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.
Phase 0 forced a batch_get_tasks full-fetch across every task just to see
descriptions, which blew past the client's token limit on larger lists.
brief.md lives on disk and has no such limit, so descriptions now render
there directly (fenced with an extended backtick run, indented under the
list bullet, so embedded headings/lists/code fences can't break the task
list's own structure). Phase 0 now treats the brief as the primary source
and only falls back to batch_get_tasks for fields it doesn't carry.
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).
"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.
Both packages restore and build cleanly at 2.1.0 (no NU1605/NU1701,
transitive Hosting/Caching.Abstractions bump to 10.0.10 resolves without
conflict). WithHttpTransport/WithRequestFilters/AddCallToolFilter/MapMcp
APIs are unchanged, so no code in External/ or Planning/ needed touching.
All 699 Worker.Tests pass.
The list-handler prompt (MergeHelperDefault) tells the handler to read
maxParallelExecutions via get_app_settings, but the DTO never carried
the field. Handler had to fall back to reading app_settings directly
from the DB on the 2026-07-29 E2E run.
## 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
External tasks finished outside a ClaudeDo run had no way to close out
their tracking task; update_task_status now permits Done alongside
Idle/Queued/Cancelled, refusing it when the task has an active
worktree so review_task stays the only path that merges.
Reminders written down as todos had no home: every task looked like Claude work.
A manual task now shows a MANUAL badge and hides send-to-queue, refine and the
planning session; the queue picker, daily prep and the list handler all skip it,
with a TaskStateService guard so the MCP surface and hub cannot start one either.
Opening a hand-driven ConPTY session stays available on purpose.
A list can be marked manual in its settings, which makes tasks created there
(UI and MCP add_task) start out manual. Toggle per task from its context menu.
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.
An embedded ConPTY session leaves its worktree changed but never touches
task status, so hand-driven work had no path into the review/merge flow.
Add SubmitTaskForReview: commit the worktree (same auto-commit as a headless
run), then transition Idle/Failed -> WaitingForReview via the new
TaskStateService.SubmitInteractiveForReviewAsync. Approve then merges it.
Surfaces: a 'Submit for review' button in the detail work console (shown for
an Idle/Failed task with a worktree) and on the ConPTY Command Center pane
header (task-based panes; closes the pane on success). Tests cover the new
transition (Idle/Failed accepted, Running/Queued/Done/Review rejected).
Interactive planning sessions launched with --permission-mode plan, which
gates EVERY MCP tool call regardless of --allowedTools (verified: even a
read-only mcp__claudedo__list_task_lists is denied under plan mode). So the
session prompted the user on the first CreateChildTask -- the whole point of
a planning session.
Switch BuildPlanningStartArgs/BuildPlanningResumeArgs to --permission-mode
default, which honours the allowlist. File edits stay blocked via the planning
system prompt + AllowedTools omitting Write/Edit/Bash. Resume also re-passes
--allowedTools, since the CLI does not restore it across --resume.
The earlier 'glob does not match' hypothesis was empirically falsified:
mcp__claudedo__*, the bare server name, and the explicit tool name all allow
the tool with zero permission_denials in default mode.
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.
- 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.
HasChangesAsync counted untracked files, so a stray file in the shared
target working dir (e.g. left by a concurrent session) blocked merge
preflights even though nothing tracked changed. Add an includeUntracked
overload defaulting to true, and pass includeUntracked: false only from
the two target-working-tree merge preflights (TaskMergeService.MergeAsync,
PlanningMergeOrchestrator.StartAsync). Auto-commit and the worktree
cleanup data-loss guard keep counting untracked files, since those
callers need to know about them.
- GitService.MergeFfOnlyAsync had no callers anywhere in code; removed.
- AgentMcpTools moved out of LifecycleMcpTools.cs into External/AgentMcpTools.cs (no behavior change).
- Worker CLAUDE.md described ZitadelAuthProvider as a Phase 2 stub; it's fully implemented (OIDC discovery + refresh-token flow), updated both mentions.
git add -A resolves the index U-stage regardless of file content, so a
conflicted file whose markers were never removed still got staged and
committed as-is. Check previously-conflicted files for leftover
<<<<<<< markers before staging; refuse with a conflict result if any
remain, leaving the repo mid-merge so Abort still cleans up.
Adds a regression test that leaves one conflict unresolved and asserts
ContinueMergeAsync refuses (no commit) and AbortMergeAsync still
restores a clean tree.
Confirmed via docs/open.md (Korrektheits-Review 2026-06-09): TaskStateService.CancelAsync
only flipped the target row to Cancelled - a Queued/Running child kept going and could
still commit into its worktree after the parent was gone.
CancelAsync now also cancels the task's own non-terminal children (Idle/Queued/Running/
WaitingForReview/WaitingForChildren) in the same pass, clearing BlockedByTaskId so no
successor is left wedged, and broadcasts TaskUpdated for each.
DeleteTask never re-evaluated a WaitingForChildren parent, so deleting
the last non-terminal child left it stuck (the BlockedByTaskId SET NULL
FK only repairs the blocked chain, not parent status). Expose
TaskStateService.TryAdvanceParentAsync on the interface and call it
from ExternalMcpService.DeleteTask after a child delete.
OnChildFinishedAsync ignored CancelAsync's result. If a chain successor
sat in a non-cancellable state (e.g. parked to Idle out of band) when
its predecessor failed/was cancelled, CancelAsync was a silent no-op and
the cascade stopped there, leaving the rest of the chain Queued+blocked
forever. Now it walks past any link CancelAsync can't touch and keeps
cancelling downstream.
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.
mika kuns