Enhance CLI with multi-platform messaging integration and configuration management

- Updated CLI to load configuration from user-specific and project-specific YAML files, prioritizing user settings.
- Introduced a new command `/platforms` to display the status of connected messaging platforms (Telegram, Discord, WhatsApp).
- Implemented a gateway system for handling messaging interactions, including session management and delivery routing for cron job outputs.
- Added support for environment variable configuration and a dedicated gateway configuration file for advanced settings.
- Enhanced documentation in README.md and added a new messaging.md file to guide users on platform integrations and setup.
- Updated toolsets to include platform-specific capabilities for Telegram, Discord, and WhatsApp, ensuring secure and tailored interactions.
This commit is contained in:
teknium1 2026-02-02 19:01:51 -08:00
parent a3ba41fce2
commit 619c72e566
37 changed files with 8559 additions and 757 deletions

View file

@ -0,0 +1,17 @@
"""
Platform adapters for messaging integrations.
Each adapter handles:
- Receiving messages from a platform
- Sending messages/responses back
- Platform-specific authentication
- Message formatting and media handling
"""
from .base import BasePlatformAdapter, MessageEvent, SendResult
__all__ = [
"BasePlatformAdapter",
"MessageEvent",
"SendResult",
]

274
gateway/platforms/base.py Normal file
View file

@ -0,0 +1,274 @@
"""
Base platform adapter interface.
All platform adapters (Telegram, Discord, WhatsApp) inherit from this
and implement the required methods.
"""
from abc import ABC, abstractmethod
from dataclasses import dataclass, field
from datetime import datetime
from typing import Dict, List, Optional, Any, Callable, Awaitable
from enum import Enum
import sys
sys.path.insert(0, str(__file__).rsplit("/", 3)[0])
from gateway.config import Platform, PlatformConfig
from gateway.session import SessionSource
class MessageType(Enum):
"""Types of incoming messages."""
TEXT = "text"
PHOTO = "photo"
VIDEO = "video"
AUDIO = "audio"
VOICE = "voice"
DOCUMENT = "document"
STICKER = "sticker"
COMMAND = "command" # /command style
@dataclass
class MessageEvent:
"""
Incoming message from a platform.
Normalized representation that all adapters produce.
"""
# Message content
text: str
message_type: MessageType = MessageType.TEXT
# Source information
source: SessionSource = None
# Original platform data
raw_message: Any = None
message_id: Optional[str] = None
# Media attachments
media_urls: List[str] = field(default_factory=list)
media_types: List[str] = field(default_factory=list)
# Reply context
reply_to_message_id: Optional[str] = None
# Timestamps
timestamp: datetime = field(default_factory=datetime.now)
def is_command(self) -> bool:
"""Check if this is a command message (e.g., /new, /reset)."""
return self.text.startswith("/")
def get_command(self) -> Optional[str]:
"""Extract command name if this is a command message."""
if not self.is_command():
return None
# Split on space and get first word, strip the /
parts = self.text.split(maxsplit=1)
return parts[0][1:].lower() if parts else None
def get_command_args(self) -> str:
"""Get the arguments after a command."""
if not self.is_command():
return self.text
parts = self.text.split(maxsplit=1)
return parts[1] if len(parts) > 1 else ""
@dataclass
class SendResult:
"""Result of sending a message."""
success: bool
message_id: Optional[str] = None
error: Optional[str] = None
raw_response: Any = None
# Type for message handlers
MessageHandler = Callable[[MessageEvent], Awaitable[Optional[str]]]
class BasePlatformAdapter(ABC):
"""
Base class for platform adapters.
Subclasses implement platform-specific logic for:
- Connecting and authenticating
- Receiving messages
- Sending messages/responses
- Handling media
"""
def __init__(self, config: PlatformConfig, platform: Platform):
self.config = config
self.platform = platform
self._message_handler: Optional[MessageHandler] = None
self._running = False
@property
def name(self) -> str:
"""Human-readable name for this adapter."""
return self.platform.value.title()
@property
def is_connected(self) -> bool:
"""Check if adapter is currently connected."""
return self._running
def set_message_handler(self, handler: MessageHandler) -> None:
"""
Set the handler for incoming messages.
The handler receives a MessageEvent and should return
an optional response string.
"""
self._message_handler = handler
@abstractmethod
async def connect(self) -> bool:
"""
Connect to the platform and start receiving messages.
Returns True if connection was successful.
"""
pass
@abstractmethod
async def disconnect(self) -> None:
"""Disconnect from the platform."""
pass
@abstractmethod
async def send(
self,
chat_id: str,
content: str,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None
) -> SendResult:
"""
Send a message to a chat.
Args:
chat_id: The chat/channel ID to send to
content: Message content (may be markdown)
reply_to: Optional message ID to reply to
metadata: Additional platform-specific options
Returns:
SendResult with success status and message ID
"""
pass
async def send_typing(self, chat_id: str) -> None:
"""
Send a typing indicator.
Override in subclasses if the platform supports it.
"""
pass
async def handle_message(self, event: MessageEvent) -> None:
"""
Process an incoming message.
Calls the registered message handler and sends the response.
"""
if not self._message_handler:
return
try:
# Send typing indicator
await self.send_typing(event.source.chat_id)
# Call the handler
response = await self._message_handler(event)
# Send response if any
if response:
await self.send(
chat_id=event.source.chat_id,
content=response,
reply_to=event.message_id
)
except Exception as e:
print(f"[{self.name}] Error handling message: {e}")
def build_source(
self,
chat_id: str,
chat_name: Optional[str] = None,
chat_type: str = "dm",
user_id: Optional[str] = None,
user_name: Optional[str] = None,
thread_id: Optional[str] = None
) -> SessionSource:
"""Helper to build a SessionSource for this platform."""
return SessionSource(
platform=self.platform,
chat_id=str(chat_id),
chat_name=chat_name,
chat_type=chat_type,
user_id=str(user_id) if user_id else None,
user_name=user_name,
thread_id=str(thread_id) if thread_id else None,
)
@abstractmethod
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
"""
Get information about a chat/channel.
Returns dict with at least:
- name: Chat name
- type: "dm", "group", "channel"
"""
pass
def format_message(self, content: str) -> str:
"""
Format a message for this platform.
Override in subclasses to handle platform-specific formatting
(e.g., Telegram MarkdownV2, Discord markdown).
Default implementation returns content as-is.
"""
return content
def truncate_message(self, content: str, max_length: int = 4096) -> List[str]:
"""
Split a long message into chunks.
Args:
content: The full message content
max_length: Maximum length per chunk (platform-specific)
Returns:
List of message chunks
"""
if len(content) <= max_length:
return [content]
chunks = []
while content:
if len(content) <= max_length:
chunks.append(content)
break
# Try to split at a newline
split_idx = content.rfind("\n", 0, max_length)
if split_idx == -1:
# No newline, split at space
split_idx = content.rfind(" ", 0, max_length)
if split_idx == -1:
# No space either, hard split
split_idx = max_length
chunks.append(content[:split_idx])
content = content[split_idx:].lstrip()
return chunks

View file

@ -0,0 +1,297 @@
"""
Discord platform adapter.
Uses discord.py library for:
- Receiving messages from servers and DMs
- Sending responses back
- Handling threads and channels
"""
import asyncio
from typing import Dict, List, Optional, Any
try:
import discord
from discord import Message as DiscordMessage, Intents
from discord.ext import commands
DISCORD_AVAILABLE = True
except ImportError:
DISCORD_AVAILABLE = False
discord = None
DiscordMessage = Any
Intents = Any
commands = None
import sys
sys.path.insert(0, str(__file__).rsplit("/", 3)[0])
from gateway.config import Platform, PlatformConfig
from gateway.platforms.base import (
BasePlatformAdapter,
MessageEvent,
MessageType,
SendResult,
)
def check_discord_requirements() -> bool:
"""Check if Discord dependencies are available."""
return DISCORD_AVAILABLE
class DiscordAdapter(BasePlatformAdapter):
"""
Discord bot adapter.
Handles:
- Receiving messages from servers and DMs
- Sending responses with Discord markdown
- Thread support
- Slash commands (future)
"""
# Discord message limits
MAX_MESSAGE_LENGTH = 2000
def __init__(self, config: PlatformConfig):
super().__init__(config, Platform.DISCORD)
self._client: Optional[commands.Bot] = None
self._ready_event = asyncio.Event()
async def connect(self) -> bool:
"""Connect to Discord and start receiving events."""
if not DISCORD_AVAILABLE:
print(f"[{self.name}] discord.py not installed. Run: pip install discord.py")
return False
if not self.config.token:
print(f"[{self.name}] No bot token configured")
return False
try:
# Set up intents
intents = Intents.default()
intents.message_content = True
intents.dm_messages = True
intents.guild_messages = True
# Create bot
self._client = commands.Bot(
command_prefix="!", # Not really used, we handle raw messages
intents=intents,
)
# Register event handlers
@self._client.event
async def on_ready():
print(f"[{self.name}] Connected as {self._client.user}")
self._ready_event.set()
@self._client.event
async def on_message(message: DiscordMessage):
# Ignore bot's own messages
if message.author == self._client.user:
return
await self._handle_message(message)
# Start the bot in background
asyncio.create_task(self._client.start(self.config.token))
# Wait for ready
await asyncio.wait_for(self._ready_event.wait(), timeout=30)
self._running = True
return True
except asyncio.TimeoutError:
print(f"[{self.name}] Timeout waiting for connection")
return False
except Exception as e:
print(f"[{self.name}] Failed to connect: {e}")
return False
async def disconnect(self) -> None:
"""Disconnect from Discord."""
if self._client:
try:
await self._client.close()
except Exception as e:
print(f"[{self.name}] Error during disconnect: {e}")
self._running = False
self._client = None
self._ready_event.clear()
print(f"[{self.name}] Disconnected")
async def send(
self,
chat_id: str,
content: str,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None
) -> SendResult:
"""Send a message to a Discord channel."""
if not self._client:
return SendResult(success=False, error="Not connected")
try:
# Get the channel
channel = self._client.get_channel(int(chat_id))
if not channel:
channel = await self._client.fetch_channel(int(chat_id))
if not channel:
return SendResult(success=False, error=f"Channel {chat_id} not found")
# Format and split message if needed
formatted = self.format_message(content)
chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
message_ids = []
reference = None
if reply_to:
try:
ref_msg = await channel.fetch_message(int(reply_to))
reference = ref_msg
except Exception:
pass # Ignore if we can't find the referenced message
for i, chunk in enumerate(chunks):
msg = await channel.send(
content=chunk,
reference=reference if i == 0 else None,
)
message_ids.append(str(msg.id))
return SendResult(
success=True,
message_id=message_ids[0] if message_ids else None,
raw_response={"message_ids": message_ids}
)
except Exception as e:
return SendResult(success=False, error=str(e))
async def send_typing(self, chat_id: str) -> None:
"""Send typing indicator."""
if self._client:
try:
channel = self._client.get_channel(int(chat_id))
if channel:
await channel.typing()
except Exception:
pass # Ignore typing indicator failures
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
"""Get information about a Discord channel."""
if not self._client:
return {"name": "Unknown", "type": "dm"}
try:
channel = self._client.get_channel(int(chat_id))
if not channel:
channel = await self._client.fetch_channel(int(chat_id))
if not channel:
return {"name": str(chat_id), "type": "dm"}
# Determine channel type
if isinstance(channel, discord.DMChannel):
chat_type = "dm"
name = channel.recipient.name if channel.recipient else str(chat_id)
elif isinstance(channel, discord.Thread):
chat_type = "thread"
name = channel.name
elif isinstance(channel, discord.TextChannel):
chat_type = "channel"
name = f"#{channel.name}"
if channel.guild:
name = f"{channel.guild.name} / {name}"
else:
chat_type = "channel"
name = getattr(channel, "name", str(chat_id))
return {
"name": name,
"type": chat_type,
"guild_id": str(channel.guild.id) if hasattr(channel, "guild") and channel.guild else None,
"guild_name": channel.guild.name if hasattr(channel, "guild") and channel.guild else None,
}
except Exception as e:
return {"name": str(chat_id), "type": "dm", "error": str(e)}
def format_message(self, content: str) -> str:
"""
Format message for Discord.
Discord uses its own markdown variant.
"""
# Discord markdown is fairly standard, no special escaping needed
return content
async def _handle_message(self, message: DiscordMessage) -> None:
"""Handle incoming Discord messages."""
# Determine message type
msg_type = MessageType.TEXT
if message.content.startswith("/"):
msg_type = MessageType.COMMAND
elif message.attachments:
# Check attachment types
for att in message.attachments:
if att.content_type:
if att.content_type.startswith("image/"):
msg_type = MessageType.PHOTO
elif att.content_type.startswith("video/"):
msg_type = MessageType.VIDEO
elif att.content_type.startswith("audio/"):
msg_type = MessageType.AUDIO
else:
msg_type = MessageType.DOCUMENT
break
# Determine chat type
if isinstance(message.channel, discord.DMChannel):
chat_type = "dm"
chat_name = message.author.name
elif isinstance(message.channel, discord.Thread):
chat_type = "thread"
chat_name = message.channel.name
else:
chat_type = "group" # Treat server channels as groups
chat_name = getattr(message.channel, "name", str(message.channel.id))
if hasattr(message.channel, "guild") and message.channel.guild:
chat_name = f"{message.channel.guild.name} / #{chat_name}"
# Get thread ID if in a thread
thread_id = None
if isinstance(message.channel, discord.Thread):
thread_id = str(message.channel.id)
# Build source
source = self.build_source(
chat_id=str(message.channel.id),
chat_name=chat_name,
chat_type=chat_type,
user_id=str(message.author.id),
user_name=message.author.display_name,
thread_id=thread_id,
)
# Build media URLs
media_urls = [att.url for att in message.attachments]
media_types = [att.content_type or "unknown" for att in message.attachments]
event = MessageEvent(
text=message.content,
message_type=msg_type,
source=source,
raw_message=message,
message_id=str(message.id),
media_urls=media_urls,
media_types=media_types,
reply_to_message_id=str(message.reference.message_id) if message.reference else None,
timestamp=message.created_at,
)
await self.handle_message(event)

View file

@ -0,0 +1,284 @@
"""
Telegram platform adapter.
Uses python-telegram-bot library for:
- Receiving messages from users/groups
- Sending responses back
- Handling media and commands
"""
import asyncio
from typing import Dict, List, Optional, Any
try:
from telegram import Update, Bot, Message
from telegram.ext import (
Application,
CommandHandler,
MessageHandler as TelegramMessageHandler,
ContextTypes,
filters,
)
from telegram.constants import ParseMode, ChatType
TELEGRAM_AVAILABLE = True
except ImportError:
TELEGRAM_AVAILABLE = False
Update = Any
Bot = Any
Message = Any
Application = Any
ContextTypes = Any
import sys
sys.path.insert(0, str(__file__).rsplit("/", 3)[0])
from gateway.config import Platform, PlatformConfig
from gateway.platforms.base import (
BasePlatformAdapter,
MessageEvent,
MessageType,
SendResult,
)
def check_telegram_requirements() -> bool:
"""Check if Telegram dependencies are available."""
return TELEGRAM_AVAILABLE
class TelegramAdapter(BasePlatformAdapter):
"""
Telegram bot adapter.
Handles:
- Receiving messages from users and groups
- Sending responses with Telegram markdown
- Forum topics (thread_id support)
- Media messages
"""
# Telegram message limits
MAX_MESSAGE_LENGTH = 4096
def __init__(self, config: PlatformConfig):
super().__init__(config, Platform.TELEGRAM)
self._app: Optional[Application] = None
self._bot: Optional[Bot] = None
async def connect(self) -> bool:
"""Connect to Telegram and start polling for updates."""
if not TELEGRAM_AVAILABLE:
print(f"[{self.name}] python-telegram-bot not installed. Run: pip install python-telegram-bot")
return False
if not self.config.token:
print(f"[{self.name}] No bot token configured")
return False
try:
# Build the application
self._app = Application.builder().token(self.config.token).build()
self._bot = self._app.bot
# Register handlers
self._app.add_handler(TelegramMessageHandler(
filters.TEXT & ~filters.COMMAND,
self._handle_text_message
))
self._app.add_handler(TelegramMessageHandler(
filters.COMMAND,
self._handle_command
))
self._app.add_handler(TelegramMessageHandler(
filters.PHOTO | filters.VIDEO | filters.AUDIO | filters.VOICE | filters.Document.ALL,
self._handle_media_message
))
# Start polling in background
await self._app.initialize()
await self._app.start()
await self._app.updater.start_polling(allowed_updates=Update.ALL_TYPES)
self._running = True
print(f"[{self.name}] Connected and polling for updates")
return True
except Exception as e:
print(f"[{self.name}] Failed to connect: {e}")
return False
async def disconnect(self) -> None:
"""Stop polling and disconnect."""
if self._app:
try:
await self._app.updater.stop()
await self._app.stop()
await self._app.shutdown()
except Exception as e:
print(f"[{self.name}] Error during disconnect: {e}")
self._running = False
self._app = None
self._bot = None
print(f"[{self.name}] Disconnected")
async def send(
self,
chat_id: str,
content: str,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None
) -> SendResult:
"""Send a message to a Telegram chat."""
if not self._bot:
return SendResult(success=False, error="Not connected")
try:
# Format and split message if needed
formatted = self.format_message(content)
chunks = self.truncate_message(formatted, self.MAX_MESSAGE_LENGTH)
message_ids = []
thread_id = metadata.get("thread_id") if metadata else None
for i, chunk in enumerate(chunks):
msg = await self._bot.send_message(
chat_id=int(chat_id),
text=chunk,
parse_mode=ParseMode.MARKDOWN,
reply_to_message_id=int(reply_to) if reply_to and i == 0 else None,
message_thread_id=int(thread_id) if thread_id else None,
)
message_ids.append(str(msg.message_id))
return SendResult(
success=True,
message_id=message_ids[0] if message_ids else None,
raw_response={"message_ids": message_ids}
)
except Exception as e:
return SendResult(success=False, error=str(e))
async def send_typing(self, chat_id: str) -> None:
"""Send typing indicator."""
if self._bot:
try:
await self._bot.send_chat_action(
chat_id=int(chat_id),
action="typing"
)
except Exception:
pass # Ignore typing indicator failures
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
"""Get information about a Telegram chat."""
if not self._bot:
return {"name": "Unknown", "type": "dm"}
try:
chat = await self._bot.get_chat(int(chat_id))
chat_type = "dm"
if chat.type == ChatType.GROUP:
chat_type = "group"
elif chat.type == ChatType.SUPERGROUP:
chat_type = "group"
if chat.is_forum:
chat_type = "forum"
elif chat.type == ChatType.CHANNEL:
chat_type = "channel"
return {
"name": chat.title or chat.full_name or str(chat_id),
"type": chat_type,
"username": chat.username,
"is_forum": getattr(chat, "is_forum", False),
}
except Exception as e:
return {"name": str(chat_id), "type": "dm", "error": str(e)}
def format_message(self, content: str) -> str:
"""
Format message for Telegram.
Telegram uses a subset of markdown. We'll use the simpler
Markdown mode (not MarkdownV2) for compatibility.
"""
# Basic escaping for Telegram Markdown
# In Markdown mode (not V2), only certain characters need escaping
return content
async def _handle_text_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle incoming text messages."""
if not update.message or not update.message.text:
return
event = self._build_message_event(update.message, MessageType.TEXT)
await self.handle_message(event)
async def _handle_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle incoming command messages."""
if not update.message or not update.message.text:
return
event = self._build_message_event(update.message, MessageType.COMMAND)
await self.handle_message(event)
async def _handle_media_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle incoming media messages."""
if not update.message:
return
msg = update.message
# Determine media type
if msg.photo:
msg_type = MessageType.PHOTO
elif msg.video:
msg_type = MessageType.VIDEO
elif msg.audio:
msg_type = MessageType.AUDIO
elif msg.voice:
msg_type = MessageType.VOICE
else:
msg_type = MessageType.DOCUMENT
event = self._build_message_event(msg, msg_type)
# Add caption as text
if msg.caption:
event.text = msg.caption
await self.handle_message(event)
def _build_message_event(self, message: Message, msg_type: MessageType) -> MessageEvent:
"""Build a MessageEvent from a Telegram message."""
chat = message.chat
user = message.from_user
# Determine chat type
chat_type = "dm"
if chat.type in (ChatType.GROUP, ChatType.SUPERGROUP):
chat_type = "group"
elif chat.type == ChatType.CHANNEL:
chat_type = "channel"
# Build source
source = self.build_source(
chat_id=str(chat.id),
chat_name=chat.title or (chat.full_name if hasattr(chat, "full_name") else None),
chat_type=chat_type,
user_id=str(user.id) if user else None,
user_name=user.full_name if user else None,
thread_id=str(message.message_thread_id) if message.message_thread_id else None,
)
return MessageEvent(
text=message.text or "",
message_type=msg_type,
source=source,
raw_message=message,
message_id=str(message.message_id),
timestamp=message.date,
)

View file

@ -0,0 +1,327 @@
"""
WhatsApp platform adapter.
WhatsApp integration is more complex than Telegram/Discord because:
- No official bot API for personal accounts
- Business API requires Meta Business verification
- Most solutions use web-based automation
This adapter supports multiple backends:
1. WhatsApp Business API (requires Meta verification)
2. whatsapp-web.js (via Node.js subprocess) - for personal accounts
3. Baileys (via Node.js subprocess) - alternative for personal accounts
For simplicity, we'll implement a generic interface that can work
with different backends via a bridge pattern.
"""
import asyncio
import json
import subprocess
from pathlib import Path
from typing import Dict, List, Optional, Any
import sys
sys.path.insert(0, str(__file__).rsplit("/", 3)[0])
from gateway.config import Platform, PlatformConfig
from gateway.platforms.base import (
BasePlatformAdapter,
MessageEvent,
MessageType,
SendResult,
)
def check_whatsapp_requirements() -> bool:
"""
Check if WhatsApp dependencies are available.
WhatsApp requires a Node.js bridge for most implementations.
"""
# Check for Node.js
try:
result = subprocess.run(
["node", "--version"],
capture_output=True,
text=True,
timeout=5
)
return result.returncode == 0
except Exception:
return False
class WhatsAppAdapter(BasePlatformAdapter):
"""
WhatsApp adapter.
This implementation uses a simple HTTP bridge pattern where:
1. A Node.js process runs the WhatsApp Web client
2. Messages are forwarded via HTTP/IPC to this Python adapter
3. Responses are sent back through the bridge
The actual Node.js bridge implementation can vary:
- whatsapp-web.js based
- Baileys based
- Business API based
Configuration:
- bridge_script: Path to the Node.js bridge script
- bridge_port: Port for HTTP communication (default: 3000)
- session_path: Path to store WhatsApp session data
"""
# WhatsApp message limits
MAX_MESSAGE_LENGTH = 65536 # WhatsApp allows longer messages
def __init__(self, config: PlatformConfig):
super().__init__(config, Platform.WHATSAPP)
self._bridge_process: Optional[subprocess.Popen] = None
self._bridge_port: int = config.extra.get("bridge_port", 3000)
self._bridge_script: Optional[str] = config.extra.get("bridge_script")
self._session_path: Path = Path(config.extra.get(
"session_path",
Path.home() / ".hermes" / "whatsapp" / "session"
))
self._message_queue: asyncio.Queue = asyncio.Queue()
async def connect(self) -> bool:
"""
Start the WhatsApp bridge.
This launches the Node.js bridge process and waits for it to be ready.
"""
if not check_whatsapp_requirements():
print(f"[{self.name}] Node.js not found. WhatsApp requires Node.js.")
return False
if not self._bridge_script:
print(f"[{self.name}] No bridge script configured.")
print(f"[{self.name}] Set 'bridge_script' in whatsapp.extra config.")
print(f"[{self.name}] See docs/messaging.md for WhatsApp setup instructions.")
return False
bridge_path = Path(self._bridge_script)
if not bridge_path.exists():
print(f"[{self.name}] Bridge script not found: {bridge_path}")
return False
try:
# Ensure session directory exists
self._session_path.mkdir(parents=True, exist_ok=True)
# Start the bridge process
self._bridge_process = subprocess.Popen(
[
"node",
str(bridge_path),
"--port", str(self._bridge_port),
"--session", str(self._session_path),
],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True,
)
# Wait for bridge to be ready (look for ready signal)
# This is a simplified version - real implementation would
# wait for an HTTP health check or specific stdout message
await asyncio.sleep(5)
if self._bridge_process.poll() is not None:
stderr = self._bridge_process.stderr.read() if self._bridge_process.stderr else ""
print(f"[{self.name}] Bridge process died: {stderr}")
return False
# Start message polling task
asyncio.create_task(self._poll_messages())
self._running = True
print(f"[{self.name}] Bridge started on port {self._bridge_port}")
print(f"[{self.name}] Scan QR code if prompted (check bridge output)")
return True
except Exception as e:
print(f"[{self.name}] Failed to start bridge: {e}")
return False
async def disconnect(self) -> None:
"""Stop the WhatsApp bridge."""
if self._bridge_process:
try:
self._bridge_process.terminate()
await asyncio.sleep(1)
if self._bridge_process.poll() is None:
self._bridge_process.kill()
except Exception as e:
print(f"[{self.name}] Error stopping bridge: {e}")
self._running = False
self._bridge_process = None
print(f"[{self.name}] Disconnected")
async def send(
self,
chat_id: str,
content: str,
reply_to: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None
) -> SendResult:
"""Send a message via the WhatsApp bridge."""
if not self._running:
return SendResult(success=False, error="Not connected")
try:
import aiohttp
async with aiohttp.ClientSession() as session:
payload = {
"chatId": chat_id,
"message": content,
}
if reply_to:
payload["replyTo"] = reply_to
async with session.post(
f"http://localhost:{self._bridge_port}/send",
json=payload,
timeout=aiohttp.ClientTimeout(total=30)
) as resp:
if resp.status == 200:
data = await resp.json()
return SendResult(
success=True,
message_id=data.get("messageId"),
raw_response=data
)
else:
error = await resp.text()
return SendResult(success=False, error=error)
except ImportError:
return SendResult(
success=False,
error="aiohttp not installed. Run: pip install aiohttp"
)
except Exception as e:
return SendResult(success=False, error=str(e))
async def send_typing(self, chat_id: str) -> None:
"""Send typing indicator via bridge."""
if not self._running:
return
try:
import aiohttp
async with aiohttp.ClientSession() as session:
await session.post(
f"http://localhost:{self._bridge_port}/typing",
json={"chatId": chat_id},
timeout=aiohttp.ClientTimeout(total=5)
)
except Exception:
pass # Ignore typing indicator failures
async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
"""Get information about a WhatsApp chat."""
if not self._running:
return {"name": "Unknown", "type": "dm"}
try:
import aiohttp
async with aiohttp.ClientSession() as session:
async with session.get(
f"http://localhost:{self._bridge_port}/chat/{chat_id}",
timeout=aiohttp.ClientTimeout(total=10)
) as resp:
if resp.status == 200:
data = await resp.json()
return {
"name": data.get("name", chat_id),
"type": "group" if data.get("isGroup") else "dm",
"participants": data.get("participants", []),
}
except Exception:
pass
return {"name": chat_id, "type": "dm"}
async def _poll_messages(self) -> None:
"""Poll the bridge for incoming messages."""
try:
import aiohttp
except ImportError:
print(f"[{self.name}] aiohttp not installed, message polling disabled")
return
while self._running:
try:
async with aiohttp.ClientSession() as session:
async with session.get(
f"http://localhost:{self._bridge_port}/messages",
timeout=aiohttp.ClientTimeout(total=30)
) as resp:
if resp.status == 200:
messages = await resp.json()
for msg_data in messages:
event = self._build_message_event(msg_data)
if event:
await self.handle_message(event)
except asyncio.CancelledError:
break
except Exception as e:
print(f"[{self.name}] Poll error: {e}")
await asyncio.sleep(5)
await asyncio.sleep(1) # Poll interval
def _build_message_event(self, data: Dict[str, Any]) -> Optional[MessageEvent]:
"""Build a MessageEvent from bridge message data."""
try:
# Determine message type
msg_type = MessageType.TEXT
if data.get("hasMedia"):
media_type = data.get("mediaType", "")
if "image" in media_type:
msg_type = MessageType.PHOTO
elif "video" in media_type:
msg_type = MessageType.VIDEO
elif "audio" in media_type or "ptt" in media_type: # ptt = voice note
msg_type = MessageType.VOICE
else:
msg_type = MessageType.DOCUMENT
# Determine chat type
is_group = data.get("isGroup", False)
chat_type = "group" if is_group else "dm"
# Build source
source = self.build_source(
chat_id=data.get("chatId", ""),
chat_name=data.get("chatName"),
chat_type=chat_type,
user_id=data.get("senderId"),
user_name=data.get("senderName"),
)
return MessageEvent(
text=data.get("body", ""),
message_type=msg_type,
source=source,
raw_message=data,
message_id=data.get("messageId"),
media_urls=data.get("mediaUrls", []),
)
except Exception as e:
print(f"[{self.name}] Error building event: {e}")
return None
# Note: A reference Node.js bridge script would be provided in scripts/whatsapp-bridge/
# It would use whatsapp-web.js or Baileys to:
# 1. Handle WhatsApp Web authentication (QR code)
# 2. Listen for incoming messages
# 3. Expose HTTP endpoints for send/receive/status