* feat: Add LINE and Telegram messaging support
This major enhancement extends Claude Code Remote with multi-platform messaging support:
## 🚀 New Features
### LINE Messaging Support
- LINE Bot API integration with token-based commands
- Secure webhook handler with signature verification
- Session management with 24-hour expiration
- Support for both individual and group chats
- User/Group ID whitelist security
### Telegram Bot Support
- Telegram Bot API with interactive buttons
- Slash command support (/cmd TOKEN command)
- Callback query handling for better UX
- Group and private chat support
- Chat ID-based authorization
### Multi-Platform Architecture
- Unified notification system supporting all platforms
- Platform-agnostic session management
- Configurable channel enabling/disabling
- Parallel webhook server support
## 🛠️ Technical Implementation
### Core Components
- `src/channels/line/` - LINE messaging implementation
- `src/channels/telegram/` - Telegram bot implementation
- `src/utils/controller-injector.js` - Command injection utility
- Multi-platform webhook servers with Express.js
### Configuration & Documentation
- Updated `.env.example` with all platform options
- Comprehensive setup guides for each platform
- Testing guide with ngrok instructions
- Updated README with multi-platform support
### Developer Experience
- npm scripts for easy platform startup
- Unified webhook launcher (`start-all-webhooks.js`)
- Individual platform launchers
- Enhanced error handling and logging
## 🔧 Usage Examples
**Telegram:** `/cmd ABC12345 analyze this code`
**LINE:** `Token ABC12345 analyze this code`
**Email:** Reply to notification emails
## 📋 Backward Compatibility
- All existing email functionality preserved
- Configuration migration path provided
- No breaking changes to existing hooks
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Complete Telegram Remote Control System with Direct Chat Mode
### 🚀 Major Features Added
- **Direct Chat Mode**: Users can chat with Claude naturally without /cmd tokens
- **Smart Monitoring**: Intelligent response detection with historical processing
- **One-Click Startup**: Complete system management via startup script
- **Auto-Notification**: Real-time Claude response detection and Telegram delivery
### 📱 Telegram Integration
- `telegram-direct-mode.js`: Direct conversation interface
- `telegram-polling.js`: Command polling with token validation
- Enhanced notification system with markdown formatting
### 🧠 Smart Monitoring System
- `smart-monitor.js`: Advanced response detection with history awareness
- `simple-monitor.js`: Lightweight monitoring alternative
- `auto-notification-daemon.js`: Background notification service
### 🛠️ System Management
- `start-telegram-claude.sh`: Complete service management script
- Environment validation and dependency checking
- Color-coded status reporting and log management
- Process lifecycle management (start/stop/restart/status)
### 📖 Documentation & Testing
- `TELEGRAM_CLAUDE_GUIDE.md`: Comprehensive user guide
- Complete test suite for all components
- Usage examples and troubleshooting guide
### 🔧 Core Improvements
- Enhanced `controller-injector.js` with proper Enter key handling
- Updated `tmux-monitor.js` with real-time output monitoring
- Improved error handling and logging throughout
- Session management with automatic cleanup
### 🎯 Key Capabilities
- **Seamless Communication**: Direct Telegram ⟷ Claude integration
- **Full Automation**: No manual intervention required
- **Robust Monitoring**: Never miss Claude responses
- **Easy Deployment**: Single script startup and management
- **Multi-Modal Support**: Ready for LINE integration expansion
### 📊 System Architecture
```
User → Telegram Bot → Direct Injection → Claude Session → Smart Monitor → Auto Notification → User
```
This completes the transformation from email-based to messaging-app-based remote Claude control,
providing a modern, efficient, and user-friendly interface for remote AI interaction.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: Enhance documentation and smart monitoring system
- Add comprehensive CLAUDE.md for Claude Code development guidance
- Update README.md with multi-platform focus and improved instructions
- Enhance smart-monitor.js with auto-approval for tool permissions
- Improve start-telegram-claude.sh with better tmux session management
- Add auto-approver.js for automated tool permission handling
Key improvements:
- Multi-platform documentation (Telegram, LINE, Email, Local)
- Enhanced troubleshooting and command reference sections
- Smart monitoring with historical response detection
- Automated tool permission approval workflow
- Better tmux integration and session management
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: Add CLAUDE.md to .gitignore and remove from tracking
- Add CLAUDE.md to .gitignore under "Claude Code development files" section
- Remove CLAUDE.md from git tracking while preserving local file
- CLAUDE.md should remain as local development documentation only
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Complete Telegram integration with multi-channel notifications
- ✅ Enhanced Telegram bot with smart buttons for personal/group chats
- ✅ Multi-channel notification system (Desktop, Telegram, Email, LINE)
- ✅ Smart sound alerts with customizable audio feedback
- ✅ Real-time command injection with tmux session management
- ✅ Intelligent session detection and conversation content extraction
- ✅ Unified README documentation with complete setup guides
- 🧹 Clean up legacy files and consolidate documentation
- 📱 Add setup scripts for easy Telegram configuration
- 🔧 Enhance webhook system with improved error handling
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Update processed messages
---------
Co-authored-by: laihenyi <henyi@henyi.org>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: laihenyi <laihenyi@users.noreply.github.com>
* Add configuration option to disable subagent notifications
- Added 'enableSubagentNotifications' config option (default: false)
- Modified notification handler to check config before sending subagent notifications
- Created documentation explaining the feature
- Updated README with note about subagent notifications
This addresses the issue where frequent subagent notifications can be distracting.
Users can now control whether they receive notifications when subagents stop/start.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add subagent activity tracking in completion emails
- Track subagent activities instead of sending individual notifications
- Include subagent activity summary in completion emails
- Update email templates to display subagent activities
- Add SubagentTracker utility to manage activity tracking
- Update documentation to explain the new behavior
This provides a better user experience by:
1. Reducing notification noise from frequent subagent activities
2. Still providing full visibility into what subagents did
3. Consolidating all information in the completion email
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Improve subagent activity details and documentation
- Enhanced activity capture to include up to 1000 characters (was 200)
- Improved email display format with better visual separation
- Added detection for initialization-only captures with helpful message
- Added configuration option for activity detail level
- Created comprehensive documentation explaining the timing limitation
- Added visual indicators for processing status
This addresses the issue where subagent outputs were truncated or only
showed initialization messages. Users now get better visibility into
what subagents are doing, with clear indication when full output is
available in tmux.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* delete redundant files and modify README
* Fix HTML escaping in email notifications
- Add _escapeHtml function to properly escape HTML entities in emails
- Escape user-generated content to prevent HTML tags from being hidden
- Fix issue where <developer> and other HTML-like strings disappeared in emails
- Apply escaping to both main email content and subagent activity summaries
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add full execution trace to email notifications
- Add getFullExecutionTrace method to capture complete terminal output
- Include execution trace in a scrollable section within emails
- Add CSS styling for visible scrollbars on desktop
- Clean trace output by removing command prompt boxes
- Add fallback message when trace is not available
This addresses issue #11 - providing transparency about task execution
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Redesign email notification UI with improved terminal aesthetics
- Reorganize content hierarchy: user request at top, response second, trace at bottom
- Preserve terminal-style commands ($ cat, $ claude-code execute, etc.)
- Remove redundant session info footer
- Implement smart execution trace capture from user input to completion
- Add TraceCapture utility to track user input timestamps
- Improve visual hierarchy while maintaining terminal aesthetics
- Use border colors (orange for user, green for success) for better distinction
- Make execution trace collapsible and de-emphasized
This improves readability while preserving the terminal charm of the project.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix execution trace filtering to show only recent activity
- Change filter logic to find LAST user input instead of first
- Search backwards through content to find most recent "> " prompt
- Only include content from that point forward
- Add fallback to show last 100 lines if no user input found
- This ensures trace shows only relevant recent execution, not entire history
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Remove duplicate content from execution trace
- Skip the first user input line (already shown in main content)
- Skip the last Claude response (already shown in main content)
- Only show intermediate execution steps and tool usage
- Clean up empty lines at beginning and end
- This avoids redundancy and focuses trace on execution details
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix execution trace to properly remove complete user input and output
- Track multi-line user input and skip all continuation lines
- Detect when user input ends (empty line or next command)
- Stop before the last Claude response to avoid truncation
- Only show intermediate execution steps between input and output
This ensures the trace shows the complete execution process without
duplicating content already displayed in the main sections.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix multi-line user input capture and trace filtering
- Capture complete multi-line user input (not just first line)
- Join continuation lines with spaces for proper display
- Preserve all execution details in trace (tool calls, outputs)
- Only skip user input and final response, keep everything in between
* Add configuration toggle for subagent activities in email
- Added 'showSubagentActivitiesInEmail' config option (default: false)
- Modified claude-remote.js to check config before including subagent activities
- Created documentation explaining the configuration
- Allows users to choose between concise emails (execution trace only) or detailed emails (both summaries)
This addresses the redundancy between execution trace and subagent activities summary,
giving users control over email content.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix Git merge conflict in email template and document subagent config
- Removed Git merge conflict markers from email text template
- Added documentation for showSubagentActivitiesInEmail config in README
- Explained that subagent activities are disabled by default for concise emails
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Update README changelog for PR #10 and issue #11
- Added entry for subagent notifications configuration (PR #10)
- Added entry for execution trace feature (issue #11)
- Maintained chronological order in changelog
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* delete redundant files
* fix#15: add local database into .gitignore
* Fix execution trace display in email notifications
- Remove collapsible details tag for better email client compatibility
- Add configuration option to toggle execution trace display
- Fix HTML escaping issue for executionTraceSection variable
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Remove data files from git tracking
These session-specific data files should not be tracked in version control
as they are machine-specific and cause issues when pulling on other machines.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix typo(?) in changelog (#13)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Naich <an.naich@gmail.com>
Co-authored-by: JessyTsui <51992423+JessyTsui@users.noreply.github.com>
* Add configuration option to disable subagent notifications
- Added 'enableSubagentNotifications' config option (default: false)
- Modified notification handler to check config before sending subagent notifications
- Created documentation explaining the feature
- Updated README with note about subagent notifications
This addresses the issue where frequent subagent notifications can be distracting.
Users can now control whether they receive notifications when subagents stop/start.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add subagent activity tracking in completion emails
- Track subagent activities instead of sending individual notifications
- Include subagent activity summary in completion emails
- Update email templates to display subagent activities
- Add SubagentTracker utility to manage activity tracking
- Update documentation to explain the new behavior
This provides a better user experience by:
1. Reducing notification noise from frequent subagent activities
2. Still providing full visibility into what subagents did
3. Consolidating all information in the completion email
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Improve subagent activity details and documentation
- Enhanced activity capture to include up to 1000 characters (was 200)
- Improved email display format with better visual separation
- Added detection for initialization-only captures with helpful message
- Added configuration option for activity detail level
- Created comprehensive documentation explaining the timing limitation
- Added visual indicators for processing status
This addresses the issue where subagent outputs were truncated or only
showed initialization messages. Users now get better visibility into
what subagents are doing, with clear indication when full output is
available in tmux.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* delete redundant files and modify README
* Fix HTML escaping in email notifications
- Add _escapeHtml function to properly escape HTML entities in emails
- Escape user-generated content to prevent HTML tags from being hidden
- Fix issue where <developer> and other HTML-like strings disappeared in emails
- Apply escaping to both main email content and subagent activity summaries
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Major changes:
- Simplify README with clearer setup guide and single-step instructions
- Add changelog section with contributor mentions for all PRs
- Create practical TODO list focusing on key features
- Move demo images to assets folder for better organization
- Remove separate email reply guides, merge content into main README
- Create ROADMAP.md for detailed future feature planning
- Remove temporary data files from tracking
This makes the project more approachable for new users while maintaining
comprehensive documentation for advanced features.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix self-reply loop issue when using same email for send/receive
- Add Message-ID tracking to prevent processing system-sent emails
- Track sent emails in sent-messages.json with auto-cleanup
- Skip system emails in both email-listener.js and relay-pty.js
- Extract session from token/headers/body for proper reply routing
- Reduce verbose logging in tmux-injector to debug level
Fixes#3🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix working directory issue - enable claude-remote to run from any directory
- Use absolute path to load .env file instead of relying on current working directory
- Fix environment variable loading in both main program and relay service
- Now claude-remote can be executed from any directory
Fixes#5
* Fix issue #6: Implement terminal-style UI for email notifications
- Redesigned email template with terminal/console aesthetic
- Used monospace fonts and dark theme for tech look
- Fixed Claude response truncation issue (removed 500 char limit)
- Increased tmux buffer capture from 50 to 200 lines
- Preserved code formatting (removed space collapsing)
- Added terminal-style command prompts and colored output
- Created test script for long content validation
* Fix terminal UI visual issues
- Fixed traffic light buttons spacing (now properly separated)
- Changed background from pure black to lighter gray (#f5f5f5)
- Terminal content background changed to softer dark (#1a1a1a)
- Code blocks background changed to #262626 for better contrast
- Improved overall visual hierarchy and readability
* Fine-tune traffic light button spacing
- Adjusted spacing between buttons from 8px to 6px
- Reduced gap after buttons from 20px to 12px
- Achieved more natural macOS-like appearance
* Use table layout for better email client compatibility
- Changed from inline-flex to table layout for traffic light buttons
- Set explicit 5px spacing between buttons using table cells
- This ensures consistent rendering across different email clients
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Fix self-reply loop issue when using same email for send/receive
- Add Message-ID tracking to prevent processing system-sent emails
- Track sent emails in sent-messages.json with auto-cleanup
- Skip system emails in both email-listener.js and relay-pty.js
- Extract session from token/headers/body for proper reply routing
- Reduce verbose logging in tmux-injector to debug level
Fixes#3🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix working directory issue - enable claude-remote to run from any directory
- Use absolute path to load .env file instead of relying on current working directory
- Fix environment variable loading in both main program and relay service
- Now claude-remote can be executed from any directory
Fixes#5
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Add Message-ID tracking to prevent processing system-sent emails
- Track sent emails in sent-messages.json with auto-cleanup
- Skip system emails in both email-listener.js and relay-pty.js
- Extract session from token/headers/body for proper reply routing
- Reduce verbose logging in tmux-injector to debug level
Fixes#3🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Shows repository star growth over time using star-history.com
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Rename HOW_TO_USE_EMAIL_REPLY.md to HOW_TO_USE_EMAIL_REPLY_ZH.md
- Rename HOW_TO_USE_EMAIL_REPLY_EN.md to HOW_TO_USE_EMAIL_REPLY.md
- Update all language switcher links accordingly
- English version is now the default (no language suffix)
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Create HOW_TO_USE_EMAIL_REPLY_EN.md with full English translation
- Add language switcher to both Chinese and English docs
- Update README.md to link to both language versions
- Ensure consistent formatting between language versions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update project name and metadata in package.json and package-lock.json
- Rename all CLI classes and main entry points
- Fix email notification sender from "TaskPing Notification System" to "Claude-Code-Remote Notification System"
- Update email subject headers from [TaskPing #token] to [Claude-Code-Remote #token]
- Rebrand daemon service and all console output messages
- Update configuration managers and installation scripts
- Modify notification channels and test templates
- Update GitHub repository URLs and author information
- Fix all remaining TaskPing references in codebase
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Replace simple text with YouTube-styled badge
- Use shields.io badge with YouTube branding
- Better visual indication of video link
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add centered layout for video section
- Add "Watch Demo Video" heading with video emoji
- Add play button emoji and "Click to watch on YouTube" text
- Make it clear this is an interactive video link
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add CCRemote_demo.png as video thumbnail
- Link thumbnail to YouTube demo video
- Improve README presentation with visual demo
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 🌍 Full English rewrite for international accessibility
- ✂️ Condensed content focusing on essential information
- 🎯 Streamlined setup process with clear steps
- 📱 Enhanced user flow explanation with examples
- 🐦 Integrated Twitter promotion (@Jiaxi_Cui) in strategic locations
- 🔥 Improved call-to-action for stars and community engagement
- 📊 Better structured troubleshooting section
- 💡 Added practical use cases and tips
Transforms verbose documentation into a clean, professional
README that quickly communicates value and drives engagement.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Rename main file: taskping.js → claude-remote.js
- Create .env.example template file with proper Claude Code Remote branding
- Update all README references from taskping commands to claude-remote.js
- Update email notification subject lines and service names
- Replace all TaskPing references with Claude Code Remote in documentation
- Standardize configuration workflow using cp .env.example .env approach
- Ensure consistent project naming throughout all user-facing content
This completes the rebranding effort to properly reflect the project's
focus on Claude Code remote control functionality.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- 🚀 New user-friendly structure with step-by-step tutorials
- 📋 Clear prerequisites and system requirements
- 🎯 Progressive learning: 5min quick start → 10min email setup → 5min hooks
- 📧 Detailed email configuration for Gmail, Outlook, and other providers
- 🎮 Complete usage workflow with real examples
- 🎯 Advanced features: multiline commands, multi-project management
- 🎬 Real-world use case scenarios
- 🔧 Comprehensive troubleshooting and debugging guide
- 🛡️ Security best practices and explanations
- 📱 Modern, engaging format with emojis and clear sections
Transforms complex technical documentation into an accessible,
step-by-step guide that any developer can follow successfully.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Exclude session files and runtime data from version control
- Keep repository clean for users
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Translated all Chinese comments and documentation to professional English
- Converted all console messages and user interface text to English
- Updated README.md with comprehensive English documentation
- Translated configuration files and templates to English
- Converted error messages and status indicators to English
- Maintained all functionality while improving international accessibility
- Used consistent technical terminology throughout the codebase
Major changes:
- README.md: Complete English rewrite with detailed usage instructions
- All .js files: Chinese comments → English technical documentation
- Configuration files: Chinese labels → English descriptions
- User messages: Chinese prompts → English user interface
- Error handling: Chinese errors → English error messages
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Initial project structure with documentation
- Email automation and notification system
- Claude command integration
- Configuration management system
- Daemon process for task monitoring
- Multi-channel notification support (email, desktop)
- Session data storage
- Development and deployment scripts
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Henter
JessyTsui
Song-Ze Yu
Naich
panda
Kevin Lin