- Added relativePath field to ImageDetectedEvent
- Compute relative path from working directory in image-watcher
- Use relativePath in frontend URL (fixes 'Failed to load image' for subdirs)
- Minor CLAUDE.md improvements
chore: bump version to 0.1461
Implements the Execution Optimizer Rework plan that enables the system
to actually use the optimizer metadata (parallelGroups, agentType,
recommendedModel, requiresFreshContext, estimatedTokens) that was
previously generated but ignored.
New components:
- ExecutionBridge: Central coordinator that loads optimized plans,
manages parallel execution within groups, and coordinates with
SpawnOrchestrator for session-based execution
- ModelSelector: Routes tasks to appropriate models (opus/sonnet/haiku)
based on user defaults and agent type overrides. Optimizer
recommendations are advisory only - user preferences always win
- GroupScheduler: Builds topologically ordered execution groups,
manages dependencies, determines execution mode (session vs task-tool)
- ContextManager: Handles fresh context requirements via /clear+/init
or new session spawning
Features:
- Parallel task execution within groups (configurable limit)
- Group-level dependency tracking (lower groups complete first)
- Partial failure handling (continue with non-dependent tasks)
- Model configuration in App Settings > Models tab
- Agent type overrides (explore, implement, test, review)
- Execution control API endpoints (start, pause, resume, cancel)
- SSE events for real-time execution progress visibility
- Execution history tracking
API endpoints:
- GET/POST/PUT /api/execution/* for execution control
- GET/PUT /api/execution/model-config for model settings
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Disposable, BufferConfig, MemoryMetrics, CleanupRegistration types
- Create src/config/buffer-limits.ts with consolidated buffer size constants
- Create src/config/map-limits.ts with Map size limits to prevent unbounded growth
- Implement BufferAccumulator utility with configurable trim and onTrim callback
- Implement LRUMap with automatic eviction and O(1) operations
- Implement CleanupManager for unified resource cleanup with isStopped guard
- Add comprehensive tests for all new utilities
This lays the foundation for memory leak prevention and performance improvements.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements image file watching in session working directories with
automatic popup display in the web UI:
- Add ImageWatcher class using chokidar for cross-platform file watching
- Add ImageDetectedEvent type for SSE broadcasting
- Integrate with session lifecycle (watch on create, unwatch on delete)
- Add image:detected SSE event handler in frontend
- Create draggable image popup window with open-in-new-tab support
- Add CSS styling with compact wizard layout
Supports: png, jpg, jpeg, gif, webp, bmp, svg
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
CPU Limiting:
- Add CpuLimitConfig type and settings in App Settings
- Use nice command for process priority (-20 to 19)
- Optional cpulimit integration for hard CPU limits (if installed)
- Applied to new sessions via screen-manager and session modules
Ralph Loop Wizard:
- 3-step wizard: Describe → Plan → Launch
- New /api/generate-plan endpoint generates implementation steps via Claude
- Plan editor with checkboxes, priorities (P0/P1/P2), reordering
- Skip plan option for manual workflows
- Compact wizard modal layout
UI Updates:
- Form section headers for grouped settings
- CPU limit status indicator (cpulimit availability)
- Wizard modal wider layout and inline fields
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Smart Respawn Integration (2.5):
- Check circuit breaker OPEN state before respawn (blocks cycle)
- Check RALPH_STATUS EXIT_SIGNAL=true to stop respawn
- Check STATUS=BLOCKED to pause respawn for human intervention
- Use RECOMMENDATION from RALPH_STATUS in update prompt
- Emit respawn:blocked SSE event with reason and details
- Show notification when respawn is blocked
- Visual blocked state with pulsing red indicator
Priority-based Todos (part of 2.3):
- Add RalphTodoPriority type (P0/P1/P2/null)
- Parse priority from todo content (P0:, Critical:, High Priority, etc.)
- Add priority field to RalphTodoItem interface
- Update frontend to display priority badges with colors
- Sort todos by priority (P0 > P1 > P2) then by status
- Add CSS for priority badges and highlighted cards
Bump version to 0.1391
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Phase 1 Ralph enhancement implementation:
- Parse RALPH_STATUS blocks from Claude output (status, tasks, files, tests)
- Circuit breaker state machine (CLOSED → HALF_OPEN → OPEN) for stuck detection
- Dual-condition exit gate (completion indicators >= 2 AND EXIT_SIGNAL)
- Frontend: circuit breaker badge (yellow warning, red stuck), status block display
- API: circuit breaker reset endpoint, ralph status endpoint
- Notifications when circuit breaker opens or exit gate is met
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Session Manager:
- Store event handlers for proper cleanup on session stop
- Add resetSessionManager() for test isolation
State Store:
- Use atomic write pattern (temp file + rename) to prevent corruption
- Add tokenStats to AppState interface
Subagent Watcher:
- Clean up pendingToolCalls on agent completion
- Add cleanupStaleAgents() for 24h+ old agents
- Clear all state maps on stop() for clean restart
Web Server:
- Remove listeners from transcript watcher before stopping
- Clean up respawn timers when session is deleted
- Use cleanupSession() in spawn orchestrator for proper resource cleanup
Frontend:
- Close existing EventSource before reconnecting to prevent duplicates
- Close failed connection before scheduling reconnect
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 300-char rolling window to catch working patterns split across PTY chunks
- Check completion message BEFORE working patterns (priority fix)
- Clear rolling window on completion message (transition point)
- Increase working pattern absence threshold from 3s to 8s
- Add Session.isWorking safety check before confirming idle
- Add 20+ more working patterns (Compiling, Building, Processing, etc.)
- Make AI idle checker prompt more conservative (err toward WORKING)
- Update documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements a "what happened while you were away" view for sessions:
- Track significant events: session start/stop, respawn cycles, state changes,
idle/working transitions, token milestones, auto-compact/clear, Ralph
completions, AI check results, hook events, errors/warnings
- Stats dashboard: respawn cycles, peak tokens, active/idle time, issue counts
- Timeline view with color-coded severity and emoji icons
- Filter events by type (all/errors/warnings/respawn/idle)
- State stuck detection (warns when state unchanged for 10+ minutes)
Click the chart icon on any session tab to open the Run Summary modal.
Files:
- src/run-summary.ts: RunSummaryTracker class with event tracking
- src/types.ts: RunSummary, RunSummaryEvent types
- src/web/server.ts: Integration with session/respawn events, API endpoint
- src/web/public/: Modal UI, timeline rendering, filter controls
- docs/run-summary-plan.md: Implementation plan
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add TokenUsageEntry and TokenStats types for daily tracking
- Add state-store methods for recording and retrieving daily usage
- Add /api/token-stats endpoint with daily breakdown and totals
- Add token stats modal with summary cards, 7-day bar chart, and table
- Record tokens periodically (5min) and on session delete
- Make header tokens clickable to open stats modal
- Fix subagents panel toggle icon direction (down when open)
- Increase subagents panel height when expanded
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add AiCheckerBase abstract class to eliminate ~700 lines of duplication
between AiIdleChecker and AiPlanChecker
- Fix missing persistence fields (completionConfirmMs, noOutputTimeoutMs)
that caused custom timing values to be lost on server restart
- Extract restoreRespawnController() helper to dedupe session restoration
logic between state.json and screens.json paths
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add restoreTokens() method to Session class for recovery after restart
- Add GlobalStats type for cumulative usage tracking across all sessions
- Accumulate tokens from deleted sessions into global stats
- Track lifetime session count with incrementSessionsCreated()
- Add /api/stats endpoint for global stats
- Include globalStats in /api/status response
- Frontend shows aggregate tokens + cost in header
- Fix respawn controller config to filter undefined values
- Add 7 new tests for global stats functionality (v0.1343)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a two-stage gate before auto-accepting plan mode prompts:
1. Strict regex pre-filter - checks for numbered options + selector
2. AI confirmation - spawns Opus to classify as PLAN_MODE or NOT_PLAN_MODE
This prevents spurious Enter key presses when Claude is paused mid-thought
or experiencing network lag, rather than showing a plan approval prompt.
New files:
- src/ai-plan-checker.ts: AI checker following ai-idle-checker.ts pattern
Config fields added to RespawnConfig:
- aiPlanCheckEnabled (default: true)
- aiPlanCheckModel (default: claude-opus-4-5-20251101)
- aiPlanCheckMaxContext (default: 8000)
- aiPlanCheckTimeoutMs (default: 60000)
- aiPlanCheckCooldownMs (default: 30000)
New events: planCheckStarted, planCheckCompleted, planCheckFailed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace the "Worked for Xm Xs" pattern as the sole primary idle
detection signal with a final AI-powered check. When pre-filter
conditions are met (output silence, no working patterns, tokens
stable), a fresh Claude CLI session is spawned in a screen to
analyze terminal output and provide a definitive IDLE/WORKING
verdict before proceeding with the respawn cycle.
New state in state machine: `ai_checking` (between pre-filter
confirmation and `sending_update`). WORKING verdict triggers a
3-minute cooldown. Errors auto-disable after 3 consecutive
failures, falling back to the existing noOutputTimeoutMs safety net.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The server was dropping the `data` field from hook-event POST requests,
so notifications always showed generic messages. Now forwards tool name,
command, question text, and reason to the frontend.
Notifications now show:
- permission_prompt: "Bash: docker push prod:latest"
- elicitation_dialog: "Merge PR #42 to main?"
- idle_prompt: custom message if provided
- stop: reason if provided
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The auto-accept feature was too aggressive - it would press Enter for any
silence without a completion message, including AskUserQuestion prompts.
Now uses the elicitation_dialog notification hook to detect when Claude is
asking a question, and blocks auto-accept in that case. Only plan mode
approvals (silence with no completion message AND no elicitation signal)
trigger auto-accept.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Wire Claude Code's official hooks system (Notification, Stop) to POST
back to Claudeman's new /api/hook-event endpoint, which broadcasts SSE
events consumed by the existing NotificationManager for desktop alerts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Ralph tracker no longer auto-enables on pattern detection. It must be
explicitly enabled per-session (via API) or globally via the new
`ralphEnabled` AppConfig setting. Adds GET/PUT /api/config endpoints
for runtime configuration. Spawn agent ralph enable is unchanged.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When Claude enters plan mode or asks a question (AskUserQuestion), output
stops without a completion message. The new autoAcceptPrompts feature
detects this state and sends Enter after a configurable delay (default 8s)
to accept the plan or select the default option, keeping Claude working
autonomously.
Enabled by default. Adds UI checkbox in the respawn config panel.
Safety: only fires once per silence period, requires prior output,
and won't fire during active respawn cycles.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The respawn controller's enabled/disabled state was not being saved,
so CLI status couldn't show whether respawn was active.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The web server now persists all per-session settings (name, mode,
auto-compact, auto-clear, respawn config, ralph state, tokens, cost)
to state.json so the CLI status/session commands can display them.
Also removes unused pendingStepConfirm property from respawn controller.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rename inner-loop-tracker.ts → ralph-tracker.ts throughout codebase
- Add ralph-config.ts for parsing .claude/ralph-loop.local.md config
- Standardize API error responses using createErrorResponse()
- Add input validation for auto-compact/auto-clear thresholds
- Update UI labels to "Ralph / Todo Tracker" consistently
- Add 46 integration tests for Ralph tracking functionality
- Update test badge to 438 total tests
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add PersistedRespawnConfig type and respawnConfig field to ScreenSession
- Add innerLoopEnabled field to ScreenSession for Ralph Wiggum tracking
- Add updateRespawnConfig, clearRespawnConfig, updateInnerLoopEnabled methods to ScreenManager
- Save respawn config when enabled/updated via API endpoints
- Save inner loop enabled state when changed via API
- Restore respawn controllers and inner loop state on server startup
This ensures respawn continues working after claudeman restarts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add isError() type guard to check if value is Error instance
- Add getErrorMessage() utility for safe error message extraction
in catch blocks (handles TypeScript 4.4+ unknown error type)
- Replace all (err as Error).message patterns with getErrorMessage(err)
across server.ts, cli.ts, ralph-loop.ts, and screen-manager.ts
- Follows TypeScript best practice of treating caught errors as unknown
This improves code safety by properly handling the case where caught
values may not be Error instances (e.g., thrown strings or objects).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add getFullScreenId() to get PID.screenName format for unambiguous attach
- Update DirectAttach.ts and index.tsx to use full screen IDs
- Remove TUI documentation from README (still in development)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
TUI now checks if web server is running on startup and offers to start
it in the background. Added new CLI options: --with-web (auto-start),
--no-web (skip check), -p (port).
TUI feature parity with web interface:
- Shell mode: press 'h' in cases view to start bash instead of Claude
- Multi-start: press 'm' to start 1-20 sessions at once
- Respawn toggle: Ctrl+R to enable/disable respawn on Claude sessions
- Session rename: API support via useSessionManager hook
Security fixes from previous analysis:
- Command injection prevention in screen-manager.ts
- Path traversal protection in server.ts
- Input validation for shell-interpolated values
Also fixes memory leak in session.ts (timer tracking) and flaky test
timeout in session-cleanup.test.ts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add comprehensive JSDoc documentation to all interfaces, types, and functions
- Add @fileoverview documentation
- Document all properties with JSDoc comments
- Add MIT LICENSE file for open source distribution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The InnerLoopTracker is now disabled by default and auto-enables when
Ralph-related patterns are detected:
- /ralph-loop command
- <promise>PHRASE</promise> completion phrases
- TodoWrite tool usage
- Iteration patterns (Iteration 5/50, [5/50])
- Todo checkboxes (- [ ]/- [x]) or indicator icons
This reduces noise for sessions that don't use Ralph loops while
maintaining full functionality when loops are detected.
Changes:
- Add `enabled` property to InnerLoopState type
- Add enable()/disable() methods to InnerLoopTracker
- Implement shouldAutoEnable() for pattern detection
- Update frontend to show "Tracking" status when enabled
- Add CSS for tracking state indicator
- Update CLAUDE.md documentation
- Add comprehensive tests for auto-enable behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add polished, animated Ralph Wiggum Loop panel with:
- Circular progress ring showing task completion percentage
- Task cards with status indicators (pending/in-progress/completed)
- Animated status badge with pulsing indicator when active
- Completion celebration animation with animated checkmark
- Smart time formatting ("1h 23m" instead of "1.38 hours")
Enhanced detection patterns based on official Ralph plugin:
- /ralph-loop command detection
- Iteration patterns: "Iteration 5/50", "[5/50]"
- Max iterations from YAML: "max-iterations: 50"
- TodoWrite tool output detection
Adds maxIterations field to InnerLoopState for tracking loop limits.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add InnerLoopTracker to detect and expose internal Claude Code state
running inside claudeman sessions by parsing terminal output patterns.
Detection patterns:
- Completion phrases: <promise>PHRASE</promise>
- Todo items: checkbox format, indicator icons, status parentheses
- Loop status: cycle counts, elapsed time, start/completion
New features:
- Inner state panel UI (collapsible, below session tabs)
- SSE events: innerLoopUpdate, innerTodoUpdate, innerCompletionDetected
- API endpoint: GET /api/sessions/:id/inner-state
- State persistence to ~/.claudeman/state-inner.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Kickstart Prompt:
- Remove Idle Timeout setting from respawn UI (uses 10s default)
- Add Kickstart Prompt field sent when /init doesn't trigger work
- New states: monitoring_init, sending_kickstart, waiting_kickstart
- Monitors 3s after /init to detect if Claude started working
Auto-Compact Context:
- Add auto-compact at 110k tokens (sends /compact with optional prompt)
- Preserves summarized context unlike /clear which wipes everything
- Optional focus prompt to guide what compact should preserve
- Blocks auto-clear while compacting to prevent conflicts
Also updates auto-clear default threshold from 100k to 140k tokens.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Monitor panel now opens by default on webapp start
- Replace "Reconcile" button with refresh icon (↻)
- Change close button to toggle (▼/▲) for collapse/expand
- Preserve session display names when saving screen info
- Use stored name when restoring sessions (no more "Restored:" prefix)
- Show session name in Monitor panel instead of screen name
- Kill screen session when closing a tab
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add screen session management infrastructure:
- ScreenManager class to create, track, and kill GNU screen sessions
- Persistence of screen sessions to ~/.claudeman/screens.json
- Process stats collection (memory, CPU, child count)
- Reconciliation to detect dead/orphan screens
New API endpoints:
- GET /api/screens - list screens with stats
- DELETE /api/screens/:sessionId - kill screen
- POST /api/screens/reconcile - find dead screens
- POST /api/screens/stats/start|stop - control stats polling
New Process Monitor panel:
- Slide-up panel with real-time stats (2s updates)
- Shows memory, CPU, child processes per screen
- Kill button for each screen session
- Reconcile button to clean up dead screens
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add token tracking to Session class (input/output tokens)
- Add auto-clear feature that sends /clear when token threshold reached
- Add API endpoint to enable respawn on existing running sessions
- Add timed duration setting for respawn (auto-stops after N minutes)
- Add TaskTracker class for background task detection and tree display
- Update UI with duration input, auto-clear settings, and "Enable on Current" button
- Add respawn timer display in banner when timed run is active
- Add token count display in respawn banner
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add buffer management for 12-24+ hour sessions
- Terminal buffer: 5MB max with auto-trim to 4MB
- Text output: 2MB max with auto-trim to 1.5MB
- Messages: 1000 max, keeps recent 800
- Add DELETE /api/sessions endpoint to kill all sessions
- Enhanced session.stop() with SIGKILL fallback
- Kill process groups to terminate child processes
- Clean up respawn controller on session delete
- Add terminal batching at 60fps for performance
- Add bufferStats to session details for monitoring
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements an autonomous respawn loop that keeps Claude Code productive:
- Detects idle state by monitoring PTY for prompt character + timeout
- Sends configurable update prompt when idle (default: "update all the docs and CLAUDE.md")
- Executes /clear and /init to reset session
- Cycles automatically
New features:
- RespawnController class with state machine (watching → update → clear → init)
- REST API endpoints for respawn control (/api/sessions/:id/respawn/*)
- Web UI controls: toggle, prompt config, idle timeout settings
- SSE events for real-time respawn status updates
- Full CLAUDE.md template with Ralph Loop instructions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claudeman manages multiple Claude CLI sessions as subprocesses with:
- Session management (start/stop/list/logs)
- Priority-based task queue with dependency support
- Ralph Loop for autonomous task assignment and completion detection
- Time-aware loops for extended work sessions
- JSON file persistence to ~/.claudeman/state.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
