The optimization introduced a duplicate 'session' variable declaration
that caused a SyntaxError, breaking the web UI entirely.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Increase chunked write size from 64KB to 128KB (halves write time)
- Start buffer fetch immediately before other setup work
- Show "Loading session..." indicator during fetch
- Parallelize session attach with buffer fetch
- Fire-and-forget resize call (don't block on it)
Reduces perceived tab switch latency by ~50-100ms for large buffers.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add Case button to mobile toolbar (between Run Claude and Run Shell)
- Add bottom sheet modal for case selection on mobile
- Show current case name on button (truncated)
- Allow creating new cases from mobile picker
- Sync selection with desktop dropdown
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix Run Claude button being squeezed on mobile (use fit-content width)
- Remove Send button from accessory bar
- Add /init, /clear, /compact buttons with confirmation dialogs
- Center toolbar buttons instead of stretching
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- 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
- Terminal has hidden textarea that was triggering scrollIntoView
- Exclude elements inside .xterm or .terminal-container
- Fixes scroll being broken when tapping terminal
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove all complex viewport tracking (was causing scroll issues)
- Remove keyboard-visible class and CSS (not needed)
- Remove --keyboard-height CSS variable (not needed)
- Simple approach: on focusin, wait 400ms, scrollIntoView
- Keep scroll-margin on phone inputs as CSS fallback
- Much more reliable and no side effects
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Revert interactive-widget viewport meta (caused iOS layout shifts)
- Delay initial viewport height capture to let viewport stabilize
- Update initialViewportHeight on window resize (address bar changes)
- Remove visualViewport scroll handler (not needed, caused issues)
- Scope keyboard CSS to .modal.active only
- Use vh instead of dvh for more stable layout
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove top/bottom positioning from modal-content when keyboard visible
- Reset --viewport-offset-top to 0 when keyboard closes
- Add focusout handler to help reset keyboard state on iOS
- Simplify modal keyboard CSS to only adjust max-height
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add KeyboardHandler module using visualViewport API for keyboard detection
- Set --keyboard-height CSS variable and toggle .keyboard-visible class
- Auto-scroll focused inputs into view after keyboard appears (350ms delay)
- Update viewport meta with interactive-widget=resizes-content for Android
- Add scroll-margin on inputs for tablet/phone breakpoints
- Resize modal-content and modal-body when keyboard visible on mobile
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Rearranged bottom toolbar: Run Claude + Run Shell left, + case selector center
- Made Run Claude button gray instead of blue gradient
- Fixed mobile CSS that was hiding toolbar-center with display:none
- Reduced toolbar height 20%, increased header height
- Tighter session tab styling (smaller padding, font, border-radius)
- Added version display to header next to logo
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
xterm.js has known limited mobile touch support because the viewport
sits underneath the screen rows. Fixed by:
- Setting xterm-viewport z-index: 10 on mobile to receive touch events
- Enabling native browser scrolling with touch-action: pan-y
- Adding -webkit-overflow-scrolling: touch for iOS momentum
- Skipping custom JS scroll handlers on mobile devices
- Moving wizard drag listeners to only attach during actual drag
See: https://github.com/xtermjs/xterm.js/issues/5377
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The imagePopups Map was not being cleaned up during SSE reconnects,
causing memory leaks from orphaned drag event listeners on document.
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>
When multiple Claudeman sessions share the same workingDir, subagents were
incorrectly attaching to the newest session instead of the actual parent.
Now uses direct claudeSessionId matching for reliable parent detection.
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>
- Add minimize button to Ralph wizard modal header
- Minimized indicator shows at bottom of screen with elapsed time
- Click indicator to restore wizard
- Add retry logic (3 attempts with exponential backoff) for plan generation
- Shows "Connection lost, retrying..." message during retries
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Research agent now explores local project first (CLAUDE.md priority)
- Added {WORKING_DIR} placeholder to research prompt
- New "Auto-Start After Plan" checkbox in advanced options
- Increased /init timeout from 10s to 3 minutes
- Added 3s delay after /init completes for stability
chore: bump version to 0.1409
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>
- Changed wizard modal detection from checking non-existent 'hidden' class
and inline style.display to correctly checking for '.active' class
- This fixes plan subagent windows not appearing during Ralph wizard
plan generation
- Also fixes connection lines between wizard, plan agents, and subagents
chore: bump version to 0.1405
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- After Ralph Wizard completes, updates case CLAUDE.md with links to all research files
- Adds /init step before starting Ralph Loop tasks to load research context
- Claude now knows where to find external resources, codebase patterns, recommendations
- Research knowledge persists across respawn cycles via CLAUDE.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a new Phase 0 research agent that runs before all other analysis agents:
- Web search for GitHub repos, documentation, tutorials
- Codebase exploration for existing patterns
- Technical recommendations and potential challenges
- Creates enriched task description for downstream agents
- Research context injected into all analysis agents via {RESEARCH_CONTEXT}
- Saves output to research/ folder with prompt.md and result.json
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>
- Add plan-orchestrator.ts with parallel subagent spawning
- Phase 1: 4 specialist subagents analyze in parallel (requirements, architecture, testing, risks)
- Phase 2: Synthesis merges and deduplicates outputs
- Phase 3: Verification subagent assigns priorities and identifies gaps
- New /api/generate-plan-detailed endpoint with SSE progress updates
- Auto-regenerate plan when switching between Standard/Enhanced modes
- Show quality score, warnings, and gaps from verification
- Rename "Detailed" to "Enhanced" button with tooltip
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add /api/sessions/:id/ralph-prompt/write endpoint to write prompt to @ralph_prompt.md
- Wizard now writes full prompt to file, then sends simple read command to Claude
- Fix session readiness check to wait for prompt character instead of notWorking flag
- Add E2E test infrastructure for ralph-loop workflow (port 3190)
- Add ralph-wizard-prod.mjs script for production testing
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>
