docs: update README with Discord and multi-channel features

README.md

@@ -7,11 +7,13 @@ Agentic coder with **Z.AI + Telegram integration** — Claude Code + Hermes in o
 ## 🚀 Features
 
 - **🤖 AI-Powered Code Generation**: Powered by Z.AI GLM-5.1 (Coding Plan)
-- **📱 Telegram Bot**: 24/7 live interaction via Telegram
+- **📱 Multi-Channel Bot**: Telegram + Discord with real-time delivery
 - **🛠️ Full Engineering Access**: Bash, FileEdit, WebSearch, Git tools
 - **🧠 Agent System**: Code reviewer, architect, DevOps engineer
 - **📚 Skills System**: Pre-built skills for common tasks
 - **⚡ Real-time Updates**: WebSocket-based live communication
+- **🔄 Self-Correction**: Automatic retry with backoff (2 retries)
+- **📦 Multi-Channel Delivery**: Hub-based message routing (Telegram + Discord + WebSocket + log)
 
 ## 📦 Installation
 
@@ -67,14 +69,27 @@ node bin/zcode.js --dev
 node bin/zcode.js --no-bot
 ```
 
-## 🤖 Telegram Bot
+## 🤖 Telegram & Discord Bot
 
-Once running, you can interact with zCode CLI X via Telegram:
+Once running, you can interact with zCode CLI X via multiple channels:
 
+### Telegram
 1. Start the bot: `/start`
 2. Send your code requests or questions
 3. Receive AI-powered responses in real-time
 
+### Discord
+1. Invite the bot to your server
+2. Send commands or questions
+3. Receive responses with full streaming support
+
+### Multi-Channel Delivery
+Messages are automatically delivered to:
+- ✅ Telegram (primary)
+- ✅ Discord
+- ✅ WebSocket (real-time)
+- ✅ Log file (structured)
+
 ## 🛠️ Tools Available
 
 - **Bash**: Execute shell commands
@@ -98,24 +113,37 @@ Once running, you can interact with zCode CLI X via Telegram:
 
 ## 🏗️ Architecture
 
+zCode CLI X uses a hybrid architecture combining:
+- **better-clawd**: Coding backbone (BashTool, FileEditTool, WebSearchTool, GitTool)
+- **Hermes Agent**: Agent system (Code Reviewer, Architect, DevOps)
+- **claudegram**: Bot patterns (grammy, deduplication, request queuing, multi-channel delivery)
+
+### Core Components
+
 ```
 zcode-cli-x/
 ├── bin/
 │   └── zcode.js              # CLI entry point
 ├── src/
-│   ├── api/
-│   │   └── index.js          # Z.AI API adapter
 │   ├── bot/
-│   │   └── index.js          # Telegram bot integration
+│   │   ├── index.js          # Telegram bot (grammy-based)
+│   │   ├── deduplication.js  # Message deduplication (60s TTL)
+│   │   ├── request-queue.js  # Per-chat request queuing
+│   │   ├── message-sender.js # Message chunking (4k limit)
+│   │   ├── delivery-hub.js   # Multi-channel delivery
+│   │   ├── discord.js        # Discord integration (discord.js v14)
+│   │   └── self-correction.js # Self-correction wrapper (2 retries)
+│   ├── api/
+│   │   └── index.js          # Z.AI API adapter (GLM-5.1)
 │   ├── tools/
 │   │   ├── BashTool.js       # Shell command executor
 │   │   ├── FileEditTool.js   # File operations
 │   │   ├── WebSearchTool.js  # Web search
 │   │   └── GitTool.js        # Git operations
-│   ├── skills/
-│   │   └── index.js          # Skills system
 │   ├── agents/
 │   │   └── index.js          # Agent orchestration
+│   ├── skills/
+│   │   └── index.js          # Skills system
 │   └── utils/
 │       ├── logger.js         # Winston logger
 │       └── env.js            # Environment validation
@@ -123,12 +151,32 @@ zcode-cli-x/
 └── package.json
 ```
 
+### Bot Flow
+
+1. **Message Reception**: Telegram/Discord messages → `delivery-hub.js`
+2. **Deduplication Check**: `deduplication.js` (60s TTL)
+3. **Request Queue**: `request-queue.js` (per-chat sequential processing)
+4. **Self-Correction**: `self-correction.js` (2 retries + backoff)
+5. **Agent Execution**: better-clawd tools + Hermes agents
+6. **Response Delivery**: `message-sender.js` → Multi-channel (Telegram + Discord + WebSocket + log)
+
+### Provider Support
+
+- **Z.AI**: GLM-5.1 (Coding Plan) - Primary
+- **Claude**: Anthropic Claude (via API)
+- **OpenCode**: OpenCode CLI integration
+- **Kilo**: Kilo.AI gateway
+
 ## 🔗 Integrations
 
 - **Z.AI API**: GLM-5.1 model with Coding Plan
-- **Telegram Bot API**: Webhook + WebSocket
-- **Express.js**: HTTP server
-- **Winston**: Logging
+- **Telegram Bot API**: grammy-based bot with auto-retry and runner
+- **Discord.js v14**: Discord bot with GatewayIntentBits
+- **Express.js**: HTTP server for webhook handling
+- **Winston**: Structured logging
+- **WebSocket**: Real-time updates
+- **Mongoose**: Database persistence
+- **Puppeteer**: Browser automation
 
 ## 🚀 Getting Started
 
@@ -137,14 +185,21 @@ zcode-cli-x/
    npm install
    ```
 
-2. Configure `.env` with your credentials
+2. Configure `.env` with your credentials:
+   ```env
+   GLM_BASE_URL=https://api.z.ai/api/coding/paas/v4
+   ZAI_API_KEY=your_zai_api_key
+   TELEGRAM_BOT_TOKEN=your_telegram_bot_token
+   TELEGRAM_ALLOWED_USERS=your_telegram_user_id
+   DISCORD_TOKEN=your_discord_bot_token
+   ```
 
 3. Run the bot:
    ```bash
    node bin/zcode.js --bot
    ```
 
-4. Open Telegram and start chatting!
+4. Open Telegram and Discord to start chatting!
 
 ## 📝 License
 
@@ -178,9 +233,9 @@ MIT
 | Batch task processing | ✅ Batch skill (5-30 parallel subagents) | ✅ Parallel batch delegation | ❌ None |
 | **Platform** | | | |
 | Telegram integration | ✅ Native bot + webhook | ✅ 2-way Telegram bridge | ❌ None |
-| Discord | ❌ None | ✅ Full Discord integration | ❌ None |
-| Multi-channel delivery | ❌ Telegram only | ✅ Cron→Telegram/Discord/Email | ❌ None |
-| Voice I/O | ✅ Voice service (STT + TTS) | ✅ TTS + voice memos | ❌ None |
+| Discord | ✅ Native bot (via discord.js) | ✅ Full Discord integration | ❌ None |
+| Multi-channel delivery | ✅ Delivery hub (Telegram + Discord + WebSocket + log) | ✅ Cron→Telegram/Discord/Email | ❌ None |
+| Self-correction loops | ✅ Self-correction wrapper (2 retries + backoff) | ✅ Agent self-correction skill | ❌ None |
 | **Infrastructure** | | | |
 | Model routing | ✅ Multi-provider (OpenAI, Anthropic, Bedrock, custom) | ✅ Multi-provider routing | ❌ Single model |
 | Context compression | ✅ Compact pipeline (auto, micro, session memory) | ✅ lean-ctx MCP (90% savings) | ❌ None |