hermes-agent/scripts/whatsapp-bridge/bridge.js

#!/usr/bin/env node
/**
 * Hermes Agent WhatsApp Bridge
 *
 * Standalone Node.js process that connects to WhatsApp via Baileys
 * and exposes HTTP endpoints for the Python gateway adapter.
 *
 * Endpoints (matches gateway/platforms/whatsapp.py expectations):
 *   GET  /messages       - Long-poll for new incoming messages
 *   POST /send           - Send a message { chatId, message, replyTo? }
 *   POST /edit           - Edit a sent message { chatId, messageId, message }
 *   POST /send-media     - Send media natively { chatId, filePath, mediaType?, caption?, fileName? }
 *   POST /typing         - Send typing indicator { chatId }
 *   GET  /chat/:id       - Get chat info
 *   GET  /health         - Health check
 *
 * Usage:
 *   node bridge.js --port 3000 --session ~/.hermes/whatsapp/session
 */

import { makeWASocket, useMultiFileAuthState, DisconnectReason, fetchLatestBaileysVersion, downloadMediaMessage } from '@whiskeysockets/baileys';
import express from 'express';
import { Boom } from '@hapi/boom';
import pino from 'pino';
import path from 'path';
import { mkdirSync, readFileSync, writeFileSync, existsSync, readdirSync } from 'fs';
import { randomBytes } from 'crypto';
import qrcode from 'qrcode-terminal';

// Parse CLI args
const args = process.argv.slice(2);
function getArg(name, defaultVal) {
  const idx = args.indexOf(`--${name}`);
  return idx !== -1 && args[idx + 1] ? args[idx + 1] : defaultVal;
}

const WHATSAPP_DEBUG =
  typeof process !== 'undefined' &&
  process.env &&
  typeof process.env.WHATSAPP_DEBUG === 'string' &&
  ['1', 'true', 'yes', 'on'].includes(process.env.WHATSAPP_DEBUG.toLowerCase());

const PORT = parseInt(getArg('port', '3000'), 10);
const SESSION_DIR = getArg('session', path.join(process.env.HOME || '~', '.hermes', 'whatsapp', 'session'));
const IMAGE_CACHE_DIR = path.join(process.env.HOME || '~', '.hermes', 'image_cache');
const PAIR_ONLY = args.includes('--pair-only');
const WHATSAPP_MODE = getArg('mode', process.env.WHATSAPP_MODE || 'self-chat'); // "bot" or "self-chat"
const ALLOWED_USERS = (process.env.WHATSAPP_ALLOWED_USERS || '').split(',').map(s => s.trim()).filter(Boolean);
const DEFAULT_REPLY_PREFIX = '⚕ *Hermes Agent*\n────────────\n';
const REPLY_PREFIX = process.env.WHATSAPP_REPLY_PREFIX === undefined
  ? DEFAULT_REPLY_PREFIX
  : process.env.WHATSAPP_REPLY_PREFIX.replace(/\\n/g, '\n');

function formatOutgoingMessage(message) {
  return REPLY_PREFIX ? `${REPLY_PREFIX}${message}` : message;
}

mkdirSync(SESSION_DIR, { recursive: true });

// Build LID → phone reverse map from session files (lid-mapping-{phone}.json)
function buildLidMap() {
  const map = {};
  try {
    for (const f of readdirSync(SESSION_DIR)) {
      const m = f.match(/^lid-mapping-(\d+)\.json$/);
      if (!m) continue;
      const phone = m[1];
      const lid = JSON.parse(readFileSync(path.join(SESSION_DIR, f), 'utf8'));
      if (lid) map[String(lid)] = phone;
    }
  } catch {}
  return map;
}
let lidToPhone = buildLidMap();

const logger = pino({ level: 'warn' });

// Message queue for polling
const messageQueue = [];
const MAX_QUEUE_SIZE = 100;

// Track recently sent message IDs to prevent echo-back loops with media
const recentlySentIds = new Set();
const MAX_RECENT_IDS = 50;

let sock = null;
let connectionState = 'disconnected';

async function startSocket() {
  const { state, saveCreds } = await useMultiFileAuthState(SESSION_DIR);
  const { version } = await fetchLatestBaileysVersion();

  sock = makeWASocket({
    version,
    auth: state,
    logger,
    printQRInTerminal: false,
    browser: ['Hermes Agent', 'Chrome', '120.0'],
    syncFullHistory: false,
    markOnlineOnConnect: false,
    // Required for Baileys 7.x: without this, incoming messages that need
    // E2EE session re-establishment are silently dropped (msg.message === null)
    getMessage: async (key) => {
      // We don't maintain a message store, so return a placeholder.
      // This is enough for Baileys to complete the retry handshake.
      return { conversation: '' };
    },
  });

  sock.ev.on('creds.update', () => { saveCreds(); lidToPhone = buildLidMap(); });

  sock.ev.on('connection.update', (update) => {
    const { connection, lastDisconnect, qr } = update;

    if (qr) {
      console.log('\n📱 Scan this QR code with WhatsApp on your phone:\n');
      qrcode.generate(qr, { small: true });
      console.log('\nWaiting for scan...\n');
    }

    if (connection === 'close') {
      const reason = new Boom(lastDisconnect?.error)?.output?.statusCode;
      connectionState = 'disconnected';

      if (reason === DisconnectReason.loggedOut) {
        console.log('❌ Logged out. Delete session and restart to re-authenticate.');
        process.exit(1);
      } else {
        // 515 = restart requested (common after pairing). Always reconnect.
        if (reason === 515) {
          console.log('↻ WhatsApp requested restart (code 515). Reconnecting...');
        } else {
          console.log(`⚠️  Connection closed (reason: ${reason}). Reconnecting in 3s...`);
        }
        setTimeout(startSocket, reason === 515 ? 1000 : 3000);
      }
    } else if (connection === 'open') {
      connectionState = 'connected';
      console.log('✅ WhatsApp connected!');
      if (PAIR_ONLY) {
        console.log('✅ Pairing complete. Credentials saved.');
        // Give Baileys a moment to flush creds, then exit cleanly
        setTimeout(() => process.exit(0), 2000);
      }
    }
  });

  sock.ev.on('messages.upsert', async ({ messages, type }) => {
    // In self-chat mode, your own messages commonly arrive as 'append' rather
    // than 'notify'. Accept both and filter agent echo-backs below.
    if (type !== 'notify' && type !== 'append') return;

    for (const msg of messages) {
      if (!msg.message) continue;

      const chatId = msg.key.remoteJid;
      if (WHATSAPP_DEBUG) {
        try {
          console.log(JSON.stringify({
            event: 'upsert', type,
            fromMe: !!msg.key.fromMe, chatId,
            senderId: msg.key.participant || chatId,
            messageKeys: Object.keys(msg.message || {}),
          }));
        } catch {}
      }
      const senderId = msg.key.participant || chatId;
      const isGroup = chatId.endsWith('@g.us');
      const senderNumber = senderId.replace(/@.*/, '');

      // Handle fromMe messages based on mode
      if (msg.key.fromMe) {
        if (isGroup || chatId.includes('status')) continue;

        if (WHATSAPP_MODE === 'bot') {
          // Bot mode: separate number. ALL fromMe are echo-backs of our own replies — skip.
          continue;
        }

        // Self-chat mode: only allow messages in the user's own self-chat
        // WhatsApp now uses LID (Linked Identity Device) format: 67427329167522@lid
        // AND classic format: 34652029134@s.whatsapp.net
        // sock.user has both: { id: "number:10@s.whatsapp.net", lid: "lid_number:10@lid" }
        const myNumber = (sock.user?.id || '').replace(/:.*@/, '@').replace(/@.*/, '');
        const myLid = (sock.user?.lid || '').replace(/:.*@/, '@').replace(/@.*/, '');
        const chatNumber = chatId.replace(/@.*/, '');
        const isSelfChat = (myNumber && chatNumber === myNumber) || (myLid && chatNumber === myLid);
        if (!isSelfChat) continue;
      }

      // Check allowlist for messages from others (resolve LID → phone if needed)
      if (!msg.key.fromMe && ALLOWED_USERS.length > 0) {
        const resolvedNumber = lidToPhone[senderNumber] || senderNumber;
        if (!ALLOWED_USERS.includes(resolvedNumber)) continue;
      }

      // Extract message body
      let body = '';
      let hasMedia = false;
      let mediaType = '';
      const mediaUrls = [];

      if (msg.message.conversation) {
        body = msg.message.conversation;
      } else if (msg.message.extendedTextMessage?.text) {
        body = msg.message.extendedTextMessage.text;
      } else if (msg.message.imageMessage) {
        body = msg.message.imageMessage.caption || '';
        hasMedia = true;
        mediaType = 'image';
        try {
          const buf = await downloadMediaMessage(msg, 'buffer', {}, { logger, reuploadRequest: sock.updateMediaMessage });
          const mime = msg.message.imageMessage.mimetype || 'image/jpeg';
          const extMap = { 'image/jpeg': '.jpg', 'image/png': '.png', 'image/webp': '.webp', 'image/gif': '.gif' };
          const ext = extMap[mime] || '.jpg';
          mkdirSync(IMAGE_CACHE_DIR, { recursive: true });
          const filePath = path.join(IMAGE_CACHE_DIR, `img_${randomBytes(6).toString('hex')}${ext}`);
          writeFileSync(filePath, buf);
          mediaUrls.push(filePath);
        } catch (err) {
          console.error('[bridge] Failed to download image:', err.message);
        }
      } else if (msg.message.videoMessage) {
        body = msg.message.videoMessage.caption || '';
        hasMedia = true;
        mediaType = 'video';
      } else if (msg.message.audioMessage || msg.message.pttMessage) {
        hasMedia = true;
        mediaType = msg.message.pttMessage ? 'ptt' : 'audio';
      } else if (msg.message.documentMessage) {
        body = msg.message.documentMessage.caption || msg.message.documentMessage.fileName || '';
        hasMedia = true;
        mediaType = 'document';
      }

      // For media without caption, use a placeholder so the API message is never empty
      if (hasMedia && !body) {
        body = `[${mediaType} received]`;
      }

      // Ignore Hermes' own reply messages in self-chat mode to avoid loops.
      if (msg.key.fromMe && ((REPLY_PREFIX && body.startsWith(REPLY_PREFIX)) || recentlySentIds.has(msg.key.id))) {
        if (WHATSAPP_DEBUG) {
          try { console.log(JSON.stringify({ event: 'ignored', reason: 'agent_echo', chatId, messageId: msg.key.id })); } catch {}
        }
        continue;
      }

      // Skip empty messages
      if (!body && !hasMedia) {
        if (WHATSAPP_DEBUG) {
          try { 
            console.log(JSON.stringify({ event: 'ignored', reason: 'empty', chatId, messageKeys: Object.keys(msg.message || {}) })); 
          } catch (err) {
            console.error('Failed to log empty message event:', err);
          }
        }
        continue;
      }

      const event = {
        messageId: msg.key.id,
        chatId,
        senderId,
        senderName: msg.pushName || senderNumber,
        chatName: isGroup ? (chatId.split('@')[0]) : (msg.pushName || senderNumber),
        isGroup,
        body,
        hasMedia,
        mediaType,
        mediaUrls,
        timestamp: msg.messageTimestamp,
      };

      messageQueue.push(event);
      if (messageQueue.length > MAX_QUEUE_SIZE) {
        messageQueue.shift();
      }
    }
  });
}

// HTTP server
const app = express();
app.use(express.json());

// Poll for new messages (long-poll style)
app.get('/messages', (req, res) => {
  const msgs = messageQueue.splice(0, messageQueue.length);
  res.json(msgs);
});

// Send a message
app.post('/send', async (req, res) => {
  if (!sock || connectionState !== 'connected') {
    return res.status(503).json({ error: 'Not connected to WhatsApp' });
  }

  const { chatId, message, replyTo } = req.body;
  if (!chatId || !message) {
    return res.status(400).json({ error: 'chatId and message are required' });
  }

  try {
    const sent = await sock.sendMessage(chatId, { text: formatOutgoingMessage(message) });

    // Track sent message ID to prevent echo-back loops
    if (sent?.key?.id) {
      recentlySentIds.add(sent.key.id);
      if (recentlySentIds.size > MAX_RECENT_IDS) {
        recentlySentIds.delete(recentlySentIds.values().next().value);
      }
    }

    res.json({ success: true, messageId: sent?.key?.id });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// Edit a previously sent message
app.post('/edit', async (req, res) => {
  if (!sock || connectionState !== 'connected') {
    return res.status(503).json({ error: 'Not connected to WhatsApp' });
  }

  const { chatId, messageId, message } = req.body;
  if (!chatId || !messageId || !message) {
    return res.status(400).json({ error: 'chatId, messageId, and message are required' });
  }

  try {
    const key = { id: messageId, fromMe: true, remoteJid: chatId };
    await sock.sendMessage(chatId, { text: formatOutgoingMessage(message), edit: key });
    res.json({ success: true });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// MIME type map and media type inference for /send-media
const MIME_MAP = {
  jpg: 'image/jpeg', jpeg: 'image/jpeg', png: 'image/png',
  webp: 'image/webp', gif: 'image/gif',
  mp4: 'video/mp4', mov: 'video/quicktime', avi: 'video/x-msvideo',
  mkv: 'video/x-matroska', '3gp': 'video/3gpp',
  pdf: 'application/pdf',
  doc: 'application/msword',
  docx: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
  xlsx: 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
};

function inferMediaType(ext) {
  if (['jpg', 'jpeg', 'png', 'webp', 'gif'].includes(ext)) return 'image';
  if (['mp4', 'mov', 'avi', 'mkv', '3gp'].includes(ext)) return 'video';
  if (['ogg', 'opus', 'mp3', 'wav', 'm4a'].includes(ext)) return 'audio';
  return 'document';
}

// Send media (image, video, document) natively
app.post('/send-media', async (req, res) => {
  if (!sock || connectionState !== 'connected') {
    return res.status(503).json({ error: 'Not connected to WhatsApp' });
  }

  const { chatId, filePath, mediaType, caption, fileName } = req.body;
  if (!chatId || !filePath) {
    return res.status(400).json({ error: 'chatId and filePath are required' });
  }

  try {
    if (!existsSync(filePath)) {
      return res.status(404).json({ error: `File not found: ${filePath}` });
    }

    const buffer = readFileSync(filePath);
    const ext = filePath.toLowerCase().split('.').pop();
    const type = mediaType || inferMediaType(ext);
    let msgPayload;

    switch (type) {
      case 'image':
        msgPayload = { image: buffer, caption: caption || undefined, mimetype: MIME_MAP[ext] || 'image/jpeg' };
        break;
      case 'video':
        msgPayload = { video: buffer, caption: caption || undefined, mimetype: MIME_MAP[ext] || 'video/mp4' };
        break;
      case 'audio': {
        const audioMime = (ext === 'ogg' || ext === 'opus') ? 'audio/ogg; codecs=opus' : 'audio/mpeg';
        msgPayload = { audio: buffer, mimetype: audioMime, ptt: ext === 'ogg' || ext === 'opus' };
        break;
      }
      case 'document':
      default:
        msgPayload = {
          document: buffer,
          fileName: fileName || path.basename(filePath),
          caption: caption || undefined,
          mimetype: MIME_MAP[ext] || 'application/octet-stream',
        };
        break;
    }

    const sent = await sock.sendMessage(chatId, msgPayload);

    // Track sent message ID to prevent echo-back loops
    if (sent?.key?.id) {
      recentlySentIds.add(sent.key.id);
      if (recentlySentIds.size > MAX_RECENT_IDS) {
        recentlySentIds.delete(recentlySentIds.values().next().value);
      }
    }

    res.json({ success: true, messageId: sent?.key?.id });
  } catch (err) {
    res.status(500).json({ error: err.message });
  }
});

// Typing indicator
app.post('/typing', async (req, res) => {
  if (!sock || connectionState !== 'connected') {
    return res.status(503).json({ error: 'Not connected' });
  }

  const { chatId } = req.body;
  if (!chatId) return res.status(400).json({ error: 'chatId required' });

  try {
    await sock.sendPresenceUpdate('composing', chatId);
    res.json({ success: true });
  } catch (err) {
    res.json({ success: false });
  }
});

// Chat info
app.get('/chat/:id', async (req, res) => {
  const chatId = req.params.id;
  const isGroup = chatId.endsWith('@g.us');

  if (isGroup && sock) {
    try {
      const metadata = await sock.groupMetadata(chatId);
      return res.json({
        name: metadata.subject,
        isGroup: true,
        participants: metadata.participants.map(p => p.id),
      });
    } catch {
      // Fall through to default
    }
  }

  res.json({
    name: chatId.replace(/@.*/, ''),
    isGroup,
    participants: [],
  });
});

// Health check
app.get('/health', (req, res) => {
  res.json({
    status: connectionState,
    queueLength: messageQueue.length,
    uptime: process.uptime(),
  });
});

// Start
if (PAIR_ONLY) {
  // Pair-only mode: just connect, show QR, save creds, exit. No HTTP server.
  console.log('📱 WhatsApp pairing mode');
  console.log(`📁 Session: ${SESSION_DIR}`);
  console.log();
  startSocket();
} else {
  app.listen(PORT, '127.0.0.1', () => {
    console.log(`🌉 WhatsApp bridge listening on port ${PORT} (mode: ${WHATSAPP_MODE})`);
    console.log(`📁 Session stored in: ${SESSION_DIR}`);
    if (ALLOWED_USERS.length > 0) {
      console.log(`🔒 Allowed users: ${ALLOWED_USERS.join(', ')}`);
    } else {
      console.log(`⚠️  No WHATSAPP_ALLOWED_USERS set — all messages will be processed`);
    }
    console.log();
    startSocket();
  });
}