowsTerminalLauncher; the wt path still uses them (kept, not removed).
- InteractiveLaunchSpecService.BuildPlanningStart/Resume map a planning
context into a LaunchSpec (planning args + env: MAX_THINKING_TOKENS,
CLAUDEDO_PLANNING_TOKEN). Hub GetPlanningStart/ResumeLaunchSpec run
StartAsync/ResumeAsync then return the spec.
- UI: OpenPlanningSession + the resume branch raise OpenPlanningConPtyRequested;
the shell opens Mission Control and hosts a planning ConPTY pane.
Env is process-global by design (sequential human-paced sessions). wt planning
code retained. Tests added for the arg/env mapping.
A --json-schema run can echo the structured {"summary":...} JSON as the
result text, which then landed verbatim in task.Result and rendered raw in
the OUTCOME card. Unwrap the summary in StreamAnalyzer when the result text
is itself such a JSON object (a plain markdown result is kept as-is), and
add a UI safety net in ApplyOutcome for rows already persisted as raw JSON.
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.
A fresh (non-resume) task-based ConPTY session now opens claude on the task's
prompt (title + description) as the positional argument, so the session starts on
the task instead of an empty prompt. Resume sessions and ad-hoc sessions are
unchanged.
BuildForTaskAsync now creates a worktree on demand (via WorktreeManager.CreateAsync,
the same path TaskRunner uses) when a task has a configured working dir but no
Active/Kept worktree, returning a fresh-start spec -- so never-run tasks can be
opened interactively. Adds BuildForDirectoryAsync + GetAdHocLaunchSpec hub/client
for ad-hoc sessions in an arbitrary directory (no task, no worktree, no skill seeding).
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).
Spawned claude processes were only torn down on graceful cancellation
(Process.Kill(entireProcessTree)). A hard worker death — Task Manager
End Task, crash, OS restart, installer update — ran no cleanup, orphaning
the claude->node->conhost tree, which lingered and piled up across
restarts.
Assign every spawned claude process to a Windows Job Object with
JOB_OBJECT_LIMIT_KILL_ON_JOB_CLOSE. The worker holds the only handle, so
when it terminates for any reason the OS tears down the whole job. No-op
on non-Windows; best-effort with a one-time warning if the Win32 calls
fail.
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.
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.
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'.
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).
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>
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
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>
1. ArgumentList (fix injection): ClaudeArgsBuilder.Build() now returns
IReadOnlyList<string>; ClaudeProcess populates ProcessStartInfo.ArgumentList
instead of Arguments, so values like system prompts are never shell-split.
DailyPrepPrompt, RefinePrompt, and WeekReportService migrated similarly.
All IClaudeProcess fakes updated.
2. ContinueAsync exception guard: wrap RunOnceAsync in try/catch matching
the RunAsync pattern so an unexpected exception never leaves the task
stuck in Running status.
3. Planning chain cascade: OnChildFinishedAsync now calls CancelAsync on
the immediate blocked successor when a child fails or is cancelled,
triggering a recursive cascade that clears the entire remaining chain
instead of leaving it wedged.
4. FailAsync guard: restrict valid source states to Running and Queued;
WaitingForReview -> Failed is now rejected, preventing an invalid
transition that could corrupt the review workflow.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Resolved sub-tasks are no longer appended to the prompt. Extracted into a
shared TaskPromptComposer so the UI's description preview can render the same
'what Claude gets' text.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- TaskRunner: extract worktree-vs-sandbox selection into
PrepareRunDirectoryAsync so RunAsync reads linearly (a small helper, not
a Strategy pattern — overkill for a two-way branch).
- App: drop the public static ServiceProvider locator; inject the provider
via constructor through AppBuilder.Configure(() => new App(services)).
Parameterless ctor + BuildAvaloniaApp() retained for the XAML designer.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
If WorktreeAddAsync succeeds but the worktrees-row insert throws, the
worktree was left on disk and branch undeleted with nothing tracking it.
Wrap the insert in try/catch and best-effort remove the worktree+branch
(non-cancellable) before rethrowing.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Clear ReviewFeedback only after a successful re-run so a failed/cancelled
run keeps it for a manual retry.
- Clear stale StartedAt/FinishedAt when rejecting a task back to the queue.
- Only non-planning standalone tasks gate on review (guard PlanningPhase).
- Hide "send to queue" for WaitingForReview tasks so review isn't bypassed.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Standalone tasks now enter WaitingForReview on success; re-queued tasks
carrying reviewer feedback resume the prior Claude session with that
feedback as the next turn.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Set the task's log path when the run is created (not at completion) so the
session terminal can replay live output when the user navigates away and back
mid-run. Remove the now-redundant inline per-row live tail (LiveTail /
HasLiveTail / TaskMessageEvent) and scroll the terminal to end after the next
layout pass so wrapping lines aren't clipped.
BUNDLE — both fixes live in the Worker run-recording / persistence layer (where a TaskRun is written after an agent finishes), NOT in ExternalMcpService.cs. Keep this disjoint from the MCP-surface bundle so the two can run in parallel without worktree conflicts. The DTO fields (tokensIn, tokensOut, resultMarkdown) already exist and are surfaced by list_runs/get_run — the bug is at write time.
1.
ClaudeDo-Task: 49a6060a-5044-4f1b-8665-5cfc064b8a82
Unify the near-identical HandleFailure/MarkFailed into a single MarkFailed that
always persists the failed state and never throws, and replace the inline
null-if-blank checks in ListMcpTools with the existing extension.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
mika kuns