fix: 修复一些typo

支持 fishaudio tts 文字转语音

Dockerfile

@@ -12,7 +12,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     && apt-get clean \
     && rm -rf /var/lib/apt/lists/*
 
-RUN python -m pip install -r requirements.txt
+RUN python -m pip install -r requirements.txt --no-cache-dir
+
+RUN python -m pip install socksio wechatpy cryptography --no-cache-dir
 
 EXPOSE 6185 
 EXPOSE 6186

astrbot/core/__init__.py

@@ -11,7 +11,8 @@ from astrbot.core.config import AstrBotConfig
 os.makedirs("data", exist_ok=True)
 
 astrbot_config = AstrBotConfig()
-html_renderer = HtmlRenderer()
+t2i_base_url = astrbot_config.get('t2i_endpoint', 'https://t2i.soulter.top/text2img')
+html_renderer = HtmlRenderer(t2i_base_url)
 logger = LogManager.GetLogger(log_name='astrbot')
 
 if os.environ.get('TESTING', ""):

astrbot/core/config/default.py

@@ -2,7 +2,7 @@
 如需修改配置，请在 `data/cmd_config.json` 中修改或者在管理面板中可视化修改。
 """
 
-VERSION = "3.4.21"
+VERSION = "3.4.23"
 DB_PATH = "data/data_v3.db"
 
 # 默认配置
@@ -29,7 +29,6 @@ DEFAULT_CONFIG = {
             "enable": False,
             "only_llm_result": True,
             "interval": "1.5,3.5",
-            "seg_prompt": "",
             "regex": ".*?[。？！~…]+|.+$"
         },
         "no_permission_reply": True,
@@ -64,14 +63,15 @@ DEFAULT_CONFIG = {
             "method": "possibility_reply",
             "possibility_reply": 0.1,
             "prompt": "",
-        },
-        "put_history_to_prompt": True,
+        }
     },
     "content_safety": {
         "internal_keywords": {"enable": True, "extra_keywords": []},
         "baidu_aip": {"enable": False, "app_id": "", "api_key": "", "secret_key": ""},
     },
-    "admins_id": [],
+    "admins_id": [
+        "astrbot"
+    ],
     "t2i": False,
     "t2i_word_threshold": 150,
     "http_proxy": "",
@@ -220,11 +220,6 @@ CONFIG_METADATA_2 = {
                                 "type": "string",
                                 "hint": "每一段回复的间隔时间，格式为 `最小时间,最大时间`。如 `0.75,2.5`",
                             },
-                            "seg_prompt": {
-                                "description": "分段提示词辅助",
-                                "type": "string",
-                                "hint": "此项为空时表达不启用这个方法。此方法会调用一次LLM请求。让 LLM 在某一句话中插入一个可以用正则表达式分隔的标记，来实现LLM基于情感分段。如: `请基于情感对以下文本进行分段, 并在两段之间添加`<seg>`以便我用正则匹配。`    然后将下面的正则表达式更换为`.+?<seg>`。",
-                            },
                             "regex": {
                                 "description": "正则表达式",
                                 "type": "string",
@@ -252,7 +247,7 @@ CONFIG_METADATA_2 = {
                         "type": "list",
                         "items": {"type": "string"},
                         "obvious_hint": True,
-                        "hint": "AstrBot 只处理所填写的 ID 发来的消息事件。为空时不启用白名单过滤。可以使用 /sid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978",
+                        "hint": "AstrBot 只处理所填写的 ID 发来的消息事件。为空时不启用白名单过滤。可以使用 /sid 指令获取在某个平台上的会话 ID。也可在 AstrBot 日志内获取会话 ID，当一条消息没通过白名单时，会输出 INFO 级别的日志。会话 ID 类似 aiocqhttp:GroupMessage:547540978。管理员可使用 /wl 添加白名单",
                     },
                     "id_whitelist_log": {
                         "description": "打印白名单日志",
@@ -283,7 +278,7 @@ CONFIG_METADATA_2 = {
                         "items": {"type": "string"},
                         "obvious_hint": True,
                         "hint": "此功能解决由于文件系统不一致导致路径不存在的问题。格式为 <原路径>:<映射路径>。如 `/app/.config/QQ:/var/lib/docker/volumes/xxxx/_data`。这样，当消息平台下发的事件中图片和语音路径以 `/app/.config/QQ` 开头时，开头被替换为 `/var/lib/docker/volumes/xxxx/_data`。这在 AstrBot 或者平台协议端使用 Docker 部署时特别有用。",
-                    }
+                    },
                 },
             },
             "content_safety": {
@@ -440,6 +435,7 @@ CONFIG_METADATA_2 = {
                         "dify_api_key": "",
                         "dify_api_base": "https://api.dify.ai/v1",
                         "dify_workflow_output_key": "",
+                        "timeout": 60,
                     },
                     "whisper(API)": {
                         "id": "whisper",
@@ -466,6 +462,15 @@ CONFIG_METADATA_2 = {
                         "openai-tts-voice": "alloy",
                         "timeout": "20",
                     },
+                    "fishaudio_tts(API)": {
+                        "id": "fishaudio_tts",
+                        "type": "fishaudio_tts_api",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "https://api.fish-audio.cn/v1",
+                        "fishaudio-tts-character": "可莉",
+                        "timeout": "20",
+                    },
                 },
                 "items": {
                     "timeout": {
@@ -479,6 +484,12 @@ CONFIG_METADATA_2 = {
                         "obvious_hint": True,
                         "hint": "OpenAI TTS 的声音。OpenAI 默认支持：'alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'",
                     },
+                    "fishaudio-tts-character": {
+                        "description": "character",
+                        "type": "string",
+                        "obvious_hint": True,
+                        "hint": "fishaudio TTS 的角色。默认为可莉。更多角色请访问：https://fish.audio/zh-CN/discovery",
+                    },
                     "whisper_hint": {
                         "description": "本地部署 Whisper 模型须知",
                         "type": "string",
@@ -732,7 +743,7 @@ CONFIG_METADATA_2 = {
                     },
                     "image_caption_prompt": {
                         "description": "图像转述提示词",
-                        "type": "string"
+                        "type": "string",
                     },
                     "active_reply": {
                         "description": "主动回复",
@@ -764,12 +775,6 @@ CONFIG_METADATA_2 = {
                             },
                         },
                     },
-                    "put_history_to_prompt": {
-                        "description": "将群聊历史记录作为 prompt",
-                        "type": "bool",
-                        "obvious_hint": True,
-                        "hint": "需要先启用 group_icl_enable。此功能会将群聊历史记录放到 prompt 再请求。如果关闭，则是放在 system_prompt。如果开启了主动回复，建议启用，模型能够更好地完成回复任务。",
-                    }
                 },
             },
         },

astrbot/core/pipeline/process_stage/method/llm_request.py

@@ -129,6 +129,9 @@ class LLMRequestSubStage(Stage):
                     req.prompt += extra_prompt
                     async for _ in self.process(event, _nested=True):
                         yield
+                else:
+                    if llm_response.completion_text:
+                        event.set_result(MessageEventResult().message(llm_response.completion_text))
 
         except BaseException as e:
             logger.error(traceback.format_exc())

astrbot/core/pipeline/result_decorate/stage.py

@@ -30,7 +30,6 @@ class ResultDecorateStage:
         # 分段回复
         self.enable_segmented_reply = ctx.astrbot_config['platform_settings']['segmented_reply']['enable']
         self.only_llm_result = ctx.astrbot_config['platform_settings']['segmented_reply']['only_llm_result']
-        self.seg_prompt = ctx.astrbot_config['platform_settings']['segmented_reply']['seg_prompt']
         self.regex = ctx.astrbot_config['platform_settings']['segmented_reply']['regex']
 
     async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
@@ -40,9 +39,8 @@ class ResultDecorateStage:
         
         handlers = star_handlers_registry.get_handlers_by_event_type(EventType.OnDecoratingResultEvent)
         for handler in handlers:
-            # TODO: 如何让这里的 handler 也能使用 LLM 能力。也许需要将 LLMRequestSubStage 提取出来。
             await handler.handler(event)
-        
+            
         if len(result.chain) > 0:
             # 回复前缀
             if self.reply_prefix:
@@ -57,19 +55,6 @@ class ResultDecorateStage:
                     new_chain = []
                     for comp in result.chain:
                         if isinstance(comp, Plain):
-                            
-                            if self.seg_prompt:
-                                try:
-                                    llm_resp = await self.ctx.plugin_manager.context.get_using_provider().text_chat(
-                                        prompt=f"{self.seg_prompt}\n{comp.text}",
-                                    )
-                                    comp.text = llm_resp.completion_text
-                                except BaseException as e:
-                                    traceback.print_exc()
-                                    logger.warning("使用 LLM 分段回复失败。将不分段回复。： " + str(e))
-                                    new_chain.append(comp)
-                                    continue
-                            
                             split_response = re.findall(self.regex, comp.text)
                             if not split_response:
                                 new_chain.append(comp)
@@ -98,7 +83,7 @@ class ResultDecorateStage:
                                 logger.error(f"由于 TTS 音频文件没找到，消息段转语音失败: {comp.text}")
                                 new_chain.append(comp)
                         except BaseException:
-                            traceback.print_exc()
+                            logger.error(traceback.format_exc())
                             logger.error("TTS 失败，使用文本发送。")
                             new_chain.append(comp)
                     else:

astrbot/core/pipeline/waking_check/stage.py

@@ -3,7 +3,7 @@ from ..context import PipelineContext
 from typing import Union, AsyncGenerator
 from astrbot.core.platform.astr_message_event import AstrMessageEvent
 from astrbot.core.message.message_event_result import MessageEventResult, MessageChain
-from astrbot.core.message.components import At
+from astrbot.core.message.components import At, Reply
 from astrbot.core.star.star_handler import star_handlers_registry, EventType
 from astrbot.core.star.filter.command_group import CommandGroupFilter
 from astrbot.core.star.filter.permission import PermissionTypeFilter
@@ -43,7 +43,7 @@ class WakingCheckStage(Stage):
             if event.message_str.startswith(wake_prefix):
                 if (
                     not event.is_private_chat()
-                    and isinstance(messages[0], At)
+                    and (isinstance(messages[0], At) or isinstance(messages[0], Reply))
                     and str(messages[0].qq) != str(event.get_self_id())
                     and str(messages[0].qq) != "all"
                 ):
@@ -86,6 +86,10 @@ class WakingCheckStage(Stage):
             if len(handler.event_filters) == 0:
                 # 不可能有这种情况, 也不允许有这种情况
                 continue
+            
+            if 'sub_command' in handler.extras_configs:
+                # 如果是子指令
+                continue
 
             for filter in handler.event_filters:
                 try:

astrbot/core/platform/astr_message_event.py

@@ -8,7 +8,7 @@ from typing import List, Union
 from astrbot.core.message.components import Plain, Image, BaseMessageComponent, Face, At, AtAll, Forward
 from astrbot.core.utils.metrics import Metric
 from astrbot.core.provider.entites import ProviderRequest
-
+from astrbot.core.db.po import Conversation
 
 @dataclass
 class MessageSesion:
@@ -305,9 +305,10 @@ class AstrMessageEvent(abc.ABC):
         prompt: str,
         func_tool_manager = None,
         session_id: str = None,
-        image_urls: List[str] = None,
-        contexts: List = None,
-        system_prompt: str = ""
+        image_urls: List[str] = [],
+        contexts: List = [],
+        system_prompt: str = "",
+        conversation: Conversation = None
     ) -> ProviderRequest:
         '''
         创建一个 LLM 请求。
@@ -316,10 +317,12 @@ class AstrMessageEvent(abc.ABC):
         ```py
         yield event.request_llm(prompt="hi")
         ```
-        
+        prompt: 提示词
+        session_id: 已经过时，留空即可
         image_urls: 可以是 base64:// 或者 http:// 开头的图片链接，也可以是本地图片路径。
-        contexts: 当指定 contexts 时，将会**只**使用 contexts 作为上下文。
+        contexts: 当指定 contexts 时，将会使用 contexts 作为上下文。
         func_tool_manager: 函数工具管理器，用于调用函数工具。用 self.context.get_llm_tool_manager() 获取。
+        conversation: 可选。如果指定，将在指定的对话中进行 LLM 请求。对话的人格会被用于 LLM 请求，并且结果将会被记录到对话中。
         '''
         return ProviderRequest(
             prompt = prompt,
@@ -327,5 +330,6 @@ class AstrMessageEvent(abc.ABC):
             image_urls = image_urls,
             func_tool = func_tool_manager,
             contexts = contexts,
-            system_prompt = system_prompt
+            system_prompt = system_prompt,
+            conversation=conversation
         )

astrbot/core/platform/sources/aiocqhttp/aiocqhttp_message_event.py

@@ -1,9 +1,7 @@
 import os
-import random
-import asyncio
 
 from astrbot.api.event import AstrMessageEvent, MessageChain
-from astrbot.api.message_components import Plain, Image, Record
+from astrbot.api.message_components import Plain, Image, Record, At
 from aiocqhttp import CQHttp
 from astrbot.core.utils.io import file_to_base64, download_image_by_url
 
@@ -33,6 +31,10 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
                 d['data'] = {
                     'file': bs64_data,
                 }
+            if isinstance(segment, At):
+                d['data'] = {
+                    'qq': str(segment.qq) # 转换为字符串
+                }
             ret.append(d)
         return ret
 

astrbot/core/platform/sources/gewechat/client.py

@@ -3,6 +3,7 @@ import asyncio
 import aiohttp
 import quart
 import base64
+import datetime
 
 from astrbot.api.platform import AstrBotMessage, MessageMember, MessageType
 from astrbot.api.message_components import Plain, Image, At, Record
@@ -67,6 +68,17 @@ class SimpleGewechatClient():
             logger.critical("收到 gewechat 下线通知。")
             return
         
+        if 'Data' in data and 'CreateTime' in data['Data']:
+            # 得到系统 UTF+8 的 ts
+            tz_offset = datetime.timedelta(hours=8)
+            tz = datetime.timezone(tz_offset)
+            ts = datetime.datetime.now(tz).timestamp()
+            create_time = data['Data']['CreateTime']
+            if create_time < ts - 30:
+                logger.warning(f"消息时间戳过旧: {create_time}，当前时间戳: {ts}")
+                return
+
+        
         abm = AstrBotMessage()
         d = data['Data']
     
@@ -143,7 +155,7 @@ class SimpleGewechatClient():
                     abm.message.append(Record(file=file_path, url=file_path))
                 
             case _:
-                logger.error(f"未实现的消息类型: {d['MsgType']}")
+                logger.info(f"未实现的消息类型: {d['MsgType']}")
                 return
         
         logger.info(f"abm: {abm}")

astrbot/core/provider/manager.py

@@ -114,22 +114,24 @@ class ProviderManager():
             try:
                 match provider_cfg['type']:
                     case "openai_chat_completion":
-                        from .sources.openai_source import ProviderOpenAIOfficial # noqa: F401
+                        from .sources.openai_source import ProviderOpenAIOfficial as ProviderOpenAIOfficial
                     case "zhipu_chat_completion":
-                        from .sources.zhipu_source import ProviderZhipu # noqa: F401
+                        from .sources.zhipu_source import ProviderZhipu as ProviderZhipu
                     case "llm_tuner":
                         logger.info("加载 LLM Tuner 工具 ...")
-                        from .sources.llmtuner_source import LLMTunerModelLoader # noqa: F401
+                        from .sources.llmtuner_source import LLMTunerModelLoader as LLMTunerModelLoader
                     case "dify":
-                        from .sources.dify_source import ProviderDify # noqa: F401
+                        from .sources.dify_source import ProviderDify as ProviderDify
                     case "googlegenai_chat_completion":
-                        from .sources.gemini_source import ProviderGoogleGenAI # noqa: F401
+                        from .sources.gemini_source import ProviderGoogleGenAI as ProviderGoogleGenAI
                     case "openai_whisper_api":
-                        from .sources.whisper_api_source import ProviderOpenAIWhisperAPI # noqa: F401
+                        from .sources.whisper_api_source import ProviderOpenAIWhisperAPI as ProviderOpenAIWhisperAPI
                     case "openai_whisper_selfhost":
-                        from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost # noqa: F401
+                        from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost as ProviderOpenAIWhisperSelfHost
                     case "openai_tts_api":
-                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI # noqa: F401
+                        from .sources.openai_tts_api_source import ProviderOpenAITTSAPI as ProviderOpenAITTSAPI
+                    case "fishaudio_tts_api":
+                        from .sources.fishaudio_tts_api_source import ProviderFishAudioTTSAPI as ProviderFishAudioTTSAPI
             except (ImportError, ModuleNotFoundError) as e:
                 logger.critical(f"加载 {provider_cfg['type']}({provider_cfg['id']}) 提供商适配器失败：{e}。可能是因为有未安装的依赖。")
                 continue

astrbot/core/provider/sources/dify_source.py

@@ -31,7 +31,9 @@ class ProviderDify(Provider):
             raise Exception("Dify API 类型不能为空。")
         self.model_name = "dify"
         self.workflow_output_key = provider_config.get("dify_workflow_output_key", "astrbot_wf_output")
-        
+        self.timeout = provider_config.get("timeout", 120)
+        if isinstance(self.timeout, str):
+            self.timeout = int(self.timeout)
         self.conversation_ids = {}
 
 
@@ -78,7 +80,8 @@ class ProviderDify(Provider):
                     query=prompt,
                     user=session_id,
                     conversation_id=conversation_id,
-                    files=files_payload
+                    files=files_payload,
+                    timeout=self.timeout
                 ):
                     logger.debug(f"dify resp chunk: {chunk}")
                     if chunk['event'] == "message" or \
@@ -96,7 +99,8 @@ class ProviderDify(Provider):
                         **session_var
                     },
                     user=session_id,
-                    files=files_payload
+                    files=files_payload,
+                    timeout=self.timeout
                 ):
                     match chunk['event']:
                         case "workflow_started":

astrbot/core/provider/sources/fishaudio_tts_api_source.py

@@ -0,0 +1,105 @@
+import uuid
+import ormsgpack
+from pydantic import BaseModel, conint
+from httpx import AsyncClient
+from typing import Annotated, Literal
+from ..provider import TTSProvider
+from ..entites import ProviderType
+from ..register import register_provider_adapter
+
+
+class ServeReferenceAudio(BaseModel):
+    audio: bytes
+    text: str
+
+
+class ServeTTSRequest(BaseModel):
+    text: str
+    chunk_length: Annotated[int, conint(ge=100, le=300, strict=True)] = 200
+    # 音频格式
+    format: Literal["wav", "pcm", "mp3"] = "mp3"
+    mp3_bitrate: Literal[64, 128, 192] = 128
+    # 参考音频
+    references: list[ServeReferenceAudio] = []
+    # 参考模型 ID
+    # 例如 https://fish.audio/m/7f92f8afb8ec43bf81429cc1c9199cb1/
+    # 其中reference_id为 7f92f8afb8ec43bf81429cc1c9199cb1
+    reference_id: str | None = None
+    # 对中英文文本进行标准化，这可以提高数字的稳定性
+    normalize: bool = True
+    # 平衡模式将延迟减少到300毫秒，但可能会降低稳定性
+    latency: Literal["normal", "balanced"] = "normal"
+
+
+@register_provider_adapter(
+    "fishaudio_tts_api", "FishAudio TTS API", provider_type=ProviderType.TEXT_TO_SPEECH
+)
+class ProviderFishAudioTTSAPI(TTSProvider):
+    def __init__(
+        self,
+        provider_config: dict,
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key: str = provider_config.get("api_key", "")
+        self.character: str = provider_config.get("fishaudio-tts-character", "可莉")
+        self.api_base: str = provider_config.get(
+            "api_base", "https://api.fish-audio.cn/v1"
+        )
+        self.headers = {
+            "Authorization": f"Bearer {self.chosen_api_key}",
+        }
+        self.set_model(provider_config.get("model", None))
+
+    async def _get_reference_id_by_character(self, character: str) -> str:
+        """
+        获取角色的reference_id
+
+        Args:
+            character: 角色名称
+
+        Returns:
+            reference_id: 角色的reference_id
+
+        exception:
+            APIException: 获取语音角色列表为空
+        """
+        sort_options = ["score", "task_count", "created_at"]
+        async with AsyncClient(base_url=self.api_base.replace("/v1", "")) as client:
+            for sort_by in sort_options:
+                params = {"title": character, "sort_by": sort_by}
+                response = await client.get(
+                    "/model", params=params, headers=self.headers
+                )
+                resp_data = response.json()
+                if resp_data["total"] == 0:
+                    continue
+                for item in resp_data["items"]:
+                    if character in item["title"]:
+                        return item["_id"]
+            return None
+
+    async def _generate_request(self, text: str) -> dict:
+        return ServeTTSRequest(
+            text=text,
+            format="wav",
+            reference_id=await self._get_reference_id_by_character(self.character),
+        )
+
+    async def get_audio(self, text: str) -> str:
+        path = f"data/temp/fishaudio_tts_api_{uuid.uuid4()}.wav"
+        self.headers["content-type"] = "application/msgpack"
+        request = await self._generate_request(text)
+        async with AsyncClient(base_url=self.api_base).stream(
+            "POST",
+            "/tts",
+            headers=self.headers,
+            content=ormsgpack.packb(request, option=ormsgpack.OPT_SERIALIZE_PYDANTIC),
+        ) as response:
+            if response.headers["content-type"] == "audio/wav":
+                with open(path, "wb") as f:
+                    async for chunk in response.aiter_bytes():
+                        f.write(chunk)
+                return path
+            text = await response.aread()
+            raise Exception(f"Fish Audio API请求失败: {text}")

astrbot/core/provider/sources/gemini_source.py

@@ -48,7 +48,12 @@ class SimpleGoogleGenAIClient():
         logger.debug(f"payload: {payload}")
         request_url = f"{self.api_base}/v1beta/models/{model}:generateContent?key={self.api_key}"
         async with self.client.post(request_url, json=payload, timeout=self.timeout) as resp:
-            response = await resp.json()
+            try:
+                response = await resp.json()
+            except Exception as e:
+                text = await resp.text()
+                logger.error(f"gemini 返回了非 json 数据: {text}")
+                raise e
             return response
 
 
@@ -181,9 +186,9 @@ class ProviderGoogleGenAI(Provider):
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
-                retry_cnt = 10
+                retry_cnt = 20
                 while retry_cnt > 0:
-                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    logger.warning(f"请求失败：{e}。上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
                     try:
                         await self.pop_record(context_query)
                         llm_response = await self._query(payloads, func_tool)
@@ -231,6 +236,9 @@ class ProviderGoogleGenAI(Provider):
                     image_data = await self.encode_image_bs64(image_path)
                 else:
                     image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                 user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
             return user_content
         else:

astrbot/core/provider/sources/openai_source.py

@@ -80,12 +80,14 @@ class ProviderOpenAIOfficial(Provider):
             raise Exception("API 返回的 completion 为空。")
         choice = completion.choices[0]
         
+        llm_response = LLMResponse("assistant")
+                
         if choice.message.content:
             # text completion
             completion_text = str(choice.message.content).strip()
-
-            return LLMResponse("assistant", completion_text, raw_completion=completion)
-        elif choice.message.tool_calls:
+            llm_response.completion_text = completion_text
+        
+        if choice.message.tool_calls:
             # tools call (function calling)
             args_ls = []
             func_name_ls = []
@@ -95,16 +97,21 @@ class ProviderOpenAIOfficial(Provider):
                         args = json.loads(tool_call.function.arguments)
                         args_ls.append(args)
                         func_name_ls.append(tool_call.function.name)
-            return LLMResponse(role="tool", tools_call_args=args_ls, tools_call_name=func_name_ls, raw_completion=completion)
-        else:
+            llm_response.role = "tool"
+            llm_response.tools_call_args = args_ls
+            llm_response.tools_call_name = func_name_ls
+
+        if not llm_response.completion_text and not llm_response.tools_call_args:
             logger.error(f"API 返回的 completion 无法解析：{completion}。")
-            raise Exception("Internal Error")
+            raise Exception(f"API 返回的 completion 无法解析：{completion}。")
+        
+        return llm_response
 
     async def text_chat(
         self,
         prompt: str,
         session_id: str=None,
-        image_urls: List[str]=None,
+        image_urls: List[str]=[],
         func_tool: FuncCall=None,
         contexts=[],
         system_prompt=None,
@@ -135,15 +142,16 @@ class ProviderOpenAIOfficial(Provider):
             # 尝试删除所有 image
             new_contexts = await self._remove_image_from_context(context_query)
             payloads['messages'] = new_contexts
+            context_query = new_contexts
             llm_response = await self._query(payloads, func_tool)
         except Exception as e:
             if "maximum context length" in str(e):
                 # 重试 10 次
-                retry_cnt = 10
+                retry_cnt = 20
                 while retry_cnt > 0:
-                    logger.warning("上下文长度超过限制。尝试弹出最早的记录然后重试。")
+                    logger.warning(f"上下文长度超过限制。尝试弹出最早的记录然后重试。当前记录条数: {len(context_query)}")
                     try:
-                        await self.pop_record(session_id)
+                        await self.pop_record(context_query)
                         llm_response = await self._query(payloads, func_tool)
                         break
                     except Exception as e:
@@ -235,6 +243,9 @@ class ProviderOpenAIOfficial(Provider):
                     image_data = await self.encode_image_bs64(image_path)
                 else:
                     image_data = await self.encode_image_bs64(image_url)
+                if not image_data:
+                    logger.warning(f"图片 {image_url} 得到的结果为空，将忽略。")
+                    continue
                 user_content["content"].append({"type": "image_url", "image_url": {"url": image_data}})
             return user_content
         else:

astrbot/core/star/register/star_handler.py

@@ -68,12 +68,14 @@ def register_command(command_name: str = None, *args, **kwargs):
         add_to_event_filters = True
     
     def decorator(awaitable):
+        if not add_to_event_filters:
+            kwargs['sub_command'] = True # 打一个标记，表示这是一个子指令，再 wakingstage 阶段这个 handler 将会直接被跳过（其父指令会接管）
         handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
         new_command.init_handler_md(handler_md)
         if add_to_event_filters:
             # 裸指令
             handler_md.event_filters.append(new_command)
-        
+             
         return awaitable
 
     return decorator
@@ -116,7 +118,7 @@ class RegisteringCommandable():
 def register_event_message_type(event_message_type: EventMessageType, **kwargs):
     '''注册一个 EventMessageType'''
     def decorator(awaitable):
-        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, kwargs)
+        handler_md = get_handler_or_create(awaitable, EventType.AdapterMessageEvent, **kwargs)
         handler_md.event_filters.append(EventMessageTypeFilter(event_message_type))
         return awaitable
 

astrbot/core/utils/dify_api_client.py

@@ -35,19 +35,30 @@ class DifyAPIClient:
                 text = await resp.text()
                 raise Exception(f"chat_messages 请求失败：{resp.status}. {text}")
             
+            buffer = ""
             while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                     break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                     
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
     async def workflow_run(
         self,
         inputs: Dict,
@@ -66,20 +77,32 @@ class DifyAPIClient:
         ) as resp:
             if resp.status != 200:
                 text = await resp.text()
-                raise Exception(f"chat_messages 请求失败：{resp.status}. {text}")
+                raise Exception(f"workflow_run 请求失败：{resp.status}. {text}")
+            
+            buffer = ""
             while True:
-                data = await resp.content.read(8192) # 防止数据过大导致高水位报错
-                if not data:
+                # 保持原有的8192字节限制，防止数据过大导致高水位报错
+                chunk = await resp.content.read(8192)
+                if not chunk:
                     break
-                if not data.strip():
-                    continue
-                elif data.startswith(b"data:"):
-                    try:
-                        json_ = json.loads(data[5:])
-                        yield json_
-                    except BaseException:
-                        pass
                     
+                buffer += chunk.decode('utf-8')
+                blocks = buffer.split('\n\n')
+                
+                # 处理完整的数据块
+                for block in blocks[:-1]:
+                    if block.strip() and block.startswith('data:'):
+                        try:
+                            json_str = block[5:]  # 移除 "data:" 前缀
+                            json_obj = json.loads(json_str)
+                            yield json_obj
+                        except json.JSONDecodeError as e:
+                            logger.error(f"JSON解析错误: {str(e)}")
+                            logger.error(f"原始数据块: {json_str}")
+                
+                # 保留最后一个可能不完整的块
+                buffer = blocks[-1] if blocks else ""
+
     async def file_upload(
         self,
         file_path: str,

astrbot/core/utils/t2i/network_strategy.py

@@ -14,11 +14,22 @@ class NetworkRenderStrategy(RenderStrategy):
             base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
         self.BASE_RENDER_URL = base_url
         self.TEMPLATE_PATH = os.path.join(os.path.dirname(__file__), "template")
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"
 
     def set_endpoint(self, base_url: str):
         if not base_url:
             base_url = ASTRBOT_T2I_DEFAULT_ENDPOINT
         self.BASE_RENDER_URL = base_url
+        
+        if self.BASE_RENDER_URL.endswith("/"):
+            self.BASE_RENDER_URL = self.BASE_RENDER_URL[:-1]
+        if not self.BASE_RENDER_URL.endswith("text2img"):
+            self.BASE_RENDER_URL += "/text2img"
+
 
     async def render_custom_template(self, tmpl_str: str, tmpl_data: dict, return_url: bool=True) -> str:
         '''使用自定义文转图模板'''

astrbot/core/zip_updator.py

@@ -110,7 +110,7 @@ class RepoZipUpdator():
         releases = await self.fetch_release_info(url=release_url)
         if not releases:
             # download from the default branch directly. 
-            logger.info(f"未在仓库 {author}/{repo} 中找到任何发布版本，正在从默认分支下载。")
+            logger.info(f"正在从默认分支下载 {author}/{repo} ")
             release_url = f"https://github.com/{author}/{repo}/archive/refs/heads/master.zip"
         else:
             release_url = releases[0]['zipball_url']

astrbot/dashboard/routes/plugin.py

@@ -1,6 +1,5 @@
 import traceback
 import aiohttp
-import uuid
 from .route import Route, Response, RouteContext
 from astrbot.core import logger
 from quart import request
@@ -49,7 +48,7 @@ class PluginRoute(Route):
                 return Response().error(message).__dict__
             return Response().ok(None, "重载成功。").__dict__
         except Exception as e:
-            logger.error(f"/api/extensions/reload: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/reload: {traceback.format_exc()}")
             return Response().error(str(e)).__dict__
     
     async def get_online_plugins(self):
@@ -59,7 +58,6 @@ class PluginRoute(Route):
             urls = [custom]
         else:
             urls = [
-                "https://soulter.github.io/AstrBot_Plugins_Collection/plugins.json",
                 "https://api.soulter.top/astrbot/plugins"
             ]
             
@@ -88,6 +86,7 @@ class PluginRoute(Route):
                 "version": plugin.version,
                 "reserved": plugin.reserved,
                 "activated": plugin.activated,
+                "online_vesion": "",
                 "handlers": await self.get_plugin_handlers_info(plugin.star_handler_full_names),
             }
             _plugin_resp.append(_t)
@@ -190,7 +189,7 @@ class PluginRoute(Route):
             logger.info(f"更新插件 {plugin_name} 成功。")
             return Response().ok(None, "更新成功。").__dict__
         except Exception as e:
-            logger.error(f"/api/extensions/update: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/update: {traceback.format_exc()}")
             return Response().error(str(e)).__dict__
         
     async def off_plugin(self):
@@ -201,7 +200,7 @@ class PluginRoute(Route):
             logger.info(f"停用插件 {plugin_name} 。")
             return Response().ok(None, "停用成功。").__dict__
         except Exception as e:
-            logger.error(f"/api/extensions/off: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/off: {traceback.format_exc()}")
             return Response().error(str(e)).__dict__
 
     async def on_plugin(self):
@@ -212,5 +211,5 @@ class PluginRoute(Route):
             logger.info(f"启用插件 {plugin_name} 。")
             return Response().ok(None, "启用成功。").__dict__
         except Exception as e:
-            logger.error(f"/api/extensions/on: {traceback.format_exc()}")
+            logger.error(f"/api/plugin/on: {traceback.format_exc()}")
             return Response().error(str(e)).__dict__

changelogs/v3.4.22.md

@@ -0,0 +1,12 @@
+# What's Changed
+
+1. fix: 400 Bad Request: The browser (or proxy) sent a request that this server could not understand. #396
+2. remove: 移除了 put_history_to_prompt。当主动回复时，将群聊记录将自动放入prompt，当未主动回复但是开启群聊增强时，群聊记录将放入system prompt
+3. fix: 插件错误信息点击关闭没反应 #394
+4. fix: 自部署文转图不生效 #352
+5. fix: Google Search 报 429 错误时，放宽 Exception 至其他搜索引擎 #405
+6. fix: 使用 Google Gemini （OpenAI 兼容）的部分情况下联网搜索等函数调用工具没被调用 #342
+7. fix: 修复尝试弹出最早的记录失效的问题
+8. fix: 移除了分段回复llm提示词辅助
+9. perf: 当图片数据为空时不加入上下文 #379
+10. 修复 dify 返回的结果带有多行数据时的 json 解析异常导致返回值为空的问题 #298 by @zhaolj

changelogs/v3.4.23.md

@@ -0,0 +1,11 @@
+# What's Changed
+
+0. ✨ 新增: 支持 海豚 AI（FishAudio） TTS API #433 by @Cvandia
+1. 🐛 修复: 当群聊主动回复时，不会带上人格的Prompt #419
+2. ✨ 新增: 支持展示插件是否有更新
+3. 👌 优化: 增加DIFY超时时间 #422
+4. 🐛 修复: 自部署文转图不生效 #352
+5. 🐛 修复: 修复 qq 回复别人的时候也会触发机器人, Onebot at 使用 string #330
+6. 👌 优化: 增加DIFY超时时间 #422
+7. 🐛 修复: 重启gewe的时候机器人会疯狂发消息 #421
+8. 🐛 修复: 修复子指令设置permission之后会导致其一定会被执行 #427

dashboard/src/components/shared/ExtensionCard.vue

@@ -2,7 +2,8 @@
 const props = defineProps({
   title: String,
   link: String,
-  logo: String
+  logo: String,
+  has_update: Boolean,
 });
 
 const open = (link: string | undefined) => {
@@ -17,6 +18,7 @@ const open = (link: string | undefined) => {
         <img v-if="logo" :src="logo" alt="logo" style="width: 40px; height: 40px; margin-right: 8px;">
         <v-card-title style="font-size: 16px;">{{ props.title }}</v-card-title>
         <v-spacer></v-spacer>
+        <v-icon color="success" v-if="has_update">mdi-arrow-up-bold</v-icon>
         <v-btn size="small" text="Read" variant="flat" border  @click="open(props.link)">帮助</v-btn>
       </div>
     </v-card-item>

dashboard/src/views/ExtensionPage.vue

@@ -25,30 +25,44 @@ import { max } from 'date-fns';
                 <v-icon>mdi-alert-circle</v-icon>
               </v-btn>
             </template>
-            <v-card>
-              <v-card-title class="headline">错误信息</v-card-title>
-              <v-card-text>{{ extension_data.message }}
-                <br>
-                <small>详情请检查控制台</small>
-              </v-card-text>
 
-              <v-card-actions>
-                <v-spacer></v-spacer>
-                <v-btn color="primary" text>关闭</v-btn>
-              </v-card-actions>
-            </v-card>
+            <template v-slot:default="{ isActive }">
+              <v-card>
+                <v-card-title class="headline">错误信息</v-card-title>
+                <v-card-text>{{ extension_data.message }}
+                  <br>
+                  <small>详情请检查控制台</small>
+                </v-card-text>
+
+                <v-card-actions>
+                  <v-spacer></v-spacer>
+                  <v-btn color="primary" text @click="isActive.value = false">关闭</v-btn>
+                </v-card-actions>
+              </v-card>
+            </template>
+
           </v-dialog>
         </div>
       </div>
     </v-col>
     <v-col cols="12" md="6" lg="3" v-for="extension in extension_data.data">
-      <ExtensionCard :key="extension.name" :title="extension.name" :link="extension.repo" :logo="extension?.logo"
+      <ExtensionCard :key="extension.name" :title="extension.name" :link="extension.repo" :logo="extension?.logo" :has_update="extension.has_update"
         style="margin-bottom: 4px;">
-        <div style="min-height: 135px; max-height: 135px; overflow: none;">
-          <span style="font-weight: bold;">By @{{ extension.author }}</span>
-          <span> | 插件有 {{ extension.handlers.length }} 个行为</span>
+        <div style="min-height: 140px; max-height: 140px; overflow: none;">
+          <div>
+            <span style="font-weight: bold;">By @{{ extension.author }}</span>
+            <span> | 插件有 {{ extension.handlers.length }} 个行为</span>
+          </div>
+          <span> 当前: <v-chip size="small" color="primary">{{ extension.version }}</v-chip>
+            <span v-if="extension.online_version">
+              | 最新: <v-chip size="small" color="primary">{{ extension.online_version }}</v-chip>
+            </span>
+            <span v-if="extension.has_update" style="font-weight: bold;">有更新
+            </span>
+          </span>
           <p style="margin-top: 8px;">{{ extension.desc }}</p>
-          <a style="font-size: 12px; cursor: pointer; text-decoration: underline; color: #555;" @click="reloadPlugin(extension.name)">重载插件</a>
+          <a style="font-size: 12px; cursor: pointer; text-decoration: underline; color: #555;"
+            @click="reloadPlugin(extension.name)">重载插件</a>
         </div>
         <div class="d-flex align-center gap-2 " style="overflow-x: auto;">
           <v-btn v-if="!extension.reserved" class="text-none mr-2" size="small" text="Read" variant="flat" border
@@ -324,6 +338,8 @@ export default {
         { title: '作者', value: 'author' },
         { title: '操作', value: 'actions', sortable: false }
       ],
+
+      alreadyCheckUpdate: false
     }
   },
   mounted() {
@@ -362,10 +378,29 @@ export default {
     getExtensions() {
       axios.get('/api/plugin/get').then((res) => {
         this.extension_data = res.data;
-
         this.checkAlreadyInstalled();
+        this.checkUpdate()
       });
     },
+
+    checkUpdate() {
+      // 遍历 extension_data 和 pluginMarketData，检查是否有更新\
+      for (let i = 0; i < this.extension_data.data.length; i++) {
+        for (let j = 0; j < this.pluginMarketData.length; j++) {
+          console.log(this.extension_data.data[i].repo, this.pluginMarketData[j].repo);
+          if (this.extension_data.data[i].repo === this.pluginMarketData[j].repo ||
+            this.extension_data.data[i].name === this.pluginMarketData[j].name) {
+            this.extension_data.data[i].online_version = this.pluginMarketData[j].version;
+            if (this.extension_data.data[i].version !== this.pluginMarketData[j].version && this.pluginMarketData[j].version !== "未知") {
+              this.extension_data.data[i].has_update = true;
+            } else {
+              this.extension_data.data[i].has_update = false;
+            }
+          }
+        }
+      }
+    },
+
     newExtension() {
       if (this.extension_url === "" && this.upload_file === null) {
         this.toast("请填写插件链接或上传插件文件", "error");
@@ -381,7 +416,7 @@ export default {
       if (this.upload_file !== null) {
         this.toast("正在从文件安装插件", "primary");
         const formData = new FormData();
-        formData.append('file', this.upload_file[0]);
+        formData.append('file', this.upload_file);
         axios.post('/api/plugin/install-upload', formData, {
           headers: {
             'Content-Type': 'multipart/form-data'
@@ -524,11 +559,13 @@ export default {
             "desc": res.data.data[key].desc,
             "author": res.data.data[key].author,
             "repo": res.data.data[key].repo,
-            "installed": false
+            "installed": false,
+            "version": res.data.data[key]?.version ? res.data.data[key].version : "未知",
           })
         }
         this.pluginMarketData = data;
         this.checkAlreadyInstalled();
+        this.checkUpdate();
       }).catch((err) => {
         this.toast("获取插件市场数据失败: " + err, "error");
       });

packages/astrbot/long_term_memory.py

@@ -33,7 +33,7 @@ class LongTermMemory:
         self.ar_possibility = self.active_reply["possibility_reply"]
         self.ar_prompt = self.active_reply.get("prompt", "")
         
-        self.put_history_to_prompt = self.config["put_history_to_prompt"]
+        # self.put_history_to_prompt = self.config["put_history_to_prompt"]
         
     async def remove_session(self, event: AstrMessageEvent) -> int:
         cnt = 0
@@ -110,11 +110,11 @@ class LongTermMemory:
         
         chats_str = '\n---\n'.join(self.session_chats[event.unified_msg_origin])
         
-        if self.put_history_to_prompt:
+        if self.enable_active_reply:
             prompt = req.prompt
             req.prompt = f"You are now in a chatroom. The chat history is as follows:\n{chats_str}"
             req.prompt += f"\nNow, a new message is coming: `{prompt}`. Please react to it. Only output your response and do not output any other information."
-            req.contexts = [] # 清空上下文，当使用了群聊增强，所有聊天记录都在一个prompt中。
+            req.contexts = [] # 清空上下文，当使用了主动回复，所有聊天记录都在一个prompt中。
         else:
             req.system_prompt += "You are now in a chatroom. The chat history is as follows: \n"
             req.system_prompt += chats_str

packages/astrbot/main.py

@@ -6,6 +6,7 @@ import astrbot.api.star as star
 import astrbot.api.event.filter as filter
 from astrbot.api.event import AstrMessageEvent, MessageEventResult
 from astrbot.api import sp
+from astrbot.api.platform import MessageType
 from astrbot.api.provider import Personality, ProviderRequest, LLMResponse
 from astrbot.core.utils.io import download_dashboard, get_dashboard_version
 from astrbot.core.star.star_handler import star_handlers_registry, StarHandlerMetadata
@@ -80,6 +81,7 @@ AstrBot 指令:
 /persona: 人格情景(op)
 /tool ls: 函数工具
 /key: API Key(op)
+/websearch: 网页搜索
 
 [其他]
 /set <变量名> <值>: 为会话定义变量。适用于 Dify 工作流输入。
@@ -227,6 +229,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("wl")
     async def wl(self, event: AstrMessageEvent, sid: str):
+        '''添加白名单。wl <sid>'''
         self.context.get_config()['platform_settings']['id_whitelist'].append(sid)
         self.context.get_config().save_config()
         event.set_result(MessageEventResult().message("添加白名单成功。"))
@@ -234,6 +237,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("dwl")
     async def dwl(self, event: AstrMessageEvent, sid: str):
+        '''删除白名单。dwl <sid>'''
         try:
             self.context.get_config()['platform_settings']['id_whitelist'].remove(sid)
             self.context.get_config().save_config()
@@ -274,7 +278,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
     @filter.permission_type(filter.PermissionType.ADMIN)
     @filter.command("reset")
     async def reset(self, message: AstrMessageEvent):
-        
+        '''重置 LLM 会话'''
         if not self.context.get_using_provider():
             message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
             return
@@ -298,7 +302,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
 
     @filter.command("model")
     async def model_ls(self, message: AstrMessageEvent, idx_or_name: Union[int, str] = None):
-                
+        '''查看或者切换模型'''
         if not self.context.get_using_provider():
             message.set_result(MessageEventResult().message("未找到任何 LLM 提供商。请先配置。"))
             return
@@ -629,7 +633,7 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
                     session_curr_cid = await self.context.conversation_manager.get_curr_conversation_id(event.unified_msg_origin)
                     
                     if not session_curr_cid:
-                        logger.error("当前未处于对话状态，无法主动回复，请使用 /switch 切换或者 /new 创建。")
+                        logger.error("当前未处于对话状态，无法主动回复，请确保 平台设置->会话隔离(unique_session) 未开启，并使用 /switch 切换或者 /new 创建一个会话。")
                         return
                     
                     conv = await self.context.conversation_manager.get_conversation(
@@ -646,7 +650,8 @@ UID: {user_id} 此 ID 可用于设置管理员。/op <UID> 授权管理员, /deo
                         prompt=prompt,
                         func_tool_manager=self.context.get_llm_tool_manager(),
                         session_id=event.session_id,
-                        contexts=history if history else []
+                        contexts=history if history else [],
+                        conversation=conv,
                     )
                 except BaseException as e:
                     logger.error(f"主动回复失败: {e}")

packages/web_searcher/engines/__init__.py

@@ -1,9 +1,30 @@
 import random
-from .config import HEADERS, USER_AGENTS
 from bs4 import BeautifulSoup
 from aiohttp import ClientSession
 from dataclasses import dataclass
 from typing import List
+import urllib.parse
+
+HEADERS = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0',
+    'Accept': '*/*', 
+    'Connection': 'keep-alive', 
+    'Accept-Language': 'en-GB,en;q=0.5'
+}
+
+USER_AGENT_BING = 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0'
+USER_AGENTS = [
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
+    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
+    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
+]
 
 
 @dataclass
@@ -38,11 +59,13 @@ class SearchEngine():
         if data:
             async with ClientSession() as session:
                 async with session.post(url, headers=headers, data=data, timeout=self.TIMEOUT) as resp:
-                    return await resp.text(encoding="utf-8")
+                    ret = await resp.text(encoding="utf-8")
+                    return ret
         else:
             async with ClientSession() as session:
                 async with session.get(url, headers=headers, timeout=self.TIMEOUT) as resp:
-                    return await resp.text(encoding="utf-8")
+                    ret = await resp.text(encoding="utf-8")
+                    return ret
                 
     
     def tidy_text(self, text: str) -> str:
@@ -53,6 +76,8 @@ class SearchEngine():
 
 
     async def search(self, query: str, num_results: int) -> List[SearchResult]:
+        query = urllib.parse.quote(query)
+        
         try:
             resp = await self._get_next_page(query)
             soup = BeautifulSoup(resp, 'html.parser')

packages/web_searcher/engines/bing.py

@@ -1,11 +1,11 @@
 from typing import List
-from .engine import SearchEngine, SearchResult
-from .config import USER_AGENT_BING
+from . import SearchEngine, SearchResult
+from . import USER_AGENT_BING
 
 class Bing(SearchEngine):
     def __init__(self) -> None:
         super().__init__()
-        self.base_url = "https://www.bing.com"
+        self.base_urls = ["https://cn.bing.com", "https://www.bing.com"]
         self.headers.update({'User-Agent': USER_AGENT_BING})
 
     def _set_selector(self, selector: str):
@@ -19,11 +19,17 @@ class Bing(SearchEngine):
         return selectors[selector]
 
     async def _get_next_page(self, query) -> str:
-        if self.page == 1:
-            await self._get_html(self.base_url)
-        url = f'{self.base_url}/search?q={query}&form=QBLH&sp=-1&lq=0&pq=hi&sc=10-2&qs=n&sk=&cvid=DE75965E2D6346D681288933984DE48F&ghsh=0&ghacc=0&ghpl='
-        return await self._get_html(url, None)
-    
+        # if self.page == 1:
+        #     await self._get_html(self.base_url)
+        for base_url in self.base_urls:
+            try:
+                url = f'{base_url}/search?q={query}'
+                return await self._get_html(url, None)
+            except Exception as _:
+                self.base_url = base_url
+                continue
+        raise Exception("Bing search failed")
+
     async def search(self, query: str, num_results: int) -> List[SearchResult]:
         results = await super().search(query, num_results)
         for result in results:

packages/web_searcher/engines/config.py

@@ -1,20 +0,0 @@
-HEADERS = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0',
-    'Accept': '*/*', 
-    'Connection': 'keep-alive', 
-    'Accept-Language': 'en-GB,en;q=0.5'
-}
-
-USER_AGENT_BING = 'Mozilla/5.0 (Windows NT 6.1; rv:84.0) Gecko/20100101 Firefox/84.0'
-USER_AGENTS = [
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
-    'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
-    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
-    'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
-]

packages/web_searcher/engines/google.py

@@ -1,7 +1,7 @@
 import os
 from googlesearch import search
 
-from .engine import SearchEngine, SearchResult
+from . import SearchEngine, SearchResult
 
 from typing import List
 

packages/web_searcher/engines/sogo.py

@@ -1,8 +1,8 @@
 import random
 import re
 from bs4 import BeautifulSoup
-from .engine import SearchEngine, SearchResult
-from .config import USER_AGENTS
+from . import SearchEngine, SearchResult
+from . import USER_AGENTS
 
 from typing import List
 

packages/web_searcher/main.py

@@ -9,7 +9,7 @@ from .engines.sogo import Sogo
 from .engines.google import Google
 from readability import Document
 from bs4 import BeautifulSoup
-from .engines.config import HEADERS, USER_AGENTS
+from .engines import HEADERS, USER_AGENTS
 
 
 @star.register(name="astrbot-web-searcher", desc="让 LLM 具有网页检索能力", author="Soulter", version="1.14.514")
@@ -85,19 +85,19 @@ class Main(star.Star):
         RESULT_NUM = 5
         try:
             results = await self.google.search(query, RESULT_NUM)
-        except BaseException as e:
+        except Exception as e:
             logger.error(f"google search error: {e}, try the next one...")
         if len(results) == 0:
             logger.debug("search google failed")
             try:
                 results = await self.bing_search.search(query, RESULT_NUM)
-            except BaseException as e:
+            except Exception as e:
                 logger.error(f"bing search error: {e}, try the next one...")
         if len(results) == 0:
             logger.debug("search bing failed")
             try:
                 results = await self.sogo_search.search(query, RESULT_NUM)
-            except BaseException as e:
+            except Exception as e:
                 logger.error(f"sogo search error: {e}")
         if len(results) == 0:
             logger.debug("search sogo failed")

requirements.txt

@@ -16,4 +16,5 @@ pyjwt
 apscheduler
 docstring_parser
 aiodocker
-silk-python
+silk-python
+ormsgpack