- 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 — 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
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
Add a "Max parallel executions" setting to the General settings tab so
the queue can run more than one task concurrently. QueueService now
tracks multiple active slots and reads the limit from app settings each
cycle, so changes take effect without restarting the worker.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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
Drop the removed tag system, fix the retired Manual status and the atomic
queue-claim location, refresh the App DI registrations to the Islands VMs,
update the Data table list, correct a stale test reference, and document the
interface-folder and single-consumer-fold conventions plus the .NET 8 build path.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
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>
Consolidate small single-purpose types into the files that own them:
StreamResult into StreamAnalyzer, the Planning context records into
PlanningSessionContext, PrimeClock/PrimeSchedulerOptions into PrimeScheduler,
AgentMcpTools into LifecycleMcpTools, the locator subclasses into
InstallArtifactLocator, LogLineViewModel into DetailsIslandViewModel,
RepoImportItemViewModel into its modal, and StepViewModel into InstallPageViewModel.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The PlanningMergeEvents record types were never instantiated (the broadcaster
uses identically-named methods), and RunNowRequestedEvent had no subscribers.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Move interface declarations into per-area Interfaces/ subfolders, merge the
small task-list filter classes into StatusFilter/SmartFlagFilter, and simplify
related services, converters and hub DTO handling.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Wire ListMcpTools, ConfigMcpTools, RunHistoryMcpTools, AgentMcpTools,
LifecycleMcpTools, and AppSettingsMcpTools into the external MCP
container and expose them via WithTools<>().
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- GetTaskLog reads at most last 256 KB; prepends truncation marker if file exceeds cap
- Wrap temp-file cleanup in finally block to prevent leak on assertion failure
- Add GetRun_NotFound_Throws, GetTaskLog_RunExistsButNoLogPath_Throws, and GetTaskLog_LargeFile_ReturnsTruncatedTail tests
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
