- Create src/utils/regex-patterns.ts with ANSI_ESCAPE_PATTERN_FULL,
ANSI_ESCAPE_PATTERN_SIMPLE, TOKEN_PATTERN, and helper functions
- Create src/utils/token-validation.ts with MAX_SESSION_TOKENS and
validation utilities
- Update session.ts, respawn-controller.ts, ai-checker-base.ts,
ralph-tracker.ts, state-store.ts to use shared utilities
- Export all new utilities from src/utils/index.ts
Reduces code duplication while maintaining pre-compiled patterns
for performance.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add _awaitingIdleConfirmation flag to prevent status bar redraws from
resetting the 2-second idle detection timeout
- Strip ANSI/OSC escape sequences before checking working patterns to
avoid false positives from window titles like '3 File Reading Task'
- Reset _awaitingIdleConfirmation on PTY exit for proper cleanup
chore: bump version to 0.1412
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace local BufferAccumulator in session.ts with shared utility
- Replace local BufferAccumulator in respawn-controller.ts with shared utility
- Import buffer constants from config/buffer-limits.ts
- Reduces code duplication and centralizes buffer management
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- SSE event listener cleanup: Track all listeners and remove on reconnect
to prevent listener accumulation (60+ listeners per connect cycle)
- Floating window cleanup: Remove drag listeners, ResizeObservers on close
- Session creation mutex: Prevent race conditions from concurrent requests
- Screen kill verification: Confirm processes are dead after kill signals
- State store circuit breaker: Prevent cascading failures with backup/recovery
- PTY spawn error handling: Wrap all spawn calls with proper error emission
- SSE graceful shutdown: Notify clients before server stops
- Async file writes: Replace blocking writeFileSync in hot paths
- DocumentFragment optimization: Batch DOM updates for plan rendering
- Timer cleanup: Clear notification/countdown timers on SSE reconnect
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix screen creation failing when using cpulimit/nice (env vars were passed
as command args instead of shell variables)
- Fix session status never becoming 'idle' after startInteractive()
- Add automatic state file cleanup on startup (removes orphaned sessions)
- Add /api/cleanup-state endpoint for manual cleanup
- Make frontend session readiness check more robust (20 attempts, multiple checks)
- Add fallback to direct PTY write if writeViaScreen fails
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>
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 creation now parallelized (3x faster for multiple tabs)
- Minimized agents badge: compact, hover-triggered, auto-hide
- Removed "Minimized Agents" header, status dots instead of text
- Click to pin dropdown open, hover for quick access
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add max 500k tokens per session limit (Claude's context is ~200k)
- Add max 100k tokens per update to prevent sudden jumps from parsing errors
- Reject "M" suffix values > 0.5M to prevent false matches in output text
- Add validation to restoreTokens() to reject corrupted values from state.json
- Add validation to addToGlobalStats() for negative and absurd values
- Fix daily sessions count: track unique session IDs instead of incrementing
on every 5-minute recording interval
- Pass sessionId to recordDailyUsage() for accurate session counting
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add parseTaskDescriptionsFromTerminalData() to parse raw terminal data in
interactive sessions (not just one-shot mode)
- Strip ANSI codes before regex matching since terminal output has embedded
codes like [1mExplore[0m
- Fix getTaskDescriptionForSubagent() to check ALL sessions with matching
project hash (not just the first one found) since multiple sessions can
share the same working directory
- Add tool_result event forwarding for subagent SSE broadcasts
The pattern Explore(Description) in terminal output is now correctly parsed
and used as the subagent window title instead of extracting from the prompt.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Subagents (Task tool background agents) are autonomous and cannot
receive input mid-execution. They complete and return results to
the parent session. Removed the input UI and API endpoint.
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>
- Stack timers row vertically (timers on top, action log below)
- Reduce action log height to 60px since it's now full width
- Filter action log to show only important entries:
- Commands sent to console
- Plan-check with action taken
- Step completions
- Skip timer starts/cancels, detection updates, ai-check status
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>
Two bugs fixed:
1. Respawn controller got stuck after AI check returned WORKING/ERROR.
The pre-filter and no-output timers fired once but were never restarted,
leaving the controller in a dead 'watching' state with no retry mechanism.
Now restarts both timers after any non-IDLE AI check result and on
cooldown expiry. Also seeds the controller's terminal buffer from the
session's existing output so the first AI check has context.
2. AI idle checker couldn't find the claude binary in restricted environments
(systemd service). The spawned screen ran `claude -p` without PATH
augmentation. Now exports getAugmentedPath() from session.ts and prepends
it in the AI checker's bash command.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The previous fix used absolute paths to spawn claude, but the CLI itself
checks if its directory is in PATH and warns if not. Instead, find where
claude is installed and prepend its directory to PATH in the spawn
environment. This ensures both execvp resolution and Claude's own PATH
check are satisfied.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When the web server runs in environments where `claude` isn't in PATH
(e.g., systemd services, non-login shells), node-pty's execvp(3) fails
with "No such file or directory". Fix by resolving the absolute path
to the claude binary using `which` with fallback to common installation
locations (~/.local/bin, /usr/local/bin, etc.). The resolved path is
cached for performance.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Instead of parsing terminal output for <spawn1337> tags, spawn capabilities
are now exposed as native MCP tools that Claude Code can call directly.
The MCP server (stdio transport) proxies requests to the existing REST API.
- Add src/mcp-server.ts with 6 tools: spawn_agent, list_agents,
get_agent_status, get_agent_result, send_agent_message, cancel_agent
- Remove src/spawn-detector.ts and all references in session.ts/server.ts
- Add CLAUDEMAN_API_URL env var propagation to sessions and screens
- Write .mcp.json to case directories during creation
- Remove spawn1337 tag documentation from case-template.md
- Add claudeman-mcp bin entry to package.json
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>
SSE Client Management:
- Add periodic health check (30s) to detect dead SSE connections
- Clean up clients with destroyed/non-writable sockets
- Clear all SSE clients on server stop
Session Lifecycle:
- Add _isStopped flag to prevent new timers after session stops
- Check flag in auto-compact/clear callbacks to avoid timer races
- Check flag in line buffer flush timer creation
Server Shutdown:
- Add _isStopping flag to prevent timer creation during shutdown
- Skip batch timer creation in terminal/output/task/state handlers
- Clear SSE health check timer on stop
Ralph Tracker:
- Call clearDebounceTimers() in clear() method (was missing)
- Add MAX_COMPLETION_PHRASE_ENTRIES (50) to trim phrase map
- Add MAX_LINE_BUFFER_SIZE (64KB) to prevent unbounded growth
- Trim line buffer when exceeding max size
Task Tracker:
- Add timestamp to pending tool uses for age-based cleanup
- Add PENDING_TOOL_USE_MAX_AGE_MS (1 hour) expiry
- Add MAX_PENDING_TOOL_USES (100) limit
- Clean up old entries on new tool use
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Reduce buffer limits (terminal: 5MB→2MB, text: 2MB→1MB) to decrease
render payload
- Add chunkedTerminalWrite() that writes in 64KB chunks via
requestAnimationFrame to avoid UI jank
- Add tail mode to /api/sessions/:id/terminal endpoint (?tail=256KB)
for faster initial load on tab switch
- Show truncation indicator when earlier output is cut
- Update CLAUDE.md with new buffer limits and performance notes
Fixes jittery behavior when switching tabs with large (2MB+) buffers.
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 state store flush on shutdown to prevent data loss from debounced saves
- Add error handling in session exit handler to ensure cleanup always runs
- Add 5s timeout to all TUI execSync calls to prevent hangs
- Cache screen -ls output with 100ms TTL (90% reduction in execSync calls)
- Add token pre-check to skip expensive regex when "token" not in data
Based on findings from security, performance, and reliability analysis.
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>
- inner-loop-tracker.ts: Comment out unused COMPLETION_SIGNAL_PATTERN, use _id
- session.ts: Remove unused execSync import and timeout constants
- task-tracker.ts: Use _context for unused parameter
- server.ts: Remove unused FastifyRequest import
All files now pass --noUnusedLocals --noUnusedParameters check.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Store TaskTracker and InnerLoopTracker handler references in class fields
- Add cleanupTrackerListeners() method to remove handlers on stop()
- Call cleanup in stop() to prevent listener accumulation
- Fixes memory leak from listener closures capturing session references
This prevents gradual memory creep when sessions are repeatedly
created and destroyed in long-running server instances.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add pre-check flags (hasCheckbox, hasTodoIndicator, etc.) before regex exec
- Skip regex patterns that can't match based on line characteristics
- Expected 60-75% reduction in regex executions for todo detection
- Add _promptResolved flag to guard against race conditions in runPrompt
- Capture promise callbacks atomically before processing in onExit
- Prevents double-resolution or resolution after promise is nulled
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix TypeScript error: assignTask() was still using string assignment
- Add extended timeout to session.test.ts afterAll hook to prevent
flaky test failures during cleanup
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Replace string concatenation (+=) with array-based BufferAccumulator
in terminal buffer handling. This reduces garbage collection pressure
during high-throughput terminal streaming.
Changes:
- Add BufferAccumulator class with auto-trim on max size
- Convert _terminalBuffer and _textOutput to BufferAccumulator in session.ts
- Convert terminalBuffer to BufferAccumulator in respawn-controller.ts
- Remove manual trim logic (now handled by BufferAccumulator)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Claude sessions spawned by Claudeman now receive environment variables:
- CLAUDEMAN_SCREEN=1 - Indicates running within Claudeman
- CLAUDEMAN_SESSION_ID - The session's unique identifier
- CLAUDEMAN_SCREEN_NAME - The GNU Screen session name (when applicable)
This helps prevent Claude from attempting to kill its own screen session
and allows sessions to be aware of their managed environment.
Also updated the default CLAUDE.md template to document this behavior.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add comprehensive module-level documentation
- Document main classes with usage examples
- Add parameter and return type documentation to key methods
- Document constants and buffer limits
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Screen attach outputs blank lines that appeared above Claude's banner.
Added flag to strip leading newlines from PTY data after buffer clear.
Only affects Claude sessions (not shell), matching the reported behavior.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Pass existing screenSession to Session constructor for restored sessions
- Skip terminal buffer clearing when attaching to restored (existing) screens
- Frontend auto-calls /interactive endpoint when selecting a restored session
- Fixes issue where restored sessions appeared broken after server restart
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Auto-compact now uses writeViaScreen with \r
- Auto-clear now uses writeViaScreen with \r
- Standardized respawn controller to use \r consistently
- Removed session name input from options modal (use right-click to rename)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Regular user input should go through PTY, only respawn controller
should use screen -X stuff. Added writeViaScreen() method for
programmatic input that needs reliable Enter key delivery.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When writing to an attached PTY connected to screen, the input doesn't
reliably reach Claude CLI. This fix uses `screen -X stuff` command to
send input directly to the screen session, bypassing the PTY attachment.
Research findings:
- Claude CLI uses Ink (React for CLI) for terminal UI
- Ink's parseKeypress detects \r as key.return (Enter)
- screen -X stuff with $'...' syntax reliably sends literal characters
Changes:
- Add ScreenManager.sendInput() using screen -X stuff
- Modify Session.write() to prefer screen -X stuff when available
- Keep \r as Enter key (what Ink expects for key.return)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add InnerLoopTracker to detect and expose internal Claude Code state
running inside claudeman sessions by parsing terminal output patterns.
Detection patterns:
- Completion phrases: <promise>PHRASE</promise>
- Todo items: checkbox format, indicator icons, status parentheses
- Loop status: cycle counts, elapsed time, start/completion
New features:
- Inner state panel UI (collapsible, below session tabs)
- SSE events: innerLoopUpdate, innerTodoUpdate, innerCompletionDetected
- API endpoint: GET /api/sessions/:id/inner-state
- State persistence to ~/.claudeman/state-inner.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Kickstart Prompt:
- Remove Idle Timeout setting from respawn UI (uses 10s default)
- Add Kickstart Prompt field sent when /init doesn't trigger work
- New states: monitoring_init, sending_kickstart, waiting_kickstart
- Monitors 3s after /init to detect if Claude started working
Auto-Compact Context:
- Add auto-compact at 110k tokens (sends /compact with optional prompt)
- Preserves summarized context unlike /clear which wipes everything
- Optional focus prompt to guide what compact should preserve
- Blocks auto-clear while compacting to prevent conflicts
Also updates auto-clear default threshold from 100k to 140k tokens.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Pre-compile regex patterns (ANSI escape, token parsing) in session.ts
- Optimize SSE broadcast to serialize JSON once for all clients
- Add DOM element caching ($() helper) to avoid repeated getElementById
- Throttle resize observer with dimension change detection
- Use array.join() for session tab HTML building
- Replace DOM-based escapeHtml with regex replacement
- Cache toast container reference
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
GNU screen creates blank space at the top when initializing sessions.
This is now handled after attaching to the screen:
- Claude sessions: emit clearTerminal event after 100ms, client clears xterm
- Shell sessions: send 'clear' command after 100ms
Also updates CLAUDE.md with documentation of the fix.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When clicking (x) on a session tab, users now choose:
- Hide Tab (Keep Screen): removes tab but screen session stays alive
- Close & Kill Screen: terminates both tab and screen session
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
