get_task/batch_get_tasks now return failureReason (max_turns|timeout|error|
cancelled|unknown) plus failureTurnsUsed/failureMaxTurns on a Failed task, so
max_turns (worktree usually fine, continue_task) is distinguishable from a
real error (reset_failed_task) without pulling get_task_log's raw NDJSON.
Classified and stamped onto TaskEntity by TaskRunner.MarkFailed via
TaskStateService.FailAsync; TaskRunEntity also keeps the CLI's raw
terminal_reason/result_subtype/errors for deeper diagnosis. reset_failed_task's
description now warns explicitly that it discards the worktree and points at
continue_task for max_turns. Surfaced on the task card's status-chip tooltip.
get_merge_conflicts and resolve_conflict_hunk let an MCP caller resolve a
leaveConflictsInTree merge hunk-by-hunk (ours/theirs/base/literal text)
instead of grep-parsing diff3 markers itself. Reuses the existing
TaskMergeService/ConflictMarkerParser machinery (adds MergeSegment.StartLine
and a non-staging TaskMergeService.WriteConflictFileAsync) rather than a
second parser. A partially resolved file is written without git add so
continue_merge keeps refusing while any hunk still has markers.
get_task_diff gained an optional paths param (git pathspec, both stat and
full-diff modes) so a large multi-file task can be narrowed to the files
actually in question instead of shipping the whole diff.
preview_merge_set now also reports Subsets: pairs where one task's changed
files are a proper subset of another's in the same set, the strongest
available post-hoc signal that a task may be redundant with another.
Before merging (or staging a conflict resolution's git add -A), compare the
branch's newly-added paths against what's currently untracked in the target
working directory. A collision aborts with a new untracked_collision status
naming the path and size, surfaced through merge_task/review_task,
preview_merge/preview_merge_set (which merge-tree alone can't see), and the
UI merge paths via FlashFooterError/ShowErrorAsync instead of a silent
catch{}. git's own preflight already refuses this while the path stays
untracked at merge time; this closes the gap once a path becomes trackable
in between (e.g. an unrelated conflict resolution's git add -A) or across
the continue_merge TOCTOU window.
preview_merge could only see file-overlap cleanliness via git merge-tree, never
whether the result compiles -- the two costliest findings of the 2026-08-06 batch
run were both merge-tree-clean but build-broken. When a list has a verify command
configured, a clean preview is now additionally materialized (via a commit-tree +
detached scratch worktree, outside the real repo, always cleaned up) and
built/tested there, without ever touching the real working tree.
preview_merge always attempts a verify run when a command is configured;
preview_merge_set only does when its new runVerify parameter is set (default off),
so a set preview never starts N builds unasked. The post-merge verify gate is
unchanged.
Every tool description now leads with what the tool does AND when to reach for
it, since MCP clients rank tools by that text. Per-parameter prose moved onto
the parameters as [Description], exhaustive result-shape enumerations and
design/history rationale dropped, and the repeated boilerplate clauses
(lean-task-ref, batch cap, refused-while-Running) pulled into McpToolDocs,
which also documents the style for future tools.
Tool-level description text: 20494 -> 13605 chars (-34%); combined with the new
parameter descriptions 18517 (-10%).
Closes gaps that caused wrong calls rather than just verbose ones:
- list_task_attachments returns metadata only, no file content
- run_task_now shares continue_task's single override slot and throws when busy
- list_runs is ordered oldest-first and feeds get_run
- workingDir on create_list/update_list is an existing local git repo path,
unvalidated until the first task run
- get_task_worktree's behind=0 also means the main ref was unreachable
Removes get_task_status_values: a whole tool entry for static reference text.
GetTask's description is now the canonical place for status meanings.
NormalizeTitleWords transliterates umlauts before tokenizing ('für' ->
'fuer'), but TitleStopWords listed 'fur' -- a token the pipeline can
never produce -- so 'für' was never filtered as filler and could push
unrelated titles past the near-duplicate threshold.
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.
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.
update_task, update_task_status, add_task, add_subtask, set_my_day,
abort_merge, review_task, and their batch variants now return a lean
TaskRefDto (id/listId/title/status/sortOrder/isMyDay) instead of the
full TaskDto. Those tools were re-sending the caller's own description
text back on every call, wasting a large share of session context on
list-handler-style runs. get_task/list_tasks/batch_get_tasks are
untouched and still return the full DTO.
Persists the merge commit SHA on WorktreeEntity for every successful
single-task and unit merge, and adds a TaskMergeService.RevertMergeAsync
+ revert_merge MCP tool that undoes a merged task's merge via
`git revert -m 1` (never reset/rewrite, since the target checkout is
shared). Rejects cleanly when there's no recorded SHA, the repo is
mid-merge/mid-revert, or the target has foreign uncommitted changes;
a conflicting revert aborts immediately. Also exposes the new
mergeCommit field via get_task_worktree.
Give an autonomous reviewer a non-destructive merge-tree preview
(status/conflicts/changedFileCount/behind) for a task's worktree branch,
plus a file-overlap check across a batch of tasks so same-file collisions
between sibling branches are visible before merging. MergeHelperDefault's
Phase 4 now calls preview_merge_set before merging a batch.
set_task_config/set_list_config now echo which fields were set vs cleared, get_list_config/get_task_config return an explicit found=false instead of null, and delete_list/run_task_now/reset_failed_task/remove_task_attachment return a confirmation record — matching the found/ok convention already used by batch_get_tasks and get_task_log.
"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.
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.
- 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.
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.
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>
Generalizes the previous merge_task fix: the WaitingForReview->Done transition
now lives in TaskMergeService.MergeAsync/ContinueMergeAsync, so the UI Merge
button (WorkerHub.MergeTask), conflict-merge, continue-merge and the external
MCP all land a merged task in Done. ApproveAndMergeAsync no longer double-approves.
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>
BUNDLE — all changes live in src/ClaudeDo.Worker/External/ExternalMcpService.cs only, so this is one worktree / one merge. Do NOT touch run-recording or data-layer code (those are separate tasks). Reuse the existing services behind the UI modals (WorktreesOverviewModalView, DiffModalView, MergeModalView) — do not reimplement git plumbing. Build green after each addition.
Add these MCP tools:
1. g
ClaudeDo-Task: f6bdfb5b-8cbf-4e65-93d4-6c758a160484
delete_task (and likely cancel_task) return no output on success. Silent success is indistinguishable from a no-op, so callers can't verify the action took effect.
Fix: return a small confirmation object, e.g. { deleted: true, id } / { cancelled: true, id }. Indicate not-found vs deleted distinctly.
ClaudeDo-Task: 97a87ebb-0d87-4ee0-800c-aa1a0b3a06c5
add_task currently marks description, createdBy, and queueImmediately as required, forcing callers to invent values for fields that have obvious defaults.
Fix: make them optional with sensible defaults — description: null, queueImmediately: false, createdBy: server default like "mcp". Keep only listId and title as truly required.
ClaudeDo-Task: b9fadf0b-a20e-4deb-932d-29ef9c0b83f3
Drops TagEntity, TagRepository, and tag wiring across data layer, worker,
and UI. Adds RemoveTags migration to clean up schema.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slice 6 of the worker state and queue consolidation refactor.
* Drop Manual, Planning, Planned, Draft, Waiting from the TaskStatus enum
and from the EF value converter; only the lifecycle values remain
(Idle, Queued, Running, Done, Failed, Cancelled).
* Add migration RetireLegacyTaskStatus that rewrites existing rows:
manual/draft -> idle, planning -> idle+planning_phase=active,
planned -> idle+planning_phase=finalized, waiting -> queued+blocked_by
derived from sort_order via a CTE with LAG().
* Reroute every call site that compared/set legacy values to the new
three-field model (Status + PlanningPhase + BlockedByTaskId), including
the planning repo helpers, MCP services, the planning chain coordinator,
and the UI view-models. TaskRowViewModel now exposes PlanningPhase to
drive the planning badge.
* Refresh Worker/CLAUDE.md and Data/CLAUDE.md, the docs/plan.md status
section, and the planning verification notes in docs/open.md.
Slice 5 of the worker state consolidation refactor.
OverrideSlotService (new in Worker/Queue/) owns RunNow, ContinueTask,
and the override-slot piece of CancelTask. QueueService keeps the
queue-slot guard for "task is already running" rejection and delegates
to OverrideSlotService for execution; CancelTask tries the override
slot first, then the queue slot. QueueSlotState is extracted to its own
file.
Folder reorg (via git mv to preserve history):
- Worker/Queue/ QueueService, OverrideSlotService, QueueSlotState
(alongside existing waker/picker)
- Worker/Lifecycle/ StaleTaskRecovery, TaskResetService, TaskMergeService
- Worker/Worktrees/ WorktreeMaintenanceService
- Worker/Agents/ AgentFileService, DefaultAgentSeeder
Worker/Services/ folder removed. All consumers updated to the new
namespaces (Program.cs, WorkerHub, ExternalMcpService,
PlanningMergeOrchestrator, all Worker tests).
OverrideSlotService is registered as a DI singleton in both the main
worker app and the external MCP app.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slice 3 of the worker state and queue consolidation refactor.
- Add IQueueWaker / QueueWaker (singleton holding the wake semaphore).
- Add IQueuePicker / QueuePicker; raw SQL UPDATE...RETURNING moves out of
TaskRepository.GetNextQueuedAgentTaskAsync (deleted) and now also filters
on blocked_by_task_id IS NULL and writes started_at on claim.
- TaskStateService takes IQueueWaker directly; the Func<QueueService>
indirection is gone. State transitions to Queued auto-wake the dispatcher.
- QueueService waits via the shared waker and dispatches via the picker.
- Drop explicit _queue.WakeQueue() calls in WorkerHub.QueuePlanningSubtasksAsync
and ExternalMcpService.AddTask. The hub WakeQueue endpoint stays for
diagnostics, delegating to _waker.Wake().
- Migrate tests; pre-existing flaky AppSettings/ExternalMcp tests untouched.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Slice 2 of the worker state consolidation refactor (spec sections 2 and 8).
Adds Worker/State/ITaskStateService + TaskStateService as the single component
that mutates Status, PlanningPhase, and BlockedByTaskId. Each transition is one
atomic ExecuteUpdate with a WHERE filter on the expected source status, so
parallel claims are TOCTOU-free. Side effects (queue wake on -> Queued, hub
TaskUpdated broadcast, chain advance + parent completion on terminal child)
are owned by the service so callers no longer need to remember them.
Migrated callers (mechanical, behavior preserved):
- TaskRunner: HandleSuccess/HandleFailure/MarkFailed/RunAsync/ContinueAsync
- StaleTaskRecovery: bulk recover stale Running tasks
- TaskResetService: status flip (worktree cleanup stays in service)
- PlanningSessionManager.StartAsync: status flip via state, token write via repo
- PlanningChainCoordinator.OnChildFinishedAsync: routes the next-sibling write
through state.UnblockAsync (Slice 4 finishes the rewrite)
- ExternalMcpService.UpdateTaskStatus: Queued case via state.EnqueueAsync
Repo Mark*Async helpers (MarkRunning/MarkDone/MarkFailed/FlipAllRunningToFailed)
are now internal; ClaudeDo.Data grants InternalsVisibleTo to ClaudeDo.Worker
and ClaudeDo.Worker.Tests for the existing repo-level tests.
DI: TaskStateService is registered as Singleton in both the main app and the
external-MCP app; the queue-wake delegate captures sp -> QueueService.WakeQueue
to break the TaskStateService -> QueueService -> TaskRunner -> TaskStateService
construction cycle. PlanningChainCoordinator takes Func<ITaskStateService> for
the same reason; Slice 3 will replace both with IQueueWaker.
Tests: TaskStateServiceTests covers happy + reject for every transition, the
parallel StartRunningAsync claim race, child-terminal chain advancement, and
stale recovery. Existing service/repo tests are updated to construct the new
state-service via a TaskStateServiceBuilder helper. Pre-existing constructor
drift in QueueService/ExternalMcp/PlanningHub tests is patched to keep the
test project building (the surrounding test logic is otherwise untouched).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
mika kuns