Merge remote-tracking branch 'origin/main' into pr-1868

.gitignore

@@ -20,4 +20,5 @@ __pycache__/
 poetry.lock
 .pytest_cache/
 botpy.log
+nano.*.save
 

README.md

@@ -78,6 +78,25 @@
   <img src="nanobot_arch.png" alt="nanobot architecture" width="800">
 </p>
 
+## Table of Contents
+
+- [News](#-news)
+- [Key Features](#key-features-of-nanobot)
+- [Architecture](#️-architecture)
+- [Features](#-features)
+- [Install](#-install)
+- [Quick Start](#-quick-start)
+- [Chat Apps](#-chat-apps)
+- [Agent Social Network](#-agent-social-network)
+- [Configuration](#️-configuration)
+- [Multiple Instances](#-multiple-instances)
+- [CLI Reference](#-cli-reference)
+- [Docker](#-docker)
+- [Linux Service](#-linux-service)
+- [Project Structure](#-project-structure)
+- [Contribute & Roadmap](#-contribute--roadmap)
+- [Star History](#-star-history)
+
 ## ✨ Features
 
 <table align="center">
@@ -208,6 +227,7 @@ Connect nanobot to your favorite chat platform.
 | **Slack** | Bot token + App-Level token |
 | **Email** | IMAP/SMTP credentials |
 | **QQ** | App ID + App Secret |
+| **Wecom** | Bot ID + Bot Secret |
 
 <details>
 <summary><b>Telegram</b> (Recommended)</summary>
@@ -677,6 +697,46 @@ nanobot gateway
 
 </details>
 
+<details>
+<summary><b>Wecom (企业微信)</b></summary>
+
+> Here we use [wecom-aibot-sdk-python](https://github.com/chengyongru/wecom_aibot_sdk) (community Python version of the official [@wecom/aibot-node-sdk](https://www.npmjs.com/package/@wecom/aibot-node-sdk)).
+>
+> Uses **WebSocket** long connection — no public IP required.
+
+**1. Install the optional dependency**
+
+```bash
+pip install nanobot-ai[wecom]
+```
+
+**2. Create a WeCom AI Bot**
+
+Go to the WeCom admin console → Intelligent Robot → Create Robot → select **API mode** with **long connection**. Copy the Bot ID and Secret.
+
+**3. Configure**
+
+```json
+{
+  "channels": {
+    "wecom": {
+      "enabled": true,
+      "botId": "your_bot_id",
+      "secret": "your_bot_secret",
+      "allowFrom": ["your_id"]
+    }
+  }
+}
+```
+
+**4. Run**
+
+```bash
+nanobot gateway
+```
+
+</details>
+
 ## 🌐 Agent Social Network
 
 🐈 nanobot is capable of linking to the agent social network (agent community). **Just send one message and your nanobot joins automatically!**
@@ -718,6 +778,7 @@ Config file: `~/.nanobot/config.json`
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.moonshot.cn](https://platform.moonshot.cn) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |
+| `ollama` | LLM (local, Ollama) | — |
 | `vllm` | LLM (local, any OpenAI-compatible server) | — |
 | `openai_codex` | LLM (Codex, OAuth) | `nanobot provider login openai-codex` |
 | `github_copilot` | LLM (GitHub Copilot, OAuth) | `nanobot provider login github-copilot` |
@@ -783,6 +844,37 @@ Connects directly to any OpenAI-compatible endpoint — LM Studio, llama.cpp, To
 
 </details>
 
+<details>
+<summary><b>Ollama (local)</b></summary>
+
+Run a local model with Ollama, then add to config:
+
+**1. Start Ollama** (example):
+```bash
+ollama run llama3.2
+```
+
+**2. Add to config** (partial — merge into `~/.nanobot/config.json`):
+```json
+{
+  "providers": {
+    "ollama": {
+      "apiBase": "http://localhost:11434"
+    }
+  },
+  "agents": {
+    "defaults": {
+      "provider": "ollama",
+      "model": "llama3.2"
+    }
+  }
+}
+```
+
+> `provider: "auto"` also works when `providers.ollama.apiBase` is configured, but setting `"provider": "ollama"` is the clearest option.
+
+</details>
+
 <details>
 <summary><b>vLLM (local / OpenAI-compatible)</b></summary>
 

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 +149,18 @@ 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,
+                )
+                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:

nanobot/channels/wecom.py

@@ -0,0 +1,352 @@
+"""WeCom (Enterprise WeChat) channel implementation using wecom_aibot_sdk."""
+
+import asyncio
+import importlib.util
+import os
+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):
+        super().__init__(config, bus)
+        self.config: WecomConfig = config
+        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 nanobot-ai[wecom]")
+            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:
+            await 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:
+                        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}"
+            filename = os.path.basename(filename)
+
+            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)

nanobot/cli/commands.py

@@ -252,7 +252,7 @@ def _make_provider(config: Config):
     from nanobot.providers.litellm_provider import LiteLLMProvider
     from nanobot.providers.registry import find_by_name
     spec = find_by_name(provider_name)
-    if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and spec.is_oauth):
+    if not model.startswith("bedrock/") and not (p and p.api_key) and not (spec and (spec.is_oauth or spec.is_local)):
         console.print("[red]Error: No API key configured.[/red]")
         console.print("Set one in ~/.nanobot/config.json under providers section")
         raise typer.Exit(1)

nanobot/config/schema.py

@@ -200,6 +200,14 @@ 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
 
 
 class ChannelsConfig(Base):
@@ -217,6 +225,7 @@ 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):
@@ -272,6 +281,7 @@ class ProvidersConfig(Base):
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
+    ollama: ProviderConfig = Field(default_factory=ProviderConfig)  # Ollama local models
     siliconflow: ProviderConfig = Field(default_factory=ProviderConfig)  # SiliconFlow (硅基流动)
     volcengine: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine (火山引擎)
     openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)
@@ -375,16 +385,25 @@ class Config(BaseSettings):
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and model_prefix and normalized_prefix == spec.name:
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
         # Match by keyword (order follows PROVIDERS registry)
         for spec in PROVIDERS:
             p = getattr(self.providers, spec.name, None)
             if p and any(_kw_matches(kw) for kw in spec.keywords):
-                if spec.is_oauth or p.api_key:
+                if spec.is_oauth or spec.is_local or p.api_key:
                     return p, spec.name
 
+        # Fallback: configured local providers can route models without
+        # provider-specific keywords (for example plain "llama3.2" on Ollama).
+        for spec in PROVIDERS:
+            if not spec.is_local:
+                continue
+            p = getattr(self.providers, spec.name, None)
+            if p and p.api_base:
+                return p, spec.name
+
         # Fallback: gateways first, then others (follows registry order)
         # OAuth providers are NOT valid fallbacks — they require explicit model selection
         for spec in PROVIDERS:
@@ -411,7 +430,7 @@ class Config(BaseSettings):
         return p.api_key if p else None
 
     def get_api_base(self, model: str | None = None) -> str | None:
-        """Get API base URL for the given model. Applies default URLs for known gateways."""
+        """Get API base URL for the given model. Applies default URLs for gateway/local providers."""
         from nanobot.providers.registry import find_by_name
 
         p, name = self._match_provider(model)
@@ -422,7 +441,7 @@ class Config(BaseSettings):
         # to avoid polluting the global litellm.api_base.
         if name:
             spec = find_by_name(name)
-            if spec and spec.is_gateway and spec.default_api_base:
+            if spec and (spec.is_gateway or spec.is_local) and spec.default_api_base:
                 return spec.default_api_base
         return None
 

nanobot/providers/registry.py

@@ -360,6 +360,23 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         strip_model_prefix=False,
         model_overrides=(),
     ),
+    # === Ollama (local, OpenAI-compatible) ===================================
+    ProviderSpec(
+        name="ollama",
+        keywords=("ollama", "nemotron"),
+        env_key="OLLAMA_API_KEY",
+        display_name="Ollama",
+        litellm_prefix="ollama_chat",  # model → ollama_chat/model
+        skip_prefixes=("ollama/", "ollama_chat/"),
+        env_extras=(),
+        is_gateway=False,
+        is_local=True,
+        detect_by_key_prefix="",
+        detect_by_base_keyword="11434",
+        default_api_base="http://localhost:11434",
+        strip_model_prefix=False,
+        model_overrides=(),
+    ),
     # === Auxiliary (not a primary LLM provider) ============================
     # Groq: mainly used for Whisper voice transcription, also usable for LLM.
     # Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.

pyproject.toml

@@ -48,6 +48,9 @@ dependencies = [
 ]
 
 [project.optional-dependencies]
+wecom = [
+    "wecom-aibot-sdk-python @ git+https://github.com/chengyongru/wecom_aibot_sdk.git@v0.1.2",
+]
 matrix = [
     "matrix-nio[e2e]>=0.25.2",
     "mistune>=3.0.0,<4.0.0",

tests/test_commands.py

@@ -114,6 +114,35 @@ def test_config_matches_openai_codex_with_hyphen_prefix():
     assert config.get_provider_name() == "openai_codex"
 
 
+def test_config_matches_explicit_ollama_prefix_without_api_key():
+    config = Config()
+    config.agents.defaults.model = "ollama/llama3.2"
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_explicit_ollama_provider_uses_default_localhost_api_base():
+    config = Config()
+    config.agents.defaults.provider = "ollama"
+    config.agents.defaults.model = "llama3.2"
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
+def test_config_auto_detects_ollama_from_local_api_base():
+    config = Config.model_validate(
+        {
+            "agents": {"defaults": {"provider": "auto", "model": "llama3.2"}},
+            "providers": {"ollama": {"apiBase": "http://localhost:11434"}},
+        }
+    )
+
+    assert config.get_provider_name() == "ollama"
+    assert config.get_api_base() == "http://localhost:11434"
+
+
 def test_find_by_model_prefers_explicit_prefix_over_generic_codex_keyword():
     spec = find_by_model("github-copilot/gpt-5.3-codex")