When an execute-mode agent stops with task_complete and the initiative has
qualityReview=true, the orchestrator now spawns a fresh execute-mode agent
to run /simplify on changed .ts/.tsx/.js files before marking the task
completed. The task transitions through quality_review status as a recursion
guard so the review agent's stop event is handled normally.
- Add apps/server/execution/quality-review.ts with three exported functions:
computeQualifyingFiles, shouldRunQualityReview, runQualityReview
- Add apps/server/execution/quality-review.test.ts (28 tests)
- Update ExecutionOrchestrator to accept agentManager, replace
handleAgentStopped with quality-review-aware logic, add getRepoPathForTask
- Update orchestrator.test.ts with 3 quality-review integration tests
- Update container.ts to pass agentManager to ExecutionOrchestrator
- Update docs/dispatch-events.md to reflect new agent:stopped behavior
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Three fixes for phases getting stuck when a detail task crashes and is retried:
1. detailPhase mutation (architect.ts): clean up orphaned pending/in_progress
detail tasks before creating new ones, preventing duplicates at the source
2. orchestrator recovery: detect and complete stale duplicate planning tasks
(same category+phase, one completed, one pending)
3. ensureBranch: catch "already exists" TOCTOU race instead of blocking phase
When an initiative has multiple end phases (leaf nodes with no
dependents), queueAllPhases now auto-creates an Integration phase
that depends on all of them. This catches cross-phase incompatibilities
(type mismatches, conflicting exports, broken tests) before review.
- Remove original task blocking in handleConflict (task is already completed by handleAgentStopped)
- Return created conflict task from handleConflict so orchestrator can queue it for dispatch
- Add dedup check to prevent duplicate resolution tasks on crash retries
- Queue conflict resolution task via dispatchManager in mergeTaskIntoPhase
- Add recovery for erroneously blocked tasks in recoverDispatchQueues
- Update tests and docs
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()
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.
ExecutionOrchestrator now listens for phase:queued and agent:stopped
events to drive the dispatch cycle, closing the gap between queueing
phases (Execute button) and actually spawning agents. Coalesced
scheduling prevents reentrancy with synchronous EventEmitter.
Introduces a chat loop where users send instructions to an agent that
applies changes (create/update/delete phases, tasks, pages) and stays
alive for follow-up messages. Includes schema + migration, repository
layer, chat prompt, file-io action field extension, output handler chat
mode, revert support for deletes, tRPC procedures, events, frontend
slide-over UI with inline changeset display and revert, and docs.
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
Enables parallel agents to communicate through a CLI-based conversation
mechanism coordinated via tRPC. Agents can ask questions to peers and
receive answers, with target resolution by agent ID, task ID, or phase ID.
Preview deployments let reviewers spin up the app at a specific branch
in local Docker containers, accessible through a single Caddy reverse
proxy port. Docker is the source of truth — no database table needed.
New module: src/preview/ with config discovery (.cw-preview.yml →
compose → Dockerfile fallback), compose generation, Docker CLI wrapper,
health checking, and port allocation (9100-9200 range).
Planning tasks (research, discuss, plan, detail, refine) have their own
architect flow and should never enter the dispatch pipeline or clutter
agent context. Three changes:
1. Phase auto-queue skips planning-category tasks
2. Safety net in getNextDispatchable() skips planning tasks
3. gatherInitiativeContext() filters to execution tasks only
Full rename across the codebase for clarity:
- breakdown (initiative→phases) is now "plan"
- decompose (phase→tasks) is now "detail"
Updates schema enums, TypeScript types, events, prompts, output handler,
tRPC procedures, CLI commands, frontend components, tests, and docs.
Also fixes 0022 migration multi-statement issue (adds statement-breakpoint markers).
