* Fix unauthenticated command injection (RCE) in Studio server
The `--studio` server (cli-tool/src/sandbox-server.js) bound to 0.0.0.0
with wildcard CORS and no authentication, and passed request-body fields
into spawn(..., { shell: true }). Because shell:true makes Node join the
argv array into a single `sh -c` string, the fields were parsed by the
shell, allowing OS command injection (RCE) via POST /api/execute (prompt)
and POST /api/install-agent (agentName), reachable from the LAN or a
malicious web page (wildcard CORS).
- Remove shell:true from all three spawns so arguments stay discrete argv
entries; shell metacharacters can no longer inject commands.
- Validate agentName against ^[A-Za-z0-9._/-]+$ before use.
- Bind the server to 127.0.0.1 only (removes the LAN vector).
- Restrict CORS to the local UI origin and reject cross-origin requests
(removes the drive-by browser vector).
Fixes GHSA-79wm-x847-7cvg.
Co-Authored-By: Claude Opus <noreply@anthropic.com>
* security: Windows-safe spawns + release bump on top of GHSA-79wm-x847-7cvg fix
Builds on @spartan8806's fix (advisory-fix-1). Adds the two pieces that fix
lacked:
- Resolve npx/claude via their .cmd shims on Windows (NPX_CMD/CLAUDE_CMD).
Without shell:true, bare spawn('npx'/'claude') fails with ENOENT on win32,
which would break agent install/local execution. This keeps the security fix
cross-platform.
- Bump version to 1.29.4 (root + cli-tool package.json) and add the 1.29.4
Security entry to CHANGELOG for the patched release.
Refs GHSA-79wm-x847-7cvg.
---------
Co-authored-by: spartan8806 <spartan8806@users.noreply.github.com>
Co-authored-by: Claude Opus <noreply@anthropic.com>
Co-authored-by: Dani <dan.avila7@gmail.com>
Completes the error tracking rollout: aitmpl-dashboard and aitmpl-cli Sentry
projects now exist alongside aitmpl-workers, and all three are verified
end-to-end (manual test events returned HTTP 200 and appeared in each
project's Issues dashboard).
- Dashboard: SENTRY_DSN set as a Cloudflare Pages secret on aitmpl-dashboard
(production). No code change needed — error-tracking.ts already read it.
- CLI: the aitmpl-cli DSN is public by design (send-only), so it ships as
DEFAULT_SENTRY_DSN in error-reporting.js instead of requiring every user
to configure their own Sentry project. Reporting itself stays opt-in
(CCT_ERROR_REPORTING=true), unaffected by this change.
- .env.example and CLAUDE.md updated to match reality; removed a stale
Vercel Deployment block left over from the Cloudflare Pages migration.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Adds free-tier Sentry error reporting to close the biggest observability
gap: automated cron/worker failures were previously invisible (aitmpl-crons
had no error handling at all). Uses a dependency-free fetch()-based Sentry
envelope client (cloudflare-workers/*/sentry.js, dashboard error-tracking.ts,
cli-tool error-reporting.js) instead of the official SDKs, to keep the
zero-dependency worker style and avoid Cloudflare Pages SSR friction.
- Cloudflare Workers: report failures + Cron Monitor check-ins in crons,
pulse, and docs-monitor (complementing, not replacing, existing Telegram
alerts). Also drops the pulse Vercel collector (VERCEL_API/collectVercel),
since the dashboard no longer deploys to Vercel.
- Dashboard: captureApiError() wired into claude-code-check, health-check,
and the three track-* endpoints.
- CLI: opt-in only crash reporting (CCT_ERROR_REPORTING=true), always
deferring to the existing CCT_NO_TRACKING/CCT_NO_ANALYTICS/CI opt-outs.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
* feat: add Loops component type with referenced components
Introduce "loops" as a new first-class component type — autonomous
agentic workflows (goal + interval + stop condition) inspired by Loop
Engineering and the Forward Future Loop Library. A loop references other
components (agents, skills, hooks, commands) and the dashboard renders
those references as clickable cards on the loop detail page.
- Add 10 starter loops under cli-tool/components/loops/
(engineering, evaluation, operations)
- Catalog generator: scan loops + write per-component content files
- Dashboard: new type in icons/types/data, /loops page, and a
"Referenced Components" section on the loop detail page
- CLI: --loop flag installs the loop to .claude/loops/ and
auto-installs its referenced components
- Docs: CLAUDE.md and cli-tool rule updated
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES
* feat: add 8 more loops (goal/loop/schedule patterns)
Expand the loops catalog to 18, drawing ideas from community "Loop
Engineering" patterns. Adds loops across the three trigger verbs
(/goal, /loop, /schedule) and emphasizes the verifier-in-the-loop and
budget / anti-spin guardrails:
- engineering/five-minute-maintainer-loop
- engineering/build-test-fix-loop
- engineering/anti-spin-build-loop
- engineering/completion-contract-loop (goal)
- engineering/goal-refiner-loop (goal)
- engineering/adversarial-review-loop (cross-model)
- operations/overnight-pr-routine-loop (schedule)
- evaluation/human-approval-loop (human-in-the-loop)
All referenced components verified to exist; catalog regenerated.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T9ynMiCHt8JwdMd8KjCkES
---------
Co-authored-by: Claude <noreply@anthropic.com>
Analytics Dashboard (Phase 1 + Phase 2):
- Replace 8663-line vanilla JS monolith with Astro static build
- New bento-grid layout with Geist design system (dark/light themes)
- ECharts (offline, tree-shaken) replaces Chart.js CDN dependency
- React island with KPI cards, token timeline, activity heatmap, agent BarList
- WebSocket client with reconnect backoff; polling fallback when WS disconnects
- API client with 30s cache; normalizes backend field names (inputTokens→totalInput)
- Build source in analytics-ui/, output committed to src/analytics-web/
- Fix: /api/activity now uses in-memory cache (was re-scanning all files on each request)
- Fix: remove duplicate /api/agents route (dead code since Express uses first match)
- Fix: /api/data and /api/fast-update no longer mutate this.data.conversations in place
TUI Modernization:
- Add src/tui.js with @clack/prompts-powered banner and helpers
- Replace inline showBanner() in bin/create-claude-config.js with tui.showBanner()
- Migrate showMainMenu() in src/index.js to @clack select() (replaces inquirer)
- Add @clack/prompts ^1.5.1 and gradient-string ^2.0.2 to dependencies
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Token Distribution by Type: compute totals from date-filtered
conversations instead of pre-aggregated detailedTokenUsage which
always contained all historical data regardless of the selected range
- Daily Productivity Trends: skip conversations outside the selected
date range (was iterating all conversations unconditionally)
- Workflow Intelligence charts: re-fetch /api/agents with startDate
and endDate query params on filter apply instead of reusing stale
initial-load data
Fixes#382
Claude Code JSONL logs use `content.name === 'Agent'` but the
analytics code only checks for `'Task'`, causing Agent Usage
Distribution, Agent Activity Timeline, and Workflow Efficiency Score
charts to show empty data.
Accept both tool names in AgentAnalyzer, chats-mobile, and
teams-dashboard.
Fixes#488
Co-authored-by: easonysliu <easonysliu@tencent.com>
- Create 3 Neon tables: installation_outcomes, website_events, api_health_logs
- Add API endpoints: track-installation-outcome, track-website-events, health-check
- Track CLI installation success/failure with timing and error classification
- Add website event tracker (search, cart, component views) with batched sendBeacon
- Add health-check cron every 15min with Discord alerts on failure
- Integrate tracking in all 6 installIndividual* functions with batchId support
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a new local web dashboard to visualize Claude Code team sessions:
- Express server on port 3338 with JSONL parsing from ~/.claude/projects/
- SVG flow diagram showing agent hierarchy and communication edges
- Click-to-open detail panel with accordion sections (interactions, messages, tasks, tools)
- Smart agent name resolution from task assignment payloads
- Team session detection filtering (TeamCreate/SendMessage protocol only)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: improve Chats Mobile security, CSS quality, and desktop layout
- Sanitize error.message with escapeHtml() to prevent XSS in innerHTML
- Replace !important overrides in .back-btn with proper specificity (.header-btn.back-btn)
- Add desktop side-by-side layout at 769px+ (360px sidebar + flexible chat view)
- Extract 100+ inline styles from analytics modal into reusable CSS classes
https://claude.ai/code/session_01Cfg7GGRKxgJoWiNj1EjWSb
* chore: standardize all 15 blog posts for consistency
Apply unified style guide across all local blog posts:
- Fix copyright year 2025 -> 2026 in all footers
- Remove inline styles from explore-components-banner (use CSS classes)
- Standardize CTA text to "800+" and relative links
- Fix OG tag prefix og:article: -> article: (code-reviewer)
- Fix www.aitmpl.com -> aitmpl.com in OG/Twitter/structured data
- Fix cover image absolute URLs to relative paths (e2b, nextjs)
- Standardize Mermaid theme to orange #F97316 (heygen)
- Fix author name to "Claude Code Templates" (neon-complete)
- Add missing explore-components-banner (security-hooks, vercel-monitor, hackathon)
- Add missing callout boxes (info-box, success-box) where absent
- Standardize CodeCopy JS and MarkdownCopier across posts
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add worktree commands and blog post for parallel development
Add 4 worktree slash commands for git worktree lifecycle management:
- /worktree-init: create parallel worktrees from task descriptions
- /worktree-check: show current worktree status and task
- /worktree-deliver: commit, push, and create PR
- /worktree-cleanup: remove merged worktrees and branches
Add blog post explaining the Skill + Commands architecture pattern
where a discoverable Skill (worktree-guide) orchestrates manual
Commands for execution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore: ignore settings.local.json in all subdirectories
Change .claude/settings.local.json to **/settings.local.json
to cover nested paths like docs/.claude/settings.local.json.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: add missing allowed-tools to worktree commands
- worktree-cleanup: add Bash(grep:*) for merge check commands
- worktree-init: add Bash(sed:*) for branch name detection
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Increased HUD panel size (padding: 30px, min-width: 280px)
- Larger fonts (labels: 16px, values: 18px)
- Implemented smooth counter animation from 0 to target value
- Counters now gradually increment instead of jumping to final value
- Added statsTarget and statsDisplay for smooth interpolation
- All three counters animate: Conversations, Components, Tool Calls
- Fixed Components counter showing 0 (now increments with component-layer2 events)
- Removed Active Days from HUD display
- Cleaned up stats.days calculation and references
- Components now properly tracked in stats.components
- Increased beam speed 5x (0.02 → 0.1) for faster completion
- Implemented beam queue system with max 10 active beams
- Removed visual effects (shadows, labels, particles) for better FPS
- Fixed duplicate counter increments (now updates once before beam)
- Added beamQueue cleanup in restart function
- Significantly improves rendering performance with many tools
- Changed from bulk toolCounts processing to individual tool-use events
- Implemented sequential dayOfYear assignment for controlled loading order
- Tools now load one by one like components (no simultaneous loading)
- Models load first (day 0), then tools (day 10+), then components
- Increased toolIncrement to 3 for proper spacing between tool animations
- Components start immediately after tools (no delay)
- Fixes extreme lag when loading many tools at once
- Change from 3 tools/frame to 1 tool every 5 frames
- Reduces processing speed from 180 tools/sec to ~12 tools/sec
- Matches component loading speed for smoother rendering
- Prevents lag on slower devices
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Implement tool queue system to process tools gradually
- Process only 3 tools per frame instead of all at once
- Prevents browser freeze when loading many tools simultaneously
- Improves rendering performance on slower devices
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Remove timeline bar and date display from visualization
- Remove numbers from right panel (Models, Tools, Components lists)
- Implement collision detection system to prevent nodes overlapping
- Add restart function to clear permanent connection beams
- Clean up token tracking (removed from frontend display)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Group Plan, Explore, Agent subagents by type instead of individual IDs
- Aggregate counts per day to reduce timeline events
- Prevents rendering issues with thousands of subagent nodes
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Display percentages instead of absolute counts for tools, models, and components
- Position nodes randomly based on percentage (higher % = closer to center)
- Add zoom in/out with mouse wheel (30%-300%)
- Add pan canvas by dragging background
- Add drag & drop for tool and component nodes
- Double-click to reset zoom/pan
- Make connection beams permanent with subtle pulse animation
- One permanent connection per node for clean visualization
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add --2025 option to launch Year-in-Review visualization
- Support --tunnel flag with --2025 for remote access
- Track analytics dashboard usage for 2025 page
- Update allowed bash commands in local settings
Usage: cct --2025 [--tunnel]
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Gource-style 3-layer circular visualization (models/tools/components)
- Interactive tooltips with usage counts for all node types
- Real-time legend panels: Models Used, Tools Used, Components Used
- Multiple animated beams based on actual tool call counts
- Backend uses totalToolCalls for accurate activity metrics
- Optimized performance (~100ms for 86 conversations)
Technical Details:
- Center layer: Model pie chart with usage-based sizing
- Middle layer (250px): Tools with count badges
- Outer layer (400px): Commands, Skills, MCPs, Subagents
- YearInReview2025 backend analyzes conversations without overhead
- Tooltip system detects hover on pie slices, circles, and outer nodes
- Frontend processes toolCounts and modelCounts for precise visualization
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated all references to point to new script locations:
- generate_components_json.py → scripts/generate_components_json.py
- generate_trending_data.py → scripts/generate_trending_data.py
Files updated:
- .github/workflows/update-json-data.yml
- CLAUDE.md
- docs/CLAUDE.md
- docs/api/README.md
- docs/guides/growth-kit-pr.md
- cli-tool/src/validation/README.md
This ensures CI/CD workflows and documentation are in sync with the new project structure.
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Fix#150: Check if pluginDef.source is a string before passing to path.join()
Marketplace aggregators use object format {source: "url", url: "..."} to
reference external repos, which caused path.join() to throw an error.
- Fix#151: Add support for "directory" source type in getMarketplaceType()
Claude Code uses "directory" for filesystem-based marketplaces, but only
"local" was being checked. Now both are recognized as Local type.
Also added "url" type recognition.
🎯 Skills Manager now detects skills from 3 sources:
- Personal: ~/.claude/skills/
- Project: .claude/skills/
- Plugin: ~/.claude/plugins/marketplaces/*/plugins/*/skills/*/
✨ Features:
- Added loadPluginSkills() to scan marketplace-installed skills
- Skills from /plugin install now appear in dashboard
- Detailed logging for debugging skill detection
- Fixed filter counts to show consistent totals
🔧 Improvements:
- Filter counts remain static regardless of active filter
- Shows total count for each category (All, Personal, Project, Plugin)
- Enhanced logging for better troubleshooting
- Supports skills installed via Claude Code plugin system
📦 Version: 1.28.3
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
When port 3337 is in use, the dashboard will automatically try the next available port
(3338, 3339, etc.) with a clear message to the user.
This prevents EADDRINUSE errors and improves user experience.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The --skills flag was conflicting with the existing --skills component installation command,
causing EADDRINUSE errors on port 3337. Changed Skills Dashboard to use --skills-manager instead.
Changes:
- bin/create-claude-config.js: --skills → --skills-manager
- src/index.js: options.skills → options.skillsManager
- SKILLS_DASHBOARD.md: Updated usage examples
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements a comprehensive Skills Dashboard accessible via `--skills` flag that visualizes
Claude Code's 3-level progressive context loading system according to official documentation.
Features:
- **Level 1: Metadata** - Always loaded (~100 tokens): name, description, allowed-tools from YAML
- **Level 2: Instructions** - When triggered (<5k tokens): SKILL.md body with workflows
- **Level 3+: Resources & Code** - As needed (unlimited): Additional markdown, scripts, templates
- Instructions: Additional .md files with specialized guidance
- Code: Executable scripts (.py, .js, .sh) run via bash without loading into context
- Resources: Reference materials (schemas, API docs, templates, examples)
Technical Implementation:
- Express.js server on port 3337 with RESTful API
- Real-time skill scanning from ~/.claude/skills and .claude/skills
- Progressive file categorization: alwaysLoaded, onDemand, progressive
- Modern UI with level cards, flow arrows, and resource categorization
- File type detection and proper context for markdown references vs executable code
Dashboard shows:
- Grid/list view of all installed skills
- Filter by source (Personal, Project, Plugin)
- Sort by name, file count, last modified
- Modal detail view with 3-level loading visualization
- Visual flow arrows between levels showing loading triggers
- Category descriptions matching official Skills documentation
Fixes context preservation issue in scanSupportingFiles() where `this` context
was lost in nested function, now using `const self = this` pattern.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace python3 with python in JSON configs on Windows
- Add cross-platform Python detection (py/python/python3)
- Update E2B sandbox to try multiple Python commands
- Follows PEP 397 Python launcher best practices
Fixed multiple issues with server shutdown:
- Added flag to prevent multiple shutdown attempts
- Remove all SIGINT/SIGTERM listeners before adding new ones
- Added isStopped flag to prevent stop() from being called multiple times
- Improved logging during shutdown process
- Fixed MaxListenersExceededWarning by properly cleaning up event listeners
This resolves the issue where pressing Ctrl+C multiple times would create
duplicate shutdown handlers and cause memory leaks.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added detailed analytics modal for each chat session including:
- Overview metrics (messages, tokens, tools, models, cache efficiency)
- Token usage breakdown with cost estimation
- Session timeline with duration tracking
- Time breakdown (Claude execution vs user conversing)
- Model information with usage percentages and message counts
- Tool usage statistics
- Components used (agents, slash commands, skills)
Key features:
- Real-time analytics calculation from JSONL conversation files
- Multi-model usage detection (Sonnet/Haiku switching)
- Intelligent time filtering (excludes long breaks)
- Cost estimation based on Claude API pricing
- Component detection from tool_use blocks
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
The 'cat | claude' command doesn't work with interactive mode
because pipe consumes stdin. Replaced with proper interactive
mode usage:
Option 1: claude "read @context-file.md and continue"
Option 2: claude (then > @context-file.md continue)
This fixes the 'Raw mode is not supported' error users were
experiencing.
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
Added two simple command options for loading context:
Option 1: Direct reference with @
claude "read @context-file.md and continue"
Option 2: Using cat (pipe)
cat context-file.md | claude
Changes:
- Replaced generic instructions with specific commands
- Added syntax-highlighted code blocks
- Clear visual separation between options
- Added tip about saving file in project directory
UI improvements:
- Dark code blocks for better readability
- Green headers for each option
- Concise, actionable instructions
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Changes:
- Header now directly addresses Claude Code instead of the user
- Clear note: "This file contains the complete conversation history"
- Removed user-facing instructions
- Simplified metadata format
- Updated modal text to reflect that file is FOR Claude Code to read
New header format:
```markdown
# Previous Conversation Context
> **Note to Claude Code**: This file contains the complete
> conversation history from a previous session. Read and
> understand this context to continue helping the user with
> their task.
**Project:** project-name
**Date:** 2025-10-29
**Messages in this export:** 100
```
Modal improvements:
- "Markdown context file that Claude Code can read"
- "Claude will read and understand the previous conversation"
- Clearer example of @ usage
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Complete overhaul of session sharing feature:
REMOVED:
- x0.at upload functionality
- Share command and QR code generation
- External file hosting dependencies
- Clone session command (--clone-session)
ADDED:
- Download conversation as Markdown file
- Context file optimized for Claude Code @ references
- Simple download modal with usage instructions
- Instructions for using @filename in Claude Code
Changes:
Backend:
- New exportSessionAsMarkdown() method in SessionSharing
- Convert conversations to readable Markdown format
- Include usage instructions in exported files
- Changed endpoint from /api/conversations/:id/share to /download
Frontend:
- Replaced "Share" button with "Download" button
- New download modal with clear instructions
- Removed QR code and upload functionality
- Direct browser download of .md files
User Experience:
- Download context file to local machine
- Add file to project repository
- Reference in Claude Code with @filename
- Continue conversation with full context
Example workflow:
1. Click Download button
2. Save claude-context-project-2025-10-27.md
3. Add to git repo
4. In Claude Code: "Read @claude-context-project-2025-10-27.md and continue"
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixes:
- Resume command now shows only conversation ID (claude --resume <id>)
instead of including user path
- Changed default project name from 'Unknown' to 'shared-session'
for consistency between export and import
- Updated default model fallback to 'claude-sonnet-4-5-20250929'
Issue: When cloning a session on another computer, the resume command
was showing the wrong format and the project was being saved as
'unknown' instead of using the correct project name.
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add session sharing and cloning functionality
Implement complete session sharing system for Claude Code conversations:
Features:
- Share button in chats interface with QR code generation
- Upload sessions to x0.at (temporary file hosting)
- Clone sessions with --clone-session command
- Limit shared sessions to last 100 messages
- Security confirmation modal with service information
- Resume command display after cloning
Backend:
- New SessionSharing class for export/upload/download/install
- Integration with ConversationAnalyzer
- x0.at upload service (tested and working)
- JSONL format conversion for Claude Code compatibility
Frontend:
- Confirmation modal with x0.at security info
- Centered QR code display
- Improved button styling (Resume, Share, Search)
- Real-time upload progress indication
CLI:
- Added --clone-session <url> parameter
- Automatic session installation to ~/.claude/projects/
- Display resume command with conversation ID
Dependencies:
- Added qrcode package for QR generation
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: improve chats UI with project grouping and unified action buttons
Major improvements to chats interface:
Project Organization:
- Group conversations by project with collapsible sections
- Projects collapsed by default for cleaner interface
- Auto-expand projects during search with matching results
- Sticky project headers for better navigation
- Project avatars with gradients and conversation counts
Terminology Update:
- Changed "conversations" to "sessions" throughout UI
- Updated empty state messages
- Consistent terminology in headers and labels
Action Buttons Enhancement:
- Unified Resume, Share, and Search buttons in center header
- Replaced emojis with professional SVG icons
- Grouped design with orange accent border
- Individual hover states (green/blue/orange)
- Responsive button group with smooth transitions
Search Improvements:
- Fixed search to work with grouped project structure
- Search in both project names and session IDs
- Auto-collapse all projects when clearing search
- Proper filter clearing in advanced search
- Maintained state management across search operations
Visual Design:
- Orange accent border highlighting action buttons (2px)
- Subtle orange background for button group
- Consistent hover effects with color coding
- Enhanced visual hierarchy
- Better spacing and alignment
🤖 Generated with Claude Code (https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add advanced search panel with filters for directory, date range, and content
- Implement in-conversation search with navigation (↑↓ arrows)
- Add folder browser with conversation counts per directory
- Add search result highlighting with current match emphasis
- Implement 3-character minimum for search to prevent performance issues
- Add ID-based message navigation for reliable infinite scroll support
- Add visual feedback with flash animations and match counters
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added detailed logging to help debug why Cloudflare component files
are not being copied to the sandbox directory.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Fixed Cloudflare sandbox to save generated files in project root using
timestamp-based directories, matching E2B's sandbox-{id} pattern.
**Changes**:
- Modified launcher.ts to accept targetDir parameter (5th argument)
- Updated LauncherConfig interface with optional targetDir field
- Modified displayResults() to use targetDir instead of process.cwd()
- Fixed TypeScript errors (workerUrl undefined, unused language variable)
- Updated src/index.js to pass targetDir to launcher
- Added cloudflare-*/ and sandbox-*/ to .gitignore
- Updated IMPLEMENTATION_SUMMARY.md with file structure details
**Directory Structure**:
- Before: `.claude/sandbox/cloudflare/cloudflare-output/`
- After: `your-project/cloudflare-{timestamp}/`
**Pattern Comparison**:
- E2B: `your-project/sandbox-{id}/`
- Cloudflare: `your-project/cloudflare-{timestamp}/`
Files now download to clean, timestamped directories in the project root,
improving organization and matching user expectations from E2B behavior.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implemented complete Cloudflare sandbox integration for executing Claude Code with automatic file downloads.
Features:
- AI-powered code generation using Claude Sonnet 4.5
- Automatic extraction and download of HTML/CSS/JS files
- TypeScript launcher and monitoring tools
- Support for web development requests with file detection
- Integration with CLI (--sandbox cloudflare)
- Global edge deployment capability
- Comprehensive documentation and debugging guides
Files Added:
- Worker source (src/index.ts) with Claude AI integration
- TypeScript launcher with file extraction
- Real-time monitoring tool
- Complete documentation suite (4 MD files)
- Configuration files (wrangler.toml, package.json, tsconfig.json)
Integration:
- Modified src/index.js to support cloudflare sandbox provider
- Split E2B and Cloudflare logic into separate functions
- Added file download functionality similar to E2B
Tested:
- Successfully generates and downloads HTML/CSS/JS files
- Works with agents (e.g., frontend-developer)
- Proper error handling and user feedback
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
Problem:
- Skills like docx require additional files (docx-js.md, ooxml.md, LICENSE.txt)
- Previous implementation only downloaded files matching specific patterns
- Skills with complex directory structures (ooxml/, scripts/) were incomplete
Solution:
- Replaced pattern-based file detection with GitHub API recursive download
- Downloads ALL files and directories in the skill directory
- Maintains executable permissions for .py and .sh files
- Simplifies code and ensures complete skill installation
Benefits:
- docx skill now includes all 59 files (SKILL.md, docx-js.md, ooxml/, scripts/, etc.)
- Works for all current and future skills without modification
- No need to maintain regex patterns or directory whitelists
Testing:
- Verified docx skill installation with all files present
- Confirmed executable permissions on Python scripts
- Total files downloaded: 59 for docx skill
## Changes Made:
### 1. Modal Text Display Improvements
- Increased error/warning message font size from 14px to 16px for better readability
- Improved line height from 1.5 to 1.6 for better spacing
- Increased margin-bottom from 4px to 8px for better visual separation
### 2. Code Preview Text Wrapping
- Removed horizontal scroll (`overflow-x: auto`) from code previews
- Added `white-space: normal` to prevent excessive whitespace at line start
- Added `word-wrap: break-word` and `overflow-wrap: break-word` for proper text wrapping
- Applied to all code preview sections:
- Error line text previews
- Warning line text previews
- Example line text in errors
- Example line text in warnings
### 3. Line Number Scroll Synchronization
- Added `position: relative` to `.code-body` for better layout control
- Added `overflow: hidden` and `max-height: 600px` to `.code-line-numbers`
- Added `max-height: 600px` to `.code-content`
- Implemented JavaScript scroll sync between line numbers and code content
- Line numbers now scroll perfectly in sync with code content
### 4. Clickable Error Line Numbers
- Added `cursor: pointer` to error/warning line numbers
- Added "Click to see details" tooltip on error/warning lines
- Implemented click event listeners on all error/warning lines
- Click handler searches through validators to find matching error
- Opens validation modal with correct validator details when clicked
- Added hover effects with `transform: translateX(-2px)` and `cursor: help`
## User Experience Improvements:
- ✅ Error messages are now larger and easier to read (16px)
- ✅ Code snippets wrap naturally without horizontal scroll
- ✅ No excessive whitespace at the beginning of code lines
- ✅ Line numbers stay synchronized during scroll
- ✅ Error line numbers are interactive and open detailed validation modals
- ✅ Better visual hierarchy with improved spacing and sizing
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
spartan