- TaskTracker.getTaskTreeLight(): strips large `output` strings from tasks
in SSE broadcasts (was serializing 5-10MB every 500ms with many subagents)
- session:created broadcasts now use toLightDetailedState() (consistent with
session:updated which already did)
- GET /api/sessions/:id returns light state (no 2-3MB terminal+text buffers)
- Ralph wizard polls /terminal?tail=2048 instead of full session endpoint
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Previously, server.stop() called cleanupSession(killMux=false) for all sessions,
which still tore down session state, removed listeners, killed PTY processes via
node-pty SIGHUP, and broadcast session:deleted. This caused Claude sessions
running inside tmux to be disrupted during COM deploys.
Now server shutdown just persists state, removes listeners, and lets the Node.js
process exit naturally. The tmux sessions survive independently, and
restoreMuxSessions() finds them alive on restart.
Also adds defense-in-depth in session.stop(): when killMux=false, skip PTY kill
entirely (just null the reference). And adds 'detached' lifecycle event type for
accurate audit logging.
Records every session create, start, exit, delete, recover, stale-clean,
mux-died, and server start/stop with timestamps, names, reasons, and exit
codes. Survives server restarts (unlike in-memory RunSummary).
- New SessionLifecycleLog singleton (src/session-lifecycle-log.ts)
- LifecycleEventType + LifecycleEntry types in types.ts
- GET /api/session-lifecycle endpoint with sessionId/event/since/limit filters
- cleanupSession() now takes reason parameter for audit trail
- state-store cleanupStaleSessions returns cleaned session IDs+names
- UI: lifecycle log modal accessible from header clipboard icon
- Auto-trims to 8k entries when exceeding 10k on server start
chore: bump version to 0.1556
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Bug 1 (CRITICAL): canonicalCount >= 1 always fired on first <promise> tag
(prompt echo). Changed to >= 2 so only 2nd+ occurrence triggers completion.
Bug 2: checkMultiLinePatterns() re-detected complete tags already handled
by processLine(), double-counting. Now only tries completion when partial
buffer is non-empty (cross-chunk scenario).
Bug 3: TodoWrite ✔ patterns required "Task #N" but real Claude Code output
is plain "✔ content". Added TODO_PLAIN_CHECKMARK_PATTERN fallback.
Includes 71 new deep tests + real-life verification.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
handleInit() called KeyboardHandler.cleanup() and MobileDetection.cleanup()
on every SSE connect but never re-initialized them, breaking keyboard
scroll-into-view and the /init /clear accessory bar on mobile.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three bugs fixed in KeyboardHandler:
1. onKeyboardShow() used sessionData.terminal (always undefined) instead of app.terminal
2. Keyboard dismiss threshold (50px) too tight for iOS address bar drift — widened to 100px
3. No terminal refit on keyboard hide — caused black gap below terminal
Also added: dynamic baseline update for initialViewportHeight, safety check in
updateLayoutForKeyboard() that forces dismiss when keyboardOffset <= 0.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Clear teams/teamTasks maps in handleInit() on SSE reconnect
- Fix saveNowAsync() race condition with in-flight promise guard
- Add setMaxListeners() on Session, WebServer, SubagentWatcher,
ImageWatcher, TmuxManager to prevent MaxListenersExceeded warnings
- Debounce persistSessionState() per-session (100ms) to reduce
redundant toState() serialization across 25+ call sites
- Cache getLightSessionsState() with 1s TTL to avoid re-serializing
all sessions on every SSE connect and /api/sessions request
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Convert sync readFileSync/statSync to async in subagent-watcher.ts to
unblock event loop on hot paths (transcript reads, liveness checks)
- Fix Map mutation during iteration in closeSessionLogViewerWindows and
closeSessionImagePopups (collect IDs first, then iterate to close)
- Unify session cleanup into shared _cleanupSessionData() method called
from both closeSession() and session:deleted handler to prevent leaks
- Add Zod validation schemas for 20+ API routes that used raw type casts
- Add consecutive error tracking (5 errors/60s triggers exit for systemd
restart) and SIGHUP handler for SSH disconnect safety
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1. handleInit crash: commit cdc822d removed Map initializations for
teammateTerminals, teammatePanesByName, teams, teamTasks, teammateMap
from the constructor but left cleanup code that iterates them.
cleanupAllFloatingWindows() crashed on "not iterable", preventing
ALL frontend data (sessions, subagents) from loading.
2. claudeSessionId null on recovered sessions: only set inside
startInteractive(), never in constructor or persisted. After server
restart, recovered sessions had null claudeSessionId, so the
hasMatchingTab check always failed → no subagent windows.
Fixes:
- Re-add all 5 missing Map initializations in app.js constructor
- Set _claudeSessionId = this.id in Session constructor (Claudeman
always passes --session-id to Claude, so they always match)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Added IS_TEST_MODE (process.env.VITEST) guards to every method in TmuxManager and
ScreenManager that touches real tmux/screen sessions. Tests can never create, kill,
discover, or send input to real sessions. Removed broken E2E test suite entirely.
Rewrote test/setup.ts from 459 lines to minimal cleanup. Rewrote tmux-related tests
to verify test-mode safety behavior.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
feat: interactive teammate tmux pane windows with xterm.js terminals
feat: auto-cleanup teams/subagents/pane windows on session delete
fix: only show agent/teammate windows when matching Claudeman tab exists
fix: UTF-8 encoding in teammate pane terminal output (Uint8Array)
fix: standalone pane window cleanup via subagentParentMap lookup
fix: xterm.js dimensions crash with deferred init + null-safe dispose
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- WebServer: Store session listener refs for explicit cleanup on delete
- RespawnController: Fix clearInterval bug (was using clearTimeout)
- RespawnController: Add try/catch to interval callbacks
- PlanOrchestrator: Guarantee progressInterval cleanup with try/finally
- SubagentWatcher: Guard idle timer against deleted agents
- Session: Add threshold validation for auto-clear/compact (1k-500k)
- Session: Add token sum overflow check in restoreTokens
- Session: Use LRUMap for _recentTaskDescriptions auto-eviction
Commit from flight QR118 in an Airbus A350-1000, stable connection thanks to Starlink!
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Backend fixes:
- Session: clear _recentTaskDescriptions Map in stop() and clearBuffers()
- Session: null promise callbacks after rejection in runPrompt() catch block
- Server: store subagent/image watcher listener refs and remove on shutdown
Frontend fixes:
- Plan file windows: store drag/resize handlers and clean up on close
- Plan file manager: store drag handler and clean up on close
- cleanupAllFloatingWindows: now cleans up plan file windows
These prevent unbounded memory growth in long-running sessions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add --session-id flag to Claude CLI startup so Claudeman and Claude share the same session ID
- Set claudeSessionId immediately on session start (no waiting for JSON messages)
- Add persistent subagentParentMap to store agent-to-tab associations permanently
- Add /api/subagent-parents endpoints for server-side persistence
- Add fallback: use active session when claudeSessionId matching fails
- Connection lines now reliably connect agent windows to their parent tabs
- Survives page refresh, reconnect, and server restart
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove TUI from git (moved to .gitignore for local development)
- Remove React/Ink dependencies (unused in published version)
- Remove tui command from CLI
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Reduce getRecentSubagents window from 60 to 15 minutes
- Skip old/completed agents when restoring window states (10 min cutoff)
- Clear old activity data when new agent with same ID is discovered
- Force close existing window for agentId before opening fresh one
Fixes issue where old prompts/input from previous Ralph Loop runs
were displayed when clicking on subagent windows.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
arkon