refactor(whatsapp): replace bridge with neonize
This commit is contained in:
chengyongru
Xubin Ren
+577
-329
@@ -1,24 +1,23 @@
|
||||
"""WhatsApp channel implementation using Node.js bridge."""
|
||||
"""WhatsApp channel implementation using neonize."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import json
|
||||
import mimetypes
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
import shutil
|
||||
import subprocess
|
||||
import time
|
||||
from collections import OrderedDict
|
||||
from contextlib import suppress
|
||||
from pathlib import Path
|
||||
from typing import Any, Literal
|
||||
from typing import Any, Literal, NamedTuple
|
||||
|
||||
from loguru import logger
|
||||
from pydantic import Field
|
||||
|
||||
from nanobot.bus.events import OutboundMessage
|
||||
from nanobot.bus.queue import MessageBus
|
||||
from nanobot.channels.base import BaseChannel
|
||||
from nanobot.config.paths import get_media_dir, get_runtime_subdir
|
||||
from nanobot.config.schema import Base
|
||||
|
||||
|
||||
@@ -26,45 +25,244 @@ class WhatsAppConfig(Base):
|
||||
"""WhatsApp channel configuration."""
|
||||
|
||||
enabled: bool = False
|
||||
bridge_url: str = "ws://localhost:3001"
|
||||
bridge_token: str = ""
|
||||
allow_from: list[str] = Field(default_factory=list)
|
||||
group_policy: Literal["open", "mention"] = "open" # "open" responds to all, "mention" only when @mentioned
|
||||
# Optional static LID->phone mappings, e.g. {"123456789012345": "15551234567"}.
|
||||
# Useful to resolve a sender's phone number from the very first message instead of
|
||||
# only after a message that carries both phone and LID. Merged with mappings the
|
||||
# bridge persists on disk (lid-mapping-*_reverse.json) under the auth directory.
|
||||
group_policy: Literal["open", "mention"] = "open"
|
||||
database_path: str = ""
|
||||
lid_mappings: dict[str, str] = Field(default_factory=dict)
|
||||
|
||||
|
||||
def _bridge_token_path() -> Path:
|
||||
from nanobot.config.paths import get_runtime_subdir
|
||||
|
||||
return get_runtime_subdir("whatsapp-auth") / "bridge-token"
|
||||
class _NeonizeAPI(NamedTuple):
|
||||
NewAClient: Any
|
||||
ConnectedEv: Any
|
||||
DisconnectedEv: Any
|
||||
MessageEv: Any
|
||||
PairStatusEv: Any
|
||||
build_jid: Any
|
||||
|
||||
|
||||
def _load_or_create_bridge_token(path: Path) -> str:
|
||||
"""Load a persisted bridge token or create one on first use."""
|
||||
if path.exists():
|
||||
token = path.read_text(encoding="utf-8").strip()
|
||||
if token:
|
||||
return token
|
||||
class _MediaInfo(NamedTuple):
|
||||
kind: str
|
||||
message: Any
|
||||
mimetype: str
|
||||
filename: str
|
||||
is_voice: bool = False
|
||||
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
token = secrets.token_urlsafe(32)
|
||||
path.write_text(token, encoding="utf-8")
|
||||
with suppress(OSError):
|
||||
path.chmod(0o600)
|
||||
return token
|
||||
|
||||
_NEONIZE_API: _NeonizeAPI | None = None
|
||||
_JID_RE = re.compile(r"^(?P<user>[^@]+)@(?P<server>[^@]+)$")
|
||||
|
||||
|
||||
def _default_database_path() -> Path:
|
||||
return get_runtime_subdir("whatsapp-auth") / "neonize.db"
|
||||
|
||||
|
||||
def _load_neonize() -> _NeonizeAPI:
|
||||
global _NEONIZE_API
|
||||
if _NEONIZE_API is not None:
|
||||
return _NEONIZE_API
|
||||
|
||||
try:
|
||||
from neonize.aioze.client import NewAClient
|
||||
from neonize.aioze.events import ConnectedEv, DisconnectedEv, MessageEv, PairStatusEv
|
||||
from neonize.utils.jid import build_jid
|
||||
except ImportError as exc:
|
||||
raise RuntimeError(
|
||||
'WhatsApp dependencies not installed. Run: pip install "nanobot-ai[whatsapp]"'
|
||||
) from exc
|
||||
|
||||
_NEONIZE_API = _NeonizeAPI(
|
||||
NewAClient=NewAClient,
|
||||
ConnectedEv=ConnectedEv,
|
||||
DisconnectedEv=DisconnectedEv,
|
||||
MessageEv=MessageEv,
|
||||
PairStatusEv=PairStatusEv,
|
||||
build_jid=build_jid,
|
||||
)
|
||||
return _NEONIZE_API
|
||||
|
||||
|
||||
def _has_field(message: Any, name: str) -> bool:
|
||||
if message is None:
|
||||
return False
|
||||
|
||||
has_field = getattr(message, "HasField", None)
|
||||
if callable(has_field):
|
||||
try:
|
||||
return bool(has_field(name))
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
list_fields = getattr(message, "ListFields", None)
|
||||
if callable(list_fields):
|
||||
try:
|
||||
return any(getattr(field, "name", "") == name for field, _ in list_fields())
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
value = getattr(message, name, None)
|
||||
return value is not None and value != "" and value != b""
|
||||
|
||||
|
||||
def _message_field(message: Any, *names: str) -> Any:
|
||||
for name in names:
|
||||
if _has_field(message, name):
|
||||
return getattr(message, name)
|
||||
return None
|
||||
|
||||
|
||||
def _safe_attr(obj: Any, name: str, default: Any = None) -> Any:
|
||||
if obj is None:
|
||||
return default
|
||||
return getattr(obj, name, default)
|
||||
|
||||
|
||||
def _jid_to_string(jid: Any) -> str:
|
||||
if jid is None:
|
||||
return ""
|
||||
if isinstance(jid, str):
|
||||
return jid.strip()
|
||||
if bool(_safe_attr(jid, "IsEmpty", False)):
|
||||
return ""
|
||||
|
||||
user = str(_safe_attr(jid, "User", "") or "").strip()
|
||||
server = str(_safe_attr(jid, "Server", "") or "").strip()
|
||||
if user and server:
|
||||
return f"{user}@{server}"
|
||||
return server or user
|
||||
|
||||
|
||||
def _normalize_jid(raw: Any) -> str:
|
||||
jid = _jid_to_string(raw).strip()
|
||||
if not jid:
|
||||
return ""
|
||||
if jid.endswith("@lid.whatsapp.net"):
|
||||
return jid[: -len(".whatsapp.net")]
|
||||
return jid
|
||||
|
||||
|
||||
def _bare_jid(raw: Any) -> str:
|
||||
jid = _normalize_jid(raw)
|
||||
if "@" not in jid:
|
||||
return jid
|
||||
return jid.split("@", 1)[0].split(":", 1)[0]
|
||||
|
||||
|
||||
def _classify_sender_ids(jids: list[Any]) -> tuple[str, str]:
|
||||
phone_id = ""
|
||||
lid_id = ""
|
||||
|
||||
for raw in jids:
|
||||
jid = _normalize_jid(raw)
|
||||
if not jid:
|
||||
continue
|
||||
match = _JID_RE.match(jid)
|
||||
if match:
|
||||
user = match.group("user").split(":", 1)[0]
|
||||
server = match.group("server")
|
||||
if server in {"s.whatsapp.net", "c.us"}:
|
||||
phone_id = phone_id or user
|
||||
elif server in {"lid", "lid.whatsapp.net"}:
|
||||
lid_id = lid_id or user
|
||||
continue
|
||||
|
||||
if not phone_id:
|
||||
phone_id = jid
|
||||
|
||||
return phone_id, lid_id
|
||||
|
||||
|
||||
def _context_infos(message: Any) -> list[Any]:
|
||||
infos: list[Any] = []
|
||||
for container in (
|
||||
message,
|
||||
_message_field(message, "extendedTextMessage"),
|
||||
_message_field(message, "imageMessage"),
|
||||
_message_field(message, "videoMessage"),
|
||||
_message_field(message, "audioMessage"),
|
||||
_message_field(message, "documentMessage"),
|
||||
_message_field(message, "stickerMessage"),
|
||||
):
|
||||
context = _message_field(container, "contextInfo")
|
||||
if context is not None:
|
||||
infos.append(context)
|
||||
return infos
|
||||
|
||||
|
||||
def _message_text(message: Any) -> str:
|
||||
conversation = str(_safe_attr(message, "conversation", "") or "").strip()
|
||||
if conversation:
|
||||
return conversation
|
||||
|
||||
extended = _message_field(message, "extendedTextMessage")
|
||||
text = str(_safe_attr(extended, "text", "") or "").strip()
|
||||
if text:
|
||||
return text
|
||||
|
||||
for field_name in ("imageMessage", "videoMessage", "documentMessage", "stickerMessage"):
|
||||
media_message = _message_field(message, field_name)
|
||||
caption = str(_safe_attr(media_message, "caption", "") or "").strip()
|
||||
if caption:
|
||||
return caption
|
||||
|
||||
return ""
|
||||
|
||||
|
||||
def _media_message(message: Any) -> _MediaInfo | None:
|
||||
image = _message_field(message, "imageMessage")
|
||||
if image is not None:
|
||||
return _MediaInfo(
|
||||
kind="image",
|
||||
message=image,
|
||||
mimetype=str(_safe_attr(image, "mimetype", "") or "image/jpeg"),
|
||||
filename=str(_safe_attr(image, "fileName", "") or ""),
|
||||
)
|
||||
|
||||
video = _message_field(message, "videoMessage")
|
||||
if video is not None:
|
||||
return _MediaInfo(
|
||||
kind="video",
|
||||
message=video,
|
||||
mimetype=str(_safe_attr(video, "mimetype", "") or "video/mp4"),
|
||||
filename=str(_safe_attr(video, "fileName", "") or ""),
|
||||
)
|
||||
|
||||
audio = _message_field(message, "audioMessage")
|
||||
if audio is not None:
|
||||
return _MediaInfo(
|
||||
kind="audio",
|
||||
message=audio,
|
||||
mimetype=str(_safe_attr(audio, "mimetype", "") or "audio/ogg"),
|
||||
filename=str(_safe_attr(audio, "fileName", "") or ""),
|
||||
is_voice=bool(_safe_attr(audio, "PTT", False) or _safe_attr(audio, "ptt", False)),
|
||||
)
|
||||
|
||||
document = _message_field(message, "documentMessage")
|
||||
if document is not None:
|
||||
return _MediaInfo(
|
||||
kind="file",
|
||||
message=document,
|
||||
mimetype=str(_safe_attr(document, "mimetype", "") or "application/octet-stream"),
|
||||
filename=str(
|
||||
_safe_attr(document, "fileName", "")
|
||||
or _safe_attr(document, "title", "")
|
||||
or ""
|
||||
),
|
||||
)
|
||||
|
||||
sticker = _message_field(message, "stickerMessage")
|
||||
if sticker is not None:
|
||||
return _MediaInfo(
|
||||
kind="sticker",
|
||||
message=sticker,
|
||||
mimetype=str(_safe_attr(sticker, "mimetype", "") or "image/webp"),
|
||||
filename=str(_safe_attr(sticker, "fileName", "") or ""),
|
||||
)
|
||||
|
||||
return None
|
||||
|
||||
|
||||
class WhatsAppChannel(BaseChannel):
|
||||
"""
|
||||
WhatsApp channel that connects to a Node.js bridge.
|
||||
|
||||
The bridge uses @whiskeysockets/baileys to handle the WhatsApp Web protocol.
|
||||
Communication between Python and Node.js is via WebSocket.
|
||||
"""
|
||||
"""WhatsApp channel using neonize's async WhatsApp client."""
|
||||
|
||||
name = "whatsapp"
|
||||
display_name = "WhatsApp"
|
||||
@@ -77,346 +275,396 @@ class WhatsAppChannel(BaseChannel):
|
||||
if isinstance(config, dict):
|
||||
config = WhatsAppConfig.model_validate(config)
|
||||
super().__init__(config, bus)
|
||||
self._ws = None
|
||||
self._client: Any | None = None
|
||||
self._connected = False
|
||||
self._processed_message_ids: OrderedDict[str, None] = OrderedDict()
|
||||
self._lid_to_phone: dict[str, str] = self._load_lid_mappings()
|
||||
self._bridge_token: str | None = None
|
||||
self._lid_to_phone = self._load_lid_mappings()
|
||||
self._self_jids: set[str] = set()
|
||||
self._started_at = 0.0
|
||||
|
||||
def _database_path(self) -> Path:
|
||||
configured = self.config.database_path.strip()
|
||||
return Path(configured).expanduser() if configured else _default_database_path()
|
||||
|
||||
def _load_lid_mappings(self) -> dict[str, str]:
|
||||
"""Seed LID->phone mappings on startup.
|
||||
|
||||
Combines two sources so the sender's phone number can be resolved from the
|
||||
very first message (instead of only after one that carries both phone and LID):
|
||||
|
||||
1. Reverse mapping files the bridge persists in the auth directory, named
|
||||
``lid-mapping-<lid>_reverse.json`` and containing the phone number string.
|
||||
2. Static ``lid_mappings`` from the channel config (takes precedence).
|
||||
"""
|
||||
from nanobot.config.paths import get_runtime_subdir
|
||||
|
||||
mapping: dict[str, str] = {}
|
||||
auth_dir = get_runtime_subdir("whatsapp-auth")
|
||||
if auth_dir.is_dir():
|
||||
for path in auth_dir.glob("lid-mapping-*_reverse.json"):
|
||||
lid = path.name[len("lid-mapping-"):-len("_reverse.json")]
|
||||
try:
|
||||
phone = json.loads(path.read_text(encoding="utf-8"))
|
||||
except Exception:
|
||||
continue
|
||||
if isinstance(phone, str) and phone.strip():
|
||||
mapping[lid] = phone.strip()
|
||||
|
||||
for lid, phone in getattr(self.config, "lid_mappings", {}).items():
|
||||
if isinstance(phone, str) and phone.strip():
|
||||
mapping[str(lid)] = phone.strip()
|
||||
|
||||
for lid, phone in self.config.lid_mappings.items():
|
||||
phone_text = str(phone).strip()
|
||||
if phone_text:
|
||||
mapping[str(lid).strip()] = phone_text
|
||||
return mapping
|
||||
|
||||
def _effective_bridge_token(self) -> str:
|
||||
"""Resolve the bridge token, generating a local secret when needed."""
|
||||
if self._bridge_token is not None:
|
||||
return self._bridge_token
|
||||
configured = self.config.bridge_token.strip()
|
||||
if configured:
|
||||
self._bridge_token = configured
|
||||
else:
|
||||
self._bridge_token = _load_or_create_bridge_token(_bridge_token_path())
|
||||
return self._bridge_token
|
||||
def _new_client(self) -> Any:
|
||||
api = _load_neonize()
|
||||
db_path = self._database_path()
|
||||
db_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
return api.NewAClient(str(db_path))
|
||||
|
||||
async def login(self, force: bool = False) -> bool:
|
||||
"""
|
||||
Set up and run the WhatsApp bridge for QR code login.
|
||||
db_path = self._database_path()
|
||||
if force:
|
||||
self._reset_database(db_path)
|
||||
|
||||
client = self._new_client()
|
||||
login_result = asyncio.get_running_loop().create_future()
|
||||
self._register_handlers(client, login_result=login_result, handle_messages=False)
|
||||
|
||||
This spawns the Node.js bridge process which handles the WhatsApp
|
||||
authentication flow. The process blocks until the user scans the QR code
|
||||
or interrupts with Ctrl+C.
|
||||
"""
|
||||
try:
|
||||
bridge_dir = _ensure_bridge_setup()
|
||||
except RuntimeError:
|
||||
self.logger.exception("bridge setup failed")
|
||||
self.logger.info("Starting WhatsApp login with neonize...")
|
||||
connect_task = await client.connect()
|
||||
self._fail_login_on_connect_task_done(connect_task, login_result)
|
||||
await login_result
|
||||
self.logger.info("WhatsApp login complete")
|
||||
return True
|
||||
except Exception as exc:
|
||||
self.logger.error("WhatsApp login failed: {}", exc)
|
||||
return False
|
||||
|
||||
env = {**os.environ}
|
||||
env["BRIDGE_TOKEN"] = self._effective_bridge_token()
|
||||
env["AUTH_DIR"] = str(_bridge_token_path().parent)
|
||||
|
||||
self.logger.info("Starting WhatsApp bridge for QR login...")
|
||||
try:
|
||||
subprocess.run(
|
||||
[shutil.which("npm"), "start"], cwd=bridge_dir, check=True, env=env
|
||||
)
|
||||
except subprocess.CalledProcessError:
|
||||
return False
|
||||
|
||||
return True
|
||||
finally:
|
||||
with suppress(Exception):
|
||||
await client.stop()
|
||||
|
||||
async def start(self) -> None:
|
||||
"""Start the WhatsApp channel by connecting to the bridge."""
|
||||
import websockets
|
||||
|
||||
bridge_url = self.config.bridge_url
|
||||
|
||||
self.logger.info("Connecting to WhatsApp bridge at {}...", bridge_url)
|
||||
|
||||
self._running = True
|
||||
self._started_at = time.time()
|
||||
client = self._new_client()
|
||||
self._client = client
|
||||
self._register_handlers(client, handle_messages=True)
|
||||
|
||||
while self._running:
|
||||
try:
|
||||
async with websockets.connect(bridge_url) as ws:
|
||||
self._ws = ws
|
||||
await ws.send(
|
||||
json.dumps({"type": "auth", "token": self._effective_bridge_token()})
|
||||
)
|
||||
self._connected = True
|
||||
self.logger.info("Connected to WhatsApp bridge")
|
||||
|
||||
# Listen for messages
|
||||
async for message in ws:
|
||||
try:
|
||||
await self._handle_bridge_message(message)
|
||||
except Exception:
|
||||
self.logger.exception("Error handling bridge message")
|
||||
|
||||
except asyncio.CancelledError:
|
||||
break
|
||||
except Exception as e:
|
||||
self._connected = False
|
||||
self._ws = None
|
||||
self.logger.warning("WhatsApp bridge connection error: {}", e)
|
||||
|
||||
if self._running:
|
||||
self.logger.info("Reconnecting in 5 seconds...")
|
||||
await asyncio.sleep(5)
|
||||
try:
|
||||
self.logger.info("Connecting WhatsApp channel with neonize...")
|
||||
await client.connect()
|
||||
await client.idle()
|
||||
except asyncio.CancelledError:
|
||||
raise
|
||||
finally:
|
||||
self._running = False
|
||||
self._connected = False
|
||||
if self._client is client:
|
||||
self._client = None
|
||||
with suppress(Exception):
|
||||
await client.stop()
|
||||
|
||||
async def stop(self) -> None:
|
||||
"""Stop the WhatsApp channel."""
|
||||
self._running = False
|
||||
self._connected = False
|
||||
client = self._client
|
||||
self._client = None
|
||||
if client is not None:
|
||||
await client.stop()
|
||||
|
||||
if self._ws:
|
||||
await self._ws.close()
|
||||
self._ws = None
|
||||
@staticmethod
|
||||
def _fail_login_on_connect_task_done(
|
||||
connect_task: asyncio.Task[Any] | None,
|
||||
login_result: asyncio.Future[None],
|
||||
) -> None:
|
||||
if connect_task is None:
|
||||
return
|
||||
|
||||
def _on_done(task: asyncio.Task[Any]) -> None:
|
||||
try:
|
||||
exc = task.exception()
|
||||
except asyncio.CancelledError:
|
||||
return
|
||||
if login_result.done():
|
||||
return
|
||||
if exc is not None:
|
||||
login_result.set_exception(exc)
|
||||
else:
|
||||
login_result.set_exception(
|
||||
RuntimeError("WhatsApp connection ended before login completed")
|
||||
)
|
||||
|
||||
connect_task.add_done_callback(_on_done)
|
||||
|
||||
async def send(self, msg: OutboundMessage) -> None:
|
||||
"""Send a message through WhatsApp."""
|
||||
if not self._ws or not self._connected:
|
||||
self.logger.warning("WhatsApp bridge not connected")
|
||||
return
|
||||
|
||||
chat_id = msg.chat_id
|
||||
client = self._client
|
||||
if client is None or not self._connected:
|
||||
raise RuntimeError("WhatsApp channel is not connected")
|
||||
|
||||
to = self._build_jid(msg.chat_id)
|
||||
if msg.content:
|
||||
try:
|
||||
payload = {"type": "send", "to": chat_id, "text": msg.content}
|
||||
await self._ws.send(json.dumps(payload, ensure_ascii=False))
|
||||
except Exception:
|
||||
self.logger.exception("Error sending message")
|
||||
raise
|
||||
await client.send_message(to, msg.content)
|
||||
|
||||
for media_path in msg.media or []:
|
||||
try:
|
||||
mime, _ = mimetypes.guess_type(media_path)
|
||||
payload = {
|
||||
"type": "send_media",
|
||||
"to": chat_id,
|
||||
"filePath": media_path,
|
||||
"mimetype": mime or "application/octet-stream",
|
||||
"fileName": media_path.rsplit("/", 1)[-1],
|
||||
}
|
||||
await self._ws.send(json.dumps(payload, ensure_ascii=False))
|
||||
except Exception:
|
||||
self.logger.exception("Error sending media {}", media_path)
|
||||
raise
|
||||
await self._send_media(client, to, media_path)
|
||||
|
||||
async def _handle_bridge_message(self, raw: str) -> None:
|
||||
"""Handle a message from the bridge."""
|
||||
try:
|
||||
data = json.loads(raw)
|
||||
except json.JSONDecodeError:
|
||||
self.logger.warning("Invalid JSON from bridge: {}", raw[:100])
|
||||
return
|
||||
def _build_jid(self, raw: str) -> Any:
|
||||
api = _load_neonize()
|
||||
target = raw.strip()
|
||||
match = _JID_RE.match(_normalize_jid(target))
|
||||
if not match:
|
||||
return api.build_jid(target)
|
||||
|
||||
msg_type = data.get("type")
|
||||
user = match.group("user").split(":", 1)[0]
|
||||
server = match.group("server")
|
||||
return api.build_jid(user, server)
|
||||
|
||||
if msg_type == "message":
|
||||
# Incoming message from WhatsApp
|
||||
# Deprecated by whatsapp: old phone number style typically: <phone>@s.whatspp.net
|
||||
pn = data.get("pn", "")
|
||||
# New LID sytle typically:
|
||||
sender = data.get("sender", "")
|
||||
content = data.get("content", "")
|
||||
message_id = data.get("id", "")
|
||||
|
||||
# Extract just the phone number or lid as chat_id
|
||||
is_group = data.get("isGroup", False)
|
||||
was_mentioned = bool(data.get("wasMentioned", False) or data.get("isReplyToBot", False))
|
||||
|
||||
if is_group and getattr(self.config, "group_policy", "open") == "mention":
|
||||
if not was_mentioned:
|
||||
return
|
||||
|
||||
# Classify by JID suffix: @s.whatsapp.net = phone, @lid.whatsapp.net = LID
|
||||
# The bridge's pn/sender fields don't consistently map to phone/LID across versions.
|
||||
raw_a = pn or ""
|
||||
participant = data.get("participant", "")
|
||||
raw_b = participant or sender or ""
|
||||
id_a = raw_a.split("@")[0] if "@" in raw_a else raw_a
|
||||
id_b = raw_b.split("@")[0] if "@" in raw_b else raw_b
|
||||
|
||||
phone_id = ""
|
||||
lid_id = ""
|
||||
for raw, extracted in [(raw_a, id_a), (raw_b, id_b)]:
|
||||
if "@s.whatsapp.net" in raw:
|
||||
phone_id = extracted
|
||||
elif "@lid.whatsapp.net" in raw:
|
||||
lid_id = extracted
|
||||
elif extracted and not phone_id:
|
||||
phone_id = extracted # best guess for bare values
|
||||
|
||||
sender_id = phone_id or self._lid_to_phone.get(lid_id, "") or lid_id or id_a or id_b
|
||||
if not self.is_allowed(sender_id):
|
||||
return
|
||||
|
||||
if message_id:
|
||||
if message_id in self._processed_message_ids:
|
||||
return
|
||||
self._processed_message_ids[message_id] = None
|
||||
while len(self._processed_message_ids) > 1000:
|
||||
self._processed_message_ids.popitem(last=False)
|
||||
|
||||
if phone_id and lid_id:
|
||||
self._lid_to_phone[lid_id] = phone_id
|
||||
|
||||
self.logger.info("Sender phone={} lid={} → sender_id={}", phone_id or "(empty)", lid_id or "(empty)", sender_id)
|
||||
|
||||
# Extract media paths (images/documents/videos downloaded by the bridge)
|
||||
media_paths = data.get("media") or []
|
||||
|
||||
# Handle voice transcription if it's a voice message
|
||||
if content == "[Voice Message]":
|
||||
if media_paths:
|
||||
self.logger.info("Transcribing voice message from {}...", sender_id)
|
||||
transcription = await self.transcribe_audio(media_paths[0])
|
||||
if transcription:
|
||||
content = transcription
|
||||
media_paths = []
|
||||
self.logger.info("Transcribed voice from {}: {}...", sender_id, transcription[:50])
|
||||
else:
|
||||
content = "[Voice Message: Transcription failed]"
|
||||
else:
|
||||
content = "[Voice Message: Audio not available]"
|
||||
|
||||
# Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
|
||||
if media_paths:
|
||||
for p in media_paths:
|
||||
mime, _ = mimetypes.guess_type(p)
|
||||
media_type = "image" if mime and mime.startswith("image/") else "file"
|
||||
media_tag = f"[{media_type}: {p}]"
|
||||
content = f"{content}\n{media_tag}" if content else media_tag
|
||||
|
||||
await self._handle_message(
|
||||
sender_id=sender_id,
|
||||
chat_id=sender, # Use full LID for replies
|
||||
content=content,
|
||||
media=media_paths,
|
||||
metadata={
|
||||
"message_id": message_id,
|
||||
"timestamp": data.get("timestamp"),
|
||||
"is_group": data.get("isGroup", False),
|
||||
"is_forwarded": bool(data.get("isForwarded", False)),
|
||||
"participant": participant or None,
|
||||
"is_reply_to_bot": data.get("isReplyToBot", False),
|
||||
},
|
||||
async def _send_media(self, client: Any, to: Any, media_path: str) -> None:
|
||||
path = str(Path(media_path).expanduser())
|
||||
mime, _ = mimetypes.guess_type(path)
|
||||
mimetype = mime or "application/octet-stream"
|
||||
if mimetype.startswith("image/"):
|
||||
await client.send_image(to, path)
|
||||
elif mimetype.startswith("video/"):
|
||||
await client.send_video(to, path)
|
||||
elif mimetype.startswith("audio/"):
|
||||
await client.send_audio(to, path)
|
||||
else:
|
||||
await client.send_document(
|
||||
to,
|
||||
path,
|
||||
filename=Path(path).name,
|
||||
mimetype=mimetype,
|
||||
)
|
||||
|
||||
elif msg_type == "status":
|
||||
# Connection status update
|
||||
status = data.get("status")
|
||||
self.logger.info("Status: {}", status)
|
||||
def _register_handlers(
|
||||
self,
|
||||
client: Any,
|
||||
*,
|
||||
login_result: asyncio.Future[None] | None = None,
|
||||
handle_messages: bool,
|
||||
) -> None:
|
||||
api = _load_neonize()
|
||||
|
||||
if status == "connected":
|
||||
self._connected = True
|
||||
elif status == "disconnected":
|
||||
self._connected = False
|
||||
@client.qr
|
||||
async def _on_qr(_: Any, qr_data: bytes) -> None:
|
||||
import segno
|
||||
|
||||
elif msg_type == "qr":
|
||||
# QR code for authentication
|
||||
self.logger.info("Scan QR code in the bridge terminal to connect WhatsApp")
|
||||
self.logger.info("Scan the WhatsApp QR code with Linked Devices")
|
||||
segno.make_qr(qr_data).terminal(compact=True)
|
||||
|
||||
elif msg_type == "error":
|
||||
self.logger.error("Bridge error: {}", data.get("error"))
|
||||
@client.event(api.ConnectedEv)
|
||||
async def _on_connected(current_client: Any, _: Any) -> None:
|
||||
self._connected = True
|
||||
try:
|
||||
await self._remember_self_jids(current_client)
|
||||
except Exception as exc:
|
||||
if login_result is not None and not login_result.done():
|
||||
login_result.set_exception(exc)
|
||||
raise
|
||||
if login_result is not None and not login_result.done():
|
||||
login_result.set_result(None)
|
||||
self.logger.info("WhatsApp connected")
|
||||
|
||||
@client.event(api.DisconnectedEv)
|
||||
async def _on_disconnected(_: Any, event: Any) -> None:
|
||||
self._connected = False
|
||||
if login_result is not None and not login_result.done():
|
||||
login_result.set_exception(
|
||||
RuntimeError(f"WhatsApp disconnected before login completed: {event}")
|
||||
)
|
||||
self.logger.warning("WhatsApp disconnected: {}", event)
|
||||
|
||||
def _ensure_bridge_setup() -> Path:
|
||||
"""
|
||||
Ensure the WhatsApp bridge is set up and built.
|
||||
@client.event(api.PairStatusEv)
|
||||
async def _on_pair_status(_: Any, event: Any) -> None:
|
||||
error = str(_safe_attr(event, "Error", "") or "")
|
||||
if error:
|
||||
exc = RuntimeError(f"WhatsApp pair status error: {error}")
|
||||
if login_result is not None and not login_result.done():
|
||||
login_result.set_exception(exc)
|
||||
raise exc
|
||||
self.logger.info("WhatsApp pair status: {}", event)
|
||||
|
||||
Returns the bridge directory. Raises RuntimeError if npm is not found
|
||||
or bridge cannot be built.
|
||||
"""
|
||||
from nanobot.config.paths import get_bridge_install_dir
|
||||
if not handle_messages:
|
||||
return
|
||||
|
||||
user_bridge = get_bridge_install_dir()
|
||||
stamp_file = user_bridge / ".nanobot-bridge-source-hash"
|
||||
@client.event(api.MessageEv)
|
||||
async def _on_message(current_client: Any, event: Any) -> None:
|
||||
try:
|
||||
await self._handle_neonize_message(current_client, event)
|
||||
except Exception:
|
||||
self.logger.exception("Error handling WhatsApp message")
|
||||
raise
|
||||
|
||||
# Find source bridge
|
||||
current_file = Path(__file__)
|
||||
pkg_bridge = current_file.parent.parent / "bridge"
|
||||
src_bridge = current_file.parent.parent.parent / "bridge"
|
||||
async def _remember_self_jids(self, client: Any) -> None:
|
||||
device = _safe_attr(client, "me")
|
||||
if device is None:
|
||||
device = await client.get_me()
|
||||
|
||||
source = None
|
||||
if (pkg_bridge / "package.json").exists():
|
||||
source = pkg_bridge
|
||||
elif (src_bridge / "package.json").exists():
|
||||
source = src_bridge
|
||||
for attr in ("JID", "LID"):
|
||||
jid = _normalize_jid(_safe_attr(device, attr))
|
||||
if jid:
|
||||
self._self_jids.add(jid)
|
||||
self._self_jids.add(_bare_jid(jid))
|
||||
|
||||
if not source:
|
||||
raise RuntimeError(
|
||||
"WhatsApp bridge source not found. "
|
||||
"Try reinstalling: pip install --force-reinstall nanobot"
|
||||
async def _handle_neonize_message(self, client: Any, event: Any) -> None:
|
||||
info = _safe_attr(event, "Info")
|
||||
message = _safe_attr(event, "Message")
|
||||
source = _safe_attr(info, "MessageSource")
|
||||
if info is None or message is None or source is None:
|
||||
raise ValueError("WhatsApp MessageEv is missing Info, Message, or MessageSource")
|
||||
|
||||
if bool(_safe_attr(source, "IsFromMe", False)):
|
||||
return
|
||||
|
||||
chat_jid = _normalize_jid(_safe_attr(source, "Chat"))
|
||||
if not chat_jid:
|
||||
raise ValueError("WhatsApp message has no chat JID")
|
||||
if chat_jid == "status@broadcast":
|
||||
return
|
||||
|
||||
timestamp = float(_safe_attr(info, "Timestamp", 0) or 0)
|
||||
if self._started_at and timestamp and timestamp < self._started_at:
|
||||
return
|
||||
|
||||
is_group = bool(_safe_attr(source, "IsGroup", False))
|
||||
if is_group and self.config.group_policy == "mention":
|
||||
if not self._is_addressed_to_bot(message):
|
||||
return
|
||||
|
||||
message_id = str(_safe_attr(info, "ID", "") or "")
|
||||
if message_id:
|
||||
if message_id in self._processed_message_ids:
|
||||
return
|
||||
self._processed_message_ids[message_id] = None
|
||||
while len(self._processed_message_ids) > 1000:
|
||||
self._processed_message_ids.popitem(last=False)
|
||||
|
||||
participant_jid = _normalize_jid(_safe_attr(source, "Sender"))
|
||||
sender_alt_jid = _normalize_jid(_safe_attr(source, "SenderAlt"))
|
||||
sender_candidates = [sender_alt_jid, participant_jid]
|
||||
if not is_group:
|
||||
sender_candidates.append(chat_jid)
|
||||
|
||||
phone_id, lid_id = _classify_sender_ids(sender_candidates)
|
||||
if phone_id and lid_id:
|
||||
self._lid_to_phone[lid_id] = phone_id
|
||||
|
||||
sender_id = phone_id or self._lid_to_phone.get(lid_id, "") or lid_id
|
||||
if not sender_id:
|
||||
raise ValueError("WhatsApp message has no resolvable sender ID")
|
||||
metadata = {
|
||||
"message_id": message_id or None,
|
||||
"timestamp": int(timestamp) if timestamp else None,
|
||||
"is_group": is_group,
|
||||
"is_forwarded": self._is_forwarded(message),
|
||||
"participant": participant_jid or None,
|
||||
"sender_alt": sender_alt_jid or None,
|
||||
"lid": lid_id or None,
|
||||
"phone": phone_id or None,
|
||||
"is_reply_to_bot": self._is_reply_to_bot(message),
|
||||
}
|
||||
if not self.is_allowed(sender_id):
|
||||
self.logger.info(
|
||||
"Passing unauthorized WhatsApp sender {} to pairing flow "
|
||||
"(phone={}, lid={}, chat={})",
|
||||
sender_id,
|
||||
phone_id or "",
|
||||
lid_id or "",
|
||||
chat_jid,
|
||||
)
|
||||
await self._handle_message(
|
||||
sender_id=sender_id,
|
||||
chat_id=chat_jid,
|
||||
content=_message_text(message),
|
||||
media=[],
|
||||
metadata=metadata,
|
||||
is_dm=not is_group,
|
||||
)
|
||||
return
|
||||
|
||||
text = _message_text(message)
|
||||
media_paths: list[str] = []
|
||||
media = _media_message(message)
|
||||
if media is not None:
|
||||
path = await self._download_media(client, event, media)
|
||||
if media.kind == "audio" and media.is_voice:
|
||||
transcription = await self.transcribe_audio(path)
|
||||
if transcription:
|
||||
text = transcription
|
||||
else:
|
||||
media_paths.append(path)
|
||||
text = self._append_media_tag(text, "audio", path)
|
||||
else:
|
||||
media_paths.append(path)
|
||||
text = self._append_media_tag(text, media.kind, path)
|
||||
|
||||
if not text and not media_paths:
|
||||
return
|
||||
|
||||
await self._handle_message(
|
||||
sender_id=sender_id,
|
||||
chat_id=chat_jid,
|
||||
content=text,
|
||||
media=media_paths,
|
||||
metadata=metadata,
|
||||
is_dm=not is_group,
|
||||
)
|
||||
|
||||
def source_hash(root: Path) -> str:
|
||||
digest = hashlib.sha256()
|
||||
for path in sorted(root.rglob("*")):
|
||||
if not path.is_file():
|
||||
continue
|
||||
rel = path.relative_to(root)
|
||||
if rel.parts and rel.parts[0] in {"node_modules", "dist"}:
|
||||
continue
|
||||
digest.update(rel.as_posix().encode("utf-8"))
|
||||
digest.update(b"\0")
|
||||
digest.update(path.read_bytes())
|
||||
digest.update(b"\0")
|
||||
return digest.hexdigest()
|
||||
def _is_addressed_to_bot(self, message: Any) -> bool:
|
||||
return self._was_mentioned(message) or self._is_reply_to_bot(message)
|
||||
|
||||
expected_hash = source_hash(source)
|
||||
current_hash = stamp_file.read_text().strip() if stamp_file.exists() else None
|
||||
def _was_mentioned(self, message: Any) -> bool:
|
||||
if not self._self_jids:
|
||||
return False
|
||||
for context in _context_infos(message):
|
||||
mentioned = (
|
||||
_safe_attr(context, "mentionedJID")
|
||||
or _safe_attr(context, "mentionedJid")
|
||||
or _safe_attr(context, "mentioned_jid")
|
||||
or []
|
||||
)
|
||||
for jid in mentioned:
|
||||
normalized = _normalize_jid(jid)
|
||||
if normalized in self._self_jids or _bare_jid(normalized) in self._self_jids:
|
||||
return True
|
||||
return False
|
||||
|
||||
if (user_bridge / "dist" / "index.js").exists() and current_hash == expected_hash:
|
||||
return user_bridge
|
||||
def _is_reply_to_bot(self, message: Any) -> bool:
|
||||
if not self._self_jids:
|
||||
return False
|
||||
for context in _context_infos(message):
|
||||
participant = _normalize_jid(
|
||||
_safe_attr(context, "participant")
|
||||
or _safe_attr(context, "Participant")
|
||||
or ""
|
||||
)
|
||||
if participant in self._self_jids or _bare_jid(participant) in self._self_jids:
|
||||
return True
|
||||
return False
|
||||
|
||||
if (user_bridge / "dist" / "index.js").exists() and current_hash != expected_hash:
|
||||
logger.info("WhatsApp bridge source changed; rebuilding bridge...")
|
||||
@staticmethod
|
||||
def _is_forwarded(message: Any) -> bool:
|
||||
for context in _context_infos(message):
|
||||
if bool(_safe_attr(context, "isForwarded", False)):
|
||||
return True
|
||||
if int(_safe_attr(context, "forwardingScore", 0) or 0) > 0:
|
||||
return True
|
||||
return False
|
||||
|
||||
npm_path = shutil.which("npm")
|
||||
if not npm_path:
|
||||
raise RuntimeError("npm not found. Please install Node.js >= 20.")
|
||||
async def _download_media(self, client: Any, event: Any, media: _MediaInfo) -> str:
|
||||
info = _safe_attr(event, "Info")
|
||||
message_id = str(_safe_attr(info, "ID", "") or "")
|
||||
path = self._media_path(message_id, media)
|
||||
await client.download_any(_safe_attr(event, "Message"), str(path))
|
||||
return str(path)
|
||||
|
||||
logger.info("Setting up WhatsApp bridge...")
|
||||
user_bridge.parent.mkdir(parents=True, exist_ok=True)
|
||||
if user_bridge.exists():
|
||||
shutil.rmtree(user_bridge)
|
||||
shutil.copytree(source, user_bridge, ignore=shutil.ignore_patterns("node_modules", "dist"))
|
||||
def _media_path(self, message_id: str, media: _MediaInfo) -> Path:
|
||||
media_dir = get_media_dir("whatsapp")
|
||||
safe_id = re.sub(r"[^A-Za-z0-9_.-]+", "_", message_id or str(int(time.time())))
|
||||
filename = Path(media.filename).name if media.filename else ""
|
||||
suffix = Path(filename).suffix if filename else ""
|
||||
if not suffix:
|
||||
suffix = mimetypes.guess_extension(media.mimetype) or {
|
||||
"image": ".jpg",
|
||||
"video": ".mp4",
|
||||
"audio": ".ogg",
|
||||
"sticker": ".webp",
|
||||
}.get(media.kind, ".bin")
|
||||
return media_dir / f"wa_{safe_id}_{secrets.token_hex(4)}{suffix}"
|
||||
|
||||
logger.info(" Installing dependencies...")
|
||||
subprocess.run([npm_path, "install"], cwd=user_bridge, check=True, capture_output=True)
|
||||
@staticmethod
|
||||
def _append_media_tag(text: str, kind: str, path: str) -> str:
|
||||
label = kind if kind in {"image", "video", "audio", "sticker"} else "file"
|
||||
tag = f"[{label}: {path}]"
|
||||
return f"{text}\n{tag}" if text else tag
|
||||
|
||||
logger.info(" Building...")
|
||||
subprocess.run([npm_path, "run", "build"], cwd=user_bridge, check=True, capture_output=True)
|
||||
stamp_file.write_text(expected_hash + "\n")
|
||||
|
||||
logger.info("Bridge ready")
|
||||
return user_bridge
|
||||
@staticmethod
|
||||
def _reset_database(path: Path) -> None:
|
||||
for candidate in (
|
||||
path,
|
||||
path.with_suffix(path.suffix + "-shm"),
|
||||
path.with_suffix(path.suffix + "-wal"),
|
||||
):
|
||||
if candidate.exists():
|
||||
candidate.unlink()
|
||||
|
||||
@@ -2,7 +2,6 @@
|
||||
|
||||
from nanobot.config.loader import get_config_path, load_config
|
||||
from nanobot.config.paths import (
|
||||
get_bridge_install_dir,
|
||||
get_cli_history_path,
|
||||
get_cron_dir,
|
||||
get_data_dir,
|
||||
@@ -29,6 +28,5 @@ __all__ = [
|
||||
"get_workspace_path",
|
||||
"is_default_workspace",
|
||||
"get_cli_history_path",
|
||||
"get_bridge_install_dir",
|
||||
"get_legacy_sessions_dir",
|
||||
]
|
||||
|
||||
@@ -66,11 +66,6 @@ def get_cli_history_path() -> Path:
|
||||
return Path.home() / ".nanobot" / "history" / "cli_history"
|
||||
|
||||
|
||||
def get_bridge_install_dir() -> Path:
|
||||
"""Return the shared WhatsApp bridge installation directory."""
|
||||
return Path.home() / ".nanobot" / "bridge"
|
||||
|
||||
|
||||
def get_legacy_sessions_dir() -> Path:
|
||||
"""Return the legacy global session directory used for migration fallback."""
|
||||
return Path.home() / ".nanobot" / "sessions"
|
||||
|
||||
Reference in New Issue
Block a user