Previously, branch computation errors and ensureBranch failures were
silently swallowed for all tasks, allowing execution agents to spawn
without proper git isolation. This caused alert-pony to commit directly
to main instead of its task branch.
- manager.ts: Verify each project worktree subdirectory exists after
createProjectWorktrees; throw if any are missing. Convert passive
cwdVerified log to a hard guard.
- dispatch/manager.ts: Make branch computation and ensureBranch errors
fatal for execution tasks (execute, verify, merge, review) while
keeping them non-fatal for planning tasks.
Three bugs causing empty phase diffs when server restarts during agent
execution:
1. Startup ordering race: reconcileAfterRestart() emitted agent:stopped
before orchestrator registered listeners — events lost. Moved
reconciliation to after orchestrator.start().
2. Stuck in_progress tasks: recoverDispatchQueues() only re-queued
pending tasks. Added recovery for in_progress tasks whose agents
are dead (not running/waiting_for_input).
3. Branch force-reset destroys work: git branch -f wiped commits when
a second agent was dispatched for the same task. Now checks if the
branch has commits beyond baseBranch before resetting.
Also adds:
- agent:crashed handler with auto-retry (MAX_TASK_RETRIES=3)
- retryCount column on tasks table + migration
- retryCount reset on manual retryBlockedTask()
Task dispatch computed baseBranch as the phase branch name but never
ensured it existed in the git clone. When phases weren't dispatched
through the PhaseDispatchManager (which creates branches), the
git worktree add failed with "fatal: invalid reference".
Now DefaultDispatchManager calls ensureBranch for both the initiative
and phase branches before spawning, matching what PhaseDispatchManager
already does.
Blocked tasks (from spawn failures) were a dead-end with no way to
recover. Add retryBlockedTask to DispatchManager that resets status
to pending and re-queues, a tRPC mutation that also kicks dispatchNext,
and a Retry button in the task slide-over when status is blocked.
Task-level approval (requiresApproval, mergeRequiresApproval,
pending_approval status) was redundant with executionMode
(yolo vs review_per_phase) and blocked the orchestrator's
phase completion flow. Tasks now complete directly;
phase-level review via executionMode is the right granularity.
Removed: schema columns (left in DB, removed from Drizzle),
TaskPendingApprovalEvent, approveTask/listPendingApprovals
procedures, findPendingApproval repository method, and all
frontend approval UI.
Wrap agentManager.spawn() in try/catch — on failure, block the task
instead of crashing the entire dispatch cycle. Move phase status update
to after branch creation succeeds — on branch failure, block the phase
and skip task queuing. Fix statement-breakpoint markers in migration
0020 to use separate lines.
- Add PhaseChangesRequestedEvent to event bus
- Add requestChangesOnPhase() to ExecutionOrchestrator: reads unresolved
comments, creates revision task (category='review'), resets phase to
in_progress, queues task for dispatch
- Expand merge-skip and branch routing to include 'review' category so
revision tasks work directly on the phase branch
- Add requestPhaseChanges tRPC procedure (reads comments from DB)
- Wire frontend: mutation replaces stub handler, window.prompt for
optional summary, loading state on button
Execution agents were spawning blind — no input files, no knowledge of
what predecessor tasks accomplished. This adds three capabilities:
1. summary column on tasks table — completeTask() reads the finishing
agent's result.message and stores it on the task record
2. dispatchNext() gathers full initiative context (initiative, phase,
sibling tasks, pages) and passes it as inputContext so agents get
.cw/input/task.md, initiative.md, phase.md, and context directories
3. context/tasks/*.md files now include the summary field in frontmatter
so dependent agents can see what prior agents accomplished
When an agent asks a question via `cw ask` targeting an idle agent,
the conversation router now auto-resumes the idle agent's session so
it can answer. Previously, questions to idle agents sat unanswered
forever because target resolution only matched running agents.
Changes:
- Add `resumeForConversation()` to AgentManager interface and implement
on MultiProviderAgentManager (mirrors resumeForCommit pattern)
- Relax createConversation target resolution: prefer running, fall back
to idle (was running-only)
- Trigger auto-resume after conversation creation for idle targets
- Add concurrency lock (conversationResumeLocks Set) to prevent
double-resume race conditions
Move src/ → apps/server/ and packages/web/ → apps/web/ to adopt
standard monorepo conventions (apps/ for runnable apps, packages/
for reusable libraries). Update all config files, shared package
imports, test fixtures, and documentation to reflect new paths.
Key fixes:
- Update workspace config to ["apps/*", "packages/*"]
- Update tsconfig.json rootDir/include for apps/server/
- Add apps/web/** to vitest exclude list
- Update drizzle.config.ts schema path
- Fix ensure-schema.ts migration path detection (3 levels up in dev,
2 levels up in dist)
- Fix tests/integration/cli-server.test.ts import paths
- Update packages/shared imports to apps/server/ paths
- Update all docs/ files with new paths
