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.
preview_merge/preview_merge_set now report isEmpty (ahead==0, or
HandlerBaseCommit==HandlerHeadCommit for a worktree-less list-handler
task) instead of leaving an empty branch indistinguishable from a small
one. preview_merge also stops throwing for worktree-less handler tasks,
falling back to their fixed commit range. review_task's parent approve
returns emptyChildren, naming the Done children whose review range
contributed nothing before the unit merge lands. TaskRefDto/TaskDto now
expose roadblockCount so a CLAUDEDO_BLOCKED child is identifiable over
MCP, since it still reaches Done per the unified parent model.
WaitingForChildren already counted as "changed" since it's outside Queued/Running,
so waiting on a planning parent returned immediately even though its children were
still running. The new opt-in flag (default false, unchanged behavior) keeps polling
through WaitingForChildren and only reports changed once the parent reaches
WaitingForReview or a terminal status.
list_tasks on a list of ~100 verbosely-described tasks could return
390k+ characters in one call, blowing past the caller's token limit.
Both tools now default to lean TaskRefDto references (no
Description/Result) and take an includeDescription flag to opt back
into the full TaskDto payload — same flag-alongside-nullable-payload
idiom already used by BatchGetTaskResult/TaskConfigResult. get_task is
unchanged.
add_task and batch_add_tasks now report up to 3 open (non-terminal)
tasks in the same list with a strongly overlapping title, so a
parallel agent can notice and mention a likely duplicate instead of
silently creating one. The task is always created regardless. Uses a
cheap normalized-word overlap heuristic (no embeddings/LLM call),
robust to German umlaut/digraph spelling variants. Breaking change:
AddTask now returns AddTaskResult { task, possibleDuplicates } instead
of a bare TaskRefDto; BatchAddTaskResult gained a PossibleDuplicates
field.
AgentStripView was superseded by WorkConsole during the task-detail
redesign but never wired into any view and never deleted. Drops the
unused Border.agent-strip / diff-meter styles and the 14 agent.* locale
keys that only it referenced, and marks A4 in the feature-unification
spec as resolved by deletion.
List settings were reachable via three doors (header button, context
menu, double-click). Drop the context menu entry, matching the same
cut already made for the "Let Claude handle it" entry point.
review-merge: worktree-less approvals run the gate too, and all three UI merge
entry points handle verify_failed explicitly.
Ui gotchas: NumericUpDown.Value is decimal? and nulls while the box is empty.
A task selected before its run started kept LatestRunSessionId null, so the
roadblock reply box and Continue stayed dead until it was re-selected.
The handoff left the Phase 1-2 tile open so its last message could be read, but
its process is gone by then and the terminal renders empty -- a dead
placeholder. It is closed on handoff now.
Also drops the WARN flood from worktree cleanup (already-unregistered worktree
and already-deleted branch are normal outcomes, not failures) and replaces the
fixed sleep in UsageGate_TransitionLogging_FiresOncePerChange with the polling
helper that already sits three lines below it in the same file.
The app is dark-only (App.axaml pins RequestedThemeVariant="Dark", Tokens.axaml
has no light variant), so every "Dark/Light" line was unverifiable by
construction. Adds the roadblock-reply session-id finding from the same pass.
Verified: max-turns hints, usage pill/modal, list-handler run end to end.
New findings: NumericUpDown null binding throws in the settings modal, the
verify gate is skipped for worktree-less tasks and unhandled in two of three
merge entry points, the handoff leaves an empty pane, worktree cleanup logs
already-done as WARN, orphaned git worktrees are invisible to the app, modal
bodies are clipped at the bottom, usage tables need formatting work.
Ten of the twelve listed bugs/nits are fixed in the code (outcome JSON,
subtask terminology, live child rows, AskUser in the detail island, Icon.Plus,
gear glyph, rename display, TurnsText, conflict Continue gate, ConPTY resume)
and the blocked-approve silent fail is handled by the WorkerHub throw. Adds the
open verification block for the planning-resume fix.
Der Button, der aus „Problem erkannt" ein „Problem gelöst" macht: startet eine interaktive Claude-Session, die dem Nutzer beim Einrichten hilft.
## Warum externes Terminal
Der ConPTY-Stack (`PtyTerminalSession`, `ConPtyPaneView`) liegt in `ClaudeDo.Ui` und ist Avalonia — der Installer ist WPF und referenziert nur Data/Releases/Localization. Beim Fresh Install sind `app\`/`worker\` außerdem noch n
ClaudeDo-Task: 4e196058-38a3-404f-9862-4cb0e90195da
Re-runs the environment checks against the installed configuration
(worker.config.json + detected install dir) without blocking navigation
and without auto-running on window open, only on a "Recheck" click.
Extracted the check-row rendering and check-run logic (busy state,
summary, Recheck command) out of SystemCheckPage into a shared
Checks/CheckListViewModel + Checks/CheckListView, composed by both
SystemCheckPage (wizard) and the new DiagnosePage (settings) instead
of duplicating it.
Documents the Checks/ + SystemCheckPage feature (gating rule, check list,
FreshInstall-only placement) and the ExecutableResolver/.cmd-shim wiring in
ClaudeDo.Worker's ClaudeCliPreflight/ClaudeProcess. Adds docs/explore-notes/installer-preflight.md
(bumped/corrected against the actual implementation) and links it from the
explore-notes README and root CLAUDE.md.
The underlying code lives only on unmerged task branches (06aca9b3.../40272c0b...),
not on main yet, and two follow-up features ("Claude Help Me" button, Config-mode
Diagnose section) were never implemented because they blocked on that same missing
merge. Both gaps are called out explicitly in the new docs and in docs/open.md's
verification checklist, instead of being asserted as done.
MaxTimeoutSeconds was 170s against runs that take tens of minutes, forcing
a dozen full-context wait rounds per long-running batch. Raise it to 900s
and raise MCP_TOOL_TIMEOUT in lockstep (ClaudeProcess + every
InteractiveLaunchSpecService launch spec) to 930000ms so the client
connection actually stays open that long instead of aborting first.
Add get_queue_state (QueueStateMcpTools): configured vs. effective
parallel-slot count (via QueueService.GetSlotCountsAsync, extracted from
the former GetEffectiveMaxParallelAsync), active slots with taskId +
startedAt including the run_task_now override slot, and queued tasks in
pick order -- so a caller can observe queue occupancy instead of inferring
it from maxParallelExecutions.
Adds a read-only get_effective_run_config(taskId) tool that reports the
model/max-turns/effort/permission-mode/agent-path/system-prompt/skills a
task will actually run with, each tagged with its source (task/list/
preset/global), plus max-turns' raw requested value and clamp status.
Extracted the model/max-turns/agent-path resolution out of
TaskRunner.ResolveConfigAsync into EffectiveRunConfigResolver so the run
path and the new reporting tool share one codepath instead of risking
drift, per docs/explore-notes/worker-task-pipeline.md's max-turns trap.
## Der Zweifel
Ein autonomer Agent und eine interaktive Session sollen sich unterschiedlich verhalten. Unklar war, ob beide denselben System-Prompt mitbekommen.
## Vorbefund (2026-08-05, beim Verfeinern erhoben — **selbst nachpruefen, nicht uebernehmen**)
Sie teilen ihn **nicht**. Pro Startweg:
| Startweg | Einstieg | System-Prompt |
|---|---|---|
| Autonomer Run | `ClaudeArgsBuilder.cs:69-73`
ClaudeDo-Task: b259a1c9a73846ce833f0b555fb1de79
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.
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.
All three brief tasks and the nine-child Usage Monitor unit are merged and main
verified green. Correct section 5: "exited with code 1 and no result" is a
catch-all, not a CLI crash — max_turns (sonnet presets default to 30 because
app_settings.model_presets is NULL) and the account session limit both surface
through the same message.
Add a dedicated Usage Monitor & Gate section to Worker CLAUDE.md, wire
UsagePillViewModel/UsageMonitorModalViewModel and the new IWorkerClient
usage surface into Ui CLAUDE.md, and record open verification points
for the pill/modal visual pass and the real gate E2E in docs/open.md.
Data CLAUDE.md already covered the new entity columns and migration.
A task that reports a roadblock but finishes successfully (Done/WaitingForReview/
Failed/Cancelled) had no way to answer it short of a full reset-and-rerun, losing
the run's context. Adds a reply textbox + Send button to the existing ROADBLOCK
card, modeled on the AskUser question card, that resumes the session via
ContinueTaskAsync with the user's own text. Gated on LatestRunSessionId (disabled
with a hint when there's nothing to resume); failures surface through the footer
error strip instead of a modal.
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.
"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.
mika kuns