refactor(gewechat): remove redundant set_webhook_url and login logic

Remove the unnecessary set_webhook_url method and its caller in botmgr,
instead inject webhook_prefix via adapter config for self-assembly.
Remove login logic from run_async since login is handled elsewhere.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.9.0"
+version = "4.9.3"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -64,7 +64,7 @@ dependencies = [
     "chromadb>=1.0.0,<2.0.0",
     "qdrant-client (>=1.15.1,<2.0.0)",
     "pyseekdb==1.1.0.post3",
-    "langbot-plugin==0.3.0",
+    "langbot-plugin==0.3.3",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "tboxsdk>=0.0.10",

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.9.0'
+__version__ = '4.9.3'

src/langbot/libs/wecom_ai_bot_api/api.py

@@ -199,6 +199,253 @@ class StreamSessionManager:
                 self._msg_index.pop(msg_id, None)
 
 
+async def download_encrypted_file(download_url: str, encoding_aes_key: str, logger: EventLogger) -> Optional[str]:
+    """Download an AES-encrypted file from WeChat Work and return as data URI.
+
+    Args:
+        download_url: The encrypted file download URL.
+        encoding_aes_key: The AES key used for decryption (base64-encoded, without trailing '=').
+        logger: Logger instance.
+
+    Returns:
+        A data URI string (e.g. 'data:image/jpeg;base64,...') or None on failure.
+    """
+    if not download_url:
+        return None
+    async with httpx.AsyncClient() as client:
+        response = await client.get(download_url)
+        if response.status_code != 200:
+            await logger.error(f'failed to get file: {response.text}')
+            return None
+        encrypted_bytes = response.content
+
+    aes_key = base64.b64decode(encoding_aes_key + '=')
+    iv = aes_key[:16]
+
+    cipher = AES.new(aes_key, AES.MODE_CBC, iv)
+    decrypted = cipher.decrypt(encrypted_bytes)
+
+    pad_len = decrypted[-1]
+    decrypted = decrypted[:-pad_len]
+
+    if decrypted.startswith(b'\xff\xd8'):
+        mime_type = 'image/jpeg'
+    elif decrypted.startswith(b'\x89PNG'):
+        mime_type = 'image/png'
+    elif decrypted.startswith((b'GIF87a', b'GIF89a')):
+        mime_type = 'image/gif'
+    elif decrypted.startswith(b'BM'):
+        mime_type = 'image/bmp'
+    elif decrypted.startswith(b'II*\x00') or decrypted.startswith(b'MM\x00*'):
+        mime_type = 'image/tiff'
+    else:
+        mime_type = 'application/octet-stream'
+
+    base64_str = base64.b64encode(decrypted).decode('utf-8')
+    return f'data:{mime_type};base64,{base64_str}'
+
+
+async def parse_wecom_bot_message(
+    msg_json: dict[str, Any], encoding_aes_key: str, logger: EventLogger
+) -> dict[str, Any]:
+    """Parse a decrypted WeChat Work AI Bot message JSON into a unified message dict.
+
+    This is the shared message parsing logic used by both webhook and WebSocket modes.
+
+    Args:
+        msg_json: The decrypted message JSON from WeChat Work.
+        encoding_aes_key: AES key for file decryption.
+        logger: Logger instance.
+
+    Returns:
+        A dict suitable for constructing a WecomBotEvent.
+    """
+    message_data: dict[str, Any] = {}
+
+    msg_type = msg_json.get('msgtype', '')
+    if msg_type:
+        message_data['msgtype'] = msg_type
+
+    if msg_json.get('chattype', '') == 'single':
+        message_data['type'] = 'single'
+    elif msg_json.get('chattype', '') == 'group':
+        message_data['type'] = 'group'
+
+    max_inline_file_size = 5 * 1024 * 1024
+
+    async def _safe_download(url: str):
+        if not url:
+            return None
+        return await download_encrypted_file(url, encoding_aes_key, logger)
+
+    if msg_type == 'text':
+        message_data['content'] = msg_json.get('text', {}).get('content')
+    elif msg_type == 'markdown':
+        message_data['content'] = msg_json.get('markdown', {}).get('content') or msg_json.get('text', {}).get(
+            'content', ''
+        )
+    elif msg_type == 'image':
+        picurl = msg_json.get('image', {}).get('url', '')
+        base64_data = await _safe_download(picurl)
+        if base64_data:
+            message_data['picurl'] = base64_data
+            message_data['images'] = [base64_data]
+    elif msg_type == 'voice':
+        voice_info = msg_json.get('voice', {}) or {}
+        download_url = voice_info.get('url')
+        message_data['voice'] = {
+            'url': download_url,
+            'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
+            'filesize': voice_info.get('filesize') or voice_info.get('size'),
+            'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
+        }
+        if voice_info.get('content'):
+            message_data['content'] = voice_info.get('content')
+        if (message_data['voice'].get('filesize') or 0) <= max_inline_file_size:
+            voice_base64 = await _safe_download(download_url)
+            if voice_base64:
+                message_data['voice']['base64'] = voice_base64
+    elif msg_type == 'video':
+        video_info = msg_json.get('video', {}) or {}
+        download_url = video_info.get('url')
+        video_data = {
+            'url': download_url,
+            'filesize': video_info.get('filesize') or video_info.get('size'),
+            'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
+            'md5sum': video_info.get('md5sum') or video_info.get('md5'),
+            'filename': video_info.get('filename') or video_info.get('name'),
+        }
+        if (video_data.get('filesize') or 0) <= max_inline_file_size:
+            video_base64 = await _safe_download(download_url)
+            if video_base64:
+                video_data['base64'] = video_base64
+        message_data['video'] = video_data
+    elif msg_type == 'file':
+        file_info = msg_json.get('file', {}) or {}
+        download_url = file_info.get('url') or file_info.get('fileurl')
+        file_data = {
+            'filename': file_info.get('filename') or file_info.get('name'),
+            'filesize': file_info.get('filesize') or file_info.get('size'),
+            'md5sum': file_info.get('md5sum') or file_info.get('md5'),
+            'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
+            'download_url': download_url,
+            'extra': file_info,
+        }
+        if (file_data.get('filesize') or 0) <= max_inline_file_size:
+            file_base64 = await _safe_download(download_url)
+            if file_base64:
+                file_data['base64'] = file_base64
+        message_data['file'] = file_data
+    elif msg_type == 'link':
+        message_data['link'] = msg_json.get('link', {})
+        if not message_data.get('content'):
+            title = message_data['link'].get('title', '')
+            desc = message_data['link'].get('description') or message_data['link'].get('digest', '')
+            message_data['content'] = '\n'.join(filter(None, [title, desc]))
+    elif msg_type == 'mixed':
+        items = msg_json.get('mixed', {}).get('msg_item', [])
+        texts = []
+        images = []
+        files = []
+        voices = []
+        videos = []
+        links = []
+        for item in items:
+            item_type = item.get('msgtype')
+            if item_type == 'text':
+                texts.append(item.get('text', {}).get('content', ''))
+            elif item_type == 'image':
+                img_url = item.get('image', {}).get('url')
+                base64_data = await _safe_download(img_url)
+                if base64_data:
+                    images.append(base64_data)
+            elif item_type == 'file':
+                file_info = item.get('file', {}) or {}
+                download_url = file_info.get('url') or file_info.get('fileurl')
+                file_data = {
+                    'filename': file_info.get('filename') or file_info.get('name'),
+                    'filesize': file_info.get('filesize') or file_info.get('size'),
+                    'md5sum': file_info.get('md5sum') or file_info.get('md5'),
+                    'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
+                    'download_url': download_url,
+                    'extra': file_info,
+                }
+                if (file_data.get('filesize') or 0) <= max_inline_file_size:
+                    file_base64 = await _safe_download(download_url)
+                    if file_base64:
+                        file_data['base64'] = file_base64
+                files.append(file_data)
+            elif item_type == 'voice':
+                voice_info = item.get('voice', {}) or {}
+                download_url = voice_info.get('url')
+                voice_data = {
+                    'url': download_url,
+                    'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
+                    'filesize': voice_info.get('filesize') or voice_info.get('size'),
+                    'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
+                }
+                if voice_info.get('content'):
+                    texts.append(voice_info.get('content'))
+                if (voice_data.get('filesize') or 0) <= max_inline_file_size:
+                    voice_base64 = await _safe_download(download_url)
+                    if voice_base64:
+                        voice_data['base64'] = voice_base64
+                voices.append(voice_data)
+            elif item_type == 'video':
+                video_info = item.get('video', {}) or {}
+                download_url = video_info.get('url')
+                video_data = {
+                    'url': download_url,
+                    'filesize': video_info.get('filesize') or video_info.get('size'),
+                    'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
+                    'md5sum': video_info.get('md5sum') or video_info.get('md5'),
+                    'filename': video_info.get('filename') or video_info.get('name'),
+                }
+                if (video_data.get('filesize') or 0) <= max_inline_file_size:
+                    video_base64 = await _safe_download(download_url)
+                    if video_base64:
+                        video_data['base64'] = video_base64
+                videos.append(video_data)
+            elif item_type == 'link':
+                links.append(item.get('link', {}))
+
+        if texts:
+            message_data['content'] = ' '.join(texts)
+        if images:
+            message_data['images'] = images
+            message_data['picurl'] = images[0]
+        if files:
+            message_data['files'] = files
+            message_data['file'] = files[0]
+        if voices:
+            message_data['voices'] = voices
+            message_data['voice'] = voices[0]
+        if videos:
+            message_data['videos'] = videos
+            message_data['video'] = videos[0]
+        if links:
+            message_data['link'] = links[0]
+        if items:
+            message_data['attachments'] = items
+    else:
+        message_data['raw_msg'] = msg_json
+
+    from_info = msg_json.get('from', {})
+    message_data['userid'] = from_info.get('userid', '')
+    message_data['username'] = from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
+
+    if msg_json.get('chattype', '') == 'group':
+        message_data['chatid'] = msg_json.get('chatid', '')
+        message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
+
+    message_data['msgid'] = msg_json.get('msgid', '')
+
+    if msg_json.get('aibotid'):
+        message_data['aibotid'] = msg_json.get('aibotid', '')
+
+    return message_data
+
+
 class WecomBotClient:
     def __init__(self, Token: str, EnCodingAESKey: str, Corpid: str, logger: EventLogger, unified_mode: bool = False):
         """企业微信智能机器人客户端。
@@ -455,196 +702,7 @@ class WecomBotClient:
         return await self._handle_post_initial_response(msg_json, nonce)
 
     async def get_message(self, msg_json):
-        message_data = {}
-
-        msg_type = msg_json.get('msgtype', '')
-        if msg_type:
-            message_data['msgtype'] = msg_type
-
-        if msg_json.get('chattype', '') == 'single':
-            message_data['type'] = 'single'
-        elif msg_json.get('chattype', '') == 'group':
-            message_data['type'] = 'group'
-
-        max_inline_file_size = 5 * 1024 * 1024  # avoid decoding very large payloads by default
-
-        async def _safe_download(url: str):
-            if not url:
-                return None
-            return await self.download_url_to_base64(url, self.EnCodingAESKey)
-
-        if msg_type == 'text':
-            message_data['content'] = msg_json.get('text', {}).get('content')
-        elif msg_type == 'markdown':
-            message_data['content'] = msg_json.get('markdown', {}).get('content') or msg_json.get('text', {}).get(
-                'content', ''
-            )
-        elif msg_type == 'image':
-            picurl = msg_json.get('image', {}).get('url', '')
-            base64_data = await _safe_download(picurl)
-            if base64_data:
-                message_data['picurl'] = base64_data
-                message_data['images'] = [base64_data]
-        elif msg_type == 'voice':
-            voice_info = msg_json.get('voice', {}) or {}
-            download_url = voice_info.get('url')
-            message_data['voice'] = {
-                'url': download_url,
-                'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
-                'filesize': voice_info.get('filesize') or voice_info.get('size'),
-                'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
-            }
-            # 企业微信智能转写文本（如果已有）直接复用，避免重复转写
-            if voice_info.get('content'):
-                message_data['content'] = voice_info.get('content')
-            if (message_data['voice'].get('filesize') or 0) <= max_inline_file_size:
-                voice_base64 = await _safe_download(download_url)
-                if voice_base64:
-                    message_data['voice']['base64'] = voice_base64
-        elif msg_type == 'video':
-            video_info = msg_json.get('video', {}) or {}
-            download_url = video_info.get('url')
-            video_data = {
-                'url': download_url,
-                'filesize': video_info.get('filesize') or video_info.get('size'),
-                'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
-                'md5sum': video_info.get('md5sum') or video_info.get('md5'),
-                'filename': video_info.get('filename') or video_info.get('name'),
-            }
-            if (video_data.get('filesize') or 0) <= max_inline_file_size:
-                video_base64 = await _safe_download(download_url)
-                if video_base64:
-                    video_data['base64'] = video_base64
-            message_data['video'] = video_data
-        elif msg_type == 'file':
-            file_info = msg_json.get('file', {}) or {}
-            download_url = file_info.get('url') or file_info.get('fileurl')
-            file_data = {
-                'filename': file_info.get('filename') or file_info.get('name'),
-                'filesize': file_info.get('filesize') or file_info.get('size'),
-                'md5sum': file_info.get('md5sum') or file_info.get('md5'),
-                'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
-                'download_url': download_url,
-                'extra': file_info,
-            }
-            if (file_data.get('filesize') or 0) <= max_inline_file_size:
-                file_base64 = await _safe_download(download_url)
-                if file_base64:
-                    file_data['base64'] = file_base64
-            message_data['file'] = file_data
-        elif msg_type == 'link':
-            message_data['link'] = msg_json.get('link', {})
-            if not message_data.get('content'):
-                title = message_data['link'].get('title', '')
-                desc = message_data['link'].get('description') or message_data['link'].get('digest', '')
-                message_data['content'] = '\n'.join(filter(None, [title, desc]))
-        elif msg_type == 'mixed':
-            items = msg_json.get('mixed', {}).get('msg_item', [])
-            texts = []
-            images = []
-            files = []
-            voices = []
-            videos = []
-            links = []
-            for item in items:
-                item_type = item.get('msgtype')
-                if item_type == 'text':
-                    texts.append(item.get('text', {}).get('content', ''))
-                elif item_type == 'image':
-                    img_url = item.get('image', {}).get('url')
-                    base64_data = await _safe_download(img_url)
-                    if base64_data:
-                        images.append(base64_data)
-                elif item_type == 'file':
-                    file_info = item.get('file', {}) or {}
-                    download_url = file_info.get('url') or file_info.get('fileurl')
-                    file_data = {
-                        'filename': file_info.get('filename') or file_info.get('name'),
-                        'filesize': file_info.get('filesize') or file_info.get('size'),
-                        'md5sum': file_info.get('md5sum') or file_info.get('md5'),
-                        'sdkfileid': file_info.get('sdkfileid') or file_info.get('fileid'),
-                        'download_url': download_url,
-                        'extra': file_info,
-                    }
-                    if (file_data.get('filesize') or 0) <= max_inline_file_size:
-                        file_base64 = await _safe_download(download_url)
-                        if file_base64:
-                            file_data['base64'] = file_base64
-                    files.append(file_data)
-                elif item_type == 'voice':
-                    voice_info = item.get('voice', {}) or {}
-                    download_url = voice_info.get('url')
-                    voice_data = {
-                        'url': download_url,
-                        'md5sum': voice_info.get('md5sum') or voice_info.get('md5'),
-                        'filesize': voice_info.get('filesize') or voice_info.get('size'),
-                        'sdkfileid': voice_info.get('sdkfileid') or voice_info.get('fileid'),
-                    }
-                    if voice_info.get('content'):
-                        texts.append(voice_info.get('content'))
-                    if (voice_data.get('filesize') or 0) <= max_inline_file_size:
-                        voice_base64 = await _safe_download(download_url)
-                        if voice_base64:
-                            voice_data['base64'] = voice_base64
-                    voices.append(voice_data)
-                elif item_type == 'video':
-                    video_info = item.get('video', {}) or {}
-                    download_url = video_info.get('url')
-                    video_data = {
-                        'url': download_url,
-                        'filesize': video_info.get('filesize') or video_info.get('size'),
-                        'sdkfileid': video_info.get('sdkfileid') or video_info.get('fileid'),
-                        'md5sum': video_info.get('md5sum') or video_info.get('md5'),
-                        'filename': video_info.get('filename') or video_info.get('name'),
-                    }
-                    if (video_data.get('filesize') or 0) <= max_inline_file_size:
-                        video_base64 = await _safe_download(download_url)
-                        if video_base64:
-                            video_data['base64'] = video_base64
-                    videos.append(video_data)
-                elif item_type == 'link':
-                    links.append(item.get('link', {}))
-
-            if texts:
-                message_data['content'] = ' '.join(texts)  # 拼接所有 text
-            if images:
-                message_data['images'] = images
-                message_data['picurl'] = images[0]  # 只保留第一个 image
-            if files:
-                message_data['files'] = files
-                message_data['file'] = files[0]
-            if voices:
-                message_data['voices'] = voices
-                message_data['voice'] = voices[0]
-            if videos:
-                message_data['videos'] = videos
-                message_data['video'] = videos[0]
-            if links:
-                message_data['link'] = links[0]
-            if items:
-                message_data['attachments'] = items
-        else:
-            message_data['raw_msg'] = msg_json
-
-        # Extract user information
-        from_info = msg_json.get('from', {})
-        message_data['userid'] = from_info.get('userid', '')
-        message_data['username'] = (
-            from_info.get('alias', '') or from_info.get('name', '') or from_info.get('userid', '')
-        )
-
-        # Extract chat/group information
-        if msg_json.get('chattype', '') == 'group':
-            message_data['chatid'] = msg_json.get('chatid', '')
-            # Try to get group name if available
-            message_data['chatname'] = msg_json.get('chatname', '') or msg_json.get('chatid', '')
-
-        message_data['msgid'] = msg_json.get('msgid', '')
-
-        if msg_json.get('aibotid'):
-            message_data['aibotid'] = msg_json.get('aibotid', '')
-
-        return message_data
+        return await parse_wecom_bot_message(msg_json, self.EnCodingAESKey, self.logger)
 
     async def _handle_message(self, event: wecombotevent.WecomBotEvent):
         """
@@ -712,39 +770,7 @@ class WecomBotClient:
         return decorator
 
     async def download_url_to_base64(self, download_url, encoding_aes_key):
-        async with httpx.AsyncClient() as client:
-            response = await client.get(download_url)
-            if response.status_code != 200:
-                await self.logger.error(f'failed to get file: {response.text}')
-                return None
-
-            encrypted_bytes = response.content
-
-        aes_key = base64.b64decode(encoding_aes_key + '=')  # base64 补齐
-        iv = aes_key[:16]
-
-        cipher = AES.new(aes_key, AES.MODE_CBC, iv)
-        decrypted = cipher.decrypt(encrypted_bytes)
-
-        pad_len = decrypted[-1]
-        decrypted = decrypted[:-pad_len]
-
-        if decrypted.startswith(b'\xff\xd8'):  # JPEG
-            mime_type = 'image/jpeg'
-        elif decrypted.startswith(b'\x89PNG'):  # PNG
-            mime_type = 'image/png'
-        elif decrypted.startswith((b'GIF87a', b'GIF89a')):  # GIF
-            mime_type = 'image/gif'
-        elif decrypted.startswith(b'BM'):  # BMP
-            mime_type = 'image/bmp'
-        elif decrypted.startswith(b'II*\x00') or decrypted.startswith(b'MM\x00*'):  # TIFF
-            mime_type = 'image/tiff'
-        else:
-            mime_type = 'application/octet-stream'
-
-        # 转 base64
-        base64_str = base64.b64encode(decrypted).decode('utf-8')
-        return f'data:{mime_type};base64,{base64_str}'
+        return await download_encrypted_file(download_url, encoding_aes_key, self.logger)
 
     async def run_task(self, host: str, port: int, *args, **kwargs):
         """

src/langbot/libs/wecom_ai_bot_api/ws_client.py

@@ -0,0 +1,596 @@
+"""WeChat Work AI Bot WebSocket long connection client.
+
+Implements the WebSocket protocol for receiving messages and sending replies
+via a persistent connection to wss://openws.work.weixin.qq.com, as an
+alternative to the HTTP callback (webhook) mode.
+
+Protocol reference: https://developer.work.weixin.qq.com/document/path/101463
+Official Node.js SDK: https://github.com/WecomTeam/aibot-node-sdk
+"""
+
+from __future__ import annotations
+
+import asyncio
+import json
+import secrets
+import time
+import traceback
+from typing import Any, Callable, Optional
+
+import aiohttp
+
+from langbot.libs.wecom_ai_bot_api import wecombotevent
+from langbot.libs.wecom_ai_bot_api.api import parse_wecom_bot_message
+from langbot.pkg.platform.logger import EventLogger
+
+DEFAULT_WS_URL = 'wss://openws.work.weixin.qq.com'
+
+# WebSocket frame command constants
+CMD_SUBSCRIBE = 'aibot_subscribe'
+CMD_HEARTBEAT = 'ping'
+CMD_MSG_CALLBACK = 'aibot_msg_callback'
+CMD_EVENT_CALLBACK = 'aibot_event_callback'
+CMD_RESPOND_MSG = 'aibot_respond_msg'
+CMD_RESPOND_WELCOME = 'aibot_respond_welcome_msg'
+CMD_RESPOND_UPDATE = 'aibot_respond_update_msg'
+CMD_SEND_MSG = 'aibot_send_msg'
+
+
+def _generate_req_id(prefix: str) -> str:
+    """Generate a unique request ID in the format: {prefix}_{timestamp}_{random}."""
+    ts = int(time.time() * 1000)
+    rand = secrets.token_hex(4)
+    return f'{prefix}_{ts}_{rand}'
+
+
+class WecomBotWsClient:
+    """WeChat Work AI Bot WebSocket long connection client.
+
+    Provides message receiving, streaming reply, proactive message sending,
+    and event callback handling over a persistent WebSocket connection.
+    """
+
+    def __init__(
+        self,
+        bot_id: str,
+        secret: str,
+        logger: EventLogger,
+        encoding_aes_key: str = '',
+        ws_url: str = DEFAULT_WS_URL,
+        heartbeat_interval: float = 30.0,
+        max_reconnect_attempts: int = -1,
+        reconnect_base_delay: float = 1.0,
+        reconnect_max_delay: float = 30.0,
+    ):
+        self.bot_id = bot_id
+        self.secret = secret
+        self.logger = logger
+        self.encoding_aes_key = encoding_aes_key
+        self.ws_url = ws_url
+        self.heartbeat_interval = heartbeat_interval
+        self.max_reconnect_attempts = max_reconnect_attempts
+        self.reconnect_base_delay = reconnect_base_delay
+        self.reconnect_max_delay = reconnect_max_delay
+
+        self._ws: Optional[aiohttp.ClientWebSocketResponse] = None
+        self._session: Optional[aiohttp.ClientSession] = None
+        self._running = False
+        self._heartbeat_task: Optional[asyncio.Task] = None
+        self._missed_pong_count = 0
+        self._max_missed_pong = 2
+        self._reconnect_attempts = 0
+
+        # Message handler registry (same pattern as WecomBotClient)
+        self._message_handlers: dict[str, list[Callable]] = {}
+        # Message deduplication
+        self._msg_id_map: dict[str, int] = {}
+
+        # Pending ACK futures: req_id -> Future[dict]
+        self._pending_acks: dict[str, asyncio.Future] = {}
+        # Per-req_id serial reply queues
+        self._reply_queues: dict[str, asyncio.Queue] = {}
+        self._reply_workers: dict[str, asyncio.Task] = {}
+        self._reply_ack_timeout = 5.0
+
+        # Stream ID tracking for WebSocket mode
+        self._stream_ids: dict[str, str] = {}  # msg_id -> req_id|stream_id
+        # Dedup: skip sending when content hasn't changed
+        self._stream_last_content: dict[str, str] = {}  # msg_id -> last content sent
+
+    # ── Public API ──────────────────────────────────────────────────
+
+    async def connect(self):
+        """Connect to WebSocket server with automatic reconnection.
+
+        This method blocks until disconnect() is called or max reconnect
+        attempts are exhausted.
+        """
+        self._running = True
+        self._reconnect_attempts = 0
+
+        while self._running:
+            try:
+                await self._connect_once()
+            except Exception:
+                if not self._running:
+                    break
+                await self.logger.error(f'WebSocket connection error: {traceback.format_exc()}')
+
+            if not self._running:
+                break
+
+            # Reconnect with exponential backoff
+            if self.max_reconnect_attempts != -1 and self._reconnect_attempts >= self.max_reconnect_attempts:
+                await self.logger.error(f'Max reconnect attempts reached ({self.max_reconnect_attempts}), giving up')
+                break
+
+            self._reconnect_attempts += 1
+            delay = min(
+                self.reconnect_base_delay * (2 ** (self._reconnect_attempts - 1)),
+                self.reconnect_max_delay,
+            )
+            await self.logger.info(f'Reconnecting in {delay:.1f}s (attempt {self._reconnect_attempts})...')
+            await asyncio.sleep(delay)
+
+    async def disconnect(self):
+        """Gracefully disconnect from the WebSocket server."""
+        self._running = False
+        if self._heartbeat_task and not self._heartbeat_task.done():
+            self._heartbeat_task.cancel()
+        for task in self._reply_workers.values():
+            if not task.done():
+                task.cancel()
+        if self._ws and not self._ws.closed:
+            await self._ws.close()
+        self._ws = None
+        if self._session and not self._session.closed:
+            await self._session.close()
+        self._session = None
+
+    def on_message(self, msg_type: str) -> Callable:
+        """Decorator to register a message handler.
+
+        Same interface as WecomBotClient.on_message for compatibility.
+
+        Args:
+            msg_type: 'single', 'group', or specific message type.
+        """
+
+        def decorator(func: Callable[[wecombotevent.WecomBotEvent], Any]):
+            if msg_type not in self._message_handlers:
+                self._message_handlers[msg_type] = []
+            self._message_handlers[msg_type].append(func)
+            return func
+
+        return decorator
+
+    async def reply_stream(
+        self,
+        req_id: str,
+        stream_id: str,
+        content: str,
+        finish: bool = False,
+    ) -> Optional[dict]:
+        """Send a streaming reply frame.
+
+        Args:
+            req_id: The req_id from the original message frame (must be passed through).
+            stream_id: The stream ID for this streaming session.
+            content: The content to send (supports Markdown).
+            finish: Whether this is the final chunk.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        body = {
+            'msgtype': 'stream',
+            'stream': {
+                'id': stream_id,
+                'finish': finish,
+                'content': content,
+            },
+        }
+        return await self._send_reply(req_id, body)
+
+    async def reply_text(self, req_id: str, content: str) -> Optional[dict]:
+        """Send a non-streaming text reply.
+
+        Args:
+            req_id: The req_id from the original message frame.
+            content: The text content to reply.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        body = {
+            'msgtype': 'markdown',
+            'markdown': {
+                'content': content,
+            },
+        }
+        return await self._send_reply(req_id, body)
+
+    async def send_message(self, chat_id: str, content: str, msgtype: str = 'markdown') -> Optional[dict]:
+        """Proactively send a message to a specified chat.
+
+        Args:
+            chat_id: The chat ID (userid for single chat, chatid for group chat).
+            content: The message content.
+            msgtype: Message type, 'markdown' by default.
+
+        Returns:
+            The ACK frame dict, or None on failure.
+        """
+        req_id = _generate_req_id(CMD_SEND_MSG)
+        body: dict[str, Any] = {
+            'chatid': chat_id,
+            'msgtype': msgtype,
+        }
+        if msgtype == 'markdown':
+            body['markdown'] = {'content': content}
+        elif msgtype == 'text':
+            body['text'] = {'content': content}
+        return await self._send_reply(req_id, body, cmd=CMD_SEND_MSG)
+
+    async def push_stream_chunk(self, msg_id: str, content: str, is_final: bool = False) -> bool:
+        """Push a streaming chunk for a given message ID.
+
+        Compatible interface with WecomBotClient.push_stream_chunk.
+
+        Args:
+            msg_id: The original message ID.
+            content: The cumulative content from the pipeline.
+            is_final: Whether this is the final chunk.
+
+        Returns:
+            True if the stream session exists and chunk was sent.
+        """
+        key = self._stream_ids.get(msg_id)
+        if not key:
+            return False
+        req_id, stream_id = key.split('|', 1)
+        try:
+            # Skip sending if content hasn't changed (e.g. during tool call argument streaming)
+            if not is_final and content == self._stream_last_content.get(msg_id):
+                return True
+            await self.reply_stream(req_id, stream_id, content, finish=is_final)
+            self._stream_last_content[msg_id] = content
+            if is_final:
+                self._stream_ids.pop(msg_id, None)
+                self._stream_last_content.pop(msg_id, None)
+            return True
+        except Exception:
+            await self.logger.error(f'Failed to push stream chunk: {traceback.format_exc()}')
+            return False
+
+    async def set_message(self, msg_id: str, content: str):
+        """Fallback: send content as a final stream chunk or direct reply.
+
+        Compatible interface with WecomBotClient.set_message.
+        """
+        handled = await self.push_stream_chunk(msg_id, content, is_final=True)
+        if not handled:
+            await self.logger.warning(f'No active stream for msg_id={msg_id}, message dropped')
+
+    # ── Connection lifecycle ────────────────────────────────────────
+
+    async def _connect_once(self):
+        """Establish a single WebSocket connection, authenticate, and listen."""
+        await self.logger.info(f'Connecting to {self.ws_url}...')
+
+        self._session = aiohttp.ClientSession()
+        try:
+            self._ws = await self._session.ws_connect(self.ws_url)
+            self._missed_pong_count = 0
+            self._reconnect_attempts = 0
+            await self.logger.info('WebSocket connected, sending auth...')
+
+            await self._send_auth()
+
+            # Wait for auth response
+            auth_ok = await self._wait_for_auth()
+            if not auth_ok:
+                await self.logger.error('Authentication failed')
+                return
+
+            await self.logger.info('Authenticated successfully')
+
+            # Start heartbeat
+            self._heartbeat_task = asyncio.create_task(self._heartbeat_loop())
+
+            try:
+                await self._listen_loop()
+            finally:
+                if self._heartbeat_task and not self._heartbeat_task.done():
+                    self._heartbeat_task.cancel()
+                self._clear_pending_acks('Connection closed')
+        finally:
+            if self._ws and not self._ws.closed:
+                await self._ws.close()
+            self._ws = None
+            if self._session and not self._session.closed:
+                await self._session.close()
+            self._session = None
+
+    async def _send_auth(self):
+        """Send the authentication frame."""
+        frame = {
+            'cmd': CMD_SUBSCRIBE,
+            'headers': {'req_id': _generate_req_id(CMD_SUBSCRIBE)},
+            'body': {
+                'bot_id': self.bot_id,
+                'secret': self.secret,
+            },
+        }
+        await self._send_frame(frame)
+
+    async def _wait_for_auth(self) -> bool:
+        """Wait for and validate the authentication response."""
+        try:
+            msg = await asyncio.wait_for(self._ws.receive(), timeout=10.0)
+            if msg.type in (aiohttp.WSMsgType.TEXT,):
+                frame = json.loads(msg.data)
+                req_id = frame.get('headers', {}).get('req_id', '')
+                if req_id.startswith(CMD_SUBSCRIBE) and frame.get('errcode') == 0:
+                    return True
+                await self.logger.error(f'Auth response: errcode={frame.get("errcode")}, errmsg={frame.get("errmsg")}')
+                return False
+            elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSED, aiohttp.WSMsgType.CLOSING):
+                await self.logger.error(f'WebSocket closed during auth: {msg.type}')
+                return False
+            await self.logger.error(f'Unexpected message type during auth: {msg.type}')
+            return False
+        except asyncio.TimeoutError:
+            await self.logger.error('Auth response timeout')
+            return False
+
+    async def _heartbeat_loop(self):
+        """Periodically send heartbeat pings."""
+        try:
+            while self._running and self._ws and not self._ws.closed:
+                await asyncio.sleep(self.heartbeat_interval)
+                if not self._running or not self._ws or self._ws.closed:
+                    break
+
+                if self._missed_pong_count >= self._max_missed_pong:
+                    await self.logger.warning(
+                        f'No heartbeat ack for {self._missed_pong_count} consecutive pings, connection considered dead'
+                    )
+                    await self._ws.close()
+                    break
+
+                self._missed_pong_count += 1
+                frame = {
+                    'cmd': CMD_HEARTBEAT,
+                    'headers': {'req_id': _generate_req_id(CMD_HEARTBEAT)},
+                }
+                try:
+                    await self._send_frame(frame)
+                except Exception:
+                    break
+        except asyncio.CancelledError:
+            pass
+
+    async def _listen_loop(self):
+        """Listen for incoming WebSocket frames and dispatch them."""
+        async for msg in self._ws:
+            if not self._running:
+                break
+            if msg.type == aiohttp.WSMsgType.TEXT:
+                try:
+                    frame = json.loads(msg.data)
+                    await self._handle_frame(frame)
+                except json.JSONDecodeError:
+                    await self.logger.error(f'Failed to parse WebSocket message: {str(msg.data)[:200]}')
+                except Exception:
+                    await self.logger.error(f'Error handling frame: {traceback.format_exc()}')
+            elif msg.type == aiohttp.WSMsgType.BINARY:
+                try:
+                    frame = json.loads(msg.data)
+                    await self._handle_frame(frame)
+                except Exception:
+                    await self.logger.error(f'Error handling binary frame: {traceback.format_exc()}')
+            elif msg.type in (aiohttp.WSMsgType.ERROR, aiohttp.WSMsgType.CLOSED, aiohttp.WSMsgType.CLOSING):
+                await self.logger.warning(f'WebSocket connection closed: {msg.type}')
+                break
+
+    # ── Frame handling ──────────────────────────────────────────────
+
+    async def _handle_frame(self, frame: dict):
+        """Route an incoming frame to the appropriate handler."""
+        cmd = frame.get('cmd', '')
+
+        # Message push
+        if cmd == CMD_MSG_CALLBACK:
+            asyncio.create_task(self._handle_message_callback(frame))
+            return
+
+        # Event push
+        if cmd == CMD_EVENT_CALLBACK:
+            asyncio.create_task(self._handle_event_callback(frame))
+            return
+
+        # No cmd → response/ACK frame, dispatch by req_id prefix
+        req_id = frame.get('headers', {}).get('req_id', '')
+
+        # Check pending ACKs first
+        if req_id in self._pending_acks:
+            future = self._pending_acks.pop(req_id)
+            if not future.done():
+                future.set_result(frame)
+            return
+
+        # Heartbeat response
+        if req_id.startswith(CMD_HEARTBEAT):
+            if frame.get('errcode') == 0:
+                self._missed_pong_count = 0
+            return
+
+        # Unknown frame
+        await self.logger.warning(f'Unknown frame: {json.dumps(frame, ensure_ascii=False)[:200]}')
+
+    async def _handle_message_callback(self, frame: dict):
+        """Handle an incoming message callback frame."""
+        try:
+            body = frame.get('body', {})
+            req_id = frame.get('headers', {}).get('req_id', '')
+
+            # Parse message using shared logic
+            message_data = await parse_wecom_bot_message(body, self.encoding_aes_key, self.logger)
+            if not message_data:
+                return
+
+            # Generate stream_id for this message and store the mapping
+            stream_id = _generate_req_id('stream')
+            msg_id = message_data.get('msgid', '')
+            if msg_id:
+                self._stream_ids[msg_id] = f'{req_id}|{stream_id}'
+            message_data['stream_id'] = stream_id
+            message_data['req_id'] = req_id
+
+            event = wecombotevent.WecomBotEvent(message_data)
+            await self._dispatch_event(event)
+        except Exception:
+            await self.logger.error(f'Error in message callback: {traceback.format_exc()}')
+
+    async def _handle_event_callback(self, frame: dict):
+        """Handle an incoming event callback frame (enter_chat, template_card_event, etc.)."""
+        try:
+            body = frame.get('body', {})
+            req_id = frame.get('headers', {}).get('req_id', '')
+
+            event_info = body.get('event', {})
+            event_type = event_info.get('eventtype', '')
+
+            message_data = {
+                'msgtype': 'event',
+                'type': body.get('chattype', 'single'),
+                'event': event_info,
+                'eventtype': event_type,
+                'msgid': body.get('msgid', ''),
+                'aibotid': body.get('aibotid', ''),
+                'req_id': req_id,
+            }
+
+            from_info = body.get('from', {})
+            message_data['userid'] = from_info.get('userid', '')
+            message_data['username'] = from_info.get('alias', '') or from_info.get('userid', '')
+
+            if body.get('chatid'):
+                message_data['chatid'] = body.get('chatid', '')
+
+            event = wecombotevent.WecomBotEvent(message_data)
+
+            # Dispatch to event-specific handlers
+            if event_type in self._message_handlers:
+                for handler in self._message_handlers[event_type]:
+                    await handler(event)
+
+            # Also dispatch to generic 'event' handlers
+            if 'event' in self._message_handlers:
+                for handler in self._message_handlers['event']:
+                    await handler(event)
+
+        except Exception:
+            await self.logger.error(f'Error in event callback: {traceback.format_exc()}')
+
+    async def _dispatch_event(self, event: wecombotevent.WecomBotEvent):
+        """Dispatch a message event to registered handlers with deduplication."""
+        try:
+            message_id = event.message_id
+            if message_id in self._msg_id_map:
+                self._msg_id_map[message_id] += 1
+                return
+            self._msg_id_map[message_id] = 1
+
+            msg_type = event.type
+            if msg_type in self._message_handlers:
+                for handler in self._message_handlers[msg_type]:
+                    await handler(event)
+        except Exception:
+            await self.logger.error(f'Error dispatching event: {traceback.format_exc()}')
+
+    # ── Reply sending with serial queue ─────────────────────────────
+
+    async def _send_reply(
+        self,
+        req_id: str,
+        body: dict,
+        cmd: str = CMD_RESPOND_MSG,
+    ) -> Optional[dict]:
+        """Send a reply frame and wait for ACK.
+
+        Replies with the same req_id are serialized to maintain ordering.
+        """
+        if not self._ws or self._ws.closed:
+            return None
+
+        frame = {
+            'cmd': cmd,
+            'headers': {'req_id': req_id},
+            'body': body,
+        }
+
+        # Ensure serial delivery per req_id
+        if req_id not in self._reply_queues:
+            self._reply_queues[req_id] = asyncio.Queue()
+            self._reply_workers[req_id] = asyncio.create_task(self._reply_queue_worker(req_id))
+
+        future: asyncio.Future = asyncio.get_event_loop().create_future()
+        await self._reply_queues[req_id].put((frame, future))
+        return await future
+
+    async def _reply_queue_worker(self, req_id: str):
+        """Process reply queue items serially for a given req_id."""
+        queue = self._reply_queues[req_id]
+        try:
+            while self._running:
+                try:
+                    frame, future = await asyncio.wait_for(queue.get(), timeout=60.0)
+                except asyncio.TimeoutError:
+                    # Queue idle, clean up worker
+                    break
+
+                try:
+                    ack = await self._send_and_wait_ack(frame)
+                    if not future.done():
+                        future.set_result(ack)
+                except Exception as e:
+                    if not future.done():
+                        future.set_exception(e)
+        except asyncio.CancelledError:
+            pass
+        finally:
+            self._reply_queues.pop(req_id, None)
+            self._reply_workers.pop(req_id, None)
+
+    async def _send_and_wait_ack(self, frame: dict) -> Optional[dict]:
+        """Send a frame and wait for the corresponding ACK."""
+        req_id = frame['headers']['req_id']
+        ack_future: asyncio.Future = asyncio.get_event_loop().create_future()
+        self._pending_acks[req_id] = ack_future
+
+        try:
+            await self._send_frame(frame)
+            result = await asyncio.wait_for(ack_future, timeout=self._reply_ack_timeout)
+            if result.get('errcode', 0) != 0:
+                await self.logger.warning(
+                    f'Reply ACK error: errcode={result.get("errcode")}, errmsg={result.get("errmsg")}'
+                )
+            return result
+        except asyncio.TimeoutError:
+            self._pending_acks.pop(req_id, None)
+            await self.logger.warning(f'Reply ACK timeout ({self._reply_ack_timeout}s) for req_id={req_id}')
+            return None
+
+    async def _send_frame(self, frame: dict):
+        """Send a JSON frame over the WebSocket connection."""
+        if self._ws and not self._ws.closed:
+            await self._ws.send_str(json.dumps(frame, ensure_ascii=False))
+
+    def _clear_pending_acks(self, reason: str):
+        """Reject all pending ACK futures on disconnection."""
+        for req_id, future in self._pending_acks.items():
+            if not future.done():
+                future.set_exception(ConnectionError(reason))
+        self._pending_acks.clear()

src/langbot/libs/wecom_api/api.py

@@ -4,7 +4,6 @@ import base64
 import binascii
 import httpx
 import traceback
-from urllib.parse import quote
 from quart import Quart
 import xml.etree.ElementTree as ET
 from typing import Callable, Dict, Any
@@ -68,31 +67,6 @@ class WecomClient:
                 await self.logger.error(f'获取accesstoken失败:{response.json()}')
                 raise Exception(f'未获取access token: {data}')
 
-    async def get_user_info(self, userid: str) -> dict:
-        """
-        Get user information by user ID using the application secret.
-
-        Args:
-            userid: The user ID to look up.
-
-        Returns:
-            dict: User information including 'name' field.
-        """
-        if not await self.check_access_token():
-            self.access_token = await self.get_access_token(self.secret)
-
-        url = self.base_url + '/user/get?access_token=' + self.access_token + '&userid=' + quote(userid)
-        async with httpx.AsyncClient() as client:
-            response = await client.get(url)
-            data = response.json()
-            if data.get('errcode') == 40014 or data.get('errcode') == 42001:
-                self.access_token = await self.get_access_token(self.secret)
-                return await self.get_user_info(userid)
-            if data.get('errcode', 0) != 0:
-                await self.logger.error(f'获取用户信息失败:{data}')
-                return {}
-            return data
-
     async def get_users(self):
         if not self.check_access_token_for_contacts():
             self.access_token_for_contacts = await self.get_access_token(self.secret_for_contacts)

src/langbot/pkg/api/http/service/bot.py

@@ -68,14 +68,20 @@ class BotService:
             'wecomcs',
             'LINE',
             'lark',
+            'gewechat',
         ]:
             webhook_prefix = self.ap.instance_config.data['api'].get('webhook_prefix', 'http://127.0.0.1:5300')
+            extra_webhook_prefix = self.ap.instance_config.data['api'].get('extra_webhook_prefix', '')
             webhook_url = f'/bots/{bot_uuid}'
             adapter_runtime_values['webhook_url'] = webhook_url
             adapter_runtime_values['webhook_full_url'] = f'{webhook_prefix}{webhook_url}'
+            adapter_runtime_values['extra_webhook_full_url'] = (
+                f'{extra_webhook_prefix}{webhook_url}' if extra_webhook_prefix else ''
+            )
         else:
             adapter_runtime_values['webhook_url'] = None
             adapter_runtime_values['webhook_full_url'] = None
+            adapter_runtime_values['extra_webhook_full_url'] = None
 
         persistence_bot['adapter_runtime_values'] = adapter_runtime_values
 

src/langbot/pkg/api/http/service/model.py

@@ -105,11 +105,16 @@ class LLMModelsService:
                 )
             )
             pipeline = result.first()
-            if pipeline is not None and pipeline.config['ai']['local-agent']['model'] == '':
-                pipeline_config = pipeline.config
-                pipeline_config['ai']['local-agent']['model'] = model_data['uuid']
-                pipeline_data = {'config': pipeline_config}
-                await self.ap.pipeline_service.update_pipeline(pipeline.uuid, pipeline_data)
+            if pipeline is not None:
+                model_config = pipeline.config.get('ai', {}).get('local-agent', {}).get('model', {})
+                if not model_config.get('primary', ''):
+                    pipeline_config = pipeline.config
+                    pipeline_config['ai']['local-agent']['model'] = {
+                        'primary': model_data['uuid'],
+                        'fallbacks': [],
+                    }
+                    pipeline_data = {'config': pipeline_config}
+                    await self.ap.pipeline_service.update_pipeline(pipeline.uuid, pipeline_data)
 
         return model_data['uuid']
 

src/langbot/pkg/core/app.py

@@ -9,6 +9,7 @@ from ..platform import botmgr as im_mgr
 from ..platform.webhook_pusher import WebhookPusher
 from ..provider.session import sessionmgr as llm_session_mgr
 from ..provider.modelmgr import modelmgr as llm_model_mgr
+
 from langbot.pkg.provider.tools import toolmgr as llm_tool_mgr
 from ..config import manager as config_mgr
 from ..command import cmdmgr
@@ -30,6 +31,7 @@ from ..api.http.service import mcp as mcp_service
 from ..api.http.service import apikey as apikey_service
 from ..api.http.service import webhook as webhook_service
 from ..api.http.service import monitoring as monitoring_service
+
 from ..discover import engine as discover_engine
 from ..storage import mgr as storagemgr
 from ..utils import logcache

src/langbot/pkg/core/stages/load_config.py

@@ -74,20 +74,26 @@ def _apply_env_overrides_to_config(cfg: dict) -> dict:
         current = cfg
 
         for i, key in enumerate(keys):
-            if not isinstance(current, dict) or key not in current:
+            if not isinstance(current, dict):
                 break
 
             if i == len(keys) - 1:
-                # At the final key - check if it's a scalar value
-                if isinstance(current[key], (dict, list)):
-                    # Skip dict and list types
-                    pass
+                # At the final key
+                if key in current:
+                    if isinstance(current[key], (dict, list)):
+                        # Skip dict and list types
+                        pass
+                    else:
+                        # Valid scalar value - convert and set it
+                        converted_value = convert_value(env_value, current[key])
+                        current[key] = converted_value
                 else:
-                    # Valid scalar value - convert and set it
-                    converted_value = convert_value(env_value, current[key])
-                    current[key] = converted_value
+                    # Key doesn't exist yet - create it as string
+                    current[key] = env_value
             else:
-                # Navigate deeper
+                # Navigate deeper - create intermediate dict if needed
+                if key not in current:
+                    current[key] = {}
                 current = current[key]
 
     return cfg
@@ -146,16 +152,50 @@ class LoadConfigStage(stage.BootingStage):
         await ap.instance_config.dump_config()
 
         # load or generate instance id
-        ap.instance_id = await config.load_json_config(
-            'data/labels/instance_id.json',
-            template_data={
-                'instance_id': f'instance_{str(uuid.uuid4())}',
-                'instance_create_ts': int(time.time()),
-            },
-            completion=False,
-        )
+        # Priority:
+        # 1. system.instance_id from config.yaml (can be set via SYSTEM__INSTANCE_ID env var)
+        # 2. data/labels/instance_id.json (if file exists)
+        # 3. Generate new and save to file
+        config_instance_id = ap.instance_config.data.get('system', {}).get('instance_id', '')
 
-        constants.instance_id = ap.instance_id.data['instance_id']
+        if config_instance_id:
+            # Use the instance_id from config.yaml
+            constants.instance_id = config_instance_id
+            # Still load/create the file for backward compat, but don't use its value
+            ap.instance_id = await config.load_json_config(
+                'data/labels/instance_id.json',
+                template_data={
+                    'instance_id': f'instance_{str(uuid.uuid4())}',
+                    'instance_create_ts': int(time.time()),
+                },
+                completion=False,
+            )
+        else:
+            # Try loading file-based instance id
+            instance_id_path = os.path.join('data', 'labels', 'instance_id.json')
+            if os.path.exists(instance_id_path):
+                # File exists, read it
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': '',
+                        'instance_create_ts': 0,
+                    },
+                    completion=False,
+                )
+                constants.instance_id = ap.instance_id.data['instance_id']
+            else:
+                # Neither config nor file, generate new and save to file
+                new_id = f'instance_{str(uuid.uuid4())}'
+                ap.instance_id = await config.load_json_config(
+                    'data/labels/instance_id.json',
+                    template_data={
+                        'instance_id': new_id,
+                        'instance_create_ts': int(time.time()),
+                    },
+                    completion=False,
+                )
+                constants.instance_id = new_id
         constants.edition = ap.instance_config.data.get('system', {}).get('edition', 'community')
 
         print(f'LangBot instance id: {constants.instance_id}')

src/langbot/pkg/persistence/migrations/dbm023_model_fallback_config.py

@@ -0,0 +1,102 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(23)
+class DBMigrateModelFallbackConfig(migration.DBMigration):
+    """Convert model field from plain UUID string to object with primary/fallbacks"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
+
+            if 'ai' not in config or 'local-agent' not in config['ai']:
+                continue
+
+            local_agent = config['ai']['local-agent']
+            changed = False
+
+            # Convert model from string to object
+            model_value = local_agent.get('model', '')
+            if isinstance(model_value, str):
+                local_agent['model'] = {
+                    'primary': model_value,
+                    'fallbacks': [],
+                }
+                changed = True
+
+            # Remove leftover fallback-models field if present
+            if 'fallback-models' in local_agent:
+                del local_agent['fallback-models']
+                changed = True
+
+            if not changed:
+                continue
+
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+
+    async def downgrade(self):
+        """Downgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text('SELECT uuid, config FROM legacy_pipelines')
+        )
+        pipelines = result.fetchall()
+
+        current_version = self.ap.ver_mgr.get_current_version()
+
+        for pipeline_row in pipelines:
+            uuid = pipeline_row[0]
+            config = json.loads(pipeline_row[1]) if isinstance(pipeline_row[1], str) else pipeline_row[1]
+
+            if 'ai' not in config or 'local-agent' not in config['ai']:
+                continue
+
+            local_agent = config['ai']['local-agent']
+
+            # Convert model from object back to string
+            model_value = local_agent.get('model', '')
+            if isinstance(model_value, dict):
+                local_agent['model'] = model_value.get('primary', '')
+            else:
+                continue
+
+            # Update using raw SQL with compatibility for both SQLite and PostgreSQL
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config::jsonb, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text(
+                        'UPDATE legacy_pipelines SET config = :config, for_version = :for_version WHERE uuid = :uuid'
+                    ),
+                    {'config': json.dumps(config), 'for_version': current_version, 'uuid': uuid},
+                )

src/langbot/pkg/persistence/migrations/dbm024_wecombot_websocket_mode.py

@@ -0,0 +1,49 @@
+from .. import migration
+
+import sqlalchemy
+import json
+
+
+@migration.migration_class(24)
+class DBMigrateWecomBotWebSocketMode(migration.DBMigration):
+    """Add enable-webhook field to existing wecombot adapter configs.
+
+    Existing wecombot bots were all using webhook mode, so we set
+    enable-webhook=true to preserve their behavior after the new
+    WebSocket long connection mode is introduced as default.
+    """
+
+    async def upgrade(self):
+        """Upgrade"""
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.text("SELECT uuid, adapter_config FROM bots WHERE adapter = 'wecombot'")
+        )
+        bots = result.fetchall()
+
+        for bot_row in bots:
+            bot_uuid = bot_row[0]
+            adapter_config = json.loads(bot_row[1]) if isinstance(bot_row[1], str) else bot_row[1]
+
+            if 'enable-webhook' in adapter_config:
+                continue
+
+            # Determine mode based on existing config: if webhook fields are present, keep webhook mode
+            has_webhook_config = bool(
+                adapter_config.get('Token') and adapter_config.get('EncodingAESKey') and adapter_config.get('Corpid')
+            )
+            adapter_config['enable-webhook'] = has_webhook_config
+
+            if self.ap.persistence_mgr.db.name == 'postgresql':
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('UPDATE bots SET adapter_config = :config::jsonb WHERE uuid = :uuid'),
+                    {'config': json.dumps(adapter_config), 'uuid': bot_uuid},
+                )
+            else:
+                await self.ap.persistence_mgr.execute_async(
+                    sqlalchemy.text('UPDATE bots SET adapter_config = :config WHERE uuid = :uuid'),
+                    {'config': json.dumps(adapter_config), 'uuid': bot_uuid},
+                )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass

src/langbot/pkg/pipeline/preproc/preproc.py

@@ -36,17 +36,36 @@ class PreProcessor(stage.PipelineStage):
         session = await self.ap.sess_mgr.get_session(query)
 
         # When not local-agent, llm_model is None
-        try:
-            llm_model = (
-                await self.ap.model_mgr.get_model_by_uuid(query.pipeline_config['ai']['local-agent']['model'])
-                if selected_runner == 'local-agent'
-                else None
-            )
-        except ValueError:
-            self.ap.logger.warning(
-                f'LLM model {query.pipeline_config["ai"]["local-agent"]["model"] + " "}not found or not configured'
-            )
-            llm_model = None
+        llm_model = None
+        if selected_runner == 'local-agent':
+            # Read model config — new format is { primary: str, fallbacks: [str] },
+            # but handle legacy plain string for backward compatibility
+            model_config = query.pipeline_config['ai']['local-agent'].get('model', {})
+            if isinstance(model_config, str):
+                # Legacy format: plain UUID string
+                primary_uuid = model_config
+                fallback_uuids = []
+            else:
+                primary_uuid = model_config.get('primary', '')
+                fallback_uuids = model_config.get('fallbacks', [])
+
+            if primary_uuid:
+                try:
+                    llm_model = await self.ap.model_mgr.get_model_by_uuid(primary_uuid)
+                except ValueError:
+                    self.ap.logger.warning(f'LLM model {primary_uuid} not found or not configured')
+
+            # Resolve fallback model UUIDs
+            if fallback_uuids:
+                valid_fallbacks = []
+                for fb_uuid in fallback_uuids:
+                    try:
+                        await self.ap.model_mgr.get_model_by_uuid(fb_uuid)
+                        valid_fallbacks.append(fb_uuid)
+                    except ValueError:
+                        self.ap.logger.warning(f'Fallback model {fb_uuid} not found, skipping')
+                if valid_fallbacks:
+                    query.variables['_fallback_model_uuids'] = valid_fallbacks
 
         conversation = await self.ap.sess_mgr.get_conversation(
             query,
@@ -61,20 +80,28 @@ class PreProcessor(stage.PipelineStage):
         query.prompt = conversation.prompt.copy()
         query.messages = conversation.messages.copy()
 
-        if selected_runner == 'local-agent' and llm_model:
+        if selected_runner == 'local-agent':
             query.use_funcs = []
-            query.use_llm_model_uuid = llm_model.model_entity.uuid
+            if llm_model:
+                query.use_llm_model_uuid = llm_model.model_entity.uuid
 
-            if llm_model.model_entity.abilities.__contains__('func_call'):
-                # Get bound plugins and MCP servers for filtering tools
+                if llm_model.model_entity.abilities.__contains__('func_call'):
+                    # Get bound plugins and MCP servers for filtering tools
+                    bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
+                    bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
+                    query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
+
+                    self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
+                    self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
+                    self.ap.logger.debug(f'Use funcs: {query.use_funcs}')
+
+            # If primary model doesn't support func_call but fallback models exist,
+            # load tools anyway since fallback models may support them
+            if not query.use_funcs and query.variables.get('_fallback_model_uuids'):
                 bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                 bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
                 query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
 
-                self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
-                self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
-                self.ap.logger.debug(f'Use funcs: {query.use_funcs}')
-
         sender_name = ''
 
         if isinstance(query.message_event, platform_events.GroupMessage):
@@ -149,6 +176,16 @@ class PreProcessor(stage.PipelineStage):
         query.variables['user_message_text'] = plain_text
 
         query.user_message = provider_message.Message(role='user', content=content_list)
+
+        # Extract knowledge base UUIDs into query variables so plugins can modify them
+        # during PromptPreProcessing before the runner performs retrieval.
+        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
+        if not kb_uuids:
+            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
+            if old_kb_uuid and old_kb_uuid != '__none__':
+                kb_uuids = [old_kb_uuid]
+        query.variables['_knowledge_base_uuids'] = list(kb_uuids)
+
         # =========== 触发事件 PromptPreProcessing
 
         event = events.PromptPreProcessing(

src/langbot/pkg/platform/botmgr.py

@@ -272,6 +272,9 @@ class PlatformManager:
         # 如果 adapter 支持 set_bot_uuid 方法，设置 bot_uuid（用于统一 webhook）
         if hasattr(adapter_inst, 'set_bot_uuid'):
             adapter_inst.set_bot_uuid(bot_entity.uuid)
+            adapter_inst.config['_webhook_prefix'] = self.ap.instance_config.data['api'].get(
+                'webhook_prefix', 'http://127.0.0.1:5300'
+            )
 
         runtime_bot = RuntimeBot(ap=self.ap, bot_entity=bot_entity, adapter=adapter_inst, logger=logger)
 

src/langbot/pkg/platform/sources/gewechat.py

@@ -0,0 +1,609 @@
+import gewechat_client
+
+import typing
+import asyncio
+import traceback
+
+import re
+import copy
+import threading
+
+from langbot.pkg.utils import httpclient
+
+import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
+import langbot_plugin.api.entities.builtin.platform.message as platform_message
+import langbot_plugin.api.entities.builtin.platform.events as platform_events
+import langbot_plugin.api.entities.builtin.platform.entities as platform_entities
+from ...utils import image
+import xml.etree.ElementTree as ET
+from typing import Optional, Tuple
+from functools import partial
+from ..logger import EventLogger
+
+
+class GewechatMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
+    def __init__(self, config: dict):
+        self.config = config
+
+    @staticmethod
+    async def yiri2target(message_chain: platform_message.MessageChain) -> list[dict]:
+        content_list = []
+        for component in message_chain:
+            if isinstance(component, platform_message.At):
+                content_list.append({'type': 'at', 'target': component.target})
+            elif isinstance(component, platform_message.Plain):
+                content_list.append({'type': 'text', 'content': component.text})
+            elif isinstance(component, platform_message.Image):
+                if not component.url:
+                    pass
+                content_list.append({'type': 'image', 'image': component.url})
+            elif isinstance(component, platform_message.Voice):
+                content_list.append({'type': 'voice', 'url': component.url, 'length': component.length})
+            elif isinstance(component, platform_message.Forward):
+                for node in component.node_list:
+                    content_list.extend(await GewechatMessageConverter.yiri2target(node.message_chain))
+                content_list.append({'type': 'image', 'image': component.url})
+            elif isinstance(component, platform_message.WeChatMiniPrograms):
+                content_list.append(
+                    {
+                        'type': 'WeChatMiniPrograms',
+                        'mini_app_id': component.mini_app_id,
+                        'display_name': component.display_name,
+                        'page_path': component.page_path,
+                        'cover_img_url': component.image_url,
+                        'title': component.title,
+                        'user_name': component.user_name,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatForwardMiniPrograms):
+                content_list.append(
+                    {
+                        'type': 'WeChatForwardMiniPrograms',
+                        'xml_data': component.xml_data,
+                        'image_url': component.image_url,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatEmoji):
+                content_list.append(
+                    {
+                        'type': 'WeChatEmoji',
+                        'emoji_md5': component.emoji_md5,
+                        'emoji_size': component.emoji_size,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatLink):
+                content_list.append(
+                    {
+                        'type': 'WeChatLink',
+                        'link_title': component.link_title,
+                        'link_desc': component.link_desc,
+                        'link_thumb_url': component.link_thumb_url,
+                        'link_url': component.link_url,
+                    }
+                )
+            elif isinstance(component, platform_message.WeChatForwardLink):
+                content_list.append({'type': 'WeChatForwardLink', 'xml_data': component.xml_data})
+            elif isinstance(component, platform_message.WeChatForwardImage):
+                content_list.append({'type': 'WeChatForwardImage', 'xml_data': component.xml_data})
+            elif isinstance(component, platform_message.WeChatForwardFile):
+                content_list.append({'type': 'WeChatForwardFile', 'xml_data': component.xml_data})
+            elif isinstance(component, platform_message.WeChatAppMsg):
+                content_list.append({'type': 'WeChatAppMsg', 'app_msg': component.app_msg})
+            elif isinstance(component, platform_message.WeChatForwardQuote):
+                content_list.append({'type': 'WeChatAppMsg', 'app_msg': component.app_msg})
+            elif isinstance(component, platform_message.Forward):
+                for node in component.node_list:
+                    if node.message_chain:
+                        content_list.extend(await GewechatMessageConverter.yiri2target(node.message_chain))
+
+        return content_list
+
+    async def target2yiri(self, message: dict, bot_account_id: str) -> platform_message.MessageChain:
+        message_list = []
+        ats_bot = False
+        content = message['Data']['Content']['string']
+        content_no_preifx = content
+        is_group_message = self._is_group_message(message)
+        if is_group_message:
+            ats_bot = self._ats_bot(message, bot_account_id)
+            if '@所有人' in content:
+                message_list.append(platform_message.AtAll())
+            elif ats_bot:
+                message_list.append(platform_message.At(target=bot_account_id))
+            content_no_preifx, _ = self._extract_content_and_sender(content)
+
+        msg_type = message['Data']['MsgType']
+
+        handler_map = {
+            1: self._handler_text,
+            3: self._handler_image,
+            34: self._handler_voice,
+            49: self._handler_compound,
+        }
+
+        handler = handler_map.get(msg_type, self._handler_default)
+        handler_result = await handler(
+            message=message,
+            content_no_preifx=content_no_preifx,
+        )
+
+        if handler_result and len(handler_result) > 0:
+            message_list.extend(handler_result)
+
+        return platform_message.MessageChain(message_list)
+
+    async def _handler_text(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
+        if message and self._is_group_message(message):
+            pattern = r'@\S{1,20}'
+            content_no_preifx = re.sub(pattern, '', content_no_preifx)
+
+        return platform_message.MessageChain([platform_message.Plain(content_no_preifx)])
+
+    async def _handler_image(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
+        try:
+            image_xml = content_no_preifx
+            if not image_xml:
+                return platform_message.MessageChain([platform_message.Unknown('[图片内容为空]')])
+
+            base64_str, image_format = await image.get_gewechat_image_base64(
+                gewechat_url=self.config['gewechat_url'],
+                gewechat_file_url=self.config['gewechat_file_url'],
+                app_id=self.config['app_id'],
+                xml_content=image_xml,
+                token=self.config['token'],
+                image_type=2,
+            )
+
+            elements = [
+                platform_message.Image(base64=f'data:image/{image_format};base64,{base64_str}'),
+                platform_message.WeChatForwardImage(xml_data=image_xml),
+            ]
+            return platform_message.MessageChain(elements)
+        except Exception as e:
+            print(f'处理图片失败: {str(e)}')
+            return platform_message.MessageChain([platform_message.Unknown('[图片处理失败]')])
+
+    async def _handler_voice(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
+        message_List = []
+        try:
+            audio_base64 = message['Data']['ImgBuf']['buffer']
+
+            if not audio_base64:
+                message_List.append(platform_message.Unknown(text='[语音内容为空]'))
+                return platform_message.MessageChain(message_List)
+
+            voice_element = platform_message.Voice(base64=f'data:audio/silk;base64,{audio_base64}')
+            message_List.append(voice_element)
+
+        except KeyError as e:
+            print(f'语音数据字段缺失: {str(e)}')
+            message_List.append(platform_message.Unknown(text='[语音数据解析失败]'))
+        except Exception as e:
+            print(f'处理语音消息异常: {str(e)}')
+            message_List.append(platform_message.Unknown(text='[语音处理失败]'))
+
+        return platform_message.MessageChain(message_List)
+
+    async def _handler_compound(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
+        try:
+            xml_data = ET.fromstring(content_no_preifx)
+            appmsg_data = xml_data.find('.//appmsg')
+            if appmsg_data:
+                data_type = appmsg_data.findtext('.//type', '')
+
+                sub_handler_map = {
+                    '57': self._handler_compound_quote,
+                    '5': self._handler_compound_link,
+                    '6': self._handler_compound_file,
+                    '33': self._handler_compound_mini_program,
+                    '36': self._handler_compound_mini_program,
+                    '2000': partial(self._handler_compound_unsupported, text='[转账消息]'),
+                    '2001': partial(self._handler_compound_unsupported, text='[红包消息]'),
+                    '51': partial(self._handler_compound_unsupported, text='[视频号消息]'),
+                }
+
+                handler = sub_handler_map.get(data_type, self._handler_compound_unsupported)
+                return await handler(
+                    message=message,
+                    xml_data=xml_data,
+                )
+            else:
+                return platform_message.MessageChain([platform_message.Unknown(text=content_no_preifx)])
+        except Exception as e:
+            print(f'解析复合消息失败: {str(e)}')
+            return platform_message.MessageChain([platform_message.Unknown(text=content_no_preifx)])
+
+    async def _handler_compound_quote(
+        self, message: Optional[dict], xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        message_list = []
+        appmsg_data = xml_data.find('.//appmsg')
+        quote_data = ''
+        user_data = ''
+        sender_id = xml_data.findtext('.//fromusername')
+        if appmsg_data:
+            user_data = appmsg_data.findtext('.//title') or ''
+            quote_data = appmsg_data.find('.//refermsg').findtext('.//content')
+            message_list.append(
+                platform_message.WeChatForwardQuote(app_msg=ET.tostring(appmsg_data, encoding='unicode'))
+            )
+        if quote_data:
+            quote_data_message_list = platform_message.MessageChain()
+            try:
+                if '<msg>' not in quote_data:
+                    quote_data_message_list.append(platform_message.Plain(quote_data))
+                else:
+                    quote_data_xml = ET.fromstring(quote_data)
+                    if quote_data_xml.find('img'):
+                        quote_data_message_list.extend(await self._handler_image(None, quote_data))
+                    elif quote_data_xml.find('voicemsg'):
+                        quote_data_message_list.extend(await self._handler_voice(None, quote_data))
+                    elif quote_data_xml.find('videomsg'):
+                        quote_data_message_list.extend(await self._handler_default(None, quote_data))
+                    else:
+                        quote_data_message_list.extend(await self._handler_compound(None, quote_data))
+            except Exception as e:
+                print(f'处理引用消息异常 expcetion:{e}')
+                quote_data_message_list.append(platform_message.Plain(quote_data))
+            message_list.append(
+                platform_message.Quote(
+                    sender_id=sender_id,
+                    origin=quote_data_message_list,
+                )
+            )
+            if len(user_data) > 0:
+                pattern = r'@\S{1,20}'
+                user_data = re.sub(pattern, '', user_data)
+                message_list.append(platform_message.Plain(user_data))
+
+        return platform_message.MessageChain(message_list)
+
+    async def _handler_compound_file(self, message: dict, xml_data: ET.Element) -> platform_message.MessageChain:
+        xml_data_str = ET.tostring(xml_data, encoding='unicode')
+        return platform_message.MessageChain([platform_message.WeChatForwardFile(xml_data=xml_data_str)])
+
+    async def _handler_compound_link(self, message: dict, xml_data: ET.Element) -> platform_message.MessageChain:
+        message_list = []
+        try:
+            appmsg = xml_data.find('.//appmsg')
+            if appmsg is None:
+                return platform_message.MessageChain()
+            message_list.append(
+                platform_message.WeChatLink(
+                    link_title=appmsg.findtext('title', ''),
+                    link_desc=appmsg.findtext('des', ''),
+                    link_url=appmsg.findtext('url', ''),
+                    link_thumb_url=appmsg.findtext('thumburl', ''),
+                )
+            )
+            xml_data_str = ET.tostring(xml_data, encoding='unicode')
+            message_list.append(platform_message.WeChatForwardLink(xml_data=xml_data_str))
+        except Exception as e:
+            print(f'解析链接消息失败: {str(e)}')
+        return platform_message.MessageChain(message_list)
+
+    async def _handler_compound_mini_program(
+        self, message: dict, xml_data: ET.Element
+    ) -> platform_message.MessageChain:
+        xml_data_str = ET.tostring(xml_data, encoding='unicode')
+        return platform_message.MessageChain([platform_message.WeChatForwardMiniPrograms(xml_data=xml_data_str)])
+
+    async def _handler_default(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
+        if message:
+            msg_type = message['Data']['MsgType']
+        else:
+            msg_type = ''
+        return platform_message.MessageChain([platform_message.Unknown(text=f'[未知消息类型 msg_type:{msg_type}]')])
+
+    def _handler_compound_unsupported(
+        self, message: dict, xml_data: str, text: Optional[str] = None
+    ) -> platform_message.MessageChain:
+        if not text:
+            text = f'[xml_data={xml_data}]'
+        content_list = []
+        content_list.append(platform_message.Unknown(text=f'[处理未支持复合消息类型[msg_type=49]|{text}'))
+
+        return platform_message.MessageChain(content_list)
+
+    def _ats_bot(self, message: dict, bot_account_id: str) -> bool:
+        ats_bot = False
+        try:
+            to_user_name = message['Wxid']
+            raw_content = message['Data']['Content']['string']
+            content_no_prefix, _ = self._extract_content_and_sender(raw_content)
+            push_content = message.get('Data', {}).get('PushContent', '')
+            ats_bot = ats_bot or ('在群聊中@了你' in push_content)
+            msg_source = message.get('Data', {}).get('MsgSource', '') or ''
+            if len(msg_source) > 0:
+                msg_source_data = ET.fromstring(msg_source)
+                at_user_list = msg_source_data.findtext('atuserlist') or ''
+                ats_bot = ats_bot or (to_user_name in at_user_list)
+            if message.get('Data', {}).get('MsgType', 0) == 49:
+                xml_data = ET.fromstring(content_no_prefix)
+                appmsg_data = xml_data.find('.//appmsg')
+                tousername = message['Wxid']
+                if appmsg_data:
+                    quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
+                    ats_bot = ats_bot or (quote_id == tousername)
+        except Exception as e:
+            print(f'Error in gewechat _ats_bot: {e}')
+        finally:
+            return ats_bot
+
+    def _extract_content_and_sender(self, raw_content: str) -> Tuple[str, Optional[str]]:
+        try:
+            regex = re.compile(r'^[a-zA-Z0-9_\-]{5,20}:')
+            line_split = raw_content.split('\n')
+            if len(line_split) > 0 and regex.match(line_split[0]):
+                raw_content = '\n'.join(line_split[1:])
+                sender_id = line_split[0].strip(':')
+                return raw_content, sender_id
+        except Exception as e:
+            print(f'_extract_content_and_sender got except: {e}')
+        finally:
+            return raw_content, None
+
+    def _is_group_message(self, message: dict) -> bool:
+        from_user_name = message['Data']['FromUserName']['string']
+        return from_user_name.endswith('@chatroom')
+
+
+class GewechatEventConverter(abstract_platform_adapter.AbstractEventConverter):
+    def __init__(self, config: dict):
+        self.config = config
+        self.message_converter = GewechatMessageConverter(config)
+
+    @staticmethod
+    async def yiri2target(event: platform_events.MessageEvent) -> dict:
+        pass
+
+    async def target2yiri(self, event: dict, bot_account_id: str) -> platform_events.MessageEvent:
+        if event['Wxid'] == event['Data']['FromUserName']['string']:
+            return None
+        if event['Data']['FromUserName']['string'].startswith('gh_') or event['Data']['FromUserName'][
+            'string'
+        ].startswith('weixin'):
+            return None
+        message_chain = await self.message_converter.target2yiri(copy.deepcopy(event), bot_account_id)
+
+        if not message_chain:
+            return None
+
+        if '@chatroom' in event['Data']['FromUserName']['string']:
+            sender_wxid = event['Data']['Content']['string'].split(':')[0]
+
+            return platform_events.GroupMessage(
+                sender=platform_entities.GroupMember(
+                    id=sender_wxid,
+                    member_name=event['Data']['FromUserName']['string'],
+                    permission=platform_entities.Permission.Member,
+                    group=platform_entities.Group(
+                        id=event['Data']['FromUserName']['string'],
+                        name=event['Data']['FromUserName']['string'],
+                        permission=platform_entities.Permission.Member,
+                    ),
+                    special_title='',
+                ),
+                message_chain=message_chain,
+                time=event['Data']['CreateTime'],
+                source_platform_object=event,
+            )
+        else:
+            return platform_events.FriendMessage(
+                sender=platform_entities.Friend(
+                    id=event['Data']['FromUserName']['string'],
+                    nickname=event['Data']['FromUserName']['string'],
+                    remark='',
+                ),
+                message_chain=message_chain,
+                time=event['Data']['CreateTime'],
+                source_platform_object=event,
+            )
+
+
+class GeWeChatAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
+    bot: gewechat_client.GewechatClient = None
+    bot_uuid: str = None
+    message_converter: GewechatMessageConverter = None
+    event_converter: GewechatEventConverter = None
+
+    listeners: typing.Dict[
+        typing.Type[platform_events.Event],
+        typing.Callable[[platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None],
+    ] = {}
+
+    def __init__(self, config: dict, logger: EventLogger):
+        super().__init__(
+            config=config,
+            logger=logger,
+        )
+
+        self.message_converter = GewechatMessageConverter(config)
+        self.event_converter = GewechatEventConverter(config)
+
+    def set_bot_uuid(self, bot_uuid: str):
+        self.bot_uuid = bot_uuid
+
+    async def handle_unified_webhook(self, bot_uuid: str, path: str, request):
+        data = await request.json
+        await self.logger.debug(f'Gewechat callback event: {data}')
+
+        if 'data' in data:
+            data['Data'] = data['data']
+        if 'type_name' in data:
+            data['TypeName'] = data['type_name']
+
+        if 'testMsg' in data:
+            return 'ok'
+        elif 'TypeName' in data and data['TypeName'] == 'AddMsg':
+            try:
+                event = await self.event_converter.target2yiri(data.copy(), self.bot_account_id)
+            except Exception:
+                await self.logger.error(f'Error in gewechat callback: {traceback.format_exc()}')
+                return 'ok'
+
+            if event and event.__class__ in self.listeners:
+                await self.listeners[event.__class__](event, self)
+
+            return 'ok'
+
+        return 'ok'
+
+    async def _handle_message(self, message: platform_message.MessageChain, target_id: str):
+        content_list = await self.message_converter.yiri2target(message)
+        at_targets = [item['target'] for item in content_list if item['type'] == 'at']
+
+        at_targets = at_targets or []
+        member_info = []
+        if at_targets:
+            member_info = self.bot.get_chatroom_member_detail(self.config['app_id'], target_id, at_targets[::-1])[
+                'data'
+            ]
+
+        for msg in content_list:
+            if msg['type'] == 'text' and at_targets:
+                for member in member_info:
+                    msg['content'] = f'@{member["nickName"]} {msg["content"]}'
+
+            handler_map = {
+                'text': lambda msg: self.bot.post_text(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    content=msg['content'],
+                    ats=','.join(at_targets),
+                ),
+                'image': lambda msg: self.bot.post_image(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    img_url=msg['image'],
+                ),
+                'WeChatForwardMiniPrograms': lambda msg: self.bot.forward_mini_app(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    xml=msg['xml_data'],
+                    cover_img_url=msg.get('image_url'),
+                ),
+                'WeChatEmoji': lambda msg: self.bot.post_emoji(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    emoji_md5=msg['emoji_md5'],
+                    emoji_size=msg['emoji_size'],
+                ),
+                'WeChatLink': lambda msg: self.bot.post_link(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    title=msg['link_title'],
+                    desc=msg['link_desc'],
+                    link_url=msg['link_url'],
+                    thumb_url=msg['link_thumb_url'],
+                ),
+                'WeChatMiniPrograms': lambda msg: self.bot.post_mini_app(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    mini_app_id=msg['mini_app_id'],
+                    display_name=msg['display_name'],
+                    page_path=msg['page_path'],
+                    cover_img_url=msg['cover_img_url'],
+                    title=msg['title'],
+                    user_name=msg['user_name'],
+                ),
+                'WeChatForwardLink': lambda msg: self.bot.forward_url(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'WeChatForwardImage': lambda msg: self.bot.forward_image(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'WeChatForwardFile': lambda msg: self.bot.forward_file(
+                    app_id=self.config['app_id'], to_wxid=target_id, xml=msg['xml_data']
+                ),
+                'voice': lambda msg: self.bot.post_voice(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    voice_url=msg['url'],
+                    voice_duration=msg['length'],
+                ),
+                'WeChatAppMsg': lambda msg: self.bot.post_app_msg(
+                    app_id=self.config['app_id'],
+                    to_wxid=target_id,
+                    appmsg=msg['app_msg'],
+                ),
+                'at': lambda msg: None,
+            }
+
+            if handler := handler_map.get(msg['type']):
+                handler(msg)
+            else:
+                await self.logger.warning(f'未处理的消息类型: {msg["type"]}')
+                continue
+
+    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
+        return await self._handle_message(message, target_id)
+
+    async def reply_message(
+        self,
+        message_source: platform_events.MessageEvent,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+    ):
+        if message_source.source_platform_object:
+            target_id = message_source.source_platform_object['Data']['FromUserName']['string']
+            return await self._handle_message(message, target_id)
+
+    async def is_muted(self, group_id: int) -> bool:
+        pass
+
+    def register_listener(
+        self,
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[
+            [platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None
+        ],
+    ):
+        self.listeners[event_type] = callback
+
+    def unregister_listener(
+        self,
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[
+            [platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None
+        ],
+    ):
+        pass
+
+    def _build_callback_url(self) -> str:
+        webhook_prefix = self.config.get('_webhook_prefix', 'http://127.0.0.1:5300').rstrip('/')
+        return f'{webhook_prefix}/bots/{self.bot_uuid}'
+
+    async def run_async(self):
+        if not self.config['token']:
+            session = httpclient.get_session()
+            async with session.post(
+                f'{self.config["gewechat_url"]}/v2/api/tools/getTokenId',
+                json={'app_id': self.config['app_id']},
+            ) as response:
+                if response.status != 200:
+                    raise Exception(f'获取gewechat token失败: {await response.text()}')
+                self.config['token'] = (await response.json())['data']
+
+        self.bot = gewechat_client.GewechatClient(f'{self.config["gewechat_url"]}/v2/api', self.config['token'])
+
+        def gewechat_init_process():
+            profile = self.bot.get_profile(self.config['app_id'])
+            self.bot_account_id = profile['data']['nickName']
+
+            try:
+                callback_url = self._build_callback_url()
+                self.bot.set_callback(self.config['token'], callback_url)
+                print(f'Gewechat 回调地址已设置: {callback_url}')
+            except Exception as e:
+                raise Exception(f'设置 Gewechat 回调失败，token失效：{e}')
+
+        threading.Thread(target=gewechat_init_process).start()
+
+        # 统一 webhook 模式下，不启动独立的 HTTP 服务
+        # 保持适配器运行
+        while True:
+            await asyncio.sleep(1)
+
+    async def kill(self) -> bool:
+        return False

src/langbot/pkg/platform/sources/gewechat.yaml

@@ -0,0 +1,51 @@
+apiVersion: v1
+kind: MessagePlatformAdapter
+metadata:
+  name: gewechat
+  label:
+    en_US: GeWeChat
+    zh_Hans: GeWeChat（个人微信）
+  description:
+    en_US: GeWeChat Adapter (Unified Webhook)
+    zh_Hans: GeWeChat 适配器（统一 Webhook），请查看文档了解使用方式
+  icon: gewechat.png
+spec:
+  config:
+    - name: gewechat_url
+      label:
+        en_US: GeWeChat URL
+        zh_Hans: GeWeChat URL
+      description:
+        en_US: GeWeChat API server address, e.g. http://127.0.0.1:2531
+        zh_Hans: GeWeChat API 服务器地址，如 http://127.0.0.1:2531
+      type: string
+      required: true
+      default: ""
+    - name: gewechat_file_url
+      label:
+        en_US: GeWeChat file download URL
+        zh_Hans: GeWeChat 文件下载URL
+      description:
+        en_US: GeWeChat file download service address
+        zh_Hans: GeWeChat 文件下载服务地址
+      type: string
+      required: true
+      default: ""
+    - name: app_id
+      label:
+        en_US: App ID
+        zh_Hans: 应用ID
+      type: string
+      required: true
+      default: ""
+    - name: token
+      label:
+        en_US: Token
+        zh_Hans: 令牌
+      type: string
+      required: true
+      default: ""
+execution:
+  python:
+    path: ./gewechat.py
+    attr: GeWeChatAdapter

src/langbot/pkg/platform/sources/lark.py

@@ -575,6 +575,127 @@ class LarkMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
 
 
 class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
+    _processed_thread_quote_cache: typing.ClassVar[dict[str, float]] = {}
+    _processed_thread_quote_cache_max_size: typing.ClassVar[int] = 4096
+    _processed_thread_quote_cache_ttl_seconds: typing.ClassVar[int] = 86400
+
+    @classmethod
+    def _prune_processed_thread_quote_cache(cls, now: typing.Optional[float] = None) -> None:
+        if now is None:
+            now = time.time()
+
+        expire_before = now - cls._processed_thread_quote_cache_ttl_seconds
+        while cls._processed_thread_quote_cache:
+            oldest_key, oldest_ts = next(iter(cls._processed_thread_quote_cache.items()))
+            if oldest_ts >= expire_before:
+                break
+            cls._processed_thread_quote_cache.pop(oldest_key, None)
+
+        while len(cls._processed_thread_quote_cache) > cls._processed_thread_quote_cache_max_size:
+            oldest_key = next(iter(cls._processed_thread_quote_cache))
+            cls._processed_thread_quote_cache.pop(oldest_key, None)
+
+    @classmethod
+    def _mark_thread_quote_processed(cls, thread_id: str) -> None:
+        now = time.time()
+        cls._prune_processed_thread_quote_cache(now)
+        cls._processed_thread_quote_cache[thread_id] = now
+
+    @classmethod
+    def _extract_quote_message_id(cls, message: EventMessage) -> typing.Optional[str]:
+        """
+        Extract the message ID to quote from the given message.
+
+        Rules:
+        - First thread reply in a topic: return parent_id and mark topic as processed
+        - Follow-up thread replies in the same topic: return None
+        - Non-thread message: return parent_id if valid (non-empty, different from message_id)
+
+        Thread reply state is kept in a bounded TTL cache to avoid unbounded memory growth.
+        """
+        parent_id = getattr(message, 'parent_id', None)
+        if not parent_id:
+            return None
+
+        message_id = getattr(message, 'message_id', None)
+        if parent_id == message_id:
+            return None
+
+        thread_id = getattr(message, 'thread_id', None)
+        if thread_id:
+            cls._prune_processed_thread_quote_cache()
+            if thread_id in cls._processed_thread_quote_cache:
+                return None
+            cls._mark_thread_quote_processed(thread_id)
+
+        return parent_id
+
+    @staticmethod
+    def _build_event_message_from_message_item(message_item: Message) -> typing.Optional[EventMessage]:
+        """
+        Build EventMessage from SDK typed Message item.
+
+        Returns None if body or content is missing.
+        """
+        body = getattr(message_item, 'body', None)
+        if not body:
+            return None
+
+        content = getattr(body, 'content', None)
+        if not content:
+            return None
+
+        event_data = {
+            'message_id': message_item.message_id,
+            'message_type': message_item.msg_type,
+            'content': content,
+            'create_time': message_item.create_time,
+            'mentions': getattr(message_item, 'mentions', []) or [],
+        }
+
+        # Preserve thread-related fields
+        if hasattr(message_item, 'parent_id') and message_item.parent_id:
+            event_data['parent_id'] = message_item.parent_id
+        if hasattr(message_item, 'root_id') and message_item.root_id:
+            event_data['root_id'] = message_item.root_id
+        if hasattr(message_item, 'thread_id') and message_item.thread_id:
+            event_data['thread_id'] = message_item.thread_id
+        if hasattr(message_item, 'chat_id') and message_item.chat_id:
+            event_data['chat_id'] = message_item.chat_id
+
+        return EventMessage(event_data)
+
+    @staticmethod
+    async def _fetch_quoted_message(
+        quote_message_id: str,
+        api_client: lark_oapi.Client,
+    ) -> typing.Optional[platform_message.MessageChain]:
+        """
+        Fetch the quoted message and convert to MessageChain.
+
+        Returns None if:
+        - API call fails
+        - Response items is empty
+        - Message item normalization fails
+        """
+        request = GetMessageRequest.builder().message_id(quote_message_id).build()
+        response = await api_client.im.v1.message.aget(request)
+
+        if not response.success():
+            return None
+
+        items = getattr(response.data, 'items', None)
+        if not items:
+            return None
+
+        message_item = items[0]
+        event_message = LarkEventConverter._build_event_message_from_message_item(message_item)
+        if event_message is None:
+            return None
+
+        quote_chain = await LarkMessageConverter.target2yiri(event_message, api_client)
+        return quote_chain
+
     @staticmethod
     async def yiri2target(
         event: platform_events.MessageEvent,
@@ -587,6 +708,23 @@ class LarkEventConverter(abstract_platform_adapter.AbstractEventConverter):
     ) -> platform_events.Event:
         message_chain = await LarkMessageConverter.target2yiri(event.event.message, api_client)
 
+        # Check for quote/reply message
+        quote_message_id = LarkEventConverter._extract_quote_message_id(event.event.message)
+        if quote_message_id:
+            quote_chain = await LarkEventConverter._fetch_quoted_message(quote_message_id, api_client)
+            if quote_chain:
+                # Filter out Source component from quoted chain, keep only content
+                quote_origin = platform_message.MessageChain(
+                    [comp for comp in quote_chain if not isinstance(comp, platform_message.Source)]
+                )
+                if quote_origin:
+                    message_chain.append(
+                        platform_message.Quote(
+                            message_id=quote_message_id,
+                            origin=quote_origin,
+                        )
+                    )
+
         if event.event.message.chat_type == 'p2p':
             return platform_events.FriendMessage(
                 sender=platform_entities.Friend(
@@ -770,6 +908,32 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             self.request_tenant_access_token(tenant_key)
         return self.tenant_access_tokens.get(tenant_key)['token'] if self.tenant_access_tokens.get(tenant_key) else None
 
+    def get_launcher_id(self, event: platform_events.MessageEvent) -> str | None:
+        """
+        Get topic-scoped launcher_id for thread-aware session isolation.
+
+        For group thread messages, returns "{group_id}_{thread_id}"
+        to ensure conversation context stays stable per topic.
+
+        Returns None for non-thread messages or P2P messages.
+        """
+        source_event = getattr(event.source_platform_object, 'event', None)
+        if not source_event:
+            return None
+
+        message = getattr(source_event, 'message', None)
+        if not message:
+            return None
+
+        thread_id = getattr(message, 'thread_id', None)
+        if not thread_id:
+            return None
+
+        if isinstance(event, platform_events.GroupMessage):
+            return f'{event.group.id}_{thread_id}'
+
+        return None
+
     def build_api_client(self, config):
         app_id = config['app_id']
         app_secret = config['app_secret']

src/langbot/pkg/platform/sources/telegram.py

@@ -42,6 +42,25 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
                         photo_bytes = f.read()
 
                 components.append({'type': 'photo', 'photo': photo_bytes})
+            elif isinstance(component, platform_message.File):
+                file_bytes = None
+
+                if component.base64:
+                    # Strip data URI prefix if present (e.g. "data:application/pdf;base64,...")
+                    b64_data = component.base64
+                    if ';base64,' in b64_data:
+                        b64_data = b64_data.split(';base64,', 1)[1]
+                    file_bytes = base64.b64decode(b64_data)
+                elif component.url:
+                    session = httpclient.get_session()
+                    async with session.get(component.url) as response:
+                        file_bytes = await response.read()
+                elif component.path:
+                    with open(component.path, 'rb') as f:
+                        file_bytes = f.read()
+
+                file_name = getattr(component, 'name', None) or 'file'
+                components.append({'type': 'document', 'document': file_bytes, 'filename': file_name})
             elif isinstance(component, platform_message.Forward):
                 for node in component.node_list:
                     components.extend(await TelegramMessageConverter.yiri2target(node.message_chain, bot))
@@ -104,6 +123,27 @@ class TelegramMessageConverter(abstract_platform_adapter.AbstractMessageConverte
                 )
             )
 
+        if message.document:
+            if message.caption:
+                message_components.extend(parse_message_text(message.caption))
+
+            file = await message.document.get_file()
+            file_name = message.document.file_name or 'document'
+            file_size = message.document.file_size or 0
+            file_format = message.document.mime_type or 'application/octet-stream'
+
+            file_bytes = None
+            async with httpclient.get_session(trust_env=True).get(file.file_path) as response:
+                file_bytes = await response.read()
+
+            message_components.append(
+                platform_message.File(
+                    name=file_name,
+                    size=file_size,
+                    base64=f'data:{file_format};base64,{base64.b64encode(file_bytes).decode("utf-8")}',
+                )
+            )
+
         return platform_message.MessageChain(message_components)
 
 
@@ -179,7 +219,10 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         application = ApplicationBuilder().token(config['token']).build()
         bot = application.bot
         application.add_handler(
-            MessageHandler(filters.TEXT | (filters.COMMAND) | filters.PHOTO | filters.VOICE, telegram_callback)
+            MessageHandler(
+                filters.TEXT | (filters.COMMAND) | filters.PHOTO | filters.VOICE | filters.Document.ALL,
+                telegram_callback,
+            )
         )
         super().__init__(
             config=config,
@@ -218,6 +261,13 @@ class TelegramAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                     continue
                 args['photo'] = telegram.InputFile(photo)
                 await self.bot.send_photo(**args)
+            elif component_type == 'document':
+                doc = component.get('document')
+                if doc is None:
+                    continue
+                filename = component.get('filename', 'file')
+                args['document'] = telegram.InputFile(doc, filename=filename)
+                await self.bot.send_document(**args)
 
     async def reply_message(
         self,

src/langbot/pkg/platform/sources/wecom.py

@@ -148,54 +148,51 @@ class WecomEventConverter(abstract_platform_adapter.AbstractEventConverter):
             pass
 
         if type(event) is platform_events.FriendMessage:
-            return event.source_platform_object
+            payload = {
+                'MsgType': 'text',
+                'Content': '',
+                'FromUserName': event.sender.id,
+                'ToUserName': bot_account_id,
+                'CreateTime': int(datetime.datetime.now().timestamp()),
+                'AgentID': event.sender.nickname,
+            }
+            wecom_event = WecomEvent.from_payload(payload=payload)
+            if not wecom_event:
+                raise ValueError('无法从 message_data 构造 WecomEvent 对象')
+
+            return wecom_event
 
     @staticmethod
-    async def target2yiri(event: WecomEvent, bot: WecomClient = None):
+    async def target2yiri(event: WecomEvent):
         """
         将 WecomEvent 转换为平台的 FriendMessage 对象。
 
         Args:
             event (WecomEvent): 企业微信事件。
-            bot (WecomClient): 企业微信客户端，用于获取用户信息。
 
         Returns:
             platform_events.FriendMessage: 转换后的 FriendMessage 对象。
         """
-        # Try to get the user's real name from the WeCom API
-        nickname = str(event.user_id)
-        if bot and event.user_id:
-            try:
-                user_info = await bot.get_user_info(event.user_id)
-                if user_info and user_info.get('name'):
-                    nickname = user_info.get('name')
-            except Exception:
-                pass  # Fall back to user_id as nickname
-
         # 转换消息链
         if event.type == 'text':
             yiri_chain = await WecomMessageConverter.target2yiri(event.message, event.message_id)
             friend = platform_entities.Friend(
                 id=f'u{event.user_id}',
-                nickname=nickname,
+                nickname=str(event.agent_id),
                 remark='',
             )
 
-            return platform_events.FriendMessage(
-                sender=friend, message_chain=yiri_chain, time=event.timestamp, source_platform_object=event
-            )
+            return platform_events.FriendMessage(sender=friend, message_chain=yiri_chain, time=event.timestamp)
         elif event.type == 'image':
             friend = platform_entities.Friend(
                 id=f'u{event.user_id}',
-                nickname=nickname,
+                nickname=str(event.agent_id),
                 remark='',
             )
 
             yiri_chain = await WecomMessageConverter.target2yiri_image(picurl=event.picurl, message_id=event.message_id)
 
-            return platform_events.FriendMessage(
-                sender=friend, message_chain=yiri_chain, time=event.timestamp, source_platform_object=event
-            )
+            return platform_events.FriendMessage(sender=friend, message_chain=yiri_chain, time=event.timestamp)
 
 
 class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
@@ -213,6 +210,7 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             'secret',
             'token',
             'EncodingAESKey',
+            'contacts_secret',
         ]
 
         missing_keys = [key for key in required_keys if key not in config]
@@ -225,7 +223,7 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             secret=config['secret'],
             token=config['token'],
             EncodingAESKey=config['EncodingAESKey'],
-            contacts_secret=config.get('contacts_secret', ''),  # Optional, kept for backward compatibility
+            contacts_secret=config['contacts_secret'],
             logger=logger,
             unified_mode=True,
             api_base_url=config.get('api_base_url', 'https://qyapi.weixin.qq.com/cgi-bin'),
@@ -250,17 +248,18 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
     ):
         Wecom_event = await WecomEventConverter.yiri2target(message_source, self.bot_account_id, self.bot)
         content_list = await WecomMessageConverter.yiri2target(message, self.bot)
-        # user_id is the original FromUserName from WecomEvent
-        user_id = Wecom_event.user_id
+        fixed_user_id = Wecom_event.user_id
+        # 删掉开头的u
+        fixed_user_id = fixed_user_id[1:]
         for content in content_list:
             if content['type'] == 'text':
-                await self.bot.send_private_msg(user_id, Wecom_event.agent_id, content['content'])
+                await self.bot.send_private_msg(fixed_user_id, Wecom_event.agent_id, content['content'])
             elif content['type'] == 'image':
-                await self.bot.send_image(user_id, Wecom_event.agent_id, content['media_id'])
+                await self.bot.send_image(fixed_user_id, Wecom_event.agent_id, content['media_id'])
             elif content['type'] == 'voice':
-                await self.bot.send_voice(user_id, Wecom_event.agent_id, content['media_id'])
+                await self.bot.send_voice(fixed_user_id, Wecom_event.agent_id, content['media_id'])
             elif content['type'] == 'file':
-                await self.bot.send_file(user_id, Wecom_event.agent_id, content['media_id'])
+                await self.bot.send_file(fixed_user_id, Wecom_event.agent_id, content['media_id'])
 
     async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
         content_list = await WecomMessageConverter.yiri2target(message, self.bot)
@@ -288,7 +287,7 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         async def on_message(event: WecomEvent):
             self.bot_account_id = event.receiver_id
             try:
-                return await callback(await self.event_converter.target2yiri(event, self.bot), self)
+                return await callback(await self.event_converter.target2yiri(event), self)
             except Exception:
                 await self.logger.error(f'Error in wecom callback: {traceback.format_exc()}')
 

src/langbot/pkg/platform/sources/wecom.yaml

@@ -39,6 +39,13 @@ spec:
       type: string
       required: true
       default: ""
+    - name: contacts_secret
+      label:
+        en_US: Contacts Secret
+        zh_Hans: 通讯录密钥
+      type: string
+      required: true
+      default: ""
     - name: api_base_url
       label:
         en_US: API Base URL

src/langbot/pkg/platform/sources/wecombot.py

@@ -11,6 +11,7 @@ import langbot_plugin.api.entities.builtin.platform.entities as platform_entitie
 from ..logger import EventLogger
 from langbot.libs.wecom_ai_bot_api.wecombotevent import WecomBotEvent
 from langbot.libs.wecom_ai_bot_api.api import WecomBotClient
+from langbot.libs.wecom_ai_bot_api.ws_client import WecomBotWsClient
 
 
 class WecomBotMessageConverter(abstract_platform_adapter.AbstractMessageConverter):
@@ -23,14 +24,18 @@ class WecomBotMessageConverter(abstract_platform_adapter.AbstractMessageConverte
         return content
 
     @staticmethod
-    async def target2yiri(event: WecomBotEvent):
+    async def target2yiri(event: WecomBotEvent, bot_name: str = ''):
         yiri_msg_list = []
         if event.type == 'group':
             yiri_msg_list.append(platform_message.At(target=event.ai_bot_id))
+
         yiri_msg_list.append(platform_message.Source(id=event.message_id, time=datetime.datetime.now()))
 
         if event.content:
-            yiri_msg_list.append(platform_message.Plain(text=event.content))
+            content = event.content
+            if bot_name:
+                content = content.replace(f'@{bot_name}', '').strip()
+            yiri_msg_list.append(platform_message.Plain(text=content))
 
         images = []
         if event.images:
@@ -133,13 +138,15 @@ class WecomBotMessageConverter(abstract_platform_adapter.AbstractMessageConverte
 
 
 class WecomBotEventConverter(abstract_platform_adapter.AbstractEventConverter):
+    def __init__(self, bot_name: str = ''):
+        self.bot_name = bot_name
+
     @staticmethod
     async def yiri2target(event: platform_events.MessageEvent):
         return event.source_platform_object
 
-    @staticmethod
-    async def target2yiri(event: WecomBotEvent):
-        message_chain = await WecomBotMessageConverter.target2yiri(event)
+    async def target2yiri(self, event: WecomBotEvent):
+        message_chain = await WecomBotMessageConverter.target2yiri(event, bot_name=self.bot_name)
         if event.type == 'single':
             return platform_events.FriendMessage(
                 sender=platform_entities.Friend(
@@ -176,34 +183,53 @@ class WecomBotEventConverter(abstract_platform_adapter.AbstractEventConverter):
 
 
 class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
-    bot: WecomBotClient
+    bot: typing.Union[WecomBotClient, WecomBotWsClient]
     bot_account_id: str
     message_converter: WecomBotMessageConverter = WecomBotMessageConverter()
-    event_converter: WecomBotEventConverter = WecomBotEventConverter()
+    event_converter: WecomBotEventConverter
     config: dict
     bot_uuid: str = None
+    _ws_mode: bool = False
+    bot_name: str = ''
+    listeners: dict = {}
 
     def __init__(self, config: dict, logger: EventLogger):
-        required_keys = ['Token', 'EncodingAESKey', 'Corpid', 'BotId']
-        missing_keys = [key for key in required_keys if key not in config]
-        if missing_keys:
-            raise Exception(f'WecomBot 缺少配置项: {missing_keys}')
+        enable_webhook = config.get('enable-webhook', False)
+        bot_name = config.get('robot_name', '')
 
-        bot = WecomBotClient(
-            Token=config['Token'],
-            EnCodingAESKey=config['EncodingAESKey'],
-            Corpid=config['Corpid'],
-            logger=logger,
-            unified_mode=True,
-        )
-        bot_account_id = config['BotId']
+        if not enable_webhook:
+            bot = WecomBotWsClient(
+                bot_id=config['BotId'],
+                secret=config['Secret'],
+                logger=logger,
+                encoding_aes_key=config.get('EncodingAESKey', ''),
+            )
+        else:
+            # Webhook callback mode
+            required_keys = ['Token', 'EncodingAESKey', 'Corpid']
+            missing_keys = [key for key in required_keys if key not in config or not config[key]]
+            if missing_keys:
+                raise Exception(f'WecomBot webhook mode missing config: {missing_keys}')
 
+            bot = WecomBotClient(
+                Token=config['Token'],
+                EnCodingAESKey=config['EncodingAESKey'],
+                Corpid=config['Corpid'],
+                logger=logger,
+                unified_mode=True,
+            )
+
+        bot_account_id = config.get('BotId', '')
+        event_converter = WecomBotEventConverter(bot_name=bot_name)
         super().__init__(
             config=config,
             logger=logger,
             bot=bot,
             bot_account_id=bot_account_id,
+            bot_name=bot_name,
+            event_converter=event_converter,
         )
+        self.listeners = {}
 
     async def reply_message(
         self,
@@ -212,7 +238,17 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         quote_origin: bool = False,
     ):
         content = await self.message_converter.yiri2target(message)
-        await self.bot.set_message(message_source.source_platform_object.message_id, content)
+        _ws_mode = not self.config.get('enable-webhook', False)
+
+        if _ws_mode:
+            event = message_source.source_platform_object
+            req_id = event.get('req_id', '')
+            if req_id:
+                await self.bot.reply_text(req_id, content)
+            else:
+                await self.bot.set_message(event.message_id, content)
+        else:
+            await self.bot.set_message(message_source.source_platform_object.message_id, content)
 
     async def reply_message_chunk(
         self,
@@ -222,31 +258,23 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         quote_origin: bool = False,
         is_final: bool = False,
     ):
-        """将流水线增量输出写入企业微信 stream 会话。
-
-        Args:
-            message_source: 流水线提供的原始消息事件。
-            bot_message: 当前片段对应的模型元信息（未使用）。
-            message: 需要回复的消息链。
-            quote_origin: 是否引用原消息（企业微信暂不支持）。
-            is_final: 标记当前片段是否为最终回复。
-
-        Returns:
-            dict: 包含 `stream` 键，标识写入是否成功。
-
-        Example:
-            在流水线 `reply_message_chunk` 调用中自动触发，无需手动调用。
-        """
-        # 转换为纯文本（智能机器人当前协议仅支持文本流）
         content = await self.message_converter.yiri2target(message)
         msg_id = message_source.source_platform_object.message_id
+        _ws_mode = not self.config.get('enable-webhook', False)
 
-        # 将片段推送到 WecomBotClient 中的队列，返回值用于判断是否走降级逻辑
-        success = await self.bot.push_stream_chunk(msg_id, content, is_final=is_final)
-        if not success and is_final:
-            # 未命中流式队列时使用旧有 set_message 兜底
-            await self.bot.set_message(msg_id, content)
-        return {'stream': success}
+        if _ws_mode:
+            success = await self.bot.push_stream_chunk(msg_id, content, is_final=is_final)
+            if not success and is_final:
+                event = message_source.source_platform_object
+                req_id = event.get('req_id', '')
+                if req_id:
+                    await self.bot.reply_text(req_id, content)
+            return {'stream': success}
+        else:
+            success = await self.bot.push_stream_chunk(msg_id, content, is_final=is_final)
+            if not success and is_final:
+                await self.bot.set_message(msg_id, content)
+            return {'stream': success}
 
     async def is_stream_output_supported(self) -> bool:
         """智能机器人侧默认开启流式能力。
@@ -259,7 +287,21 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         return True
 
     async def send_message(self, target_type, target_id, message):
-        pass
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
+            content = await self.message_converter.yiri2target(message)
+            await self.bot.send_message(target_id, content)
+        else:
+            pass
+
+    async def on_message(self, event: WecomBotEvent):
+        try:
+            lb_event = await self.event_converter.target2yiri(event)
+            if lb_event:
+                await self.listeners[type(lb_event)](lb_event, self)
+        except Exception:
+            await self.logger.error(f'Error in wecombot callback: {traceback.format_exc()}')
+            print(traceback.format_exc())
 
     def register_listener(
         self,
@@ -268,18 +310,13 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             [platform_events.Event, abstract_platform_adapter.AbstractMessagePlatformAdapter], None
         ],
     ):
-        async def on_message(event: WecomBotEvent):
-            try:
-                return await callback(await self.event_converter.target2yiri(event), self)
-            except Exception:
-                await self.logger.error(f'Error in wecombot callback: {traceback.format_exc()}')
-                print(traceback.format_exc())
+        self.listeners[event_type] = callback
 
         try:
             if event_type == platform_events.FriendMessage:
-                self.bot.on_message('single')(on_message)
+                self.bot.on_message('single')(self.on_message)
             elif event_type == platform_events.GroupMessage:
-                self.bot.on_message('group')(on_message)
+                self.bot.on_message('group')(self.on_message)
         except Exception:
             print(traceback.format_exc())
 
@@ -288,29 +325,28 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         self.bot_uuid = bot_uuid
 
     async def handle_unified_webhook(self, bot_uuid: str, path: str, request):
-        """处理统一 webhook 请求。
-
-        Args:
-            bot_uuid: Bot 的 UUID
-            path: 子路径（如果有的话）
-            request: Quart Request 对象
-
-        Returns:
-            响应数据
-        """
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
+            return None
         return await self.bot.handle_unified_webhook(request)
 
     async def run_async(self):
-        # 统一 webhook 模式下，不启动独立的 Quart 应用
-        # 保持运行但不启动独立端口
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
+            await self.bot.connect()
+        else:
 
-        async def keep_alive():
-            while True:
-                await asyncio.sleep(1)
+            async def keep_alive():
+                while True:
+                    await asyncio.sleep(1)
 
-        await keep_alive()
+            await keep_alive()
 
     async def kill(self) -> bool:
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
+            await self.bot.disconnect()
+            return True
         return False
 
     async def unregister_listener(

src/langbot/pkg/platform/sources/wecombot.yaml

@@ -11,35 +11,71 @@ metadata:
   icon: wecombot.png
 spec:
   config:
+    - name: BotId
+      label:
+        en_US: BotId
+        zh_Hans: 机器人ID (BotId)
+      type: string
+      required: true
+      default: ""
+    - name: robot_name
+      label:
+        en_US: Robot Name
+        zh_Hans: 机器人名称
+      type: string
+      required: true
+      default: ""
+    - name: enable-webhook
+      label:
+        en_US: Enable Webhook Mode
+        zh_Hans: 启用Webhook模式
+      description:
+        en_US: If enabled, the bot will use webhook mode to receive messages. Otherwise, it will use WS long connection mode
+        zh_Hans: 如果启用，机器人将使用 Webhook 模式接收消息。否则，将使用 WS 长连接模式
+      type: boolean
+      required: true
+      default: false
+    - name: Secret
+      label:
+        en_US: Secret
+        zh_Hans: 机器人密钥 (Secret)
+      description:
+        en_US: Required for WebSocket long connection mode
+        zh_Hans: 使用 WS 长连接模式时必填
+      type: string
+      required: false
+      default: ""
     - name: Corpid
       label:
         en_US: Corpid
         zh_Hans: 企业ID
+      description:
+        en_US: Required for Webhook mode
+        zh_Hans: 使用 Webhook 模式时必填
       type: string
-      required: true
+      required: false
       default: ""
     - name: Token
       label:
         en_US: Token
         zh_Hans: 令牌 (Token)
+      description:
+        en_US: Required for Webhook mode
+        zh_Hans: 使用 Webhook 模式时必填
       type: string
-      required: true
+      required: false
       default: ""
     - name: EncodingAESKey
       label:
         en_US: EncodingAESKey
         zh_Hans: 消息加解密密钥 (EncodingAESKey)
-      type: string
-      required: true
-      default: ""
-    - name: BotId
-      label:
-        en_US: BotId
-        zh_Hans: 机器人ID
+      description:
+        en_US: Required for Webhook mode. Optional for WebSocket mode (used for file decryption)
+        zh_Hans: 使用 Webhook 模式时必填。WebSocket 模式下可选（用于文件解密）
       type: string
       required: false
       default: ""
 execution:
   python:
     path: ./wecombot.py
-    attr: WecomBotAdapter
+    attr: WecomBotAdapter

src/langbot/pkg/plugin/handler.py

@@ -555,6 +555,18 @@ class RuntimeConnectionHandler(handler.Handler):
             except Exception as e:
                 return _make_rag_error_response(e, 'VectorStoreError', collection_id=collection_id)
 
+        @self.action(PluginToRuntimeAction.VECTOR_LIST)
+        async def vector_list(data: dict[str, Any]) -> handler.ActionResponse:
+            collection_id = data['collection_id']
+            filters = data.get('filters')
+            limit = data.get('limit', 20)
+            offset = data.get('offset', 0)
+            try:
+                items, total = await self.ap.rag_runtime_service.vector_list(collection_id, filters, limit, offset)
+                return handler.ActionResponse.success(data={'items': items, 'total': total})
+            except Exception as e:
+                return _make_rag_error_response(e, 'VectorStoreError', collection_id=collection_id)
+
         @self.action(PluginToRuntimeAction.GET_KNOWLEDEGE_FILE_STREAM)
         async def get_knowledge_file_stream(data: dict[str, Any]) -> handler.ActionResponse:
             storage_path = data['storage_path']
@@ -565,6 +577,16 @@ class RuntimeConnectionHandler(handler.Handler):
             except Exception as e:
                 return _make_rag_error_response(e, 'FileServiceError', storage_path=storage_path)
 
+        @self.action(PluginToRuntimeAction.LIST_PARSERS)
+        async def list_parsers(data: dict[str, Any]) -> handler.ActionResponse:
+            """Plugin requests host to list available parser plugins."""
+            mime_type = data.get('mime_type')
+            try:
+                parsers = await self.ap.knowledge_service.list_parsers(mime_type)
+                return handler.ActionResponse.success(data={'parsers': parsers})
+            except Exception as e:
+                return _make_rag_error_response(e, 'ParserDiscoveryError', mime_type=mime_type)
+
         @self.action(PluginToRuntimeAction.INVOKE_PARSER)
         async def invoke_parser(data: dict[str, Any]) -> handler.ActionResponse:
             """Plugin requests host to invoke a parser plugin."""
@@ -589,6 +611,98 @@ class RuntimeConnectionHandler(handler.Handler):
             except Exception as e:
                 return _make_rag_error_response(e, 'ParserError')
 
+        # ================= Knowledge Base Query APIs =================
+
+        @self.action(PluginToRuntimeAction.LIST_PIPELINE_KNOWLEDGE_BASES)
+        async def list_pipeline_knowledge_bases(data: dict[str, Any]) -> handler.ActionResponse:
+            """List knowledge bases configured for the current query's pipeline."""
+            query_id = data['query_id']
+
+            if query_id not in self.ap.query_pool.cached_queries:
+                return handler.ActionResponse.error(
+                    message=f'Query with query_id {query_id} not found',
+                )
+
+            query = self.ap.query_pool.cached_queries[query_id]
+
+            kb_uuids = []
+            if query.pipeline_config:
+                local_agent_config = query.pipeline_config.get('ai', {}).get('local-agent', {})
+                kb_uuids = local_agent_config.get('knowledge-bases', [])
+                # Backward compatibility
+                if not kb_uuids:
+                    old_kb_uuid = local_agent_config.get('knowledge-base', '')
+                    if old_kb_uuid and old_kb_uuid != '__none__':
+                        kb_uuids = [old_kb_uuid]
+
+            knowledge_bases = []
+            for kb_uuid in kb_uuids:
+                kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
+                if kb:
+                    knowledge_bases.append(
+                        {
+                            'uuid': kb.get_uuid(),
+                            'name': kb.get_name(),
+                            'description': kb.knowledge_base_entity.description or '',
+                        }
+                    )
+
+            return handler.ActionResponse.success(data={'knowledge_bases': knowledge_bases})
+
+        @self.action(PluginToRuntimeAction.RETRIEVE_KNOWLEDGE_BASE)
+        async def retrieve_knowledge_base(data: dict[str, Any]) -> handler.ActionResponse:
+            """Retrieve documents from a knowledge base within the pipeline's scope."""
+            query_id = data['query_id']
+            kb_id = data['kb_id']
+            query_text = data['query_text']
+            top_k = data.get('top_k', 5)
+            filters = data.get('filters', {})
+
+            if query_id not in self.ap.query_pool.cached_queries:
+                return handler.ActionResponse.error(
+                    message=f'Query with query_id {query_id} not found',
+                )
+
+            query = self.ap.query_pool.cached_queries[query_id]
+
+            # Validate kb_id is in pipeline's allowed list
+            allowed_kb_uuids = []
+            if query.pipeline_config:
+                local_agent_config = query.pipeline_config.get('ai', {}).get('local-agent', {})
+                allowed_kb_uuids = local_agent_config.get('knowledge-bases', [])
+                if not allowed_kb_uuids:
+                    old_kb_uuid = local_agent_config.get('knowledge-base', '')
+                    if old_kb_uuid and old_kb_uuid != '__none__':
+                        allowed_kb_uuids = [old_kb_uuid]
+
+            if kb_id not in allowed_kb_uuids:
+                return handler.ActionResponse.error(
+                    message=f'Knowledge base {kb_id} is not configured for this pipeline',
+                )
+
+            kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_id)
+            if not kb:
+                return handler.ActionResponse.error(
+                    message=f'Knowledge base {kb_id} not found',
+                )
+
+            try:
+                session_name = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+                entries = await kb.retrieve(
+                    query_text,
+                    settings={
+                        'top_k': top_k,
+                        'filters': filters,
+                        'session_name': session_name,
+                        'bot_uuid': query.bot_uuid or '',
+                        'sender_id': str(query.sender_id),
+                    },
+                )
+                results = [entry.model_dump(mode='json') for entry in entries]
+                return handler.ActionResponse.success(data={'results': results})
+            except Exception as e:
+                return _make_rag_error_response(e, 'RetrievalError', kb_id=kb_id)
+
         @self.action(CommonAction.PING)
         async def ping(data: dict[str, Any]) -> handler.ActionResponse:
             """Ping"""
@@ -895,7 +1009,7 @@ class RuntimeConnectionHandler(handler.Handler):
         result = await self.call_action(
             LangBotToRuntimeAction.RAG_INGEST_DOCUMENT,
             {'plugin_author': plugin_author, 'plugin_name': plugin_name, 'context': context_data},
-            timeout=300,  # Ingestion can be slow
+            timeout=1200,  # Ingestion can be slow for large documents
         )
         return result
 

src/langbot/pkg/provider/modelmgr/requesters/anthropicmsgs.py

@@ -288,10 +288,10 @@ class AnthropicMessages(requester.ProviderAPIRequester):
             think_started = False
             think_ended = False
             finish_reason = False
-            content = ''
             tool_name = ''
             tool_id = ''
             async for chunk in await self.client.messages.create(**args):
+                content = ''
                 tool_call = {'id': None, 'function': {'name': None, 'arguments': None}, 'type': 'function'}
                 if isinstance(
                     chunk, anthropic.types.raw_content_block_start_event.RawContentBlockStartEvent

src/langbot/pkg/provider/runners/localagent.py

@@ -4,6 +4,7 @@ import json
 import copy
 import typing
 from .. import runner
+from ..modelmgr import requester as modelmgr_requester
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 import langbot_plugin.api.entities.builtin.rag.context as rag_context
@@ -26,29 +27,114 @@ Respond in the same language as the user's input.
 
 @runner.runner_class('local-agent')
 class LocalAgentRunner(runner.RequestRunner):
-    """本地Agent请求运行器"""
+    """Local agent request runner"""
 
-    class ToolCallTracker:
-        """工具调用追踪器"""
+    async def _get_model_candidates(
+        self,
+        query: pipeline_query.Query,
+    ) -> list[modelmgr_requester.RuntimeLLMModel]:
+        """Build ordered list of models to try: primary model + fallback models."""
+        candidates = []
 
-        def __init__(self):
-            self.active_calls: dict[str, dict] = {}
-            self.completed_calls: list[provider_message.ToolCall] = []
+        # Primary model
+        if query.use_llm_model_uuid:
+            try:
+                primary = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
+                candidates.append(primary)
+            except ValueError:
+                self.ap.logger.warning(f'Primary model {query.use_llm_model_uuid} not found')
+
+        # Fallback models
+        fallback_uuids = (query.variables or {}).get('_fallback_model_uuids', [])
+        for fb_uuid in fallback_uuids:
+            try:
+                fb_model = await self.ap.model_mgr.get_model_by_uuid(fb_uuid)
+                candidates.append(fb_model)
+            except ValueError:
+                self.ap.logger.warning(f'Fallback model {fb_uuid} not found, skipping')
+
+        return candidates
+
+    async def _invoke_with_fallback(
+        self,
+        query: pipeline_query.Query,
+        candidates: list[modelmgr_requester.RuntimeLLMModel],
+        messages: list,
+        funcs: list,
+        remove_think: bool,
+    ) -> tuple[provider_message.Message, modelmgr_requester.RuntimeLLMModel]:
+        """Try non-streaming invocation with sequential fallback. Returns (message, model_used)."""
+        last_error = None
+        for model in candidates:
+            try:
+                msg = await model.provider.invoke_llm(
+                    query,
+                    model,
+                    messages,
+                    funcs if model.model_entity.abilities.__contains__('func_call') else [],
+                    extra_args=model.model_entity.extra_args,
+                    remove_think=remove_think,
+                )
+                return msg, model
+            except Exception as e:
+                last_error = e
+                self.ap.logger.warning(f'Model {model.model_entity.name} failed: {e}, trying next fallback...')
+        raise last_error or RuntimeError('No model candidates available')
+
+    async def _invoke_stream_with_fallback(
+        self,
+        query: pipeline_query.Query,
+        candidates: list[modelmgr_requester.RuntimeLLMModel],
+        messages: list,
+        funcs: list,
+        remove_think: bool,
+    ) -> tuple[typing.AsyncGenerator, modelmgr_requester.RuntimeLLMModel]:
+        """Try streaming invocation with sequential fallback. Returns (stream_generator, model_used).
+
+        Fallback is only possible before any chunks have been yielded to the client.
+        Once streaming starts, the model is committed.
+        """
+        last_error = None
+        for model in candidates:
+            try:
+                stream = model.provider.invoke_llm_stream(
+                    query,
+                    model,
+                    messages,
+                    funcs if model.model_entity.abilities.__contains__('func_call') else [],
+                    extra_args=model.model_entity.extra_args,
+                    remove_think=remove_think,
+                )
+                # Attempt to get the first chunk to verify the stream works
+                first_chunk = await stream.__anext__()
+
+                async def _chain_stream(first, rest):
+                    yield first
+                    async for chunk in rest:
+                        yield chunk
+
+                return _chain_stream(first_chunk, stream), model
+            except StopAsyncIteration:
+                # Empty stream — treat as success (model returned nothing)
+                async def _empty_stream():
+                    return
+                    yield  # make it a generator
+
+                return _empty_stream(), model
+            except Exception as e:
+                last_error = e
+                self.ap.logger.warning(f'Model {model.model_entity.name} stream failed: {e}, trying next fallback...')
+        raise last_error or RuntimeError('No model candidates available')
 
     async def run(
         self, query: pipeline_query.Query
     ) -> typing.AsyncGenerator[provider_message.Message | provider_message.MessageChunk, None]:
-        """运行请求"""
+        """Run request"""
         pending_tool_calls = []
 
-        # Get knowledge bases list (new field)
-        kb_uuids = query.pipeline_config['ai']['local-agent'].get('knowledge-bases', [])
-
-        # Fallback to old field for backward compatibility
-        if not kb_uuids:
-            old_kb_uuid = query.pipeline_config['ai']['local-agent'].get('knowledge-base', '')
-            if old_kb_uuid and old_kb_uuid != '__none__':
-                kb_uuids = [old_kb_uuid]
+        # Get knowledge bases list from query variables (set by PreProcessor,
+        # may have been modified by plugins during PromptPreProcessing)
+        kb_uuids = query.variables.get('_knowledge_base_uuids', [])
 
         user_message = copy.deepcopy(query.user_message)
 
@@ -77,6 +163,7 @@ class LocalAgentRunner(runner.RequestRunner):
                 result = await kb.retrieve(
                     user_message_text,
                     settings={
+                        'bot_uuid': query.bot_uuid or '',
                         'sender_id': str(query.sender_id),
                         'session_name': f'{query.session.launcher_type.value}_{query.session.launcher_id}',
                     },
@@ -119,51 +206,51 @@ class LocalAgentRunner(runner.RequestRunner):
 
         remove_think = query.pipeline_config['output'].get('misc', '').get('remove-think')
 
-        use_llm_model = await self.ap.model_mgr.get_model_by_uuid(query.use_llm_model_uuid)
+        # Build ordered candidate list (primary + fallbacks)
+        candidates = await self._get_model_candidates(query)
+        if not candidates:
+            raise RuntimeError('No LLM model configured for local-agent runner')
 
         self.ap.logger.debug(
-            f'localagent req: query={query.query_id} req_messages={req_messages} use_llm_model={query.use_llm_model_uuid}'
+            f'localagent req: query={query.query_id} req_messages={req_messages} '
+            f'candidates={[m.model_entity.name for m in candidates]}'
         )
 
         if not is_stream:
-            # 非流式输出，直接请求
-
-            msg = await use_llm_model.provider.invoke_llm(
+            # Non-streaming: invoke with fallback
+            msg, use_llm_model = await self._invoke_with_fallback(
                 query,
-                use_llm_model,
+                candidates,
                 req_messages,
                 query.use_funcs,
-                extra_args=use_llm_model.model_entity.extra_args,
-                remove_think=remove_think,
+                remove_think,
             )
             yield msg
             final_msg = msg
         else:
-            # 流式输出，需要处理工具调用
+            # Streaming: invoke with fallback
             tool_calls_map: dict[str, provider_message.ToolCall] = {}
             msg_idx = 0
-            accumulated_content = ''  # 从开始累积的所有内容
+            accumulated_content = ''
             last_role = 'assistant'
             msg_sequence = 1
-            async for msg in use_llm_model.provider.invoke_llm_stream(
+
+            stream_src, use_llm_model = await self._invoke_stream_with_fallback(
                 query,
-                use_llm_model,
+                candidates,
                 req_messages,
                 query.use_funcs,
-                extra_args=use_llm_model.model_entity.extra_args,
-                remove_think=remove_think,
-            ):
+                remove_think,
+            )
+            async for msg in stream_src:
                 msg_idx = msg_idx + 1
 
-                # 记录角色
                 if msg.role:
                     last_role = msg.role
 
-                # 累积内容
                 if msg.content:
                     accumulated_content += msg.content
 
-                # 处理工具调用
                 if msg.tool_calls:
                     for tool_call in msg.tool_calls:
                         if tool_call.id not in tool_calls_map:
@@ -175,21 +262,18 @@ class LocalAgentRunner(runner.RequestRunner):
                                 ),
                             )
                         if tool_call.function and tool_call.function.arguments:
-                            # 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
                             tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
-                # continue
-                # 每8个chunk或最后一个chunk时，输出所有累积的内容
+
                 if msg_idx % 8 == 0 or msg.is_final:
                     msg_sequence += 1
                     yield provider_message.MessageChunk(
                         role=last_role,
-                        content=accumulated_content,  # 输出所有累积内容
+                        content=accumulated_content,
                         tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
                         is_final=msg.is_final,
                         msg_sequence=msg_sequence,
                     )
 
-            # 创建最终消息用于后续处理
             final_msg = provider_message.MessageChunk(
                 role=last_role,
                 content=accumulated_content,
@@ -204,7 +288,8 @@ class LocalAgentRunner(runner.RequestRunner):
 
         req_messages.append(final_msg)
 
-        # 持续请求，只要还有待处理的工具调用就继续处理调用
+        # Once a model succeeds, commit to it for the tool call loop
+        # (no fallback mid-conversation — different models may interpret tool results differently)
         while pending_tool_calls:
             for tool_call in pending_tool_calls:
                 try:
@@ -245,7 +330,6 @@ class LocalAgentRunner(runner.RequestRunner):
 
                     req_messages.append(msg)
                 except Exception as e:
-                    # 工具调用出错，添加一个报错信息到 req_messages
                     err_msg = provider_message.Message(role='tool', content=f'err: {e}', tool_call_id=tool_call.id)
 
                     yield err_msg
@@ -253,39 +337,38 @@ class LocalAgentRunner(runner.RequestRunner):
                     req_messages.append(err_msg)
 
             self.ap.logger.debug(
-                f'localagent req: query={query.query_id} req_messages={req_messages} use_llm_model={query.use_llm_model_uuid}'
+                f'localagent req: query={query.query_id} req_messages={req_messages} '
+                f'use_llm_model={use_llm_model.model_entity.name}'
             )
 
             if is_stream:
                 tool_calls_map = {}
                 msg_idx = 0
-                accumulated_content = ''  # 从开始累积的所有内容
+                accumulated_content = ''
                 last_role = 'assistant'
                 msg_sequence = first_end_sequence
 
-                async for msg in use_llm_model.provider.invoke_llm_stream(
+                tool_stream_src = use_llm_model.provider.invoke_llm_stream(
                     query,
                     use_llm_model,
                     req_messages,
-                    query.use_funcs,
+                    query.use_funcs if use_llm_model.model_entity.abilities.__contains__('func_call') else [],
                     extra_args=use_llm_model.model_entity.extra_args,
                     remove_think=remove_think,
-                ):
+                )
+                async for msg in tool_stream_src:
                     msg_idx += 1
 
-                    # 记录角色
                     if msg.role:
                         last_role = msg.role
 
-                    # 第一次请求工具调用时的内容
+                    # Prepend first-round content on first chunk of tool-call round
                     if msg_idx == 1:
                         accumulated_content = first_content if first_content is not None else accumulated_content
 
-                    # 累积内容
                     if msg.content:
                         accumulated_content += msg.content
 
-                    # 处理工具调用
                     if msg.tool_calls:
                         for tool_call in msg.tool_calls:
                             if tool_call.id not in tool_calls_map:
@@ -297,15 +380,13 @@ class LocalAgentRunner(runner.RequestRunner):
                                     ),
                                 )
                             if tool_call.function and tool_call.function.arguments:
-                                # 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
                                 tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
 
-                    # 每8个chunk或最后一个chunk时，输出所有累积的内容
                     if msg_idx % 8 == 0 or msg.is_final:
                         msg_sequence += 1
                         yield provider_message.MessageChunk(
                             role=last_role,
-                            content=accumulated_content,  # 输出所有累积内容
+                            content=accumulated_content,
                             tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
                             is_final=msg.is_final,
                             msg_sequence=msg_sequence,
@@ -318,12 +399,12 @@ class LocalAgentRunner(runner.RequestRunner):
                     msg_sequence=msg_sequence,
                 )
             else:
-                # 处理完所有调用，再次请求
+                # Non-streaming: use committed model directly (no fallback in tool loop)
                 msg = await use_llm_model.provider.invoke_llm(
                     query,
                     use_llm_model,
                     req_messages,
-                    query.use_funcs,
+                    query.use_funcs if use_llm_model.model_entity.abilities.__contains__('func_call') else [],
                     extra_args=use_llm_model.model_entity.extra_args,
                     remove_think=remove_think,
                 )

src/langbot/pkg/rag/service/runtime.py

@@ -75,6 +75,31 @@ class RAGRuntimeService:
             count = await self.ap.vector_db_mgr.delete_by_filter(collection_name=collection_id, filter=filters)
         return count
 
+    async def vector_list(
+        self,
+        collection_id: str,
+        filters: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        """Handle VECTOR_LIST action.
+
+        Args:
+            collection_id: The collection to list from.
+            filters: Optional metadata filters.
+            limit: Maximum number of items to return.
+            offset: Number of items to skip.
+
+        Returns:
+            Tuple of (items, total).
+        """
+        return await self.ap.vector_db_mgr.list_by_filter(
+            collection_name=collection_id,
+            filter=filters,
+            limit=limit,
+            offset=offset,
+        )
+
     async def get_file_stream(self, storage_path: str) -> bytes:
         """Handle GET_KNOWLEDEGE_FILE_STREAM action.
 

src/langbot/pkg/utils/constants.py

@@ -2,7 +2,7 @@ import langbot
 
 semantic_version = f'v{langbot.__version__}'
 
-required_database_version = 22
+required_database_version = 24
 """Tag the version of the database schema, used to check if the database needs to be migrated"""
 
 debug_mode = False

src/langbot/pkg/vector/filter_utils.py

@@ -49,17 +49,25 @@ def normalize_filter(
 def strip_unsupported_fields(
     triples: list[tuple[str, str, Any]],
     supported_fields: set[str],
+    field_aliases: dict[str, str] | None = None,
 ) -> list[tuple[str, str, Any]]:
     """Return only triples whose field is in *supported_fields*.
 
+    If *field_aliases* is provided, aliased field names are mapped to the
+    canonical backend name before the support check.  For example,
+    ``{'uuid': 'chunk_uuid'}`` allows callers to use ``uuid`` which is
+    transparently rewritten to ``chunk_uuid``.
+
     Dropped fields are logged at WARNING level so the caller knows they were
     silently ignored (useful for Milvus / pgvector which only store a fixed
     schema).
     """
+    aliases = field_aliases or {}
     kept: list[tuple[str, str, Any]] = []
     for field, op, value in triples:
-        if field in supported_fields:
-            kept.append((field, op, value))
+        resolved = aliases.get(field, field)
+        if resolved in supported_fields:
+            kept.append((resolved, op, value))
         else:
             logger.warning(
                 'Filter field %r is not supported by this backend and will be ignored (supported: %s)',

src/langbot/pkg/vector/mgr.py

@@ -100,7 +100,7 @@ class VectorDBManager:
     ) -> list[dict]:
         """Proxy: Search vectors.
 
-        Returns a list of dicts with keys: 'id', 'score', 'metadata'.
+        Returns a list of dicts with keys: 'id', 'distance', 'metadata'.
         The underlying VectorDatabase.search returns Chroma-style format:
         { 'ids': [['id1']], 'distances': [[0.1]], 'metadatas': [[{}]] }
         """
@@ -130,7 +130,7 @@ class VectorDBManager:
             parsed_results.append(
                 {
                     'id': id_val,
-                    'score': r_dists[i] if r_dists and i < len(r_dists) else 0.0,
+                    'distance': r_dists[i] if r_dists and i < len(r_dists) else 0.0,
                     'metadata': r_metas[i] if r_metas and i < len(r_metas) else {},
                 }
             )
@@ -157,3 +157,17 @@ class VectorDBManager:
             Number of deleted vectors (best-effort; some backends return 0).
         """
         return await self.vector_db.delete_by_filter(collection_name, filter)
+
+    async def list_by_filter(
+        self,
+        collection_name: str,
+        filter: dict | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict], int]:
+        """Proxy: List vectors by metadata filter with pagination.
+
+        Returns:
+            Tuple of (items, total).
+        """
+        return await self.vector_db.list_by_filter(collection_name, filter, limit, offset)

src/langbot/pkg/vector/vdb.py

@@ -92,6 +92,28 @@ class VectorDatabase(abc.ABC):
         """
         pass
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        """List vectors matching the given metadata filter with pagination.
+
+        Args:
+            collection: Collection name.
+            filter: Optional metadata filter dict in canonical format.
+            limit: Maximum number of items to return.
+            offset: Number of items to skip.
+
+        Returns:
+            Tuple of (items, total) where items is a list of dicts with
+            keys 'id', 'document', 'metadata', and total is the best-effort
+            count of all matching vectors (-1 if unknown).
+        """
+        return [], -1
+
     @abc.abstractmethod
     async def get_or_create_collection(self, collection: str):
         """Get or create collection."""

src/langbot/pkg/vector/vdbs/chroma.py

@@ -221,6 +221,41 @@ class ChromaVectorDatabase(VectorDatabase):
         self.ap.logger.info(f"Deleted embeddings from Chroma collection '{collection}' by filter")
         return 0  # Chroma delete does not return a count
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        col = await self.get_or_create_collection(collection)
+        get_kwargs: dict[str, Any] = dict(
+            include=['metadatas', 'documents'],
+            limit=limit,
+            offset=offset,
+        )
+        if filter:
+            get_kwargs['where'] = filter
+        results = await asyncio.to_thread(col.get, **get_kwargs)
+
+        ids = results.get('ids', [])
+        metadatas = results.get('metadatas', []) or [None] * len(ids)
+        documents = results.get('documents', []) or [None] * len(ids)
+
+        items = []
+        for i, vid in enumerate(ids):
+            items.append(
+                {
+                    'id': vid,
+                    'document': documents[i] if i < len(documents) else None,
+                    'metadata': metadatas[i] if i < len(metadatas) else {},
+                }
+            )
+
+        # Chroma col.count() gives total in collection; filtered count not available
+        total = await asyncio.to_thread(col.count) if not filter else -1
+        return items, total
+
     async def delete_collection(self, collection: str):
         if collection in self._collections:
             del self._collections[collection]

src/langbot/pkg/vector/vdbs/milvus.py

@@ -11,11 +11,14 @@ from langbot.pkg.core import app
 # silently dropped with a warning.
 _MILVUS_SUPPORTED_FIELDS = {'text', 'file_id', 'chunk_uuid'}
 
+# Callers use canonical metadata key 'uuid' but Milvus stores it as 'chunk_uuid'.
+_MILVUS_FIELD_ALIASES = {'uuid': 'chunk_uuid'}
+
 
 def _build_milvus_expr(filter_dict: dict[str, Any]) -> str:
     """Translate canonical filter dict into a Milvus boolean expression string."""
     triples = normalize_filter(filter_dict)
-    triples = strip_unsupported_fields(triples, _MILVUS_SUPPORTED_FIELDS)
+    triples = strip_unsupported_fields(triples, _MILVUS_SUPPORTED_FIELDS, _MILVUS_FIELD_ALIASES)
     if not triples:
         return ''
 
@@ -340,6 +343,62 @@ class MilvusVectorDatabase(VectorDatabase):
         self.ap.logger.info(f"Deleted embeddings from Milvus collection '{collection}' by filter")
         return 0  # Milvus delete does not return a count
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        collection = self._normalize_collection_name(collection)
+        await self.get_or_create_collection(collection)
+
+        query_kwargs: dict[str, Any] = dict(
+            collection_name=collection,
+            output_fields=['text', 'file_id', 'chunk_uuid'],
+            limit=limit,
+            offset=offset,
+        )
+        if filter:
+            expr = _build_milvus_expr(filter)
+            if expr:
+                query_kwargs['filter'] = expr
+
+        results = await asyncio.to_thread(self.client.query, **query_kwargs)
+
+        items = []
+        for row in results:
+            items.append(
+                {
+                    'id': row.get('id', ''),
+                    'document': row.get('text'),
+                    'metadata': {
+                        'text': row.get('text', ''),
+                        'file_id': row.get('file_id', ''),
+                        'uuid': row.get('chunk_uuid', ''),
+                    },
+                }
+            )
+
+        # Milvus query with count(*)
+        total = -1
+        try:
+            count_kwargs: dict[str, Any] = dict(
+                collection_name=collection,
+                output_fields=['count(*)'],
+            )
+            if filter:
+                expr = _build_milvus_expr(filter)
+                if expr:
+                    count_kwargs['filter'] = expr
+            count_result = await asyncio.to_thread(self.client.query, **count_kwargs)
+            if count_result:
+                total = count_result[0].get('count(*)', -1)
+        except Exception:
+            pass
+
+        return items, total
+
     async def delete_collection(self, collection: str):
         """Delete a Milvus collection
 

src/langbot/pkg/vector/vdbs/pgvector_db.py

@@ -13,6 +13,9 @@ Base = declarative_base()
 # pgvector schema only stores these metadata fields.
 _PG_SUPPORTED_FIELDS = {'text', 'file_id', 'chunk_uuid'}
 
+# Callers use canonical metadata key 'uuid' but pgvector stores it as 'chunk_uuid'.
+_PG_FIELD_ALIASES = {'uuid': 'chunk_uuid'}
+
 # Map schema field names to SQLAlchemy columns (resolved lazily from PgVectorEntry).
 _PG_COLUMN_MAP = {
     'text': 'text',
@@ -37,7 +40,7 @@ class PgVectorEntry(Base):
 def _build_pg_conditions(filter_dict: dict[str, Any]) -> list:
     """Translate canonical filter dict into a list of SQLAlchemy conditions."""
     triples = normalize_filter(filter_dict)
-    triples = strip_unsupported_fields(triples, _PG_SUPPORTED_FIELDS)
+    triples = strip_unsupported_fields(triples, _PG_SUPPORTED_FIELDS, _PG_FIELD_ALIASES)
 
     conditions = []
     for field, op, value in triples:
@@ -309,6 +312,65 @@ class PgVectorDatabase(VectorDatabase):
                 self.ap.logger.error(f'Error deleting from pgvector by filter: {e}')
                 raise
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        await self.get_or_create_collection(collection)
+
+        async with self.AsyncSessionLocal() as session:
+            try:
+                from sqlalchemy import select, func
+
+                stmt = (
+                    select(
+                        PgVectorEntry.id,
+                        PgVectorEntry.text,
+                        PgVectorEntry.file_id,
+                        PgVectorEntry.chunk_uuid,
+                    )
+                    .filter(PgVectorEntry.collection == collection)
+                    .offset(offset)
+                    .limit(limit)
+                )
+
+                count_stmt = (
+                    select(func.count()).select_from(PgVectorEntry).filter(PgVectorEntry.collection == collection)
+                )
+
+                if filter:
+                    for cond in _build_pg_conditions(filter):
+                        stmt = stmt.filter(cond)
+                        count_stmt = count_stmt.filter(cond)
+
+                result = await session.execute(stmt)
+                rows = result.fetchall()
+
+                count_result = await session.execute(count_stmt)
+                total = count_result.scalar() or 0
+
+                items = []
+                for row in rows:
+                    items.append(
+                        {
+                            'id': row.id,
+                            'document': row.text or '',
+                            'metadata': {
+                                'text': row.text or '',
+                                'file_id': row.file_id or '',
+                                'uuid': row.chunk_uuid or '',
+                            },
+                        }
+                    )
+
+                return items, total
+            except Exception as e:
+                self.ap.logger.error(f'Error listing from pgvector: {e}')
+                raise
+
     async def delete_collection(self, collection: str):
         """Delete all vectors in a collection
 

src/langbot/pkg/vector/vdbs/qdrant.py

@@ -150,6 +150,97 @@ class QdrantVectorDatabase(VectorDatabase):
         self.ap.logger.info(f"Deleted embeddings from Qdrant collection '{collection}' by filter")
         return 0  # Qdrant delete does not return a count
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[dict[str, Any]], int]:
+        exists = await self.client.collection_exists(collection)
+        if not exists:
+            return [], 0
+
+        qdrant_filter = _build_qdrant_filter(filter) if filter else None
+
+        # Qdrant scroll uses cursor-based pagination (offset = point ID),
+        # not numeric skip.  To support numeric offset we scroll through
+        # `offset + limit` items and discard the first `offset`.
+        remaining_to_skip = offset
+        remaining_to_collect = limit
+        cursor: int | str | None = None
+        collected: list[dict[str, Any]] = []
+
+        while remaining_to_skip > 0 or remaining_to_collect > 0:
+            batch_size = remaining_to_skip + remaining_to_collect if remaining_to_skip > 0 else remaining_to_collect
+            scroll_kwargs: dict[str, Any] = dict(
+                collection_name=collection,
+                limit=min(batch_size, 256),
+                with_payload=True if remaining_to_skip == 0 else False,
+                with_vectors=False,
+            )
+            if qdrant_filter:
+                scroll_kwargs['scroll_filter'] = qdrant_filter
+            if cursor is not None:
+                scroll_kwargs['offset'] = cursor
+
+            points, next_cursor = await self.client.scroll(**scroll_kwargs)
+            if not points:
+                break
+
+            for point in points:
+                if remaining_to_skip > 0:
+                    remaining_to_skip -= 1
+                    continue
+                if remaining_to_collect <= 0:
+                    break
+                # Re-fetch payload if we skipped it during the skip phase
+                payload = point.payload or {}
+                collected.append(
+                    {
+                        'id': str(point.id),
+                        'document': payload.get('text') or payload.get('document'),
+                        'metadata': payload,
+                    }
+                )
+                remaining_to_collect -= 1
+
+            if next_cursor is None:
+                break
+            cursor = next_cursor
+
+        # If we skipped without payload, re-fetch the collected items' payloads
+        # (only needed when offset > 0 and items were collected in a skip batch)
+        if offset > 0 and collected:
+            refetch_ids = [item['id'] for item in collected if not item.get('metadata')]
+            if refetch_ids:
+                fetched_points = await self.client.retrieve(
+                    collection_name=collection,
+                    ids=refetch_ids,
+                    with_payload=True,
+                    with_vectors=False,
+                )
+                payload_map = {str(p.id): p.payload or {} for p in fetched_points}
+                for item in collected:
+                    if item['id'] in payload_map:
+                        payload = payload_map[item['id']]
+                        item['metadata'] = payload
+                        item['document'] = payload.get('text') or payload.get('document')
+
+        # Use count() for accurate total (supports filter)
+        total = -1
+        try:
+            count_result = await self.client.count(
+                collection_name=collection,
+                count_filter=qdrant_filter,
+                exact=True,
+            )
+            total = count_result.count
+        except Exception:
+            pass
+
+        return collected, total
+
     async def delete_collection(self, collection: str):
         try:
             await self.client.delete_collection(collection)

src/langbot/pkg/vector/vdbs/seekdb.py

@@ -340,6 +340,50 @@ class SeekDBVectorDatabase(VectorDatabase):
         self.ap.logger.info(f"Deleted embeddings from SeekDB collection '{collection}' by filter")
         return 0  # SeekDB delete does not return a count
 
+    async def list_by_filter(
+        self,
+        collection: str,
+        filter: Dict[str, Any] | None = None,
+        limit: int = 20,
+        offset: int = 0,
+    ) -> tuple[list[Dict[str, Any]], int]:
+        exists = await asyncio.to_thread(self.client.has_collection, collection)
+        if not exists:
+            return [], 0
+
+        if collection not in self._collections:
+            coll = await asyncio.to_thread(self.client.get_collection, collection, embedding_function=None)
+            self._collections[collection] = coll
+        else:
+            coll = self._collections[collection]
+
+        get_kwargs: Dict[str, Any] = dict(
+            include=['metadatas', 'documents'],
+            limit=limit,
+            offset=offset,
+        )
+        if filter:
+            get_kwargs['where'] = filter
+
+        results = await asyncio.to_thread(coll.get, **get_kwargs)
+
+        ids = results.get('ids', [])
+        metadatas = results.get('metadatas', []) or [None] * len(ids)
+        documents = results.get('documents', []) or [None] * len(ids)
+
+        items = []
+        for i, vid in enumerate(ids):
+            items.append(
+                {
+                    'id': vid,
+                    'document': documents[i] if i < len(documents) else None,
+                    'metadata': metadatas[i] if i < len(metadatas) else {},
+                }
+            )
+
+        total = await asyncio.to_thread(coll.count) if not filter else -1
+        return items, total
+
     async def delete_collection(self, collection: str):
         """Delete the entire collection.
 

src/langbot/templates/config.yaml

@@ -2,6 +2,7 @@ admins: []
 api:
     port: 5300
     webhook_prefix: 'http://127.0.0.1:5300'
+    extra_webhook_prefix: ''
 command:
     enable: true
     prefix:
@@ -15,6 +16,7 @@ proxy:
     http: ''
     https: ''
 system:
+    instance_id: ''
     edition: community
     recovery_key: ''
     allow_modify_login_info: true

src/langbot/templates/default-pipeline-config.json

@@ -41,7 +41,10 @@
             "runner": "local-agent"
         },
         "local-agent": {
-            "model": "",
+            "model": {
+                "primary": "",
+                "fallbacks": []
+            },
             "max-round": 10,
             "prompt": [
                 {

src/langbot/templates/metadata/pipeline/ai.yaml

@@ -59,8 +59,11 @@ stages:
         label:
           en_US: Model
           zh_Hans: 模型
-        type: llm-model-selector
+        type: model-fallback-selector
         required: true
+        default:
+          primary: ''
+          fallbacks: []
       - name: max-round
         label:
           en_US: Max Round

src/langbot/templates/metadata/sensitive-words.json

@@ -2,77 +2,5 @@
     "说明": "mask将替换敏感词中的每一个字，若mask_word值不为空，则将敏感词整个替换为mask_word的值",
     "mask": "*",
     "mask_word": "",
-    "words": [
-        "习近平",
-        "胡锦涛",
-        "江泽民",
-        "温家宝",
-        "李克强",
-        "李长春",
-        "毛泽东",
-        "邓小平",
-        "周恩来",
-        "马克思",
-        "社会主义",
-        "共产党",
-        "共产主义",
-        "大陆官方",
-        "北京政权",
-        "中华帝国",
-        "中国政府",
-        "共狗",
-        "六四事件",
-        "天安门",
-        "六四",
-        "政治局常委",
-        "两会",
-        "共青团",
-        "学潮",
-        "八九",
-        "二十大",
-        "民进党",
-        "台独",
-        "台湾独立",
-        "台湾国",
-        "国民党",
-        "台湾民国",
-        "中华民国",
-        "pornhub",
-        "Pornhub",
-        "[Yy]ou[Pp]orn",
-        "porn",
-        "Porn",
-        "[Xx][Vv]ideos",
-        "[Rr]ed[Tt]ube",
-        "[Xx][Hh]amster",
-        "[Ss]pank[Ww]ire",
-        "[Ss]pank[Bb]ang",
-        "[Tt]ube8",
-        "[Yy]ou[Jj]izz",
-        "[Bb]razzers",
-        "[Nn]aughty[ ]?[Aa]merica",
-        "作爱",
-        "做爱",
-        "性交",
-        "性爱",
-        "自慰",
-        "阴茎",
-        "淫妇",
-        "肛交",
-        "交配",
-        "性关系",
-        "性活动",
-        "色情",
-        "色图",
-        "涩图",
-        "裸体",
-        "小穴",
-        "淫荡",
-        "性爱",
-        "翻墙",
-        "VPN",
-        "科学上网",
-        "挂梯子",
-        "GFW"
-    ]
+    "words": []
 }

tests/unit_tests/config/test_webhook_display_prefix.py

@@ -91,14 +91,15 @@ class TestWebhookDisplayPrefix:
 
     def test_default_webhook_prefix(self):
         """Test that the default webhook display prefix is correctly set"""
-        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300'}}
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
 
         # Should have the default value
         assert cfg['api']['webhook_prefix'] == 'http://127.0.0.1:5300'
+        assert cfg['api']['extra_webhook_prefix'] == ''
 
     def test_webhook_prefix_env_override(self):
         """Test overriding webhook_prefix via environment variable"""
-        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300'}}
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
 
         # Set environment variable
         os.environ['API__WEBHOOK_PREFIX'] = 'https://example.com:8080'
@@ -112,7 +113,7 @@ class TestWebhookDisplayPrefix:
 
     def test_webhook_prefix_with_custom_domain(self):
         """Test webhook_prefix with custom domain"""
-        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300'}}
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
 
         # Set to a custom domain
         os.environ['API__WEBHOOK_PREFIX'] = 'https://bot.mycompany.com'
@@ -126,7 +127,7 @@ class TestWebhookDisplayPrefix:
 
     def test_webhook_prefix_with_subdirectory(self):
         """Test webhook_prefix with subdirectory path"""
-        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300'}}
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
 
         # Set to a URL with subdirectory
         os.environ['API__WEBHOOK_PREFIX'] = 'https://example.com/langbot'
@@ -138,6 +139,37 @@ class TestWebhookDisplayPrefix:
         # Cleanup
         del os.environ['API__WEBHOOK_PREFIX']
 
+    def test_extra_webhook_prefix_default_empty(self):
+        """Test that extra_webhook_prefix defaults to empty string"""
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
+
+        bot_uuid = 'test-bot-uuid'
+        webhook_prefix = cfg['api'].get('webhook_prefix', 'http://127.0.0.1:5300')
+        extra_webhook_prefix = cfg['api'].get('extra_webhook_prefix', '')
+        webhook_url = f'/bots/{bot_uuid}'
+
+        assert f'{webhook_prefix}{webhook_url}' == 'http://127.0.0.1:5300/bots/test-bot-uuid'
+        # extra should be empty when not configured
+        assert extra_webhook_prefix == ''
+
+    def test_extra_webhook_prefix_env_override(self):
+        """Test overriding extra_webhook_prefix via environment variable"""
+        cfg = {'api': {'port': 5300, 'webhook_prefix': 'http://127.0.0.1:5300', 'extra_webhook_prefix': ''}}
+
+        os.environ['API__EXTRA_WEBHOOK_PREFIX'] = 'https://extra.example.com'
+
+        result = _apply_env_overrides_to_config(cfg)
+
+        assert result['api']['extra_webhook_prefix'] == 'https://extra.example.com'
+
+        bot_uuid = 'test-bot-uuid'
+        extra_prefix = result['api']['extra_webhook_prefix']
+        webhook_url = f'/bots/{bot_uuid}'
+        assert f'{extra_prefix}{webhook_url}' == 'https://extra.example.com/bots/test-bot-uuid'
+
+        # Cleanup
+        del os.environ['API__EXTRA_WEBHOOK_PREFIX']
+
 
 if __name__ == '__main__':
     pytest.main([__file__, '-v'])

tests/unit_tests/pipeline/conftest.py

@@ -194,7 +194,7 @@ def sample_query(sample_message_chain, sample_message_event, mock_adapter):
         pipeline_config={
             'ai': {
                 'runner': {'runner': 'local-agent'},
-                'local-agent': {'model': 'test-model-uuid', 'prompt': 'test-prompt'},
+                'local-agent': {'model': {'primary': 'test-model-uuid', 'fallbacks': []}, 'prompt': 'test-prompt'},
             },
             'output': {'misc': {'at-sender': False, 'quote-origin': False}},
             'trigger': {'misc': {'combine-quote-message': False}},
@@ -219,7 +219,7 @@ def sample_pipeline_config():
     return {
         'ai': {
             'runner': {'runner': 'local-agent'},
-            'local-agent': {'model': 'test-model-uuid', 'prompt': 'test-prompt'},
+            'local-agent': {'model': {'primary': 'test-model-uuid', 'fallbacks': []}, 'prompt': 'test-prompt'},
         },
         'output': {'misc': {'at-sender': False, 'quote-origin': False}},
         'trigger': {'misc': {'combine-quote-message': False}},

web/package.json

@@ -102,5 +102,10 @@
     "typescript": "^5.8.3",
     "typescript-eslint": "^8.31.1"
   },
-  "packageManager": "pnpm@8.9.2+sha512.b9d35fe91b2a5854dadc43034a3e7b2e675fa4b56e20e8e09ef078fa553c18f8aed44051e7b36e8b8dd435f97eb0c44c4ff3b44fc7c6fa7d21e1fac17bbe661e"
-}
+  "packageManager": "pnpm@8.9.2+sha512.b9d35fe91b2a5854dadc43034a3e7b2e675fa4b56e20e8e09ef078fa553c18f8aed44051e7b36e8b8dd435f97eb0c44c4ff3b44fc7c6fa7d21e1fac17bbe661e",
+  "pnpm": {
+    "overrides": {
+      "minimatch": "3.1.3"
+    }
+  }
+}

web/pnpm-lock.yaml

@@ -4,6 +4,9 @@ settings:
   autoInstallPeers: true
   excludeLinksFromLockfile: false
 
+overrides:
+  minimatch: 3.1.3
+
 dependencies:
   '@dnd-kit/core':
     specifier: ^6.3.1
@@ -345,7 +348,7 @@ packages:
     dependencies:
       '@eslint/object-schema': 2.1.7
       debug: 4.4.3
-      minimatch: 3.1.2
+      minimatch: 3.1.3
     transitivePeerDependencies:
       - supports-color
     dev: true
@@ -375,7 +378,7 @@ packages:
       ignore: 5.3.2
       import-fresh: 3.3.1
       js-yaml: 4.1.1
-      minimatch: 3.1.2
+      minimatch: 3.1.3
       strip-json-comments: 3.1.1
     transitivePeerDependencies:
       - supports-color
@@ -2260,7 +2263,7 @@ packages:
       '@typescript-eslint/types': 8.54.0
       '@typescript-eslint/visitor-keys': 8.54.0
       debug: 4.4.3
-      minimatch: 9.0.5
+      minimatch: 3.1.3
       semver: 7.7.3
       tinyglobby: 0.2.15
       ts-api-utils: 2.4.0(typescript@5.9.3)
@@ -2678,12 +2681,6 @@ packages:
       concat-map: 0.0.1
     dev: true
 
-  /brace-expansion@2.0.2:
-    resolution: {integrity: sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==}
-    dependencies:
-      balanced-match: 1.0.2
-    dev: true
-
   /braces@3.0.3:
     resolution: {integrity: sha512-yQbXgO/OSZVD2IsiLlro+7Hf6Q18EJrKSEsdoMzKePKXct3gvD8oLcOQdIzGupr5Fj+EDe8gO/lxc1BzfMpxvA==}
     engines: {node: '>=8'}
@@ -3345,7 +3342,7 @@ packages:
       hasown: 2.0.2
       is-core-module: 2.16.1
       is-glob: 4.0.3
-      minimatch: 3.1.2
+      minimatch: 3.1.3
       object.fromentries: 2.0.8
       object.groupby: 1.0.3
       object.values: 1.2.1
@@ -3376,7 +3373,7 @@ packages:
       hasown: 2.0.2
       jsx-ast-utils: 3.3.5
       language-tags: 1.0.9
-      minimatch: 3.1.2
+      minimatch: 3.1.3
       object.fromentries: 2.0.8
       safe-regex-test: 1.1.0
       string.prototype.includes: 2.0.1
@@ -3428,7 +3425,7 @@ packages:
       estraverse: 5.3.0
       hasown: 2.0.2
       jsx-ast-utils: 3.3.5
-      minimatch: 3.1.2
+      minimatch: 3.1.3
       object.entries: 1.1.9
       object.fromentries: 2.0.8
       object.values: 1.2.1
@@ -3498,7 +3495,7 @@ packages:
       is-glob: 4.0.3
       json-stable-stringify-without-jsonify: 1.0.1
       lodash.merge: 4.6.2
-      minimatch: 3.1.2
+      minimatch: 3.1.3
       natural-compare: 1.4.0
       optionator: 0.9.4
     transitivePeerDependencies:
@@ -5113,19 +5110,12 @@ packages:
     engines: {node: '>=18'}
     dev: true
 
-  /minimatch@3.1.2:
-    resolution: {integrity: sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==}
+  /minimatch@3.1.3:
+    resolution: {integrity: sha512-M2GCs7Vk83NxkUyQV1bkABc4yxgz9kILhHImZiBPAZ9ybuvCb0/H7lEl5XvIg3g+9d4eNotkZA5IWwYl0tibaA==}
     dependencies:
       brace-expansion: 1.1.12
     dev: true
 
-  /minimatch@9.0.5:
-    resolution: {integrity: sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==}
-    engines: {node: '>=16 || 14 >=14.17'}
-    dependencies:
-      brace-expansion: 2.0.2
-    dev: true
-
   /minimist@1.2.8:
     resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==}
     dev: true

web/src/app/home/bots/components/bot-form/BotForm.tsx

@@ -1,4 +1,4 @@
-import React, { useEffect, useState } from 'react';
+import React, { useEffect, useMemo, useState } from 'react';
 import {
   IChooseAdapterEntity,
   IPipelineEntity,
@@ -113,115 +113,73 @@ export default function BotForm({
   const [dynamicFormConfigList, setDynamicFormConfigList] = useState<
     IDynamicFormItemSchema[]
   >([]);
-  const [filteredDynamicFormConfigList, setFilteredDynamicFormConfigList] =
-    useState<IDynamicFormItemSchema[]>([]);
   const [, setIsLoading] = useState<boolean>(false);
   const [webhookUrl, setWebhookUrl] = useState<string>('');
-  const webhookInputRef = React.useRef<HTMLInputElement>(null);
+  const [extraWebhookUrl, setExtraWebhookUrl] = useState<string>('');
   const [copied, setCopied] = useState<boolean>(false);
+  const [extraCopied, setExtraCopied] = useState<boolean>(false);
 
   // Watch adapter and adapter_config for filtering
   const currentAdapter = form.watch('adapter');
   const currentAdapterConfig = form.watch('adapter_config');
 
-  // Serialize adapter_config to a stable string so it can be used as a
-  // useEffect dependency without triggering on every render.  form.watch()
-  // returns a new object reference each time, which would otherwise cause
-  // the filtering effect below to loop indefinitely.
-  const adapterConfigJson = JSON.stringify(currentAdapterConfig);
+  // Derive the filtered config list via useMemo instead of useEffect+setState
+  // to avoid creating new array references that would cause DynamicFormComponent
+  // to re-subscribe its form.watch, re-emit values, and trigger an infinite loop.
+  // Only depend on the specific field we care about (enable-webhook) rather than
+  // the entire currentAdapterConfig object, which changes on every emission.
+  const enableWebhook = currentAdapterConfig?.['enable-webhook'];
+  const filteredDynamicFormConfigList = useMemo(() => {
+    if (currentAdapter === 'lark' && enableWebhook === false) {
+      // Hide encrypt-key field when webhook is disabled
+      return dynamicFormConfigList.filter(
+        (config) => config.name !== 'encrypt-key',
+      );
+    }
+    // For non-Lark adapters or when webhook is enabled/undefined, show all fields
+    return dynamicFormConfigList;
+  }, [currentAdapter, enableWebhook, dynamicFormConfigList]);
 
   useEffect(() => {
     setBotFormValues();
   }, []);
 
-  // Filter dynamic form config list based on enable-webhook status for Lark adapter
-  useEffect(() => {
-    if (currentAdapter === 'lark') {
-      const enableWebhook = currentAdapterConfig?.['enable-webhook'];
-      if (enableWebhook === false) {
-        // Hide encrypt-key field when webhook is disabled
-        setFilteredDynamicFormConfigList(
-          dynamicFormConfigList.filter(
-            (config) => config.name !== 'encrypt-key',
-          ),
-        );
-      } else {
-        // Show all fields when webhook is enabled or undefined
-        setFilteredDynamicFormConfigList(dynamicFormConfigList);
-      }
+  // 复制到剪贴板的辅助函数
+  const copyToClipboard = (
+    text: string,
+    setStatus: React.Dispatch<React.SetStateAction<boolean>>,
+  ) => {
+    if (navigator.clipboard && navigator.clipboard.writeText) {
+      navigator.clipboard
+        .writeText(text)
+        .then(() => {
+          setStatus(true);
+          setTimeout(() => setStatus(false), 2000);
+        })
+        .catch(() => {
+          // 降级：创建临时textarea复制
+          fallbackCopy(text, setStatus);
+        });
     } else {
-      // For non-Lark adapters, show all fields
-      setFilteredDynamicFormConfigList(dynamicFormConfigList);
+      fallbackCopy(text, setStatus);
     }
-  }, [currentAdapter, adapterConfigJson, dynamicFormConfigList]);
+  };
 
-  // 复制到剪贴板的辅助函数 - 使用页面上的真实input元素
-  const copyToClipboard = () => {
-    console.log('[Copy] Attempting to copy from input element');
-
-    const inputElement = webhookInputRef.current;
-    if (!inputElement) {
-      console.error('[Copy] Input element not found');
-      return;
-    }
-
-    try {
-      // 确保input元素可见且未被禁用
-      inputElement.disabled = false;
-      inputElement.readOnly = false;
-
-      // 聚焦并选中所有文本
-      inputElement.focus();
-      inputElement.select();
-
-      // 尝试使用现代API
-      if (navigator.clipboard && navigator.clipboard.writeText) {
-        console.log(
-          '[Copy] Using Clipboard API with input value:',
-          inputElement.value,
-        );
-        navigator.clipboard
-          .writeText(inputElement.value)
-          .then(() => {
-            console.log('[Copy] Clipboard API success');
-            inputElement.blur(); // 取消选中
-            inputElement.readOnly = true;
-            setCopied(true);
-            setTimeout(() => setCopied(false), 2000);
-          })
-          .catch((err) => {
-            console.error(
-              '[Copy] Clipboard API failed, trying execCommand:',
-              err,
-            );
-            // 降级到execCommand
-            const successful = document.execCommand('copy');
-            console.log('[Copy] execCommand result:', successful);
-            inputElement.blur();
-            inputElement.readOnly = true;
-            if (successful) {
-              setCopied(true);
-              setTimeout(() => setCopied(false), 2000);
-            }
-          });
-      } else {
-        // 直接使用execCommand
-        console.log(
-          '[Copy] Using execCommand with input value:',
-          inputElement.value,
-        );
-        const successful = document.execCommand('copy');
-        console.log('[Copy] execCommand result:', successful);
-        inputElement.blur();
-        inputElement.readOnly = true;
-        if (successful) {
-          setCopied(true);
-          setTimeout(() => setCopied(false), 2000);
-        }
-      }
-    } catch (err) {
-      console.error('[Copy] Copy failed:', err);
-      inputElement.readOnly = true;
+  const fallbackCopy = (
+    text: string,
+    setStatus: React.Dispatch<React.SetStateAction<boolean>>,
+  ) => {
+    const textarea = document.createElement('textarea');
+    textarea.value = text;
+    textarea.style.position = 'fixed';
+    textarea.style.opacity = '0';
+    document.body.appendChild(textarea);
+    textarea.select();
+    const successful = document.execCommand('copy');
+    document.body.removeChild(textarea);
+    if (successful) {
+      setStatus(true);
+      setTimeout(() => setStatus(false), 2000);
     }
   };
 
@@ -246,6 +204,7 @@ export default function BotForm({
             } else {
               setWebhookUrl('');
             }
+            setExtraWebhookUrl(val.extra_webhook_full_url || '');
           })
           .catch((err) => {
             toast.error(
@@ -255,6 +214,7 @@ export default function BotForm({
       } else {
         form.reset();
         setWebhookUrl('');
+        setExtraWebhookUrl('');
       }
     });
   }
@@ -327,14 +287,20 @@ export default function BotForm({
     setAdapterNameToDynamicConfigMap(adapterNameToDynamicConfigMap);
   }
 
-  async function getBotConfig(
-    botId: string,
-  ): Promise<z.infer<typeof formSchema> & { webhook_full_url?: string }> {
+  async function getBotConfig(botId: string): Promise<
+    z.infer<typeof formSchema> & {
+      webhook_full_url?: string;
+      extra_webhook_full_url?: string;
+    }
+  > {
     return new Promise((resolve, reject) => {
       httpClient
         .getBot(botId)
         .then((res) => {
           const bot = res.bot;
+          const runtimeValues = bot.adapter_runtime_values as
+            | Record<string, unknown>
+            | undefined;
           resolve({
             adapter: bot.adapter,
             description: bot.description,
@@ -342,10 +308,12 @@ export default function BotForm({
             adapter_config: bot.adapter_config,
             enable: bot.enable ?? true,
             use_pipeline_uuid: bot.use_pipeline_uuid ?? '',
-            webhook_full_url: bot.adapter_runtime_values
-              ? ((bot.adapter_runtime_values as Record<string, unknown>)
-                  .webhook_full_url as string)
-              : undefined,
+            webhook_full_url: runtimeValues?.webhook_full_url as
+              | string
+              | undefined,
+            extra_webhook_full_url: runtimeValues?.extra_webhook_full_url as
+              | string
+              | undefined,
           });
         })
         .catch((err) => {
@@ -536,13 +504,11 @@ export default function BotForm({
 
                 {/* Webhook 地址显示（统一 Webhook 模式） */}
                 {webhookUrl &&
-                  (currentAdapter !== 'lark' ||
-                    currentAdapterConfig?.['enable-webhook'] !== false) && (
+                  (currentAdapter !== 'lark' || enableWebhook !== false) && (
                     <FormItem>
                       <FormLabel>{t('bots.webhookUrl')}</FormLabel>
                       <div className="flex items-center gap-2">
                         <Input
-                          ref={webhookInputRef}
                           value={webhookUrl}
                           readOnly
                           className="flex-1 bg-gray-50 dark:bg-gray-900"
@@ -555,7 +521,7 @@ export default function BotForm({
                           type="button"
                           variant="outline"
                           size="sm"
-                          onClick={copyToClipboard}
+                          onClick={() => copyToClipboard(webhookUrl, setCopied)}
                         >
                           {copied ? (
                             <Check className="h-4 w-4 text-green-600 mr-2" />
@@ -565,8 +531,37 @@ export default function BotForm({
                           {t('common.copy')}
                         </Button>
                       </div>
+                      {extraWebhookUrl && (
+                        <div className="flex items-center gap-2 mt-2">
+                          <Input
+                            value={extraWebhookUrl}
+                            readOnly
+                            className="flex-1 bg-gray-50 dark:bg-gray-900"
+                            onClick={(e) => {
+                              (e.target as HTMLInputElement).select();
+                            }}
+                          />
+                          <Button
+                            type="button"
+                            variant="outline"
+                            size="sm"
+                            onClick={() =>
+                              copyToClipboard(extraWebhookUrl, setExtraCopied)
+                            }
+                          >
+                            {extraCopied ? (
+                              <Check className="h-4 w-4 text-green-600 mr-2" />
+                            ) : (
+                              <Copy className="h-4 w-4 mr-2" />
+                            )}
+                            {t('common.copy')}
+                          </Button>
+                        </div>
+                      )}
                       <p className="text-sm text-gray-500 mt-1">
-                        {t('bots.webhookUrlHint')}
+                        {extraWebhookUrl
+                          ? t('bots.webhookUrlHintEither')
+                          : t('bots.webhookUrlHint')}
                       </p>
                     </FormItem>
                   )}
@@ -673,7 +668,7 @@ export default function BotForm({
                 </div>
                 <DynamicFormComponent
                   itemConfigList={filteredDynamicFormConfigList}
-                  initialValues={form.watch('adapter_config')}
+                  initialValues={currentAdapterConfig}
                   onSubmit={(values) => {
                     form.setValue('adapter_config', values);
                   }}

web/src/app/home/components/dynamic-form/DynamicFormComponent.tsx

@@ -11,7 +11,7 @@ import {
   FormMessage,
 } from '@/components/ui/form';
 import DynamicFormItemComponent from '@/app/home/components/dynamic-form/DynamicFormItemComponent';
-import { useCallback, useEffect, useRef } from 'react';
+import { useEffect, useRef } from 'react';
 import { extractI18nObject } from '@/i18n/I18nProvider';
 import { useTranslation } from 'react-i18next';
 
@@ -34,6 +34,35 @@ export default function DynamicFormComponent({
   const previousInitialValues = useRef(initialValues);
   const { t } = useTranslation();
 
+  // Normalize a form value according to its field type.
+  // This ensures legacy/malformed data (e.g. a plain string for
+  // model-fallback-selector) is coerced to the expected shape
+  // so that downstream components never crash.
+  const normalizeFieldValue = (
+    item: IDynamicFormItemSchema,
+    value: unknown,
+  ): unknown => {
+    if (item.type === 'model-fallback-selector') {
+      if (value != null && typeof value === 'object' && !Array.isArray(value)) {
+        const obj = value as Record<string, unknown>;
+        return {
+          primary: typeof obj.primary === 'string' ? obj.primary : '',
+          fallbacks: Array.isArray(obj.fallbacks)
+            ? (obj.fallbacks as unknown[]).filter(
+                (v): v is string => typeof v === 'string',
+              )
+            : [],
+        };
+      }
+      // Legacy string format or any other unexpected type
+      return {
+        primary: typeof value === 'string' ? value : '',
+        fallbacks: [],
+      };
+    }
+    return value;
+  };
+
   // 根据 itemConfigList 动态生成 zod schema
   const formSchema = z.object(
     itemConfigList.reduce(
@@ -73,6 +102,12 @@ export default function DynamicFormComponent({
           case 'bot-selector':
             fieldSchema = z.string();
             break;
+          case 'model-fallback-selector':
+            fieldSchema = z.object({
+              primary: z.string(),
+              fallbacks: z.array(z.string()),
+            });
+            break;
           case 'prompt-editor':
             fieldSchema = z.array(
               z.object({
@@ -110,10 +145,10 @@ export default function DynamicFormComponent({
     resolver: zodResolver(formSchema),
     defaultValues: itemConfigList.reduce((acc, item) => {
       // 优先使用 initialValues，如果没有则使用默认值
-      const value = initialValues?.[item.name] ?? item.default;
+      const rawValue = initialValues?.[item.name] ?? item.default;
       return {
         ...acc,
-        [item.name]: value,
+        [item.name]: normalizeFieldValue(item, rawValue),
       };
     }, {} as FormValues),
   });
@@ -138,7 +173,8 @@ export default function DynamicFormComponent({
       // 合并默认值和初始值
       const mergedValues = itemConfigList.reduce(
         (acc, item) => {
-          acc[item.name] = initialValues[item.name] ?? item.default;
+          const rawValue = initialValues[item.name] ?? item.default;
+          acc[item.name] = normalizeFieldValue(item, rawValue) as object;
           return acc;
         },
         {} as Record<string, object>,
@@ -160,39 +196,44 @@ export default function DynamicFormComponent({
   const onSubmitRef = useRef(onSubmit);
   onSubmitRef.current = onSubmit;
 
-  // Track the last emitted values to avoid emitting identical snapshots,
-  // which would cause the parent to call setValue with an equivalent object,
-  // triggering a re-render loop.
-  const lastEmittedRef = useRef<string>('');
-
-  const emitValues = useCallback(() => {
+  // 监听表单值变化
+  useEffect(() => {
+    // Emit initial form values immediately so the parent always has a valid snapshot,
+    // even if the user saves without modifying any field.
+    // form.watch(callback) only fires on subsequent changes, not on mount.
     const formValues = form.getValues();
-    const finalValues = itemConfigList.reduce(
+    const initialFinalValues = itemConfigList.reduce(
       (acc, item) => {
         acc[item.name] = formValues[item.name] ?? item.default;
         return acc;
       },
       {} as Record<string, object>,
     );
-    const serialized = JSON.stringify(finalValues);
-    if (serialized !== lastEmittedRef.current) {
-      lastEmittedRef.current = serialized;
-      onSubmitRef.current?.(finalValues);
-    }
-  }, [form, itemConfigList]);
+    onSubmitRef.current?.(initialFinalValues);
 
-  // 监听表单值变化
-  useEffect(() => {
-    // Emit initial form values immediately so the parent always has a valid snapshot,
-    // even if the user saves without modifying any field.
-    // form.watch(callback) only fires on subsequent changes, not on mount.
-    emitValues();
+    // Update previousInitialValues to the emitted snapshot so that if the
+    // parent writes these values back as new initialValues, the deep
+    // comparison in the initialValues-sync useEffect won't detect a change
+    // and won't trigger an infinite update loop.
+    previousInitialValues.current = initialFinalValues as Record<
+      string,
+      object
+    >;
 
     const subscription = form.watch(() => {
-      emitValues();
+      const formValues = form.getValues();
+      const finalValues = itemConfigList.reduce(
+        (acc, item) => {
+          acc[item.name] = formValues[item.name] ?? item.default;
+          return acc;
+        },
+        {} as Record<string, object>,
+      );
+      onSubmitRef.current?.(finalValues);
+      previousInitialValues.current = finalValues as Record<string, object>;
     });
     return () => subscription.unsubscribe();
-  }, [form, itemConfigList, emitValues]);
+  }, [form, itemConfigList]);
 
   return (
     <Form {...form}>
@@ -231,6 +272,7 @@ export default function DynamicFormComponent({
 
           // All fields are disabled when editing (creation_settings are immutable)
           const isFieldDisabled = !!isEditing;
+
           return (
             <FormField
               key={config.id}

web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx

@@ -124,6 +124,28 @@ export default function DynamicFormItemComponent({
     }
   }, [config.type]);
 
+  useEffect(() => {
+    if (config.type === DynamicFormItemType.MODEL_FALLBACK_SELECTOR) {
+      httpClient
+        .getProviderLLMModels()
+        .then((resp) => {
+          let models = resp.models;
+          if (
+            systemInfo.disable_models_service ||
+            userInfo?.account_type !== 'space'
+          ) {
+            models = models.filter(
+              (m) => m.provider?.requester !== 'space-chat-completions',
+            );
+          }
+          setLlmModels(models);
+        })
+        .catch((err) => {
+          toast.error('Failed to get LLM model list: ' + err.msg);
+        });
+    }
+  }, [config.type]);
+
   useEffect(() => {
     if (
       config.type === DynamicFormItemType.KNOWLEDGE_BASE_SELECTOR ||
@@ -171,12 +193,7 @@ export default function DynamicFormItemComponent({
       return <Textarea {...field} className="min-h-[120px]" />;
 
     case DynamicFormItemType.BOOLEAN:
-      return (
-        <Switch
-          checked={field.value ?? false}
-          onCheckedChange={field.onChange}
-        />
-      );
+      return <Switch checked={field.value} onCheckedChange={field.onChange} />;
 
     case DynamicFormItemType.STRING_ARRAY:
       return (
@@ -227,7 +244,7 @@ export default function DynamicFormItemComponent({
 
     case DynamicFormItemType.SELECT:
       return (
-        <Select value={field.value ?? ''} onValueChange={field.onChange}>
+        <Select value={field.value} onValueChange={field.onChange}>
           <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
             <SelectValue placeholder={t('common.select')} />
           </SelectTrigger>
@@ -318,6 +335,193 @@ export default function DynamicFormItemComponent({
         </Select>
       );
 
+    case DynamicFormItemType.MODEL_FALLBACK_SELECTOR: {
+      // Group models by provider
+      const groupedModelsForFallback = llmModels.reduce(
+        (acc, model) => {
+          const providerName =
+            model.provider?.name || model.provider?.requester || 'Unknown';
+          if (!acc[providerName]) acc[providerName] = [];
+          acc[providerName].push(model);
+          return acc;
+        },
+        {} as Record<string, LLMModel[]>,
+      );
+
+      const rawModelValue = field.value;
+      const modelValue: { primary: string; fallbacks: string[] } =
+        rawModelValue != null &&
+        typeof rawModelValue === 'object' &&
+        !Array.isArray(rawModelValue)
+          ? {
+              primary:
+                typeof (rawModelValue as Record<string, unknown>).primary ===
+                'string'
+                  ? ((rawModelValue as Record<string, unknown>)
+                      .primary as string)
+                  : '',
+              fallbacks: Array.isArray(
+                (rawModelValue as Record<string, unknown>).fallbacks,
+              )
+                ? (
+                    (rawModelValue as Record<string, unknown>)
+                      .fallbacks as unknown[]
+                  ).filter((v): v is string => typeof v === 'string')
+                : [],
+            }
+          : {
+              primary: typeof rawModelValue === 'string' ? rawModelValue : '',
+              fallbacks: [],
+            };
+
+      const renderModelSelect = (
+        value: string,
+        onChange: (val: string) => void,
+        placeholder: string,
+      ) => (
+        <Select value={value} onValueChange={onChange}>
+          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+            <SelectValue placeholder={placeholder} />
+          </SelectTrigger>
+          <SelectContent>
+            {Object.entries(groupedModelsForFallback).map(
+              ([providerName, models]) => (
+                <SelectGroup key={providerName}>
+                  <SelectLabel>{providerName}</SelectLabel>
+                  {models.map((model) => (
+                    <SelectItem key={model.uuid} value={model.uuid}>
+                      <span className="inline-flex items-center gap-1">
+                        {model.name}
+                        {model.abilities?.includes('vision') && (
+                          <Eye className="h-3 w-3 text-muted-foreground" />
+                        )}
+                        {model.abilities?.includes('func_call') && (
+                          <Wrench className="h-3 w-3 text-muted-foreground" />
+                        )}
+                      </span>
+                    </SelectItem>
+                  ))}
+                </SelectGroup>
+              ),
+            )}
+          </SelectContent>
+        </Select>
+      );
+
+      const updateValue = (patch: Partial<typeof modelValue>) => {
+        field.onChange({ ...modelValue, ...patch });
+      };
+
+      const addFallbackModel = () => {
+        updateValue({ fallbacks: [...modelValue.fallbacks, ''] });
+      };
+
+      const updateFallbackModel = (index: number, value: string) => {
+        const updated = [...modelValue.fallbacks];
+        updated[index] = value;
+        updateValue({ fallbacks: updated });
+      };
+
+      const removeFallbackModel = (index: number) => {
+        const updated = [...modelValue.fallbacks];
+        updated.splice(index, 1);
+        updateValue({ fallbacks: updated });
+      };
+
+      const moveFallbackModel = (index: number, direction: 'up' | 'down') => {
+        const updated = [...modelValue.fallbacks];
+        const newIndex = direction === 'up' ? index - 1 : index + 1;
+        if (newIndex < 0 || newIndex >= updated.length) return;
+        [updated[index], updated[newIndex]] = [
+          updated[newIndex],
+          updated[index],
+        ];
+        updateValue({ fallbacks: updated });
+      };
+
+      return (
+        <div className="space-y-3">
+          {/* Primary model selector */}
+          <div>
+            <p className="text-xs text-muted-foreground mb-1">
+              {t('models.fallback.primary')}
+            </p>
+            {renderModelSelect(
+              modelValue.primary,
+              (val) => updateValue({ primary: val }),
+              t('models.selectModel'),
+            )}
+          </div>
+
+          {/* Fallback models */}
+          {modelValue.fallbacks.length > 0 && (
+            <div className="space-y-2">
+              <p className="text-xs text-muted-foreground">
+                {t('models.fallback.fallbackList')}
+              </p>
+              {modelValue.fallbacks.map((fbUuid: string, index: number) => (
+                <div key={index} className="flex items-center gap-2">
+                  <span className="text-xs text-muted-foreground w-4 shrink-0">
+                    {index + 1}.
+                  </span>
+                  <div className="flex-1">
+                    {renderModelSelect(
+                      fbUuid,
+                      (val) => updateFallbackModel(index, val),
+                      t('models.selectModel'),
+                    )}
+                  </div>
+                  <div className="flex gap-1 shrink-0">
+                    <Button
+                      type="button"
+                      variant="ghost"
+                      size="sm"
+                      className="h-8 w-8 p-0"
+                      onClick={() => moveFallbackModel(index, 'up')}
+                      disabled={index === 0}
+                    >
+                      ↑
+                    </Button>
+                    <Button
+                      type="button"
+                      variant="ghost"
+                      size="sm"
+                      className="h-8 w-8 p-0"
+                      onClick={() => moveFallbackModel(index, 'down')}
+                      disabled={index === modelValue.fallbacks.length - 1}
+                    >
+                      ↓
+                    </Button>
+                    <Button
+                      type="button"
+                      variant="ghost"
+                      size="sm"
+                      className="h-8 w-8 p-0 text-destructive"
+                      onClick={() => removeFallbackModel(index)}
+                    >
+                      <X className="h-4 w-4" />
+                    </Button>
+                  </div>
+                </div>
+              ))}
+            </div>
+          )}
+
+          {/* Add fallback button */}
+          <Button
+            type="button"
+            variant="outline"
+            size="sm"
+            className="w-full"
+            onClick={addFallbackModel}
+          >
+            <Plus className="h-4 w-4 mr-1" />
+            {t('models.fallback.addFallback')}
+          </Button>
+        </div>
+      );
+    }
+
     case DynamicFormItemType.KNOWLEDGE_BASE_SELECTOR:
       // Group KBs by Knowledge Engine name
       const kbsByEngine = knowledgeBases.reduce(

web/src/app/home/components/models-dialog/ModelsDialog.tsx

@@ -463,14 +463,16 @@ export default function ModelsDialog({
                     )
                   : t('models.providerCount', { count: otherProviders.length })}
               </span>
-              <Button
-                size="sm"
-                variant="outline"
-                onClick={handleCreateProvider}
-              >
-                <Plus className="h-4 w-4 mr-1" />
-                {t('models.addProvider')}
-              </Button>
+              <div className="flex gap-2">
+                <Button
+                  size="sm"
+                  variant="outline"
+                  onClick={handleCreateProvider}
+                >
+                  <Plus className="h-4 w-4 mr-1" />
+                  {t('models.addProvider')}
+                </Button>
+              </div>
             </div>
 
             {/* Provider List */}

web/src/app/home/knowledge/components/kb-form/KBForm.tsx

@@ -1,4 +1,4 @@
-import { useEffect, useState } from 'react';
+import { useEffect, useMemo, useState } from 'react';
 import Link from 'next/link';
 import { useForm } from 'react-hook-form';
 import { zodResolver } from '@hookform/resolvers/zod';
@@ -242,11 +242,17 @@ export default function KBForm({
   };
 
   // Convert creation schema to dynamic form items (same as ExternalKBForm)
-  const configFormItems = parseCreationSchema(selectedEngine?.creation_schema);
+  // Memoize to avoid regenerating UUIDs on every render, which would cause
+  // DynamicFormComponent's useEffect to re-fire and trigger an infinite loop.
+  const configFormItems = useMemo(
+    () => parseCreationSchema(selectedEngine?.creation_schema),
+    [selectedEngine?.creation_schema],
+  );
 
   // Convert retrieval schema to dynamic form items
-  const retrievalFormItems = parseCreationSchema(
-    selectedEngine?.retrieval_schema,
+  const retrievalFormItems = useMemo(
+    () => parseCreationSchema(selectedEngine?.retrieval_schema),
+    [selectedEngine?.retrieval_schema],
   );
 
   // Show loading state

web/src/app/home/plugins/components/plugin-market/PluginMarketComponent.tsx

@@ -1,13 +1,6 @@
 'use client';
 
-import {
-  useState,
-  useEffect,
-  useCallback,
-  useRef,
-  Suspense,
-  useMemo,
-} from 'react';
+import { useState, useEffect, useCallback, useRef, Suspense } from 'react';
 import { Input } from '@/components/ui/input';
 import {
   Select,
@@ -70,7 +63,7 @@ function MarketPageContent({
     RecommendationList[]
   >([]);
 
-  const pageSize = 16; // 每页16个，4行x4列
+  const pageSize = 12; // 每页12个
   const searchTimeoutRef = useRef<NodeJS.Timeout | null>(null);
   const scrollContainerRef = useRef<HTMLDivElement | null>(null);
 
@@ -330,38 +323,7 @@ function MarketPageContent({
     };
   }, []);
 
-  // 计算所有推荐插件的 ID 集合
-  const recommendedPluginIds = useMemo(() => {
-    const ids = new Set<string>();
-    recommendationLists.forEach((list) => {
-      list.plugins.forEach((plugin) => {
-        ids.add(`${plugin.author} / ${plugin.name}`);
-      });
-    });
-    return ids;
-  }, [recommendationLists]);
-
-  // 过滤掉已在推荐列表中展示的插件
-  // 仅在显示推荐列表的条件下（无搜索、无筛选、第一页或后续页的累积数据中）进行过滤
-  // 注意：如果用户翻页，我们希望一直保持去重，否则推荐过的插件会在第二页出现
-  // 但是推荐列表只在第一页且无筛选时显示。
-  // 如果用户进行了筛选/搜索，推荐列表不显示，此时不需要去重。
-  const visiblePlugins = useMemo(() => {
-    const showRecommendations =
-      !searchQuery && componentFilter === 'all' && selectedTags.length === 0;
-
-    if (!showRecommendations) {
-      return plugins;
-    }
-
-    return plugins.filter((p) => !recommendedPluginIds.has(p.pluginId));
-  }, [
-    plugins,
-    recommendedPluginIds,
-    searchQuery,
-    componentFilter,
-    selectedTags,
-  ]);
+  const visiblePlugins = plugins;
 
   // 加载更多
   const loadMore = useCallback(() => {

web/src/app/home/plugins/components/plugin-market/RecommendationLists.tsx

@@ -47,10 +47,12 @@ function RecommendationListRow({
   list,
   tagNames,
   onInstall,
+  isLast,
 }: {
   list: RecommendationList;
   tagNames: Record<string, string>;
   onInstall: (author: string, pluginName: string) => void;
+  isLast: boolean;
 }) {
   const { t } = useTranslation();
   const [page, setPage] = useState(0);
@@ -143,7 +145,9 @@ function RecommendationListRow({
           />
         ))}
       </div>
-      {totalPages > 1 && <div className="border-b border-border mt-6" />}
+      {totalPages > 1 && !isLast && (
+        <div className="border-b border-border mt-6" />
+      )}
     </div>
   );
 }
@@ -161,12 +165,13 @@ export function RecommendationLists({
 
   return (
     <div className="mt-6">
-      {lists.map((list) => (
+      {lists.map((list, index) => (
         <RecommendationListRow
           key={list.uuid}
           list={list}
           tagNames={tagNames}
           onInstall={onInstall}
+          isLast={index === lists.length - 1}
         />
       ))}
       <div className="border-b border-border mb-6" />

web/src/app/home/plugins/components/plugin-market/plugin-market-card/PluginMarketCardComponent.tsx

@@ -17,7 +17,7 @@ import {
   FileText,
   Info,
 } from 'lucide-react';
-import { useState } from 'react';
+import { useState, useRef, useEffect } from 'react';
 import { Button } from '@/components/ui/button';
 
 export default function PluginMarketCardComponent({
@@ -31,6 +31,43 @@ export default function PluginMarketCardComponent({
 }) {
   const { t } = useTranslation();
   const [isHovered, setIsHovered] = useState(false);
+  const bottomRef = useRef<HTMLDivElement>(null);
+  const [visibleTags, setVisibleTags] = useState(2);
+
+  // Measure how many tags fit in the bottom row
+  useEffect(() => {
+    const tags = cardVO.tags;
+    if (!bottomRef.current || !tags || tags.length === 0) return;
+
+    const measure = () => {
+      const container = bottomRef.current;
+      if (!container) return;
+      const width = container.offsetWidth;
+      const availableForTags = width - 140 - 80;
+      if (availableForTags <= 0) {
+        setVisibleTags(0);
+        return;
+      }
+      const tagWidth = 80;
+      const plusBadgeWidth = 40;
+      const maxTags = Math.max(
+        0,
+        Math.floor((availableForTags - plusBadgeWidth) / tagWidth),
+      );
+      if (maxTags >= tags.length) {
+        setVisibleTags(tags.length);
+      } else {
+        setVisibleTags(Math.max(1, maxTags));
+      }
+    };
+
+    measure();
+    const observer = new ResizeObserver(measure);
+    observer.observe(bottomRef.current);
+    return () => observer.disconnect();
+  }, [cardVO.tags]);
+
+  const remainingTags = cardVO.tags ? cardVO.tags.length - visibleTags : 0;
 
   function handleInstallClick(e: React.MouseEvent) {
     e.stopPropagation();
@@ -135,10 +172,13 @@ export default function PluginMarketCardComponent({
         </div>
 
         {/* 下部分：下载量、标签和组件列表 */}
-        <div className="w-full flex flex-row items-center justify-between gap-2 px-0 sm:px-[0.4rem] flex-shrink-0">
-          <div className="flex flex-row items-center justify-start gap-2 flex-wrap">
+        <div
+          ref={bottomRef}
+          className="w-full flex flex-row items-center justify-between gap-2 px-0 sm:px-[0.4rem] flex-shrink-0 overflow-hidden"
+        >
+          <div className="flex flex-row items-center justify-start gap-2 min-w-0 overflow-hidden">
             {/* 下载数量 */}
-            <div className="flex flex-row items-center gap-[0.3rem] sm:gap-[0.4rem]">
+            <div className="flex flex-row items-center gap-[0.3rem] sm:gap-[0.4rem] flex-shrink-0">
               <svg
                 className="w-4 h-4 sm:w-[1.2rem] sm:h-[1.2rem] text-[#2563eb] dark:text-[#5b8def] flex-shrink-0"
                 xmlns="http://www.w3.org/2000/svg"
@@ -156,14 +196,14 @@ export default function PluginMarketCardComponent({
               </div>
             </div>
 
-            {/* Tags */}
-            {cardVO.tags && cardVO.tags.length > 0 && (
-              <div className="flex flex-wrap gap-1.5">
-                {cardVO.tags.slice(0, 2).map((tag) => (
+            {/* Tags - adaptive */}
+            {cardVO.tags && cardVO.tags.length > 0 && visibleTags > 0 && (
+              <div className="flex flex-row items-center gap-1.5 overflow-hidden flex-shrink min-w-0">
+                {cardVO.tags.slice(0, visibleTags).map((tag) => (
                   <Badge
                     key={tag}
                     variant="secondary"
-                    className="text-[0.65rem] sm:text-[0.7rem] px-2 py-0.5 h-5 flex items-center gap-1 flex-shrink-0"
+                    className="text-[0.65rem] sm:text-[0.7rem] px-2 py-0.5 h-5 flex items-center gap-1 flex-shrink-0 whitespace-nowrap"
                   >
                     <svg
                       className="w-2.5 h-2.5 flex-shrink-0"
@@ -178,15 +218,17 @@ export default function PluginMarketCardComponent({
                       <path d="M20.59 13.41l-7.17 7.17a2 2 0 0 1-2.83 0L2 12V2h10l8.59 8.59a2 2 0 0 1 0 2.82z" />
                       <line x1="7" y1="7" x2="7.01" y2="7" />
                     </svg>
-                    <span className="truncate">{tagNames[tag] || tag}</span>
+                    <span className="truncate max-w-[5rem]">
+                      {tagNames[tag] || tag}
+                    </span>
                   </Badge>
                 ))}
-                {cardVO.tags.length > 2 && (
+                {remainingTags > 0 && (
                   <Badge
                     variant="outline"
-                    className="text-[0.65rem] sm:text-[0.7rem] px-2 py-0.5 h-5 flex items-center flex-shrink-0"
+                    className="text-[0.65rem] sm:text-[0.7rem] px-1.5 py-0.5 h-5 flex items-center flex-shrink-0 whitespace-nowrap"
                   >
-                    +{cardVO.tags.length - 2}
+                    +{remainingTags}
                   </Badge>
                 )}
               </div>

web/src/app/infra/entities/form/dynamic.ts

@@ -35,6 +35,7 @@ export enum DynamicFormItemType {
   SELECT = 'select',
   LLM_MODEL_SELECTOR = 'llm-model-selector',
   EMBEDDING_MODEL_SELECTOR = 'embedding-model-selector',
+  MODEL_FALLBACK_SELECTOR = 'model-fallback-selector',
   PROMPT_EDITOR = 'prompt-editor',
   UNKNOWN = 'unknown',
   KNOWLEDGE_BASE_SELECTOR = 'knowledge-base-selector',

web/src/app/login/page.tsx

@@ -23,7 +23,7 @@ import {
 import { useEffect, useState } from 'react';
 import { httpClient, initializeUserInfo } from '@/app/infra/http';
 import { useRouter } from 'next/navigation';
-import { Mail, Lock, Loader2 } from 'lucide-react';
+import { Mail, Lock, Loader2, AlertCircle, RefreshCw } from 'lucide-react';
 import langbotIcon from '@/app/assets/langbot-logo.webp';
 import { toast } from 'sonner';
 import { useTranslation } from 'react-i18next';
@@ -46,6 +46,8 @@ export default function Login() {
   const [accountType, setAccountType] = useState<AccountType | null>(null);
   const [hasPassword, setHasPassword] = useState(false);
   const [loading, setLoading] = useState(true);
+  const [loadError, setLoadError] = useState<string | null>(null);
+  const [retrying, setRetrying] = useState(false);
 
   const form = useForm<z.infer<ReturnType<typeof formSchema>>>({
     resolver: zodResolver(formSchema(t)),
@@ -61,6 +63,7 @@ export default function Login() {
 
   async function checkAccountInfo() {
     try {
+      setLoadError(null);
       const res = await httpClient.getAccountInfo();
       if (!res.initialized) {
         router.push('/register');
@@ -72,11 +75,22 @@ export default function Login() {
 
       // Also check if already logged in
       checkIfAlreadyLoggedIn();
-    } catch {
+    } catch (err) {
+      const errorMessage =
+        err instanceof Error ? err.message : t('common.loginLoadError');
+      setLoadError(errorMessage);
       setLoading(false);
     }
   }
 
+  async function handleRetry() {
+    setRetrying(true);
+    setLoading(true);
+    setLoadError(null);
+    await checkAccountInfo();
+    setRetrying(false);
+  }
+
   function checkIfAlreadyLoggedIn() {
     httpClient
       .checkUserToken()
@@ -129,6 +143,54 @@ export default function Login() {
     );
   }
 
+  // Show error state when account info failed to load
+  if (loadError) {
+    return (
+      <div className="min-h-screen flex items-center justify-center bg-gray-50 dark:bg-neutral-900">
+        <Card className="w-[375px] shadow-lg dark:shadow-white/10">
+          <CardHeader>
+            <div className="flex justify-between items-center mb-6">
+              <ThemeToggle />
+              <LanguageSelector />
+            </div>
+            <img
+              src={langbotIcon.src}
+              alt="LangBot"
+              className="w-16 h-16 mb-4 mx-auto"
+            />
+            <CardTitle className="text-2xl text-center">
+              {t('common.welcome')}
+            </CardTitle>
+          </CardHeader>
+          <CardContent className="space-y-4">
+            <div className="flex flex-col items-center gap-3 py-4">
+              <AlertCircle className="h-10 w-10 text-destructive" />
+              <p className="text-sm text-center text-muted-foreground">
+                {t('common.loginLoadErrorDesc')}
+              </p>
+              <code className="text-xs bg-muted px-3 py-2 rounded max-w-full overflow-x-auto block text-center text-muted-foreground">
+                {loadError}
+              </code>
+              <Button
+                onClick={handleRetry}
+                disabled={retrying}
+                variant="outline"
+                className="mt-2 cursor-pointer"
+              >
+                {retrying ? (
+                  <Loader2 className="mr-2 h-4 w-4 animate-spin" />
+                ) : (
+                  <RefreshCw className="mr-2 h-4 w-4" />
+                )}
+                {t('common.retry')}
+              </Button>
+            </div>
+          </CardContent>
+        </Card>
+      </div>
+    );
+  }
+
   // Determine what to show based on account type
   const showLocalLogin =
     accountType === 'local' || (accountType === 'space' && hasPassword);

web/src/i18n/locales/en-US.ts

@@ -11,6 +11,10 @@ const enUS = {
     continueToLogin: 'Login to continue',
     loginSuccess: 'Login successful',
     loginFailed: 'Login failed, please check your email and password',
+    loginLoadError: 'Unable to connect to server',
+    loginLoadErrorDesc:
+      'Unable to connect to the LangBot backend. Please make sure the service is running and try again.',
+    retry: 'Retry',
     enterEmail: 'Enter email address',
     enterPassword: 'Enter password',
     invalidEmail: 'Please enter a valid email address',
@@ -236,6 +240,11 @@ const enUS = {
     modelsCount: '{{count}} model(s)',
     expandModels: 'Expand',
     collapseModels: 'Collapse',
+    fallback: {
+      primary: 'Primary Model',
+      fallbackList: 'Fallback Models',
+      addFallback: 'Add Fallback Model',
+    },
   },
   bots: {
     title: 'Bots',
@@ -279,6 +288,8 @@ const enUS = {
     webhookUrlCopied: 'Webhook URL copied',
     webhookUrlHint:
       'Click the input to select all, then press Ctrl+C (Mac: Cmd+C) to copy, or click the button',
+    webhookUrlHintEither:
+      'Use either of the two URLs above in your platform configuration',
     logLevel: 'Log Level',
     allLevels: 'All Levels',
     selectLevel: 'Select Level',

web/src/i18n/locales/ja-JP.ts

@@ -1,4 +1,4 @@
-const jaJP = {
+const jaJP = {
   common: {
     login: 'ログイン',
     logout: 'ログアウト',
@@ -12,6 +12,10 @@ const jaJP = {
     loginSuccess: 'ログインに成功しました',
     loginFailed:
       'ログインに失敗しました。メールアドレスまたはパスワードをご確認ください',
+    loginLoadError: 'サーバーに接続できません',
+    loginLoadErrorDesc:
+      'LangBot バックエンドに接続できません。サービスが起動していることを確認してから再試行してください。',
+    retry: '再試行',
     enterEmail: 'メールアドレスを入力',
     enterPassword: 'パスワードを入力',
     invalidEmail: '有効なメールアドレスを入力してください',
@@ -241,6 +245,11 @@ const jaJP = {
     modelsCount: '{{count}} 個のモデル',
     expandModels: '展開',
     collapseModels: '折りたたむ',
+    fallback: {
+      primary: 'プライマリモデル',
+      fallbackList: 'フォールバックモデル',
+      addFallback: 'フォールバックモデルを追加',
+    },
   },
   bots: {
     title: 'ボット',
@@ -284,6 +293,8 @@ const jaJP = {
     webhookUrlCopied: 'Webhook URL をコピーしました',
     webhookUrlHint:
       '入力ボックスをクリックして全選択し、Ctrl+C (Mac: Cmd+C) でコピーするか、右側のボタンをクリックしてください',
+    webhookUrlHintEither:
+      '上記の2つのURLのいずれかをプラットフォーム設定に使用してください',
     logLevel: 'ログレベル',
     allLevels: 'すべてのレベル',
     selectLevel: 'レベルを選択',

web/src/i18n/locales/zh-Hans.ts

@@ -11,6 +11,9 @@ const zhHans = {
     continueToLogin: '登录以继续',
     loginSuccess: '登录成功',
     loginFailed: '登录失败，请检查邮箱和密码是否正确',
+    loginLoadError: '无法连接到服务器',
+    loginLoadErrorDesc: '无法连接到 LangBot 后端服务，请确认服务已启动后重试。',
+    retry: '重试',
     enterEmail: '输入邮箱地址',
     enterPassword: '输入密码',
     invalidEmail: '请输入有效的邮箱地址',
@@ -227,6 +230,11 @@ const zhHans = {
     modelsCount: '{{count}} 个模型',
     expandModels: '展开',
     collapseModels: '收起',
+    fallback: {
+      primary: '主模型',
+      fallbackList: '备用模型',
+      addFallback: '添加备用模型',
+    },
   },
   bots: {
     title: '机器人',
@@ -268,6 +276,7 @@ const zhHans = {
     webhookUrlCopied: 'Webhook 地址已复制',
     webhookUrlHint:
       '点击输入框自动全选，然后按 Ctrl+C (Mac: Cmd+C) 复制，或点击右侧按钮',
+    webhookUrlHintEither: '以上两个地址任选其一填入平台配置即可',
     logLevel: '日志级别',
     allLevels: '全部级别',
     selectLevel: '选择级别',

web/src/i18n/locales/zh-Hant.ts

@@ -11,6 +11,9 @@ const zhHant = {
     continueToLogin: '登入以繼續',
     loginSuccess: '登入成功',
     loginFailed: '登入失敗，請檢查電子郵件和密碼是否正確',
+    loginLoadError: '無法連線到伺服器',
+    loginLoadErrorDesc: '無法連線到 LangBot 後端服務，請確認服務已啟動後重試。',
+    retry: '重試',
     enterEmail: '輸入電子郵件地址',
     enterPassword: '輸入密碼',
     invalidEmail: '請輸入有效的電子郵件地址',
@@ -226,6 +229,11 @@ const zhHant = {
     modelsCount: '{{count}} 個模型',
     expandModels: '展開',
     collapseModels: '收起',
+    fallback: {
+      primary: '主模型',
+      fallbackList: '備用模型',
+      addFallback: '新增備用模型',
+    },
   },
   bots: {
     title: '機器人',
@@ -267,6 +275,7 @@ const zhHant = {
     webhookUrlCopied: 'Webhook 位址已複製',
     webhookUrlHint:
       '點擊輸入框自動全選，然後按 Ctrl+C (Mac: Cmd+C) 複製，或點擊右側按鈕',
+    webhookUrlHintEither: '以上兩個地址任選其一填入平台配置即可',
     logLevel: '日誌級別',
     allLevels: '全部級別',
     selectLevel: '選擇級別',