From a660a25504b48170579a57496378e2fd843a556f Mon Sep 17 00:00:00 2001 From: chengyongru <2755839590@qq.com> Date: Mon, 9 Mar 2026 22:00:45 +0800 Subject: [PATCH] feat(wecom): add wecom channel [wobsocket] support text/audio[wecom support audio message by default] --- nanobot/channels/manager.py | 14 +- nanobot/channels/wecom.py | 352 ++++++++++++++++++++++++++++++++++++ nanobot/config/schema.py | 9 + pyproject.toml | 1 + 4 files changed, 375 insertions(+), 1 deletion(-) create mode 100644 nanobot/channels/wecom.py diff --git a/nanobot/channels/manager.py b/nanobot/channels/manager.py index 51539dd..369795a 100644 --- a/nanobot/channels/manager.py +++ b/nanobot/channels/manager.py @@ -7,7 +7,6 @@ from typing import Any from loguru import logger -from nanobot.bus.events import OutboundMessage from nanobot.bus.queue import MessageBus from nanobot.channels.base import BaseChannel from nanobot.config.schema import Config @@ -150,6 +149,19 @@ class ChannelManager: except ImportError as e: logger.warning("Matrix channel not available: {}", e) + # WeCom channel + if self.config.channels.wecom.enabled: + try: + from nanobot.channels.wecom import WecomChannel + self.channels["wecom"] = WecomChannel( + self.config.channels.wecom, + self.bus, + groq_api_key=self.config.providers.groq.api_key, + ) + logger.info("WeCom channel enabled") + except ImportError as e: + logger.warning("WeCom channel not available: {}", e) + self._validate_allow_from() def _validate_allow_from(self) -> None: diff --git a/nanobot/channels/wecom.py b/nanobot/channels/wecom.py new file mode 100644 index 0000000..dc97311 --- /dev/null +++ b/nanobot/channels/wecom.py @@ -0,0 +1,352 @@ +"""WeCom (Enterprise WeChat) channel implementation using wecom_aibot_sdk.""" + +import asyncio +import importlib.util +from collections import OrderedDict +from typing import Any + +from loguru import logger + +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 +from nanobot.config.schema import WecomConfig + +WECOM_AVAILABLE = importlib.util.find_spec("wecom_aibot_sdk") is not None + +# Message type display mapping +MSG_TYPE_MAP = { + "image": "[image]", + "voice": "[voice]", + "file": "[file]", + "mixed": "[mixed content]", +} + + +class WecomChannel(BaseChannel): + """ + WeCom (Enterprise WeChat) channel using WebSocket long connection. + + Uses WebSocket to receive events - no public IP or webhook required. + + Requires: + - Bot ID and Secret from WeCom AI Bot platform + """ + + name = "wecom" + + def __init__(self, config: WecomConfig, bus: MessageBus, groq_api_key: str = ""): + super().__init__(config, bus) + self.config: WecomConfig = config + self.groq_api_key = groq_api_key + self._client: Any = None + self._processed_message_ids: OrderedDict[str, None] = OrderedDict() + self._loop: asyncio.AbstractEventLoop | None = None + self._generate_req_id = None + # Store frame headers for each chat to enable replies + self._chat_frames: dict[str, Any] = {} + + async def start(self) -> None: + """Start the WeCom bot with WebSocket long connection.""" + if not WECOM_AVAILABLE: + logger.error("WeCom SDK not installed. Run: pip install wecom-aibot-sdk-python") + return + + if not self.config.bot_id or not self.config.secret: + logger.error("WeCom bot_id and secret not configured") + return + + from wecom_aibot_sdk import WSClient, generate_req_id + + self._running = True + self._loop = asyncio.get_running_loop() + self._generate_req_id = generate_req_id + + # Create WebSocket client + self._client = WSClient({ + "bot_id": self.config.bot_id, + "secret": self.config.secret, + "reconnect_interval": 1000, + "max_reconnect_attempts": -1, # Infinite reconnect + "heartbeat_interval": 30000, + }) + + # Register event handlers + self._client.on("connected", self._on_connected) + self._client.on("authenticated", self._on_authenticated) + self._client.on("disconnected", self._on_disconnected) + self._client.on("error", self._on_error) + self._client.on("message.text", self._on_text_message) + self._client.on("message.image", self._on_image_message) + self._client.on("message.voice", self._on_voice_message) + self._client.on("message.file", self._on_file_message) + self._client.on("message.mixed", self._on_mixed_message) + self._client.on("event.enter_chat", self._on_enter_chat) + + logger.info("WeCom bot starting with WebSocket long connection") + logger.info("No public IP required - using WebSocket to receive events") + + # Connect + await self._client.connect_async() + + # Keep running until stopped + while self._running: + await asyncio.sleep(1) + + async def stop(self) -> None: + """Stop the WeCom bot.""" + self._running = False + if self._client: + self._client.disconnect() + logger.info("WeCom bot stopped") + + async def _on_connected(self, frame: Any) -> None: + """Handle WebSocket connected event.""" + logger.info("WeCom WebSocket connected") + + async def _on_authenticated(self, frame: Any) -> None: + """Handle authentication success event.""" + logger.info("WeCom authenticated successfully") + + async def _on_disconnected(self, frame: Any) -> None: + """Handle WebSocket disconnected event.""" + reason = frame.body if hasattr(frame, 'body') else str(frame) + logger.warning("WeCom WebSocket disconnected: {}", reason) + + async def _on_error(self, frame: Any) -> None: + """Handle error event.""" + logger.error("WeCom error: {}", frame) + + async def _on_text_message(self, frame: Any) -> None: + """Handle text message.""" + await self._process_message(frame, "text") + + async def _on_image_message(self, frame: Any) -> None: + """Handle image message.""" + await self._process_message(frame, "image") + + async def _on_voice_message(self, frame: Any) -> None: + """Handle voice message.""" + await self._process_message(frame, "voice") + + async def _on_file_message(self, frame: Any) -> None: + """Handle file message.""" + await self._process_message(frame, "file") + + async def _on_mixed_message(self, frame: Any) -> None: + """Handle mixed content message.""" + await self._process_message(frame, "mixed") + + async def _on_enter_chat(self, frame: Any) -> None: + """Handle enter_chat event (user opens chat with bot).""" + try: + # Extract body from WsFrame dataclass or dict + if hasattr(frame, 'body'): + body = frame.body or {} + elif isinstance(frame, dict): + body = frame.get("body", frame) + else: + body = {} + + chat_id = body.get("chatid", "") if isinstance(body, dict) else "" + + if chat_id and self.config.welcome_message: + await self._client.reply_welcome(frame, { + "msgtype": "text", + "text": {"content": self.config.welcome_message}, + }) + except Exception as e: + logger.error("Error handling enter_chat: {}", e) + + async def _process_message(self, frame: Any, msg_type: str) -> None: + """Process incoming message and forward to bus.""" + try: + # Extract body from WsFrame dataclass or dict + if hasattr(frame, 'body'): + body = frame.body or {} + elif isinstance(frame, dict): + body = frame.get("body", frame) + else: + body = {} + + # Ensure body is a dict + if not isinstance(body, dict): + logger.warning("Invalid body type: {}", type(body)) + return + + # Extract message info + msg_id = body.get("msgid", "") + if not msg_id: + msg_id = f"{body.get('chatid', '')}_{body.get('sendertime', '')}" + + # Deduplication check + if msg_id in self._processed_message_ids: + return + self._processed_message_ids[msg_id] = None + + # Trim cache + while len(self._processed_message_ids) > 1000: + self._processed_message_ids.popitem(last=False) + + # Extract sender info from "from" field (SDK format) + from_info = body.get("from", {}) + sender_id = from_info.get("userid", "unknown") if isinstance(from_info, dict) else "unknown" + + # For single chat, chatid is the sender's userid + # For group chat, chatid is provided in body + chat_type = body.get("chattype", "single") + chat_id = body.get("chatid", sender_id) + + content_parts = [] + + if msg_type == "text": + text = body.get("text", {}).get("content", "") + if text: + content_parts.append(text) + + elif msg_type == "image": + image_info = body.get("image", {}) + file_url = image_info.get("url", "") + aes_key = image_info.get("aeskey", "") + + if file_url and aes_key: + file_path = await self._download_and_save_media(file_url, aes_key, "image") + if file_path: + import os + filename = os.path.basename(file_path) + content_parts.append(f"[image: {filename}]\n[Image: source: {file_path}]") + else: + content_parts.append("[image: download failed]") + else: + content_parts.append("[image: download failed]") + + elif msg_type == "voice": + voice_info = body.get("voice", {}) + # Voice message already contains transcribed content from WeCom + voice_content = voice_info.get("content", "") + if voice_content: + content_parts.append(f"[voice] {voice_content}") + else: + content_parts.append("[voice]") + + elif msg_type == "file": + file_info = body.get("file", {}) + file_url = file_info.get("url", "") + aes_key = file_info.get("aeskey", "") + file_name = file_info.get("name", "unknown") + + if file_url and aes_key: + file_path = await self._download_and_save_media(file_url, aes_key, "file", file_name) + if file_path: + content_parts.append(f"[file: {file_name}]\n[File: source: {file_path}]") + else: + content_parts.append(f"[file: {file_name}: download failed]") + else: + content_parts.append(f"[file: {file_name}: download failed]") + + elif msg_type == "mixed": + # Mixed content contains multiple message items + msg_items = body.get("mixed", {}).get("item", []) + for item in msg_items: + item_type = item.get("type", "") + if item_type == "text": + text = item.get("text", {}).get("content", "") + if text: + content_parts.append(text) + else: + content_parts.append(MSG_TYPE_MAP.get(item_type, f"[{item_type}]")) + + else: + content_parts.append(MSG_TYPE_MAP.get(msg_type, f"[{msg_type}]")) + + content = "\n".join(content_parts) if content_parts else "" + + if not content: + return + + # Store frame for this chat to enable replies + self._chat_frames[chat_id] = frame + + # Forward to message bus + # Note: media paths are included in content for broader model compatibility + await self._handle_message( + sender_id=sender_id, + chat_id=chat_id, + content=content, + media=None, + metadata={ + "message_id": msg_id, + "msg_type": msg_type, + "chat_type": chat_type, + } + ) + + except Exception as e: + logger.error("Error processing WeCom message: {}", e) + + async def _download_and_save_media( + self, + file_url: str, + aes_key: str, + media_type: str, + filename: str | None = None, + ) -> str | None: + """ + Download and decrypt media from WeCom. + + Returns: + file_path or None if download failed + """ + try: + data, fname = await self._client.download_file(file_url, aes_key) + + if not data: + logger.warning("Failed to download media from WeCom") + return None + + media_dir = get_media_dir("wecom") + if not filename: + filename = fname or f"{media_type}_{hash(file_url) % 100000}" + + file_path = media_dir / filename + file_path.write_bytes(data) + logger.debug("Downloaded {} to {}", media_type, file_path) + return str(file_path) + + except Exception as e: + logger.error("Error downloading media: {}", e) + return None + + async def send(self, msg: OutboundMessage) -> None: + """Send a message through WeCom.""" + if not self._client: + logger.warning("WeCom client not initialized") + return + + try: + content = msg.content.strip() + if not content: + return + + # Get the stored frame for this chat + frame = self._chat_frames.get(msg.chat_id) + if not frame: + logger.warning("No frame found for chat {}, cannot reply", msg.chat_id) + return + + # Use streaming reply for better UX + stream_id = self._generate_req_id("stream") + + # Send as streaming message with finish=True + await self._client.reply_stream( + frame, + stream_id, + content, + finish=True, + ) + + logger.debug("WeCom message sent to {}", msg.chat_id) + + except Exception as e: + logger.error("Error sending WeCom message: {}", e) diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index 803cb61..63eae48 100644 --- a/nanobot/config/schema.py +++ b/nanobot/config/schema.py @@ -199,7 +199,15 @@ class QQConfig(Base): ) # Allowed user openids (empty = public access) +class WecomConfig(Base): + """WeCom (Enterprise WeChat) AI Bot channel configuration.""" + enabled: bool = False + bot_id: str = "" # Bot ID from WeCom AI Bot platform + secret: str = "" # Bot Secret from WeCom AI Bot platform + allow_from: list[str] = Field(default_factory=list) # Allowed user IDs + welcome_message: str = "" # Welcome message for enter_chat event + react_emoji: str = "eyes" # Emoji for message reactions class ChannelsConfig(Base): """Configuration for chat channels.""" @@ -216,6 +224,7 @@ class ChannelsConfig(Base): slack: SlackConfig = Field(default_factory=SlackConfig) qq: QQConfig = Field(default_factory=QQConfig) matrix: MatrixConfig = Field(default_factory=MatrixConfig) + wecom: WecomConfig = Field(default_factory=WecomConfig) class AgentDefaults(Base): diff --git a/pyproject.toml b/pyproject.toml index 62cf616..fac53ce 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -44,6 +44,7 @@ dependencies = [ "json-repair>=0.57.0,<1.0.0", "chardet>=3.0.2,<6.0.0", "openai>=2.8.0", + "wecom-aibot-sdk-python>=0.1.2", ] [project.optional-dependencies]