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 = "4.9.1"
+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==0.3.1",
+    "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__ = '4.9.1'
+__version__ = '4.9.3'

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/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/pipeline/preproc/preproc.py

@@ -176,6 +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/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/wecombot.py

@@ -24,14 +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:
@@ -134,13 +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(
@@ -180,13 +186,16 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
     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):
         enable_webhook = config.get('enable-webhook', False)
+        bot_name = config.get('robot_name', '')
 
         if not enable_webhook:
             bot = WecomBotWsClient(
@@ -195,7 +204,6 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 logger=logger,
                 encoding_aes_key=config.get('EncodingAESKey', ''),
             )
-            ws_mode = True
         else:
             # Webhook callback mode
             required_keys = ['Token', 'EncodingAESKey', 'Corpid']
@@ -210,17 +218,18 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                 logger=logger,
                 unified_mode=True,
             )
-            ws_mode = False
 
         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._ws_mode = ws_mode
+        self.listeners = {}
 
     async def reply_message(
         self,
@@ -229,7 +238,9 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         quote_origin: bool = False,
     ):
         content = await self.message_converter.yiri2target(message)
-        if self._ws_mode:
+        _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:
@@ -249,8 +260,9 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
     ):
         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)
 
-        if self._ws_mode:
+        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
@@ -275,12 +287,22 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         return True
 
     async def send_message(self, target_type, target_id, message):
-        if self._ws_mode:
+        _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,
         event_type: typing.Type[platform_events.Event],
@@ -288,18 +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())
 
@@ -308,12 +325,14 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
         self.bot_uuid = bot_uuid
 
     async def handle_unified_webhook(self, bot_uuid: str, path: str, request):
-        if self._ws_mode:
+        _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):
-        if self._ws_mode:
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
             await self.bot.connect()
         else:
 
@@ -324,7 +343,8 @@ class WecomBotAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
             await keep_alive()
 
     async def kill(self) -> bool:
-        if self._ws_mode:
+        _ws_mode = not self.config.get('enable-webhook', False)
+        if _ws_mode:
             await self.bot.disconnect()
             return True
         return False

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

@@ -18,6 +18,13 @@ spec:
       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

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']
@@ -675,11 +687,15 @@ class RuntimeConnectionHandler(handler.Handler):
                 )
 
             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]
@@ -993,7 +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

@@ -132,14 +132,9 @@ class LocalAgentRunner(runner.RequestRunner):
         """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)
 

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/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

@@ -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/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}},

uv.lock

@@ -1832,7 +1832,7 @@ wheels = [
 
 [[package]]
 name = "langbot"
-version = "4.9.1"
+version = "4.9.3"
 source = { editable = "." }
 dependencies = [
     { name = "aiocqhttp" },
@@ -1937,7 +1937,7 @@ requires-dist = [
     { name = "ebooklib", specifier = ">=0.18" },
     { name = "gewechat-client", specifier = ">=0.1.5" },
     { name = "html2text", specifier = ">=2024.2.26" },
-    { name = "langbot-plugin", specifier = "==0.3.1" },
+    { name = "langbot-plugin", specifier = "==0.3.3" },
     { name = "langchain", specifier = ">=0.2.0" },
     { name = "langchain-text-splitters", specifier = ">=0.0.1" },
     { name = "lark-oapi", specifier = ">=1.4.15" },
@@ -1993,7 +1993,7 @@ dev = [
 
 [[package]]
 name = "langbot-plugin"
-version = "0.3.1"
+version = "0.3.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiofiles" },
@@ -2011,9 +2011,9 @@ dependencies = [
     { name = "watchdog" },
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/4e/ed/b440e26ebc40983abf00dd343338101ada3381065fb3347401ba75f873fe/langbot_plugin-0.3.1.tar.gz", hash = "sha256:0839dcb4cfe689fc670d0ded29b57e6a3f683d8f7326eaa771a5b753675459ac", size = 170285, upload-time = "2026-03-12T15:07:01.918Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/08/be/78a0375aec6aad34bc2f00e2b4d2511ec597e8143cf8596d0736e8767904/langbot_plugin-0.3.3.tar.gz", hash = "sha256:5b07609b9b08f8b24fefcf29b97b9882838c140143de6d4bac2f320511ef4374", size = 170709, upload-time = "2026-03-19T12:40:23.877Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/13/81/d3c4142911792838b90384a28f7dd1540d0862303293c53ba77e69fc0e15/langbot_plugin-0.3.1-py3-none-any.whl", hash = "sha256:8139796926fe8385b7b546ef865e29b1b8d8e28249e20f3b5417d42d3181ec62", size = 144813, upload-time = "2026-03-12T15:07:03.69Z" },
+    { url = "https://files.pythonhosted.org/packages/92/53/c708f3ef9459420974f1b131cffd43cfb2f97220350c26a6b5fbadbd6211/langbot_plugin-0.3.3-py3-none-any.whl", hash = "sha256:cca94a2ed07c1d3ec4be33f97268746908ed304b528d0eb7f23308677fe619ca", size = 145188, upload-time = "2026-03-19T12:40:25.094Z" },
 ]
 
 [[package]]

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,
@@ -113,109 +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');
 
+  // 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, currentAdapterConfig, 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);
     }
   };
 
@@ -240,6 +204,7 @@ export default function BotForm({
             } else {
               setWebhookUrl('');
             }
+            setExtraWebhookUrl(val.extra_webhook_full_url || '');
           })
           .catch((err) => {
             toast.error(
@@ -249,6 +214,7 @@ export default function BotForm({
       } else {
         form.reset();
         setWebhookUrl('');
+        setExtraWebhookUrl('');
       }
     });
   }
@@ -321,14 +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,
@@ -336,10 +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) => {
@@ -530,13 +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"
@@ -549,7 +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" />
@@ -559,8 +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>
                   )}
@@ -667,7 +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

@@ -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(
@@ -116,10 +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),
   });
@@ -144,7 +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>,
@@ -181,6 +211,15 @@ export default function DynamicFormComponent({
     );
     onSubmitRef.current?.(initialFinalValues);
 
+    // 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(() => {
       const formValues = form.getValues();
       const finalValues = itemConfigList.reduce(
@@ -191,6 +230,7 @@ export default function DynamicFormComponent({
         {} as Record<string, object>,
       );
       onSubmitRef.current?.(finalValues);
+      previousInitialValues.current = finalValues as Record<string, object>;
     });
     return () => subscription.unsubscribe();
   }, [form, itemConfigList]);

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

@@ -348,10 +348,31 @@ export default function DynamicFormItemComponent({
         {} as Record<string, LLMModel[]>,
       );
 
-      const modelValue = field.value as {
-        primary: string;
-        fallbacks: string[];
-      };
+      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,

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',
@@ -284,6 +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

@@ -12,6 +12,10 @@
     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',
@@ -289,6 +293,8 @@
     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',
@@ -273,6 +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',
@@ -272,6 +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',