- 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
TanStack Router plugin was picking up test files under routes/__tests__/,
causing routeTree.gen.ts to regenerate in a loop. Added routeFileIgnorePattern
and removed stale radar.test.tsx.
Add isAgentRunning prop to all four radar drilldown dialog components.
When true, subscribe to relevant SSE events and trigger refetch on
matching events for the current agentId. Show a "Last refreshed: just now"
timestamp that ticks to "Xs ago" in the dialog footer. Reset on close.
- CompactionEventsDialog, SubagentSpawnsDialog, QuestionsAskedDialog:
subscribe to agent:waiting events
- InterAgentMessagesDialog: subscribe to conversation:created and
conversation:answered events (matches on fromAgentId)
- Update DrilldownDialogProps type with isAgentRunning?: boolean
- Add test coverage for all new behavior across all four dialogs
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add isAgentRunning? to DrilldownDialogProps interface
- Import and render all four dialog components in RadarPage
- Replace MetricCell helper with per-type td elements using data-testid
attributes for reliable test targeting
- Add drilldown state (type/agentId/agentName) and isAgentRunning derivation
- Wire non-zero metric cell onClick handlers to open the correct dialog
- Zero cells retain no onClick handler
- Extend radar.test.tsx with 8 new dialog integration test cases covering
open/close behavior and isAgentRunning prop passing
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Adds "Radar" nav item to AppLayout between Agents and Inbox
- Creates /radar route with validateSearch for timeRange/status/initiativeId/mode filters
- Summary stat cards for questions, messages, subagents, compactions aggregates
- Agent activity table with client-side sorting on all 10 columns (default: started desc)
- Real-time SSE updates via useLiveUpdates invalidating agent namespace
- Loading skeleton (5 rows) and empty state messaging
- Non-zero metric cells show cursor-pointer for future drilldown dialogs
- 12-test suite covering rendering, sorting, filtering, nav, and states
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the remaining two Radar drilldown dialogs following the
established AddAccountDialog pattern. Both use tRPC lazy queries,
skeleton loading, and expandable rows via useState<number | null>.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements two Radar drilldown dialog components following the
AddAccountDialog pattern (Radix UI Dialog + tRPC lazy query + skeleton
loading). CompactionEventsDialog shows a simple table of compaction
events; SubagentSpawnsDialog adds expandable rows that reveal the full
Agent tool prompt. Shared DrilldownDialogProps type in types.ts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Re-recorded all 4 cassette files to reflect current prompt templates.
Added `workdir/**` to vitest exclude list to prevent test discovery
in agent worktree directories.
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.
Each SSE client registers a listener per event type (30+ types), so a
few concurrent connections easily exceed the previous limit of 100.
Listeners are properly cleaned up on disconnect via eventBusIterable's
finally block, so this is not a real leak.
Replace the original design document / brainstorm with a focused project
README covering what Codewalkers does, getting started, architecture,
supported providers, CLI reference, workflow, development, testing, and
links to detailed docs.
Replaces the placeholder body in apps/web/src/routes/hq.tsx with the
full Headquarters page. The component fetches from getHeadquartersDashboard,
subscribes to live SSE invalidations via useLiveUpdates, and renders the
four action sections or an empty state. Includes skeleton loading and
error-with-retry states. Also adds apps/web/src/components/ui/skeleton.tsx
(standard shadcn component not yet in the project).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Derives currentTodos from the most recent TodoWrite tool_call on each render
- Renders a TASKS strip between the header and scroll area with status icons
(CheckCircle2 for completed, Loader2/animate-spin for in_progress, Circle for pending)
- Caps the strip at 5 rows and shows "+ N more" for overflow
- Updates collapsed tool_result preview to show "{subagent_type} result" for
Task tool results instead of the raw first-80-chars substring
- Adds 10 new tests covering all todo strip states and Task preview variants
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Extend ParsedMessage.meta with toolInput to expose raw tool arguments
- Add toolUseRegistry to correlate tool_result blocks back to originating tool_use
- Set toolInput on tool_call messages and populate meta.toolName/toolInput on tool_result
- Fix tool_result with is_error:true now correctly produces type "error"
- Add catch-all for unknown top-level event types (emits system message)
- Add catch-all for unknown assistant content block types (emits system message)
- Add unit tests covering all 8 scenarios including regression cases
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
tool_result messages now render as a single collapsible preview line
(ChevronRight + first 80 chars) and expand on click to show full content.
system messages drop the Badge/border-l and render as a dim mono inline
line. expandedResults state resets when agentId changes.
Adds full test coverage in AgentOutputViewer.test.tsx (9 tests).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements the five section components consumed by the HQ page:
- HQWaitingForInputSection, HQNeedsReviewSection, HQNeedsApprovalSection,
HQBlockedSection, HQEmptyState with typed props from RouterOutputs.
- Shared types.ts defines the 5 item types from getHeadquartersDashboard.
- Adds RouterOutputs export to trpc.ts via inferRouterOutputs<AppRouter>.
- 22 unit tests verify rendering, navigation CTAs, truncation, and edge cases.
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>
- Create apps/web/src/routes/hq.tsx with HeadquartersPage shell component
- Add "HQ" as first entry in AppLayout.tsx navItems array
- Change root redirect from /initiatives to /hq
- Regenerate routeTree.gen.ts with the new /hq route
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
retryBlockedTask was not in the centralized invalidation map, so the
mutation succeeded server-side but the UI never refreshed. Also changed
the button to wait for the mutation response before closing the slide-over
and show a loading spinner.
The `get(id)` method on SimpleGitWorktreeManager used `path.endsWith(id)`
to find worktrees. Since all agents working on the same project create
worktrees with the same project name suffix (e.g., "codewalk-district"),
cleanup for one agent could match and delete another agent's worktree.
Fix: match on `basename(worktreesDir)/id` so each manager's lookups are
scoped to its own worktree base directory.
- Adds syncAllMutation calling trpc.syncAllProjects once for all cards
- Shows Sync All button in header when ≥1 project exists (hidden otherwise)
- Propagates isPending to ProjectCard.syncAllPending to disable per-card sync
- On success: toasts all-success or failure count; invalidates listProjects + getProjectSyncStatus per project
- On network error: toasts Sync failed with err.message
- Adds unit tests for ProjectSyncManager.syncAllProjects: empty list, all succeed, partial failure, result shape, and failure counting logic
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Previously a single "that name or URL" message was thrown regardless of which
column violated uniqueness. Now the catch block inspects the error string from
SQLite to emit a name-specific or url-specific message, with a generic fallback
when neither column can be identified.
Adds vitest tests covering all four scenarios: name conflict, url conflict,
unknown column conflict, and non-UNIQUE error passthrough.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
prevStateRef was initialized with current state, so when the page loaded
with an already-idle conflict agent, the transition guard was immediately
false and dismiss() never fired. Initialize with null instead.
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.
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.
