🎉 chore: bump to v3.4.6

feat: 支持并完善服务提供商默认配置模板接口
perf: 面板文件更新检查和引导提示和AboutPage
2025-01-13 02:17:23 +08:00 · 2025-01-13 02:05:57 +08:00 · 2025-01-12 13:01:40 +08:00 · 2025-01-12 12:23:27 +08:00 · 2025-01-12 12:18:19 +08:00 · 2025-01-12 11:45:39 +08:00
45 changed files with 995 additions and 183 deletions
@@ -1,6 +1,8 @@

 <p align="center">
-<img width=200 src="https://github.com/user-attachments/assets/3dd6a669-0830-4db4-b821-c8b279ea19a6"/>
+
+<img src="https://github.com/user-attachments/assets/de10f24d-cd64-433a-90b8-16c0a60de24a" width=500>
+
 </p>

 <div align="center">
@@ -26,7 +28,8 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 ## ✨ 多消息平台部署

 1. QQ 群、QQ 频道、微信个人号、Telegram。
-2. 支持文本转图片，Markdown 渲染。
+2. 内置 Web Chat，即使不部署到消息平台也能聊天。
+3. 支持文本转图片，Markdown 渲染。
   
 ## ✨ 多 LLM 配置

@@ -35,6 +38,7 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 3. 支持 LLMTuner 载入微调模型。
 4. 支持 Ollama 载入自部署模型。
 4. 支持网页搜索（Web Search）、自然语言待办提醒。
+5. 支持 Whisper 语音转文字

 ## ✨ 管理面板

@@ -52,58 +56,14 @@ AstrBot 是一个松耦合、异步、支持多消息平台部署、具有易用
 基于 Docker 的沙箱化代码执行器（Beta 测试中）

 > [!NOTE]
-> 文件输入/输出目前仅支持 Napcat（QQ）
-
-<div align='center'>
-<img src="https://github.com/user-attachments/assets/700a545e-7450-4f23-90ff-af6d0d60e501" height=300>
-
-<img src="https://github.com/user-attachments/assets/0b0c5344-e98b-4902-92ad-fe9f0bb10c2a" height=300>
-
-<img src="https://github.com/user-attachments/assets/b9b98ff4-8630-46fb-9a39-ecbad9d601ae" height=300>
-
-<img src="https://github.com/user-attachments/assets/9fe6e44c-e4f6-4347-9d5f-281677d47feb" height=300>
-
-</div>
-
-
-
-## ✨ Demo
+> 文件输入/输出目前仅测试了 Napcat(QQ), Lagrange(QQ)

 <div align='center'>

-<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
-
-_✨ 多模态、网页搜索、长文本转图片（可配置） ✨_
-
-<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
-
-_✨ 自然语言待办事项 ✨_
-
-<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
-<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
-
-_✨ 插件系统——部分插件展示 ✨_
-
-<img src="https://github.com/user-attachments/assets/caadf2bd-a0ee-43d0-a95e-566d63e3e34d" height=330>
-<img src="https://github.com/user-attachments/assets/b418f281-e920-49db-9fe1-d6a13ce28a84" height=350>
-
-_✨ 管理面板 ✨_
-
-
-
+<img src="https://github.com/user-attachments/assets/4ee688d9-467d-45c8-99d6-368f9a8a92d8" width="600">

 </div>

-
-<!-- ## ✨ ATRI [Beta 测试]
-
-该功能作为插件载入。插件仓库地址：[astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
-
-1. 基于《ATRI ~ My Dear Moments》主角 ATRI 角色台词作为微调数据集的 `Qwen1.5-7B-Chat Lora` 微调模型。
-2. 长期记忆
-3. 表情包理解与回复
-4. TTS
-    -->
 ## ✨ 云部署

 [![Run on Repl.it](https://repl.it/badge/github/Soulter/AstrBot)](https://repl.it/github/Soulter/AstrBot)
@@ -124,3 +84,46 @@ _✨ 管理面板 ✨_
 - Star 这个项目！
 - 在[爱发电](https://afdian.com/a/soulter)支持我！
 - 在[微信](https://drive.soulter.top/f/pYfA/d903f4fa49a496fda3f16d2be9e023b5.png)支持我~
+
+
+
+## ✨ Demo
+
+<div align='center'>
+
+<img src="https://github.com/user-attachments/assets/0378f407-6079-4f64-ae4c-e97ab20611d2" height=500>
+
+_✨ 多模态、网页搜索、长文本转图片（可配置） ✨_
+
+<img src="https://github.com/user-attachments/assets/8ec12797-e70f-460a-959e-48eca39ca2bb" height=100>
+
+_✨ 自然语言待办事项 ✨_
+
+<img src="https://github.com/user-attachments/assets/e137a9e1-340a-4bf2-bb2b-771132780735" height=150>
+<img src="https://github.com/user-attachments/assets/480f5e82-cf6a-4955-a869-0d73137aa6e1" height=150>
+
+_✨ 插件系统——部分插件展示 ✨_
+
+<img src="https://github.com/user-attachments/assets/592a8630-14c7-4e06-b496-9c0386e4f36c" width=600>
+
+_✨ 管理面板 ✨_
+
+![webchat](https://drive.soulter.top/f/vlsA/ezgif-5-fb044b2542.gif)
+
+_✨ 内置 Web Chat，在线与机器人交互 ✨_
+
+</div>
+
+
+<!-- ## ✨ ATRI [Beta 测试]
+
+该功能作为插件载入。插件仓库地址：[astrbot_plugin_atri](https://github.com/Soulter/astrbot_plugin_atri)
+
+1. 基于《ATRI ~ My Dear Moments》主角 ATRI 角色台词作为微调数据集的 `Qwen1.5-7B-Chat Lora` 微调模型。
+2. 长期记忆
+3. 表情包理解与回复
+4. TTS
+    -->
+
+_アトリは、高性能ですから!_
+
@@ -1,2 +1,2 @@
-from astrbot.core.provider import Provider, Personality, ProviderMetaData
-from astrbot.core.provider.entites import ProviderRequest
+from astrbot.core.provider import Provider, STTProvider, Personality
+from astrbot.core.provider.entites import ProviderRequest, ProviderType, ProviderMetaData
@@ -20,6 +20,6 @@ if os.environ.get('TESTING', ""):
 db_helper = SQLiteDatabase(DB_PATH)
 sp = SharedPreferences() # 简单的偏好设置存储
 pip_installer = PipInstaller(astrbot_config.get('pip_install_arg', ''))
-web_chat_queue = asyncio.Queue()
-web_chat_back_queue = asyncio.Queue()
+web_chat_queue = asyncio.Queue(maxsize=32)
+web_chat_back_queue = asyncio.Queue(maxsize=32)
 WEBUI_SK = "Advanced_System_for_Text_Response_and_Bot_Operations_Tool"
@@ -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 = "3.4.4"
+VERSION = "3.4.6"
 DB_PATH = "data/data_v3.db"

 # 默认配置
@@ -33,6 +33,10 @@ DEFAULT_CONFIG = {
        "default_personality": "如果用户寻求帮助或者打招呼，请告诉他可以用 /help 查看 AstrBot 帮助。",
        "prompt_prefix": "",
    },
+    "provider_stt_settings": {
+      "enable": False,
+      "provider_id": "",  
+    },
    "content_safety": {
        "internal_keywords": {"enable": True, "extra_keywords": []},
        "baidu_aip": {"enable": False, "app_id": "", "api_key": "", "secret_key": ""},
@@ -315,9 +319,30 @@ CONFIG_METADATA_2 = {
                        "dify_api_key": "",
                        "dify_api_base": "https://api.dify.ai/v1",
                        "dify_workflow_output_key": "",
+                    },
+                    "whisper(API)": {
+                        "id": "whisper",
+                        "type": "openai_whisper_api",
+                        "enable": False,
+                        "api_key": "",
+                        "api_base": "",
+                        "model": "whisper-1",
+                    },
+                    "whisper(本地加载)": {
+                        "whisper_hint": "(不用修改我)",
+                        "enable": False,
+                        "id": "whisper",
+                        "type": "openai_whisper_selfhost",
+                        "model": "tiny",
                    }
                },
                "items": {
+                    "whisper_hint": {
+                        "description": "本地部署 Whisper 模型须知",
+                        "type": "string",
+                        "hint": "启用前请 pip 安装 openai-whisper 库（N卡用户大约下载 2GB，主要是 torch 和 cuda，CPU 用户大约下载 1 GB），并且安装 ffmpeg。否则将无法正常转文字。",
+                        "obvious_hint": True
+                    },
                    "id": {
                        "description": "ID",
                        "type": "string",
@@ -416,7 +441,8 @@ CONFIG_METADATA_2 = {
                    "enable": {
                        "description": "启用大语言模型聊天",
                        "type": "bool",
-                        "hint": "是否启用大语言模型聊天。默认启用",
+                        "hint": "如需切换大语言模型提供商，请使用 `/provider` 命令。",
+                        "obvious_hint": True
                    },
                    "wake_prefix": {
                        "description": "LLM 聊天额外唤醒前缀",
@@ -450,6 +476,23 @@ CONFIG_METADATA_2 = {
                    },
                },
            },
+            "provider_stt_settings": {
+                "description": "语音转文本(STT)",
+                "type": "object",
+                "items": {
+                    "enable": {
+                        "description": "启用语音转文本(STT)",
+                        "type": "bool",
+                        "hint": "启用前请在 服务提供商配置 处创建支持 语音转文本任务 的提供商。如 whisper。",
+                        "obvious_hint": True
+                    },
+                    "provider_id": {
+                        "description": "提供商 ID，不填则默认第一个STT提供商",
+                        "type": "string",
+                        "hint": "语音转文本提供商 ID。如果不填写将使用载入的第一个提供商。",
+                    },
+                },
+            },
        },
    },
    "misc_config_group": {
@@ -123,7 +123,7 @@ class Record(BaseMessageComponent):
    proxy: T.Optional[bool] = True
    timeout: T.Optional[int] = 0
    # 额外
-    path: T.Optional[str]
+    path: T.Optional[str] # 用这个

    def __init__(self, file: T.Optional[str], **_):
        for k in _.keys():
@@ -3,6 +3,7 @@ from astrbot.core.message.message_event_result import MessageEventResult, EventR
 from .waking_check.stage import WakingCheckStage
 from .whitelist_check.stage import WhitelistCheckStage
 from .content_safety_check.stage import ContentSafetyCheckStage
+from .preprocess_stage.stage import PreProcessStage
 from .process_stage.stage import ProcessStage
 from .result_decorate.stage import ResultDecorateStage
 from .respond.stage import RespondStage
@@ -12,6 +13,7 @@ STAGES_ORDER = [
    "WhitelistCheckStage", # 检查是否在群聊/私聊白名单
    "RateLimitCheckStage", # 检查会话是否超过频率限制
    "ContentSafetyCheckStage", # 检查内容安全
+    "PreProcessStage", # 预处理
    "ProcessStage", # 交由 Stars 处理（a.k.a 插件），或者 LLM 调用
    "ResultDecorateStage", # 处理结果，比如添加回复前缀、t2i、转换为语音 等
    "RespondStage" # 发送消息
@@ -21,6 +23,7 @@ __all__ = [
    "WakingCheckStage",
    "WhitelistCheckStage",
    "ContentSafetyCheckStage",
+    "PreProcessStage",
    "ProcessStage",
    "ResultDecorateStage",
    "RespondStage",
@@ -0,0 +1,57 @@
+import traceback
+import asyncio
+from typing import Union, AsyncGenerator
+from ..stage import Stage, register_stage
+from ..context import PipelineContext
+from astrbot.core.platform.astr_message_event import AstrMessageEvent
+from astrbot.core import logger
+from astrbot.core.message.components import Plain, Record
+
+@register_stage
+class PreProcessStage(Stage):
+    
+    async def initialize(self, ctx: PipelineContext) -> None:
+        self.ctx = ctx
+        self.config = ctx.astrbot_config
+        self.plugin_manager = ctx.plugin_manager
+        
+        self.stt_settings: dict = self.config.get('provider_stt_settings', {})
+        
+
+    async def process(self, event: AstrMessageEvent) -> Union[None, AsyncGenerator[None, None]]:
+        '''在处理事件之前的预处理'''
+
+        if self.stt_settings.get('enable', False):
+            # STT 处理
+            # TODO: 独立
+            stt_provider = self.plugin_manager.context.provider_manager.curr_stt_provider_inst
+            if stt_provider:
+                message_chain = event.get_messages()
+                for idx, component in enumerate(message_chain):
+                    if isinstance(component, Record) and component.url:
+                        
+                        path = component.url
+                        
+                        path.removeprefix("file:///")
+                        
+                        retry = 5
+                        
+                        for i in range(retry):
+                            try:
+                                result = await stt_provider.get_text(audio_url=path)
+                                if result:
+                                    logger.info("语音转文本结果: " + result)
+                                    message_chain[idx] = Plain(result)
+                                    event.message_str += result
+                                    event.message_obj.message_str += result
+                                break
+                            except FileNotFoundError as e:
+                                # napcat workaround
+                                logger.warning(e)
+                                logger.warning(f"语音文件不存在: {path}, 重试中: {i + 1}/{retry}")
+                                await asyncio.sleep(0.5)
+                                continue
+                            except BaseException as e:
+                                logger.error(traceback.format_exc())
+                                logger.error(f"语音转文本失败: {e}")
+                                break
@@ -41,4 +41,8 @@ class PipelineScheduler():
    async def execute(self, event: AstrMessageEvent):
        '''执行 pipeline'''
        await self._process_stages(event)
+        
+        if not event._has_send_oper and event.get_platform_name() == "webchat":
+            await event.send(None)
+        
        logger.debug("pipeline 执行完毕。")
@@ -1,7 +1,12 @@
 from dataclasses import dataclass
@dataclass
 class PlatformMetadata():
-    name: str # 平台的名称
-    description: str # 平台的描述
+    name: str
+    '''平台的名称'''
+    description: str
+    '''平台的描述'''
    
-    default_config_tmpl: dict = None # 平台的默认配置模板
+    default_config_tmpl: dict = None
+    '''平台的默认配置模板'''
+    adapter_display_name: str = None
+    '''显示在 WebUI 配置页中的平台名称，如空则是 name'''
@@ -7,7 +7,12 @@ platform_registry: List[PlatformMetadata] = []
 platform_cls_map: Dict[str, Type] = {}
 '''维护了平台适配器名称和适配器类的映射'''

-def register_platform_adapter(adapter_name: str, desc: str, default_config_tmpl: dict = None):
+def register_platform_adapter(
+    adapter_name: str, 
+    desc: str, 
+    default_config_tmpl: dict = None,
+    adapter_display_name: str = None
+):
    '''用于注册平台适配器的带参装饰器。
    
    default_config_tmpl 指定了平台适配器的默认配置模板。用户填写好后将会作为 platform_config 传入你的 Platform 类的实现类。 
@@ -26,7 +31,8 @@ def register_platform_adapter(adapter_name: str, desc: str, default_config_tmpl:
        pm = PlatformMetadata(
            name=adapter_name,
            description=desc,
-            default_config_tmpl=default_config_tmpl
+            default_config_tmpl=default_config_tmpl,
+            adapter_display_name=adapter_display_name
        )
        platform_registry.append(pm)
        platform_cls_map[adapter_name] = cls
@@ -13,6 +13,7 @@ from .aiocqhttp_message_event import AiocqhttpMessageEvent
 from astrbot.core.platform.astr_message_event import MessageSesion
 from ...register import register_platform_adapter
 from aiocqhttp.exceptions import ActionFailed
+from astrbot.core.utils.io import download_file

@register_platform_adapter("aiocqhttp", "适用于 OneBot 标准的消息平台适配器，支持反向 WebSockets。")
 class AiocqhttpAdapter(Platform):
@@ -81,22 +82,36 @@ class AiocqhttpAdapter(Platform):
            if t == 'text':
                message_str += m['data']['text'].strip()
            elif t == 'file':
-                try:
-                    # Napcat, LLBot
-                    ret = await self.bot.call_action(action="get_file", file_id=event.message[0]['data']['file_id'])
-                    if not ret.get('file', None):
-                        raise ValueError(f"无法解析文件响应: {ret}")
-                    if not os.path.exists(ret['file']):
-                        raise FileNotFoundError(f"文件不存在: {ret['file']}。如果您使用 Docker 部署了 AstrBot 或者消息协议端(Napcat等),暂时无法获取用户上传的文件。")
+                if m['data']['url'] and m['data']['url'].startswith("http"):
+                    # Lagrange
+                    logger.info("guessing lagrange")
+                    
+                    file_name = m['data'].get('file_name', "file")
+                    path = os.path.join("data/temp", file_name)
+                    await download_file(m['data']['url'], path)
                    
                    m['data'] = {
-                        "file": ret['file'],
-                        "name": ret['file_name']
+                        "file": path,
+                        "name": file_name
                    }
-                except ActionFailed as e:
-                    logger.error(f"获取文件失败: {e}，此消息段将被忽略。")
-                except BaseException as e:
-                    logger.error(f"获取文件失败: {e}，此消息段将被忽略。")
+                
+                else:
+                    try:
+                        # Napcat, LLBot
+                        ret = await self.bot.call_action(action="get_file", file_id=event.message[0]['data']['file_id'])
+                        if not ret.get('file', None):
+                            raise ValueError(f"无法解析文件响应: {ret}")
+                        if not os.path.exists(ret['file']):
+                            raise FileNotFoundError(f"文件不存在: {ret['file']}。如果您使用 Docker 部署了 AstrBot 或者消息协议端(Napcat等),暂时无法获取用户上传的文件。")
+                        
+                        m['data'] = {
+                            "file": ret['file'],
+                            "name": ret['file_name']
+                        }
+                    except ActionFailed as e:
+                        logger.error(f"获取文件失败: {e}，此消息段将被忽略。")
+                    except BaseException as e:
+                        logger.error(f"获取文件失败: {e}，此消息段将被忽略。")
                    
            a = ComponentTypes[t](**m['data'])  # noqa: F405
            abm.message.append(a)
@@ -5,7 +5,7 @@ import os
 from typing import Awaitable, Any
 from astrbot.api.platform import Platform, AstrBotMessage, MessageMember, MessageType, PlatformMetadata
 from astrbot.api.event import MessageChain
-from astrbot.api.message_components import Plain, Image  # noqa: F403
+from astrbot.api.message_components import Plain, Image, Record  # noqa: F403
 from astrbot.api import logger
 from astrbot.core import web_chat_queue, web_chat_back_queue
 from .webchat_event import WebChatMessageEvent
@@ -70,6 +70,14 @@ class WebChatAdapter(Platform):
                    abm.message.append(Image.fromFileSystem(os.path.join(self.imgs_dir, img)))
            else:
                abm.message.append(Image.fromFileSystem(os.path.join(self.imgs_dir, payload['image_url'])))
+        if payload['audio_url']:
+            if isinstance(payload['audio_url'], list):
+                for audio in payload['audio_url']:
+                    path = os.path.join(self.imgs_dir, audio)
+                    abm.message.append(Record(file=path, path=path))
+            else:
+                path = os.path.join(self.imgs_dir, payload['audio_url'])
+                abm.message.append(Record(file=path, path=path))
            
        logger.debug(f"WebChatAdapter: {abm.message}")
        
@@ -12,9 +12,13 @@ class WebChatMessageEvent(AstrMessageEvent):
        os.makedirs(self.imgs_dir, exist_ok=True)        

    async def send(self, message: MessageChain):
+        if not message:
+            web_chat_back_queue.put_nowait(None)
+            return
+        
        for comp in message.chain:
            if isinstance(comp, Plain):
-                await web_chat_back_queue.put(comp.text)
+                web_chat_back_queue.put_nowait(comp.text)
            elif isinstance(comp, Image):
                # save image to local
                filename = str(uuid.uuid4()) + ".jpg"
@@ -26,6 +30,6 @@ class WebChatMessageEvent(AstrMessageEvent):
                            f.write(f2.read())
                elif comp.file and comp.file.startswith("http"):
                    await download_image_by_url(comp.file, path=path)
-                await web_chat_back_queue.put(f"[IMAGE]{filename}")
-        await web_chat_back_queue.put(None)
+                web_chat_back_queue.put_nowait(f"[IMAGE]{filename}")
+        web_chat_back_queue.put_nowait(None)
        await super().send(message)
@@ -1,4 +1,4 @@
-from .provider import Provider, Personality
+from .provider import Provider, Personality, STTProvider

 from .entites import ProviderMetaData

@@ -6,4 +6,5 @@ __all__ = [
    "Provider",
    "Personality",
    "ProviderMetaData",
+    "STTProvider"
 ]
@@ -1,13 +1,27 @@
+import enum
 from dataclasses import dataclass, field
-from typing import List, Dict
+from typing import List, Dict, Type
 from .func_tool_manager import FuncCall


+class ProviderType(enum.Enum):
+    CHAT_COMPLETION = "chat_completion"
+    SPEECH_TO_TEXT = "speech_to_text"
+    TEXT_TO_SPEECH = "text_to_speech"
+    
@dataclass
 class ProviderMetaData():
-    type: str # 提供商适配器名称，如 openai, ollama
-    desc: str = "" # 提供商适配器描述.
+    type: str
+    '''提供商适配器名称，如 openai, ollama'''
+    desc: str = ""
+    '''提供商适配器描述.'''
+    provider_type: ProviderType = ProviderType.CHAT_COMPLETION
+    cls_type: Type = None
    
+    default_config_tmpl: dict = None
+    '''平台的默认配置模板'''
+    provider_display_name: str = None
+    '''显示在 WebUI 配置页中的提供商名称，如空则是 type'''

@dataclass
 class ProviderRequest():
@@ -1,6 +1,7 @@
 import traceback
 from astrbot.core.config.astrbot_config import AstrBotConfig
-from .provider import Provider
+from .provider import Provider, STTProvider
+from .entites import ProviderType
 from typing import List
 from astrbot.core.db import BaseDatabase
 from collections import defaultdict
@@ -11,10 +12,17 @@ class ProviderManager():
    def __init__(self, config: AstrBotConfig, db_helper: BaseDatabase):
        self.providers_config: List = config['provider']
        self.provider_settings: dict = config['provider_settings']
+        self.provider_stt_settings: dict = config.get('provider_stt_settings', {})
+        
        self.provider_insts: List[Provider] = []
        '''加载的 Provider 的实例'''
+        self.stt_provider_insts: List[STTProvider] = []
+        '''加载的 Speech To Text Provider 的实例'''
        self.llm_tools = llm_tools
        self.curr_provider_inst: Provider = None
+        '''当前使用的 Provider 实例'''
+        self.curr_stt_provider_inst: STTProvider = None
+        '''当前使用的 Speech To Text Provider 实例'''
        self.loaded_ids = defaultdict(bool)
        self.db_helper = db_helper
        
@@ -31,19 +39,29 @@ class ProviderManager():
                raise ValueError(f"Provider ID 重复：{provider_cfg['id']}。")
            self.loaded_ids[provider_cfg['id']] = True
            
-            match provider_cfg['type']:
-                case "openai_chat_completion":
-                    from .sources.openai_source import ProviderOpenAIOfficial # noqa: F401
-                case "zhipu_chat_completion":
-                    from .sources.zhipu_source import ProviderZhipu # noqa: F401
-                case "llm_tuner":
-                    logger.info("加载 LLM Tuner 工具 ...")
-                    from .sources.llmtuner_source import LLMTunerModelLoader # noqa: F401
-                case "dify":
-                    from .sources.dify_source import ProviderDify # noqa: F401
-                case "googlegenai_chat_completion":
-                    from .sources.gemini_source import ProviderGoogleGenAI # noqa: F401
-                    
+            try:
+                match provider_cfg['type']:
+                    case "openai_chat_completion":
+                        from .sources.openai_source import ProviderOpenAIOfficial # noqa: F401
+                    case "zhipu_chat_completion":
+                        from .sources.zhipu_source import ProviderZhipu # noqa: F401
+                    case "llm_tuner":
+                        logger.info("加载 LLM Tuner 工具 ...")
+                        from .sources.llmtuner_source import LLMTunerModelLoader # noqa: F401
+                    case "dify":
+                        from .sources.dify_source import ProviderDify # noqa: F401
+                    case "googlegenai_chat_completion":
+                        from .sources.gemini_source import ProviderGoogleGenAI # noqa: F401
+                    case "openai_whisper_api":
+                        from .sources.whisper_api_source import ProviderOpenAIWhisperAPI # noqa: F401
+                    case "openai_whisper_selfhost":
+                        from .sources.whisper_selfhosted_source import ProviderOpenAIWhisperSelfHost # noqa: F401
+            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
+            except Exception as e:
+                logger.critical(f"加载 {provider_cfg['type']}({provider_cfg['id']}) 提供商适配器失败：{e}。未知原因")
+                continue
            
    async def initialize(self):
        for provider_config in self.providers_config:
@@ -53,23 +71,54 @@ class ProviderManager():
                logger.error(f"未找到适用于 {provider_config['type']}({provider_config['id']}) 的提供商适配器，请检查是否已经安装或者名称填写错误。已跳过。")
                continue
            selected_provider_id = sp.get("curr_provider")
-            cls_type = provider_cls_map[provider_config['type']]
+            selected_stt_provider_id = self.provider_stt_settings.get("provider_id")
+            provider_enabled = self.provider_settings.get("enable", False)
+            stt_enabled = self.provider_stt_settings.get("enable", False)
+            
+            provider_metadata = provider_cls_map[provider_config['type']]
            logger.info(f"尝试实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器 ...")
            try:
-                inst = cls_type(provider_config, self.provider_settings, self.db_helper, self.provider_settings.get('persistant_history', True))
-                self.provider_insts.append(inst)
-                if selected_provider_id == provider_config['id']:
-                    self.curr_provider_inst = inst
-                    logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前提供商适配器。")
+                # 按任务实例化提供商
+                
+                if provider_metadata.provider_type == ProviderType.SPEECH_TO_TEXT:
+                    # STT 任务
+                    inst = provider_metadata.cls_type(provider_config, self.provider_settings)
+                    
+                    if getattr(inst, "initialize", None):
+                        await inst.initialize()
+                    
+                    self.stt_provider_insts.append(inst)
+                    if selected_stt_provider_id == provider_config['id'] and stt_enabled:
+                        self.curr_stt_provider_inst = inst
+                        logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前语音转文本提供商适配器。")
+                    
+                elif provider_metadata.provider_type == ProviderType.CHAT_COMPLETION:
+                    # 文本生成任务
+                    inst = provider_metadata.cls_type(provider_config, self.provider_settings, self.db_helper, self.provider_settings.get('persistant_history', True))
+                    
+                    if getattr(inst, "initialize", None):
+                        await inst.initialize()
+                    
+                    self.provider_insts.append(inst)
+                    if selected_provider_id == provider_config['id'] and provider_enabled:
+                        self.curr_provider_inst = inst
+                        logger.info(f"已选择 {provider_config['type']}({provider_config['id']}) 作为当前提供商适配器。")
+                        
            except Exception as e:
                traceback.print_exc()
                logger.error(f"实例化 {provider_config['type']}({provider_config['id']}) 提供商适配器失败：{e}")
        
-        if len(self.provider_insts) > 0 and not self.curr_provider_inst:
+        if len(self.provider_insts) > 0 and not self.curr_provider_inst and provider_enabled:
            self.curr_provider_inst = self.provider_insts[0]
            
+        if len(self.stt_provider_insts) > 0 and not self.curr_stt_provider_inst and stt_enabled:
+            self.curr_stt_provider_inst = self.stt_provider_insts[0]
+            
        if not self.curr_provider_inst:
-            logger.warning("未启用任何提供商适配器。")
+            logger.warning("未启用任何用于 文本生成 的提供商适配器。")
+        if self.provider_stt_settings.get("enable"):
+            if not self.curr_stt_provider_inst:
+                logger.warning("未启用任何用于 语音转文本 的提供商适配器。")

    def get_insts(self):
        return self.provider_insts
@@ -125,6 +125,33 @@ class Provider(abc.ABC):
        '''重置某一个 session_id 的上下文'''
        raise NotImplementedError()

+    def meta(self) -> ProviderMeta:
+        '''获取 Provider 的元数据'''
+        return ProviderMeta(
+            id=self.provider_config['id'],
+            model=self.get_model(),
+            type=self.provider_config['type']
+        )
+        
+        
+class STTProvider():
+    def __init__(self, provider_config: dict, provider_settings: dict) -> None:
+        self.provider_config = provider_config
+        self.provider_settings = provider_settings
+    
+    @abc.abstractmethod
+    async def get_text(self, audio_url: str) -> str:
+        '''获取音频的文本'''
+        raise NotImplementedError()
+    
+    def set_model(self, model_name: str):
+        '''设置当前使用的模型名称'''
+        self.model_name = model_name
+    
+    def get_model(self) -> str:
+        '''获取当前使用的模型'''
+        return self.provider_config.get("model", "")
+    
    def meta(self) -> ProviderMeta:
        '''获取 Provider 的元数据'''
        return ProviderMeta(
@@ -1,28 +1,45 @@
 from typing import List, Dict, Type
-from .entites import ProviderMetaData
+from .entites import ProviderMetaData, ProviderType
 from astrbot.core import logger
 from .func_tool_manager import FuncCall

 provider_registry: List[ProviderMetaData] = []
 '''维护了通过装饰器注册的 Provider'''
-provider_cls_map: Dict[str, Type] = {}
-'''维护了 Provider 类型名称和 Provider 类的映射'''
+provider_cls_map: Dict[str, ProviderMetaData] = {}
+'''维护了 Provider 类型名称和 ProviderMetadata 的映射'''

 llm_tools = FuncCall()

-def register_provider_adapter(provider_type_name: str, desc: str):
+def register_provider_adapter(
+    provider_type_name: str, 
+    desc: str, 
+    provider_type: ProviderType = ProviderType.CHAT_COMPLETION,
+    default_config_tmpl: dict = None,
+    provider_display_name: str = None
+):
    '''用于注册平台适配器的带参装饰器'''
    def decorator(cls):
        if provider_type_name in provider_cls_map:
            raise ValueError(f"检测到大模型提供商适配器 {provider_type_name} 已经注册，可能发生了大模型提供商适配器类型命名冲突。")
+        
+        # 添加必备选项
+        if default_config_tmpl:
+            if 'type' not in default_config_tmpl:
+                default_config_tmpl['type'] = provider_type_name
+            if 'enable' not in default_config_tmpl:
+                default_config_tmpl['enable'] = False

        pm = ProviderMetaData(
            type=provider_type_name,
            desc=desc,
+            provider_type=provider_type,
+            cls_type=cls,
+            default_config_tmpl=default_config_tmpl,
+            provider_display_name=provider_display_name
        )
        provider_registry.append(pm)
-        provider_cls_map[provider_type_name] = cls
-        logger.debug(f"Provider {provider_type_name} 已注册")
+        provider_cls_map[provider_type_name] = pm
+        logger.debug(f"服务提供商 Provider {provider_type_name} 已注册")
        return cls
    
    return decorator
@@ -0,0 +1,101 @@
+import uuid
+import os
+import io
+from openai import AsyncOpenAI, NOT_GIVEN
+from ..provider import STTProvider
+from ..entites import ProviderType
+from astrbot.core.utils.io import download_file
+from ..register import register_provider_adapter
+from astrbot.core import logger
+
+@register_provider_adapter("openai_whisper_api", "OpenAI Whisper API", provider_type=ProviderType.SPEECH_TO_TEXT)
+class ProviderOpenAIWhisperAPI(STTProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.chosen_api_key = provider_config.get("api_key", "")
+
+        self.client = AsyncOpenAI(
+            api_key=self.chosen_api_key,
+            base_url=provider_config.get("api_base", None),
+            timeout=provider_config.get("timeout", NOT_GIVEN),
+        )
+        
+        self.set_model(provider_config.get("model", None))
+        
+    async def _convert_audio(self, path: str) -> str:
+        from pyffmpeg import FFmpeg
+        filename = str(uuid.uuid4()) + '.mp3'
+        ff = FFmpeg()
+        output_path = ff.convert(path, os.path.join('data/temp', filename))
+        return output_path
+    
+    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
+        import wave
+        
+        with wave.open(output_path, 'wb') as wav:
+            wav.setnchannels(1)
+            wav.setsampwidth(2)
+            wav.setframerate(24000)
+            wav.writeframes(input_io.read())
+            
+        return output_path
+
+    async def _convert_silk(self, path: str) -> str:
+        import pysilk
+        filename = str(uuid.uuid4()) + '.wav'
+        output_path = os.path.join('data/temp', filename)
+        with open(path, "rb") as f:
+            input_data = f.read()
+            if input_data.startswith(b'\x02'):
+                # tencent 我爱你
+                input_data = input_data[1:]
+            input_io = io.BytesIO(input_data)
+            output_io = io.BytesIO()
+            pysilk.decode(input_io, output_io, 24000)
+            output_io.seek(0)
+            await self._pcm_to_wav(output_io, output_path)
+        
+        return output_path
+    
+    async def _is_silk_file(self, file_path):
+        silk_header = b"SILK"
+        with open(file_path, "rb") as f:
+            file_header = f.read(8)
+
+        if silk_header in file_header:
+            return True
+        else:
+            return False
+
+    async def get_text(self, audio_url: str) -> str:
+        '''only supports mp3, mp4, mpeg, m4a, wav, webm'''
+        is_tencent = False
+        
+        if audio_url.startswith("http"):
+            if "multimedia.nt.qq.com.cn" in audio_url:
+                is_tencent = True
+            
+            name = str(uuid.uuid4())
+            path = os.path.join("data/temp", name)
+            await download_file(audio_url, path)
+            audio_url = path
+        
+        if not os.path.exists(audio_url):
+            raise FileNotFoundError(f"文件不存在: {audio_url}")
+        
+        if audio_url.endswith(".amr") or audio_url.endswith(".silk") or is_tencent:
+            is_silk = await self._is_silk_file(audio_url)
+            if is_silk:
+                logger.info("Converting silk file to wav ...")
+                audio_url = await self._convert_silk(audio_url)
+
+        
+        result = await self.client.audio.transcriptions.create(
+            model=self.model_name,
+            file=open(audio_url, "rb"),
+        )
+        return result.text
@@ -0,0 +1,99 @@
+import uuid
+import os
+import io
+import asyncio
+import whisper
+from ..provider import STTProvider
+from ..entites import ProviderType
+from astrbot.core.utils.io import download_file
+from ..register import register_provider_adapter
+from astrbot.core import logger
+
+
+@register_provider_adapter("openai_whisper_selfhost", "OpenAI Whisper 模型部署", provider_type=ProviderType.SPEECH_TO_TEXT)
+class ProviderOpenAIWhisperSelfHost(STTProvider):
+    def __init__(
+        self, 
+        provider_config: dict, 
+        provider_settings: dict,
+    ) -> None:
+        super().__init__(provider_config, provider_settings)
+        self.set_model(provider_config.get("model", None))
+        self.model = None
+    
+    async def initialize(self):
+        loop = asyncio.get_event_loop()
+        logger.info("下载或者加载 Whisper 模型中，这可能需要一些时间 ...")
+        self.model = await loop.run_in_executor(None, whisper.load_model, self.model_name)
+        logger.info("Whisper 模型加载完成。")
+        
+    async def _convert_audio(self, path: str) -> str:
+        from pyffmpeg import FFmpeg
+        filename = str(uuid.uuid4()) + '.mp3'
+        ff = FFmpeg()
+        output_path = ff.convert(path, os.path.join('data/temp', filename))
+        return output_path
+    
+    async def _pcm_to_wav(self, input_io: io.BytesIO, output_path: str) -> str:
+        import wave
+        
+        with wave.open(output_path, 'wb') as wav:
+            wav.setnchannels(1)
+            wav.setsampwidth(2)
+            wav.setframerate(24000)
+            wav.writeframes(input_io.read())
+            
+        return output_path
+
+    async def _convert_silk(self, path: str) -> str:
+        import pysilk
+        filename = str(uuid.uuid4()) + '.wav'
+        output_path = os.path.join('data/temp', filename)
+        with open(path, "rb") as f:
+            input_data = f.read()
+            if input_data.startswith(b'\x02'):
+                # tencent 我爱你
+                input_data = input_data[1:]
+            input_io = io.BytesIO(input_data)
+            output_io = io.BytesIO()
+            pysilk.decode(input_io, output_io, 24000)
+            output_io.seek(0)
+            await self._pcm_to_wav(output_io, output_path)
+        
+        return output_path
+    
+    async def _is_silk_file(self, file_path):
+        silk_header = b"SILK"
+        with open(file_path, "rb") as f:
+            file_header = f.read(8)
+
+        if silk_header in file_header:
+            return True
+        else:
+            return False
+
+    async def get_text(self, audio_url: str) -> str:
+        loop = asyncio.get_event_loop()
+        
+        is_tencent = False
+        
+        if audio_url.startswith("http"):
+            if "multimedia.nt.qq.com.cn" in audio_url:
+                is_tencent = True
+            
+            name = str(uuid.uuid4())
+            path = os.path.join("data/temp", name)
+            await download_file(audio_url, path)
+            audio_url = path
+        
+        if not os.path.exists(audio_url):
+            raise FileNotFoundError(f"文件不存在: {audio_url}")
+        
+        if audio_url.endswith(".amr") or audio_url.endswith(".silk") or is_tencent:
+            is_silk = await self._is_silk_file(audio_url)
+            if is_silk:
+                logger.info("Converting silk file to wav ...")
+                audio_url = await self._convert_silk(audio_url)
+
+        result = await loop.run_in_executor(None, self.model.transcribe, audio_url)
+        return result['text']
@@ -17,10 +17,6 @@ from .filter.regex import RegexFilter
 from typing import Awaitable
 from astrbot.core.rag.knowledge_db_mgr import KnowledgeDBManager

-class StarCommand(TypedDict):
-    full_command_name: str
-    command_name: str
-
 class Context:
    '''
    暴露给插件的接口上下文。
@@ -168,13 +164,13 @@ class Context:
    
    def register_provider(self, provider: Provider):
        '''
-        注册一个 LLM Provider。
+        注册一个 LLM Provider(Chat_Completion 类型)。
        '''
        self.provider_manager.provider_insts.append(provider)
        
    def get_provider_by_id(self, provider_id: str) -> Provider:
        '''
-        通过 ID 获取 LLM Provider。
+        通过 ID 获取 LLM Provider(Chat_Completion 类型)。
        '''
        for provider in self.provider_manager.provider_insts:
            if provider.meta().id == provider_id:
@@ -183,13 +179,13 @@ class Context:
    
    def get_all_providers(self) -> List[Provider]:
        '''
-        获取所有 LLM Provider。
+        获取所有 LLM Provider(Chat_Completion 类型)。
        '''
        return self.provider_manager.provider_insts
    
    def get_using_provider(self) -> Provider:
        '''
-        获取当前使用的 LLM Provider。
+        获取当前使用的 LLM Provider(Chat_Completion 类型)。
        
        通过 /provider 指令切换。
        '''
@@ -87,7 +87,7 @@ async def download_image_by_url(url: str, post: bool = False, post_data: dict =
                        with open(path, "wb") as f:
                            f.write(await resp.read())
                        return path
-    except aiohttp.client_exceptions.ClientConnectorSSLError:
+    except aiohttp.client.ClientConnectorSSLError:
        # 关闭SSL验证
        ssl_context = ssl.create_default_context()
        ssl_context.set_ciphers('DEFAULT')
@@ -116,8 +116,18 @@ async def download_file(url: str, path: str):
                        if not chunk:
                            break
                        f.write(chunk)
-    except Exception as e:
-        raise e
+    except aiohttp.client.ClientConnectorSSLError:
+        # 关闭SSL验证
+        ssl_context = ssl.create_default_context()
+        ssl_context.set_ciphers('DEFAULT')
+        async with aiohttp.ClientSession(trust_env=False) as session:
+            async with session.get(url, ssl=ssl_context, timeout=20) as resp:
+                with open(path, 'wb') as f:
+                    while True:
+                        chunk = await resp.content.read(8192)
+                        if not chunk:
+                            break
+                        f.write(chunk)

 def file_to_base64(file_path: str) -> str:
    with open(file_path, "rb") as f:
@@ -1,4 +1,5 @@
 import asyncio
+import traceback
 from astrbot.core import logger
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from .server import AstrBotDashboard
@@ -13,8 +14,16 @@ class AstrBotDashBoardLifecycle:
        
    async def start(self):
        core_lifecycle = AstrBotCoreLifecycle(self.log_broker, self.db)
-        await core_lifecycle.initialize()
-        core_task = core_lifecycle.start()
+        
+        core_task = []
+        try:
+            await core_lifecycle.initialize()
+            core_task = core_lifecycle.start()
+        except Exception as e:
+            logger.critical(f"初始化 AstrBot 失败：{e} !!!!!!!")
+            logger.critical(f"初始化 AstrBot 失败：{e} !!!!!!!")
+            logger.critical(f"初始化 AstrBot 失败：{e} !!!!!!!")
+        
        self.dashboard_server = AstrBotDashboard(core_lifecycle, self.db)
        task = asyncio.gather(core_task, self.dashboard_server.run())
        
@@ -6,9 +6,11 @@ from astrbot.core import web_chat_queue, web_chat_back_queue
 from quart import request, Response as QuartResponse, g
 from astrbot.core.db import BaseDatabase
 import asyncio
+from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
+

 class ChatRoute(Route):
-    def __init__(self, context: RouteContext, db: BaseDatabase) -> None:
+    def __init__(self, context: RouteContext, db: BaseDatabase, core_lifecycle: AstrBotCoreLifecycle) -> None:
        super().__init__(context)
        self.routes = {
            '/chat/send': ('POST', self.chat),
@@ -17,11 +19,24 @@ class ChatRoute(Route):
            '/chat/get_conversation': ('GET', self.get_conversation),
            '/chat/delete_conversation': ('GET', self.delete_conversation),
            '/chat/get_file': ('GET', self.get_file),
-            '/chat/post_image': ('POST', self.post_image)
+            '/chat/post_image': ('POST', self.post_image),
+            '/chat/post_file': ('POST', self.post_file),
+            '/chat/status': ('GET', self.status),
        }
        self.db = db
+        self.core_lifecycle = core_lifecycle
        self.register_routes()
        self.imgs_dir = "data/webchat/imgs"
+        
+        self.supported_imgs = ['jpg', 'jpeg', 'png', 'gif', 'webp']
+        
+    async def status(self):
+        has_llm_enabled = self.core_lifecycle.provider_manager.curr_provider_inst is not None
+        has_stt_enabled = self.core_lifecycle.provider_manager.curr_stt_provider_inst is not None
+        return Response().ok(data={
+            'llm_enabled': has_llm_enabled,
+            'stt_enabled': has_stt_enabled
+        }).__dict__
    
    async def get_file(self):
        filename = request.args.get('filename')
@@ -30,7 +45,13 @@ class ChatRoute(Route):
        
        try:
            with open(os.path.join(self.imgs_dir, filename), "rb") as f:
-                return QuartResponse(f.read(), mimetype="image/jpeg")
+                if filename.endswith(".wav"):
+                    return QuartResponse(f.read(), mimetype="audio/wav")
+                elif filename.split('.')[-1] in self.supported_imgs:
+                    return QuartResponse(f.read(), mimetype="image/jpeg")
+                else:
+                    return QuartResponse(f.read())
+                
        except FileNotFoundError:
            return Response().error("File not found").__dict__
        
@@ -47,6 +68,25 @@ class ChatRoute(Route):
        return Response().ok(data={
            'filename': filename
        }).__dict__
+        
+    async def post_file(self):
+        post_data = await request.files
+        if 'file' not in post_data:
+            return Response().error("Missing key: file").__dict__
+        
+        file = post_data['file']
+        filename = f"{str(uuid.uuid4())}"
+        print(file)
+        # 通过文件格式判断文件类型
+        if file.content_type.startswith('audio'):
+            filename += ".wav"
+        
+        path = os.path.join(self.imgs_dir, filename)
+        await file.save(path)
+        
+        return Response().ok(data={
+            'filename': filename
+        }).__dict__

    async def chat(self):
        username = g.get('username', 'guest')
@@ -61,20 +101,26 @@ class ChatRoute(Route):
        message = post_data['message']
        conversation_id = post_data['conversation_id']
        image_url = post_data.get('image_url')
-        if not message and not image_url:
-            return Response().error("Message and image_url are empty").__dict__
+        audio_url = post_data.get('audio_url')
+        if not message and not image_url and not audio_url:
+            return Response().error("Message and image_url and audio_url are empty").__dict__
        if not conversation_id:
            return Response().error("conversation_id is empty").__dict__
        
        await web_chat_queue.put((username, conversation_id, {
            'message': message,
-            'image_url': image_url # list
+            'image_url': image_url, # list
+            'audio_url': audio_url
        }))
        
        async def stream():
            ret = []
            while True:
-                result = await web_chat_back_queue.get()
+                try:
+                    result = await asyncio.wait_for(web_chat_back_queue.get(), timeout=30)  # 设置超时时间为5秒
+                except asyncio.TimeoutError:
+                    yield '[Error] 30 秒内没有返回数据，已放弃。\n'
+                    return
                
                if result is None:
                    break
@@ -98,6 +144,8 @@ class ChatRoute(Route):
            }
            if image_url:
                new_his['image_url'] = image_url
+            if audio_url:
+                new_his['audio_url'] = audio_url
            history.append(new_his)
            for r in ret:
                history.append({
@@ -8,6 +8,7 @@ from astrbot.core.config.astrbot_config import AstrBotConfig
 from astrbot.core.star.config import update_config
 from astrbot.core.core_lifecycle import AstrBotCoreLifecycle
 from astrbot.core.platform.register import platform_registry
+from astrbot.core.provider.register import provider_registry

 def try_cast(value: str, type_: str):
    if type_ == "int" and value.isdigit():
@@ -123,11 +124,18 @@ class ConfigRoute(Route):
    async def _get_astrbot_config(self):
        config = self.config
        
+        # 平台适配器的默认配置模板注入
        platform_default_tmpl = CONFIG_METADATA_2['platform_group']['metadata']['platform']['config_template']
        for platform in platform_registry:
            if platform.default_config_tmpl:
                platform_default_tmpl[platform.name] = platform.default_config_tmpl
        
+        # 服务提供商的默认配置模板注入
+        provider_default_tmpl = CONFIG_METADATA_2['provider_group']['metadata']['provider']['config_template']
+        for provider in provider_registry:
+            if provider.default_config_tmpl:
+                provider_default_tmpl[provider.type] = provider.default_config_tmpl
+        
        return {
            "metadata": CONFIG_METADATA_2,
            "config": config
@@ -3,7 +3,7 @@ class StaticFileRoute(Route):
    def __init__(self, context: RouteContext) -> None:
        super().__init__(context)
        
-        index_ = ['/', '/auth/login', '/config', '/logs', '/extension', '/dashboard/default', '/project-atri', '/console']
+        index_ = ['/', '/auth/login', '/config', '/logs', '/extension', '/dashboard/default', '/project-atri', '/console', '/chat']
        for i in index_:
            self.app.add_url_rule(i, view_func=self.index)
    
@@ -31,7 +31,7 @@ class AstrBotDashboard():
        self.lr = LogRoute(self.context, core_lifecycle.log_broker)
        self.sfr = StaticFileRoute(self.context)
        self.ar = AuthRoute(self.context)
-        self.chat_route = ChatRoute(self.context, db)
+        self.chat_route = ChatRoute(self.context, db, core_lifecycle)
        
    async def auth_middleware(self):
        if not request.path.startswith("/api"):
@@ -68,8 +68,14 @@ class AstrBotDashboard():
        
    def run(self):
        ip_addr = get_local_ip_addresses()
-        logger.info(f"""🌈 管理面板已启动，可访问
+        logger.info(f"""
+✨✨✨
+AstrBot 管理面板已启动，可访问
+
 1. http://{ip_addr}:6185
 2. http://localhost:6185
-登录。默认用户名和密码是 astrbot。""")
+
+默认用户名和密码是 astrbot。
+✨✨✨
+""")
        return self.app.run_task(host="0.0.0.0", port=6185, shutdown_trigger=self.shutdown_trigger_placeholder)
@@ -0,0 +1,9 @@
+# What's Changed
+
+- 支持接入 STT（语音转文字）Provider
+- 内置支持 OpenAI Whisper API/本地运行模型。[看这里](https://astrbot.lwl.lol/use/whisper.html)
+- WebChat 支持语音输入
+- WebChat 支持显示当前 Provider 状态
+- 优化了 WebChat 在没有消息返回时的处理方式
+- 修复了 reminder 在初始化历史待办时没有正常传入 session_id 的问题
+- 代码执行器在成功回复后清空文件 buffer。
@@ -0,0 +1,9 @@
+# What's Changed
+
+- 文件和语音功能适配 Lagrange
+- 面板文件更新检查和引导提示
+- WebUI AboutPage 关于页
+- 支持并完善服务提供商（Provider）默认配置模板接口
+- 修复 WebUI 配置页官方文档链接 404 的问题
+- 修复 WebUI WebChat 刷新时 404 的问题
+- 优化 download_file 的 SSL 连接错误处理
@@ -33,8 +33,6 @@
    "vue3-apexcharts": "1.4.4",
    "vue3-print-nb": "0.1.4",
    "vuetify": "3.3.14",
-    "xterm": "^5.3.0",
-    "xterm-addon-fit": "^0.8.0",
    "yup": "1.2.0"
  },
  "devDependencies": {
@@ -0,0 +1,40 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Generator: Adobe Illustrator 24.1.2, SVG Export Plug-In . SVG Version: 6.00 Build 0)  -->
+<svg version="1.1" id="Layer_3" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
+	 viewBox="0 0 128 128" style="enable-background:new 0 0 128 128;" xml:space="preserve">
+<g>
+	<linearGradient id="SVGID_1_" gradientUnits="userSpaceOnUse" x1="93.7287" y1="106.6446" x2="52.9011" y2="81.6944">
+		<stop  offset="0.0969" style="stop-color:#FFB300"/>
+		<stop  offset="1" style="stop-color:#FFB300;stop-opacity:0"/>
+	</linearGradient>
+	<path style="fill:url(#SVGID_1_);" d="M123.04,107.67c-4.08-4.12-9.38-9.48-14.92-15.06c-0.34,1.29-0.93,2.39-1.79,3.26
+		c-6.43,6.43-25.6-1.99-45.31-19.1c-2.46-2.13-16.74,20.28-14.1,22.87c3.27,3.2,26,17.86,33.78,20.73
+		c22.66,8.35,34.3,0.22,38.24-3.59C121.16,114.61,122.51,111.5,123.04,107.67z"/>
+	<linearGradient id="SVGID_2_" gradientUnits="userSpaceOnUse" x1="115.2813" y1="82.3624" x2="14.863" y2="0.8196">
+		<stop  offset="0" style="stop-color:#FFB300"/>
+		<stop  offset="0.7062" style="stop-color:#FDD835"/>
+		<stop  offset="0.8408" style="stop-color:#FDDC36"/>
+		<stop  offset="0.9842" style="stop-color:#FFE93A"/>
+		<stop  offset="1" style="stop-color:#FFEB3B"/>
+	</linearGradient>
+	<path style="fill:url(#SVGID_2_);" d="M25.05,27.7c-1.54-4.81-2.88-11.1-0.4-13.5c7.51-7.3,31.69,4.88,54.25,27.43
+		c22.55,22.55,34.84,46.84,27.43,54.25c-0.07,0.07-0.16,0.13-0.23,0.2c6.13,5.82,12.2,11.6,16.1,15.31
+		c4.87-14.43-6.45-44.11-31.5-69.96c-4.07-4.2-16.12-16.56-26.55-23.56C54.61,11.47,44.19,5.59,32.57,4.2
+		C25,3.29,11.45,5.24,14.25,15.98c0.55,2.12,2.31,7.22,8.15,13.3C23.56,30.49,25.56,29.3,25.05,27.7z"/>
+	<g>
+		<path style="fill:#FDD835;" d="M55.98,42.1l-0.75,20c-0.06,1.53,0.72,2.98,2.04,3.77l16.86,10.11c1.85,1.25,1.46,4.09-0.66,4.79
+			L54.79,85.5c-1.51,0.38-2.69,1.57-3.06,3.08l-4.89,19.93c-0.62,2.15-3.43,2.65-4.76,0.85L31.06,92.91
+			c-0.85-1.26-2.31-1.97-3.83-1.85L7.49,92.61c-2.23,0.07-3.58-2.45-2.28-4.27l12.6-16.19c0.96-1.23,1.16-2.89,0.52-4.31
+			l-7.88-17.57c-0.76-2.1,1.22-4.17,3.35-3.49l18.39,6.95c1.44,0.54,3.05,0.26,4.22-0.74l15.22-13
+			C53.39,38.62,55.96,39.87,55.98,42.1z"/>
+		<g>
+			<path style="fill:#FFFF8D;" d="M46.99,59.33l4.66-12.75c0.28-0.7,0.7-1.93,1.79-1.4c0.86,0.42,0.46,2.43,0.46,2.43l-1.05,11.54
+				c-0.41,4.39-1.6,5.38-3.3,5.49C47.6,64.75,45.65,62.98,46.99,59.33z"/>
+		</g>
+		<g>
+			<path style="fill:#F4B400;" d="M53.89,83.73l14.53-3.13c0.73-0.18,2.01-0.42,1.64-1.58c-0.29-0.91-2.34-0.8-2.34-0.8l-10.97-0.86
+				c-3.21-0.38-5.72,0.14-6.74,1.84C48.65,81.48,49.89,84.32,53.89,83.73z"/>
+		</g>
+	</g>
+</g>
+</svg>
@@ -213,11 +213,5 @@ commonStore.getStartTime();
        </v-card-actions>
      </v-card>
    </v-dialog>
-
-
-    <v-btn class="text-primary mr-4" @click="open('https://github.com/Soulter/AstrBot')" color="lightprimary"
-      variant="flat" rounded="sm">
-      GitHub Star! 🌟
-    </v-btn>
  </v-app-bar>
 </template>
@@ -17,7 +17,7 @@ const sidebarMenu = shallowRef(sidebarItems);
      </template>
    </v-list>
    <div class="text-center">
-      <v-chip color="inputBorder" size="small"> v{{ version }} </v-chip>
+      <v-chip color="inputBorder" size="small"> {{ version }} </v-chip>
    </div>

    <div style="position: absolute; bottom: 32px; width: 100%" class="text-center">
@@ -28,7 +28,14 @@ const sidebarMenu = shallowRef(sidebarItems);
      </v-list-item>
      <small style="display: block;" v-if="buildVer">构建: {{ buildVer }}</small>
      <small style="display: block;" v-else="buildVer">构建: embedded</small>
-      <small style="display: block; margin-top: 8px;">© 2024 AstrBot</small>
+      <v-tooltip text="使用 /dashbord_update 指令更新管理面板">
+        <template v-slot:activator="{ props }">
+          <small v-bind="props" v-if="buildVer != version" style="display: block; margin-top: 4px;">面板有更新</small>
+        </template>
+      </v-tooltip>
+
+      
+      <small style="display: block; margin-top: 8px;">© 2025 AstrBot</small>
    </div>

  </v-navigation-drawer>
@@ -54,14 +61,14 @@ export default {
        // 不是版本，不显示 😎
        return
      }
-      this.buildVer = res
+      this.buildVer = res.replace(/\s+/g, '')
    })
  },
  methods: {
    get_version() {
      axios.get('/api/stat/version')
        .then((res) => {
-          this.version = res.data.data.version;
+          this.version = "v" + res.data.data.version;
        })
        .catch((err) => {
          console.log(err);
@@ -40,6 +40,11 @@ const sidebarItem: menu[] = [
    icon: 'mdi-console',
    to: '/console'
  },
+  {
+    title: '关于',
+    icon: 'mdi-information',
+    to: '/about'
+  },
  // {
  //   title: 'Project ATRI',
  //   icon: 'mdi-grain',
@@ -41,6 +41,11 @@ const MainRoutes = {
      name: 'Chat',
      path: '/chat',
      component: () => import('@/views/ChatPage.vue')
+    },
+    {
+      name: 'About',
+      path: '/about',
+      component: () => import('@/views/AboutPage.vue')
    }
  ]
 };
@@ -0,0 +1,61 @@
+<template>
+    <v-card style="height: 100%;">
+        <v-card-text style="padding: 0; height: 100%;">
+            <div
+                style="display: flex; justify-content: center; align-items: center; height: 100%; flex-direction: column;">
+                <div @click="selectedLogo = selectedLogo == 0 ? 1 : 0" style="height: 300px;">
+                    <img v-if="selectedLogo == 0" width="300" src="@/assets/images/logo-waifu.png" alt="AstrBot Logo" class="fade-in">
+                    <img v-if="selectedLogo == 1" width="300" src="@/assets/images/logo-normal.svg" alt="AstrBot Logo" class="fade-in">
+                </div>
+
+                <h1 class="mt-8">AstrBot</h1>
+
+                <span style="color: #777;" class="mt-4">By <a href="https://soulter.top">Soulter</a> And <a href="https://github.com/Soulter/AstrBot/graphs/contributors">AstrBot Contributors</a></span>
+
+                <v-btn class="text-primary mt-16" @click="open('https://github.com/Soulter/AstrBot')"
+                    color="lightprimary" variant="flat" rounded="sm">
+                    Star 这个项目! 🌟
+                </v-btn>
+
+                <v-btn class="text-primary mt-4" @click="open('https://github.com/Soulter/AstrBot/issues')"
+                    color="lightprimary" variant="flat" rounded="sm">
+                    有使用问题或者功能建议？提交 Issue！
+                </v-btn>
+            </div>
+
+        </v-card-text>
+    </v-card>
+</template>
+<script>
+export default {
+    name: 'AboutPage',
+    data() {
+        return {
+            selectedLogo: 0
+        }
+    },
+
+    methods: {
+        open(url) {
+            window.open(url, '_blank');
+        }
+    }
+}
+
+</script>
+
+<style>
+@keyframes fadeIn {
+    from {
+        opacity: 0;
+    }
+
+    to {
+        opacity: 1;
+    }
+}
+
+.fade-in {
+    animation: fadeIn 0.2s ease-in-out;
+}
+</style>
@@ -20,7 +20,7 @@ marked.setOptions({
                        :disabled="!currCid">+ 创建对话</v-btn>

                    <v-card class="mx-auto" min-width="200">
-                        <v-list dense nav rounded="xl" v-if="conversations.length > 0"
+                        <v-list dense nav v-if="conversations.length > 0" style="max-height: 500px; overflow-y: auto;"
                            @update:selected="getConversationMessages">
                            <v-list-item v-for="(item, i) in conversations" :key="item.cid" :value="item.cid"
                                color="primary" rounded="xl">
@@ -31,12 +31,24 @@ marked.setOptions({
                        </v-list>
                    </v-card>

+                    <div>
+
+                        <v-chip class="mt-4" color="primary" :append-icon="status?.llm_enabled ? 'mdi-check' : 'mdi-close'">
+                            LLM
+                        </v-chip>
+
+                        <v-chip class="mt-4 ml-2" color="success" :append-icon="status?.stt_enabled ? 'mdi-check' : 'mdi-close'">
+                            语音转文本
+                        </v-chip>
+                    </div>
+
                    <v-btn variant="tonal" rounded="xl"
                        style="position: fixed; bottom: 48px; margin-bottom: 16px; min-width: 200px;" v-if="currCid"
                        @click="deleteConversation(currCid)" color="error">删除此对话</v-btn>
                </div>
+
                <div style="height: 100%; width: 100%;">
-                    <div style="height: calc(100% - 130px); overflow-y: auto; padding: 16px; " ref="messageContainer">
+                    <div style="height: calc(100% - 120px); overflow-y: auto; padding: 16px; " ref="messageContainer">
                        <div class="fade-in" v-if="messages.length == 0"
                            style="height: 100%; display: flex; justify-content: center; align-items: center; flex-direction: column;">
                            <div>
@@ -49,6 +61,12 @@ marked.setOptions({
                                    style="background-color: #eee; padding-left: 4px; padding-right: 4px; margin: 2px; border-radius: 4px;">/help</span>
                                <span>获取帮助 😊</span>
                            </div>
+                            <div style="margin-top: 8px; color: #aaa;">
+                                <span>按</span>
+                                <span
+                                    style="background-color: #eee; padding-left: 4px; padding-right: 4px; margin: 2px; border-radius: 4px;">K</span>
+                                <span>开始语音 🎤</span>
+                            </div>

                        </div>
                        <div v-else style="max-height: 100%; padding: 16px; max-width: 700px; margin: 0 auto;">
@@ -58,13 +76,21 @@ marked.setOptions({
                                    <div
                                        style="padding: 12px; border-radius: 8px; background-color: rgba(94, 53, 177, 0.15)">
                                        <span>{{ msg.message }}</span>
-                                        <div style="display: flex; gap: 8px; margin-top: 8px;" v-if="msg.image_url && msg.image_url.length > 0">
+                                        <div style="display: flex; gap: 8px; margin-top: 8px;"
+                                            v-if="msg.image_url && msg.image_url.length > 0">
                                            <div v-for="(img, index) in msg.image_url" :key="index"
                                                style="position: relative; display: inline-block;">
                                                <img :src="img"
                                                    style="width: 100px; height: 100px; border-radius: 8px; box-shadow: 0 0 5px rgba(0, 0, 0, 0.1);" />
                                            </div>
                                        </div>
+                                        <!-- audio -->
+                                        <div>
+                                            <audio controls v-if="msg.audio_url && msg.audio_url.length > 0">
+                                                <source :src="msg.audio_url" type="audio/wav">
+                                                Your browser does not support the audio element.
+                                            </audio>
+                                        </div>
                                    </div>
                                </div>
                                <div v-else style="display: flex; justify-content: flex-start; gap: 16px;">
@@ -79,26 +105,36 @@ marked.setOptions({

                        <div
                            style="width: 100%; justify-content: center; align-items: center; display: flex; flex-direction: column; margin-top: 8px;">
-                            
-                            <v-text-field id="input-field" variant="outlined" v-model="prompt" label="聊天吧!"
+
+                            <v-text-field id="input-field" variant="outlined" v-model="prompt" :label="inputFieldLabel"
                                placeholder="Start typing..." loading clear-icon="mdi-close-circle" clearable
-                                @click:clear="clearMessage" @keyup.enter="sendMessage"
-                                style="width: 100%; max-width: 930px;">
+                                @click:clear="clearMessage" style="width: 100%; max-width: 850px;">
                                <template v-slot:loader>
-                                    <v-progress-linear
-                                    :active="loadingChat"
-                                    :color="color"
-                                    height="6"
-                                    indeterminate
-                                    ></v-progress-linear>
+                                    <v-progress-linear :active="loadingChat" height="6"
+                                        indeterminate></v-progress-linear>
                                </template>

                                <template v-slot:append>
-                                    <v-icon @click="sendMessage" size="35" icon="mdi-arrow-up-circle" />
+                                    <v-tooltip text="发送">
+                                        <template v-slot:activator="{ props }">
+                                            <v-icon v-bind="props" @click="sendMessage" size="35"
+                                                icon="mdi-arrow-up-circle" />
+                                        </template>
+                                    </v-tooltip>
+
+
+                                    <v-tooltip text="语音输入">
+                                        <template v-slot:activator="{ props }">
+                                            <v-icon :color="isRecording ? 'error' : ''" v-bind="props"
+                                                @click="isRecording ? stopRecording() : startRecording()" size="35"
+                                                icon="mdi-record-circle" />
+                                        </template>
+                                    </v-tooltip>
+
                                </template>
                            </v-text-field>

-                            <div>
+                            <div style="display: flex; gap: 8px; margin-top: -8px;">
                                <div v-for="(img, index) in stagedImagesUrl" :key="index"
                                    style="position: relative; display: inline-block;">
                                    <img :src="img"
@@ -106,6 +142,15 @@ marked.setOptions({
                                    <v-icon @click="removeImage(index)" size="20" color="red"
                                        style="position: absolute; top: 0; right: 0; cursor: pointer;">mdi-close-circle</v-icon>
                                </div>
+                                <div style="display: inline-block; width: 50px; height: 50px;">
+                                    <div v-if="stagedAudioUrl"
+                                        style="position: relative; padding: 6px; border-radius: 8px; background-color: rgba(94, 53, 177, 0.15); display: inline-block;">
+                                        新录音
+                                        <v-icon @click="removeAudio" size="20" color="red"
+                                            style="position: absolute; top: 0; right: 0; cursor: pointer;">mdi-close-circle</v-icon>
+                                    </div>
+
+                                </div>
                            </div>
                        </div>
                    </div>
@@ -128,18 +173,95 @@ export default {
            conversations: [],
            currCid: '',
            stagedImagesUrl: [],
-            loadingChat: false
+            loadingChat: false,
+
+            inputFieldLabel: '聊天吧!',
+
+            isRecording: false,
+            audioChunks: [],
+            stagedAudioUrl: "",
+            mediaRecorder: null,
+
+            status: {},
+            statusText: ''
        }
    },

    mounted() {
+        this.checkStatus();
        this.getConversations();
        let inputField = document.getElementById('input-field');
        inputField.addEventListener('paste', this.handlePaste);
-
+        inputField.addEventListener('keydown', function (e) {
+            if (e.keyCode == 13 && !e.shiftKey) {
+                e.preventDefault();
+                this.sendMessage();
+            }
+        }.bind(this));
+        document.addEventListener('keydown', function (e) {
+            if (e.keyCode == 75) {
+                this.isRecording ? this.stopRecording() : this.startRecording();
+            }
+        }.bind(this));
    },

    methods: {
+
+        removeAudio() {
+            this.stagedAudioUrl = null;
+        },
+
+        checkStatus() {
+            axios.get('/api/chat/status').then(response => {
+                console.log(response.data);
+                this.status = response.data.data;
+            }).catch(err => {
+                console.error(err);
+            });
+        },
+
+        async startRecording() {
+            const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+            this.mediaRecorder = new MediaRecorder(stream);
+            this.mediaRecorder.ondataavailable = (event) => {
+                this.audioChunks.push(event.data);
+            };
+            this.mediaRecorder.start();
+            this.isRecording = true;
+            this.inputFieldLabel = "录音中，请说话...";
+        },
+
+        async stopRecording() {
+            this.isRecording = false;
+            this.inputFieldLabel = "聊天吧!";
+            this.mediaRecorder.stop();
+            this.mediaRecorder.onstop = async () => {
+                const audioBlob = new Blob(this.audioChunks, { type: 'audio/wav' });
+                this.audioChunks = [];
+
+                this.mediaRecorder.stream.getTracks().forEach(track => track.stop());
+
+                const formData = new FormData();
+                formData.append('file', audioBlob);
+
+                try {
+                    const response = await axios.post('/api/chat/post_file', formData, {
+                        headers: {
+                            'Content-Type': 'multipart/form-data',
+                            'Authorization': 'Bearer ' + localStorage.getItem('token')
+                        }
+                    });
+
+                    const audio = response.data.data.filename;
+                    console.log('Audio uploaded:', audio);
+
+                    this.stagedAudioUrl = `/api/chat/get_file?filename=${audio}`;
+                } catch (err) {
+                    console.error('Error uploading audio:', err);
+                }
+            };
+        },
+
        async handlePaste(event) {
            console.log('Pasting image...');
            const items = event.clipboardData.items;
@@ -160,7 +282,6 @@ export default {
                        const img = response.data.data.filename;
                        this.stagedImagesUrl.push(`/api/chat/get_file?filename=${img}`);

-                        scrollToBottom();
                    } catch (err) {
                        console.error('Error uploading image:', err);
                    }
@@ -198,6 +319,9 @@ export default {
                            message[i].image_url[j] = `/api/chat/get_file?filename=${message[i].image_url[j]}`;
                        }
                    }
+                    if (message[i].audio_url) {
+                        message[i].audio_url = `/api/chat/get_file?filename=${message[i].audio_url}`;
+                    }
                }
                this.messages = message;
            }).catch(err => {
@@ -250,24 +374,26 @@ export default {
            this.messages.push({
                type: 'user',
                message: this.prompt,
-                image_url: this.stagedImagesUrl
+                image_url: this.stagedImagesUrl,
+                audio_url: this.stagedAudioUrl
            });

-            // let bot_resp = {
-            //     type: 'bot',
-            //     message: ref('')
-            // }
-
-            // this.messages.push(bot_resp);
-
            this.scrollToBottom();

+            // images
            let image_filenames = [];
            for (let i = 0; i < this.stagedImagesUrl.length; i++) {
                let img = this.stagedImagesUrl[i].replace('/api/chat/get_file?filename=', '');
                image_filenames.push(img);
            }

+            // audio
+            let audio_filenames = [];
+            if (this.stagedAudioUrl) {
+                let audio = this.stagedAudioUrl.replace('/api/chat/get_file?filename=', '');
+                audio_filenames.push(audio);
+            }
+
            this.loadingChat = true;


@@ -277,11 +403,17 @@ export default {
                    'Content-Type': 'application/json',
                    'Authorization': 'Bearer ' + localStorage.getItem('token')
                },
-                body: JSON.stringify({ message: this.prompt, conversation_id: this.currCid, image_url: image_filenames })  // 发送请求体
+                body: JSON.stringify({
+                    message: this.prompt,
+                    conversation_id: this.currCid,
+                    image_url: image_filenames,
+                    audio_url: audio_filenames
+                })  // 发送请求体
            })
                .then(response => {
                    this.prompt = '';
                    this.stagedImagesUrl = [];
+                    this.stagedAudioUrl = "";

                    this.loadingChat = false;

@@ -83,7 +83,7 @@ import { VueMonacoEditor } from '@guolao/vue-monaco-editor'

      <div style="margin-left: 16px; padding-bottom: 16px">
        <small>不了解配置？请见 <a
-            href="https://astrbot.soulter.top/docs/%E5%BC%80%E5%A7%8B%E4%B8%8A%E6%89%8B/%E9%85%8D%E7%BD%AE%E6%96%87%E4%BB%B6">官方文档</a>
+            href="https://astrbot.soulter.top/">官方文档</a>
          或 <a
            href="https://qm.qq.com/cgi-bin/qm/qr?k=EYGsuUTfe00_iOu9JTXS7_TEpMkXOvwv&jump_from=webapi&authKey=uUEMKCROfsseS+8IzqPjzV3y1tzy4AkykwTib2jNkOFdzezF9s9XknqnIaf3CDft">加群询问</a>。</small>
      </div>
@@ -40,8 +40,11 @@ async def check_dashboard_files():
    if os.path.exists("data/dist"):
        if os.path.exists("data/dist/assets/version"):
            with open("data/dist/assets/version", "r") as f:
-                if f.read() != VERSION:
+                v = f.read().strip()
+                if v != f"v{VERSION}":
                    logger.warning("检测到管理面板有更新。可以使用 /dashboard update 命令更新。")
+                else:
+                    logger.info("管理面板文件已是最新。")
        return
    
    logger.info("开始下载管理面板文件...")
@@ -45,7 +45,7 @@ class Main(star.Star):
 /deop <admin_id>: 取消管理员
 /wl <sid>: 添加会话白名单
 /dwl <sid>: 删除会话白名单
-/dashboard update: 更新管理面板
+/dashboard_update: 更新管理面板

 [大模型]
 /provider: 查看、切换大模型提供商
@@ -113,7 +113,7 @@ class Main(star.Star):
    async def initialize(self):
        ok = await self.is_docker_available()
        if not ok:
-            logger.warning("Docker 不可用，代码解释器将无法使用，astrbot-python-interpreter 将自动禁用。")
+            logger.info("Docker 不可用，代码解释器将无法使用，astrbot-python-interpreter 将自动禁用。")
            await self.context._star_manager.turn_off_plugin("astrbot-python-interpreter")
                
    async def file_upload(self, file_path: str):
@@ -141,7 +141,7 @@ class Main(star.Star):
            await docker.version()
            return True
        except aiodocker.exceptions.DockerError as e:
-            logger.error(f"检查 Docker 可用性时出现问题: {e}")
+            logger.info(f"检查 Docker 可用性: {e}")
            return False
        
    async def get_image_name(self) -> str:
@@ -150,7 +150,7 @@ class Main(star.Star):
            return f"{self.config['sandbox']['docker_mirror']}/{self.config['sandbox']['image']}"
        return self.config["sandbox"]["image"]
    
-    async def _save_config(self):
+    def _save_config(self):
        with open(PATH, "w") as f:
            json.dump(self.config, f)
        
@@ -207,7 +207,7 @@ class Main(star.Star):
 """)
        else:
            self.config["sandbox"]["docker_mirror"] = url
-            await self._save_config()
+            self._save_config()
            yield event.plain_result("设置 Docker 镜像地址成功。")

    @pi.command("repull")
@@ -363,10 +363,24 @@ class Main(star.Star):
                    logger.warning(f"未从沙箱输出中捕获到合法的输出。沙箱输出日志: {logs}")
                    break
            else:
+                # 成功了
+                self.user_file_msg_buffer.pop(event.get_session_id())
                return
        
        yield event.plain_result("经过多次尝试后，未从沙箱输出中捕获到合法的输出，请更换问法或者查看日志。")
-            
+        
+    @pi.command("cleanfile")
+    async def pi_cleanfile(self, event: AstrMessageEvent):
+        '''清理用户上传的文件'''
+        for file in self.user_file_msg_buffer[event.get_session_id()]:
+            try:
+                os.remove(file)
+            except BaseException as e:
+                logger.error(f"删除文件 {file} 失败: {e}")
+                
+        self.user_file_msg_buffer.pop(event.get_session_id())
+        yield event.plain_result(f"用户 {event.get_session_id()} 上传的文件已清理。")
+
    
    async def run_container(self, container: aiodocker.docker.DockerContainer, timeout: int = 20) -> list[str]:
        '''Run the container and get the output'''
@@ -0,0 +1 @@
+aiodocker
@@ -34,7 +34,7 @@ class Main(star.Star):
                    self.scheduler.add_job(
                        self._reminder_callback, 
                        trigger='date', 
-                        args=[reminder["text"], reminder], 
+                        args=[group, reminder], 
                        run_date=datetime.datetime.strptime(reminder["datetime"], "%Y-%m-%d %H:%M"),
                        misfire_grace_time=60
                    )
@@ -42,7 +42,7 @@ class Main(star.Star):
                    self.scheduler.add_job(
                        self._reminder_callback, 
                        trigger='cron', 
-                        args=[reminder["text"], reminder], 
+                        args=[group, reminder], 
                        misfire_grace_time=60,
                        **self._parse_cron_expr(reminder["cron"])
                    )
@@ -16,4 +16,5 @@ aiocqhttp
 pyjwt
 apscheduler
 docstring_parser
-aiodocker
+aiodocker
+silk-python
Author	SHA1	Message	Date
Soulter	a20446aeb9	🎉 chore: bump to v3.4.6	2025-01-13 02:17:23 +08:00
Soulter	7b23d76559	feat: 支持并完善服务提供商默认配置模板接口	2025-01-13 02:05:57 +08:00
Soulter	8315cf5818	perf: 面板文件更新检查和引导提示和AboutPage	2025-01-12 13:01:40 +08:00
Soulter	ed16265bde	fix: 更新官方文档链接并优化管理面板版本检查日志	2025-01-12 12:23:27 +08:00
Soulter	dff205faf6	feat: 添加聊天功能路由和更新管理面板命令	2025-01-12 12:18:19 +08:00
Soulter	9aae8aee0c	Update README.md	2025-01-12 11:45:39 +08:00
Soulter	7c818ced2b	perf: 文件和语音功能适配 Lagrange	2025-01-12 11:44:33 +08:00
Soulter	218e887558	fix: download_file 修复 SSL 连接错误处理	2025-01-12 11:44:33 +08:00
Soulter	a68860b35a	chore: compress the banner	2025-01-12 10:52:17 +08:00
Soulter	82d4d43383	🎉 Bump to v3.4.5	2025-01-11 23:35:22 +08:00
Soulter	94618e8feb	feat: 添加 aiodocker 依赖	2025-01-11 22:02:15 +08:00
Soulter	55de7d4494	🎉 Bump to v3.4.5	2025-01-11 21:40:48 +08:00
Soulter	7ed639f741	🎉 bump to v3.4.5	2025-01-11 21:06:06 +08:00
Soulter	41f2870c29	Merge pull request #236 from Soulter/feat-stt 支持 Speech To Text，并适配腾讯修改过的 Silk 语音格式	2025-01-11 21:00:04 +08:00
Soulter	ba198490fa	feat: 支持自部署 Whisper 模型	2025-01-11 20:31:21 +08:00
Soulter	0f9ab082ab	perf: 优化webchat，没有结果返回时的反馈	2025-01-11 19:45:42 +08:00
Soulter	97b58965f2	feat: webchat可显示Provider状态	2025-01-11 19:31:56 +08:00
Soulter	f2566c68e3	feat: 按 K 语音	2025-01-11 19:07:26 +08:00
Soulter	a456bf5449	fix: 初始化reminder时的一些问题	2025-01-11 18:55:18 +08:00
Soulter	a09998f910	feat: webchat 支持语音输入	2025-01-11 18:54:40 +08:00
Soulter	be662b913c	feat: 支持 Whisper STT，并适配 Tencent 语音格式	2025-01-11 17:19:28 +08:00
Soulter	e7ddc8448d	perf: 代码执行器在成功执行后清空文件buffer	2025-01-11 11:31:56 +08:00