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
- Split FileDiff into FileDiff (metadata-only) and FileDiffDetail (with hunks)
so the phase branch diff no longer requires client-side diff parsing
- ReviewTab now reads diffQuery.data.files (FileStatEntry[]) and maps
path → newPath for sidebar and DiffViewer; no parseUnifiedDiff call
in the phase branch view path
- Commit view still parses rawDiff via parseUnifiedDiff → FileDiffDetail[]
- Pass phaseId, commitMode, comments, expandAll to DiffViewer
- Pass totalAdditions/totalDeletions from server to ReviewHeader stats bar
- Wire Expand all button in ReviewHeader to expandAll toggle state
- Update FileCard to use FileDiffDetail and status (replaces changeType)
- Update ReviewSidebar to use file.status instead of file.changeType
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Creates diff-cache.ts module with generic DiffCache<T> class (TTL, prefix
invalidation, env-var configuration) and exports phaseMetaCache / fileDiffCache
singletons. Wires cache into getPhaseReviewDiff via getHeadCommitHash on
BranchManager. Adds 6 unit tests for DiffCache and 5 integration tests
verifying cache hit/miss behaviour, prefix invalidation, and NOT_FOUND guard.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds windowed rendering to FilesView in ReviewSidebar.tsx using
react-window 2.x (List component). File lists with more than 50 rows
render only visible items, keeping the DOM lean for large diffs.
- Install react-window 2.x and @types/react-window in apps/web
- Flatten directory-grouped file tree into a typed Row[] array via useMemo
- Use VariableSizeList-equivalent react-window 2.x List with rowHeight fn
(32px for dir-headers, 40px for file rows); falls back to plain DOM
render for ≤50 rows to avoid overhead on small diffs
- Directories are collapsible: clicking the dir-header toggles collapse,
removing its file rows from the Row[] and from the virtual list
- Preserve sidebar scroll offset across Files ↔ Commits tab switches via
filesScrollOffsetRef passed from ReviewSidebar into FilesView
- Clicking a file calls listRef.scrollToRow({ index, align: "smart" })
to keep the clicked row visible in the virtual list
- Root-level files (directory === "") render without a dir-header,
preserving existing behavior
- Add resolve.dedupe for react/react-dom in vitest.config.ts to prevent
duplicate-React errors after local workspace package installation
- Add 6 Vitest + RTL tests covering: large-list DOM count, small-list
fallback, collapse, re-expand, tab-switch smoke, root-level files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Rewrites getPhaseReviewDiff to return file-level metadata (path, status,
additions, deletions) instead of a raw diff string, eliminating 10MB+
payloads for large repos. Adds getFileDiff for on-demand per-file hunk
content with binary detection via numstat. Multi-project initiatives
prefix file paths with the project name to avoid collisions.
Adds integration tests that use real local git repos + in-memory SQLite
to verify both procedures end-to-end (binary files, deleted files,
spaces in paths, error cases).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds FileStatEntry type and two new primitives to the BranchManager
port and SimpleGitBranchManager adapter, enabling split diff
procedures in the tRPC layer without returning raw multi-megabyte diffs.
- FileStatEntry captures path, status, additions/deletions, oldPath
(renames), and optional projectId for multi-project routing
- diffBranchesStat uses --name-status + --numstat, detects binary
files (shown as - / - in numstat), handles spaces in filenames
- diffFileSingle returns raw unified diff for a single file path
Integrates main branch changes (headquarters dashboard, task retry count,
agent prompt persistence, remote sync improvements) with the initiative's
errand agent feature. Both features coexist in the merged result.
Key resolutions:
- Schema: take main's errands table (nullable projectId, no conflictFiles,
with errandsRelations); migrate to 0035_faulty_human_fly
- Router: keep both errandProcedures and headquartersProcedures
- Errand prompt: take main's simpler version (no question-asking flow)
- Manager: take main's status check (running|idle only, no waiting_for_input)
- Tests: update to match removed conflictFiles field and undefined vs null
Add five new tRPC query procedures powering the Radar page's per-agent
behavioral metrics (questions asked, subagent spawns, compaction events,
inter-agent messages) plus the batch repository methods they require.
Repository changes:
- LogChunkRepository: add findByAgentIds() for batch fetching without N+1
- ConversationRepository: add countByFromAgentIds() and findByFromAgentId()
- Drizzle adapters: implement all three new methods using inArray()
- InMemoryConversationRepository (integration test): implement new methods
tRPC procedures added:
- agent.listForRadar: filtered agent list with per-agent metrics computed
from log chunks (questionsCount, subagentsCount, compactionsCount) and
conversation counts (messagesCount); supports timeRange/status/mode/initiative filters
- agent.getCompactionEvents: compact system init chunks for one agent (cap 200)
- agent.getSubagentSpawns: Agent tool_use entries with prompt preview (cap 200)
- agent.getQuestionsAsked: AskUserQuestion tool calls with questions array (cap 200)
- conversation.getByFromAgent: conversations by fromAgentId with toAgentName resolved
All 13 new unit tests pass; existing test suite unaffected.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
getHeadquartersDashboard had no section for active conflict agents,
so initiatives with a running conflict-* agent disappeared from all
HQ sections. Add resolvingConflicts array to surface them.
- `errand.get` now returns `conflictFiles: string[]` (always an array,
never null) with defensive JSON.parse error handling
- `errand.get` returns `projectPath: string | null` computed from
workspaceRoot + getProjectCloneDir so cw errand resolve can locate
the worktree without a second tRPC call
- Add `apps/server/db/repositories/drizzle/errand.test.ts` covering
conflictFiles store/retrieve, null for non-conflict errands, and
findAll including conflictFiles
- Update `errand.test.ts` mock to include getProjectCloneDir and fix
conflictFiles expectation from null to []
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Wires errand command group into CLI with start, list, chat, diff,
complete, merge, resolve, abandon, and delete subcommands. All
commands call tRPC procedures via createDefaultTrpcClient(). The
start command validates description length client-side (≤200 chars)
before making any network calls.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the errand workflow for small isolated changes that spawn a
dedicated agent in a git worktree:
- errand.create: branch + worktree + DB record + agent spawn
- errand.list / errand.get / errand.diff: read procedures
- errand.complete: transitions active→pending_review, stops agent
- errand.merge: merges branch, handles conflicts with conflictFiles
- errand.delete / errand.abandon: cleanup worktree, branch, agent
- errand.sendMessage: delivers user message directly to running agent
Supporting changes:
- Add 'errand' to AgentMode union and agents.mode enum
- Add sendUserMessage() to AgentManager interface and MockAgentManager
- MockAgentManager now accepts optional agentRepository to persist agents
to the DB (required for FK constraint satisfaction in tests)
- Add ORDER BY createdAt DESC, id DESC to errand findAll
- Fix dispatch/manager.test.ts missing sendUserMessage mock
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Aggregates all user-blocking action items into a single composite query:
- waitingForInput: agents paused on questions (oldest first)
- pendingReviewInitiatives: initiatives awaiting content review
- pendingReviewPhases: phases awaiting diff review
- planningInitiatives: active initiatives with all phases pending and no running agents
- blockedPhases: phases in blocked state with optional last-message snippet
Wired into appRouter and covered by 10 unit tests using in-memory Drizzle DB
and an inline MockAgentManager (no real processes required).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The errand agent can now write { "status": "questions", ... } to
signal.json to pause mid-task and ask the user for clarification.
The session ends cleanly; the user answers via UI or CLI; the system
resumes the agent with their answers via sendUserMessage.
Two changes:
- buildErrandPrompt: adds "Option B" explaining the questions signal
format and the resume-on-answer lifecycle, alongside the existing
inline-question approach.
- sendUserMessage: extends allowed statuses from running|idle to also
include waiting_for_input, so agents paused on a questions signal
can be resumed when the user replies.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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.
Implements three primitives needed before errand tRPC procedures can be wired up:
- agentManager.sendUserMessage(agentId, message): resumes an errand agent with a
raw user message, bypassing the conversations table and conversationResumeLocks.
Throws on missing agent, invalid status, or absent sessionId.
- writeErrandManifest(options): writes .cw/input/errand.md (YAML frontmatter),
.cw/input/manifest.json (errandId/agentId/agentName/mode, no files/contextFiles),
and .cw/expected-pwd.txt to an agent workdir.
- buildErrandPrompt(description): minimal prompt for errand agents; exported from
prompts/errand.ts and re-exported from prompts/index.ts.
Also fixes a pre-existing TypeScript error in lifecycle/controller.test.ts (missing
backoffMs property in RetryPolicy mock introduced by a concurrent agent commit).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace SESSION_STARTUP (full test suite run) and CONTEXT_MANAGEMENT
(progress file refs) with a minimal startup block (pwd, git status,
CLAUDE.md). Add skipPromptExtras option to SpawnAgentOptions to skip
inter-agent communication and preview deployment instructions. Conflict
agents now go straight to the resolution protocol — one post-resolution
test run instead of two.
Add 'resolving_conflict' to InitiativeActivityState and detect active
conflict agents (name starts with conflict-) in deriveInitiativeActivity.
Conflict resolution takes priority over pending_review since the agent
is actively working.
- Add resolving_conflict to shared types and activity derivation
- Include conflict agents in listInitiatives agent filter (name + mode)
- Map resolving_conflict to urgent variant with pulse in InitiativeCard
- Add merge: prefix to INITIATIVE_LIST_RULES for merge event routing
- Add spawnConflictResolutionAgent to INVALIDATION_MAP
- Add getActiveConflictAgent to detail page agent: SSE invalidation
Implements three primitives needed before errand tRPC procedures can be wired up:
- agentManager.sendUserMessage(agentId, message): resumes an errand agent with a
raw user message, bypassing the conversations table and conversationResumeLocks.
Throws on missing agent, invalid status, or absent sessionId.
- writeErrandManifest(options): writes .cw/input/errand.md (YAML frontmatter),
.cw/input/manifest.json (errandId/agentId/agentName/mode, no files/contextFiles),
and .cw/expected-pwd.txt to an agent workdir.
- buildErrandPrompt(description): minimal prompt for errand agents; exported from
prompts/errand.ts and re-exported from prompts/index.ts.
Also fixes a pre-existing TypeScript error in lifecycle/controller.test.ts (missing
backoffMs property in RetryPolicy mock introduced by a concurrent agent commit).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds an Output/Details tab bar to the agents page right-panel. The Details
tab renders AgentDetailsPanel, which surfaces agent metadata (status, mode,
provider, initiative link, task name, exit code), input files with a
file-picker UI, and the effective prompt text — all streamed via the new
getAgent/getAgentInputFiles/getAgentPrompt tRPC procedures.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- getAgentOutput now returns timestamped chunks ({ content, createdAt }[])
instead of a flat string, preserving DB chunk timestamps
- parseAgentOutput accepts TimestampedChunk[] and propagates timestamps
to each ParsedMessage
- AgentOutputViewer displays HH:MM:SS timestamps on text, tool_call,
system, and session_end messages
- Live subscription chunks get client-side Date.now() timestamps
- Fix horizontal scroll: overflow-x-hidden + break-words on content areas
- AgentLogsTab polls getTaskAgent every 5s until an agent is found,
then stops polling for live subscription to take over
- Fix slide-over layout: details tab scrolls independently, logs tab
fills remaining flex space for proper AgentOutputViewer sizing
The `getAgentPrompt` tRPC procedure previously read exclusively from
`.cw/agent-logs/<name>/PROMPT.md`. Once the cleanup-manager removes
that directory, the prompt is gone forever.
Adds a `prompt` text column to the `agents` table and writes the fully
assembled prompt (including workspace layout, inter-agent comms, and
preview sections) to the DB in the same `repository.update()` call
that saves pid/outputFilePath after spawn.
`getAgentPrompt` now reads from DB first (`agent.prompt`) and falls
back to the filesystem only for agents spawned before this change.
Addresses review comment [MMcmVlEK16bBfkJuXvG6h].
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
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()
Pre-merge mergeability check via `git merge-tree --write-tree` (dry-run, no
side effects). When conflicts exist the "Merge & Push" button is disabled and
a ConflictResolutionPanel shows conflict files with options to resolve manually
or spawn a conflict-resolution agent. Agent questions appear inline via
QuestionForm; on completion the mergeability re-checks automatically.
New server-side: MergeabilityResult type, BranchManager.checkMergeability,
conflict-resolution prompt, checkInitiativeMergeability query,
spawnConflictResolutionAgent mutation, getActiveConflictAgent query.
New frontend: useConflictAgent hook, ConflictResolutionPanel component,
mergeability badge + panel integration in InitiativeReview.
Adds a new mutation that accepts an email + raw OAuth token and upserts
the account — creating it if it doesn't exist, updating credentials if
it does. Covers all four scenarios with unit tests (new, existing,
empty-email, empty-token validation).
Snapshots were stale since migration 0008. Generated a schema-derived
snapshot at 0032 so drizzle-kit generate works again (zero diff on
current schema.ts). Also fixed migration 0032 to use statement-breakpoint
separator required by better-sqlite3.
- Added 0032_snapshot.json derived from current schema.ts
- Fixed 0032 SQL to use --> statement-breakpoint between statements
- Updated CLAUDE.md and database-migrations.md with correct workflow
drizzle-kit generate has been broken since migration 0008 (stale snapshots).
The actual workflow is hand-written SQL + manual _journal.json registration.
Updated CLAUDE.md and database-migrations.md to reflect reality and prevent
future migrations from silently failing to apply.
Completed phases showed "No phases pending review" because:
1. Frontend filtered only pending_review phases
2. Server rejected non-pending_review phases
3. After merge, three-dot diff returned empty (merge base moved)
Fix: store pre-merge merge base hash on phase, use it to reconstruct
diffs for completed phases. Frontend now shows both pending_review and
completed phases with read-only mode (Merged badge) for completed ones.
Adds exitCode to AgentInfo type and propagates it through all toAgentInfo()
implementations. Enhances getAgent to also return taskName and initiativeName
from their respective repositories. Adds two new filesystem-reading tRPC
procedures for the Agent Details tab: getAgentInputFiles (reads .cw/input/
files with binary detection, 500 KB cap, sorted) and getAgentPrompt (reads
.cw/agent-logs/<name>/PROMPT.md with 1 MB cap and structured ENOENT handling).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
