fix: english logging

fix: resolve Discord/Misskey hot reload issue by fixing client_self_id misuse
fixes: #7187 closes: #7188
2026-07-04 19:50:16 +08:00 · 2026-04-03 14:01:11 +08:00 · 2026-04-03 13:41:56 +08:00 · 2026-04-03 13:15:04 +08:00 · 2026-04-03 09:03:29 +08:00 · 2026-04-02 16:16:22 +08:00
46 changed files with 1586 additions and 261 deletions
--- a/1
+++ b/1
@@ -12,6 +12,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
    ca-certificates \
    bash \
    ffmpeg \
+    libavcodec-extra \
    curl \
    gnupg \
    git \
--- a/README.md
+++ b/README.md
@@ -92,6 +92,9 @@ Update `astrbot`:
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> AstrBot deployed via `uv` **does not support upgrading through the WebUI**. To update, please run the command above from the command line.
+
 ### Docker Deployment

 For users familiar with containers and looking for a more stable, production-ready deployment method, we recommend deploying AstrBot with Docker / Docker Compose.
@@ -184,6 +187,7 @@ Connect AstrBot to your favorite chat platform.
 | Coze | LLMOps Platforms |
 | OpenAI Whisper | Speech-to-Text Services |
 | SenseVoice | Speech-to-Text Services |
+| Xiaomi MiMo Omni | Speech-to-Text Services |
 | OpenAI TTS | Text-to-Speech Services |
 | Gemini TTS | Text-to-Speech Services |
 | GPT-Sovits-Inference | Text-to-Speech Services |
@@ -193,6 +197,7 @@ Connect AstrBot to your favorite chat platform.
 | Alibaba Cloud Bailian TTS | Text-to-Speech Services |
 | Azure TTS | Text-to-Speech Services |
 | Minimax TTS | Text-to-Speech Services |
+| Xiaomi MiMo TTS | Text-to-Speech Services |
 | Volcano Engine TTS | Text-to-Speech Services |

 ## ❤️ Sponsors
--- a/README_fr.md
+++ b/README_fr.md
@@ -92,6 +92,9 @@ Mettre à jour `astrbot` :
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> AstrBot déployé via `uv` **ne prend pas en charge la mise à jour via le WebUI**. Pour mettre à jour, exécutez la commande ci-dessus depuis le terminal.
+
 ### Déploiement Docker

 Pour les utilisateurs familiers avec les conteneurs et qui souhaitent une méthode plus stable et adaptée à la production, nous recommandons de déployer AstrBot avec Docker / Docker Compose.
@@ -184,6 +187,7 @@ Connectez AstrBot à vos plateformes de chat préférées.
 | Coze | Plateformes LLMOps |
 | OpenAI Whisper | Services de reconnaissance vocale |
 | SenseVoice | Services de reconnaissance vocale |
+| Xiaomi MiMo Omni | Services de reconnaissance vocale |
 | OpenAI TTS | Services de synthèse vocale |
 | Gemini TTS | Services de synthèse vocale |
 | GPT-Sovits-Inference | Services de synthèse vocale |
@@ -193,6 +197,7 @@ Connectez AstrBot à vos plateformes de chat préférées.
 | Alibaba Cloud Bailian TTS | Services de synthèse vocale |
 | Azure TTS | Services de synthèse vocale |
 | Minimax TTS | Services de synthèse vocale |
+| Xiaomi MiMo TTS | Services de synthèse vocale |
 | Volcano Engine TTS | Services de synthèse vocale |

 ## ❤️ Contribuer
--- a/README_ja.md
+++ b/README_ja.md
@@ -92,6 +92,9 @@ astrbot run
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> `uv` 経由でデプロイした AstrBot は、**WebUI からのバージョンアップグレードに対応していません**。更新するには、上記のコマンドをコマンドラインで実行してください。
+
 ### Docker デプロイ

 コンテナ運用に慣れており、より安定した本番向けのデプロイ方法を求めるユーザーには、Docker / Docker Compose での AstrBot デプロイをおすすめします。
@@ -185,6 +188,7 @@ AstrBot をよく使うチャットプラットフォームに接続できます
 | Coze | LLMOps プラットフォーム |
 | OpenAI Whisper | 音声認識サービス |
 | SenseVoice | 音声認識サービス |
+| Xiaomi MiMo Omni | 音声認識サービス |
 | OpenAI TTS | 音声合成サービス |
 | Gemini TTS | 音声合成サービス |
 | GPT-Sovits-Inference | 音声合成サービス |
@@ -194,6 +198,7 @@ AstrBot をよく使うチャットプラットフォームに接続できます
 | Alibaba Cloud 百炼 TTS | 音声合成サービス |
 | Azure TTS | 音声合成サービス |
 | Minimax TTS | 音声合成サービス |
+| Xiaomi MiMo TTS | 音声合成サービス |
 | Volcano Engine TTS | 音声合成サービス |

 ## ❤️ コントリビューション
--- a/README_ru.md
+++ b/README_ru.md
@@ -92,6 +92,9 @@ astrbot run
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> AstrBot, развёрнутый через `uv`, **не поддерживает обновление через WebUI**. Для обновления выполните указанную выше команду из командной строки.
+
 ### Развёртывание Docker

 Для пользователей, знакомых с контейнерами и которым нужен более стабильный и подходящий для production способ, мы рекомендуем разворачивать AstrBot через Docker / Docker Compose.
@@ -184,6 +187,7 @@ yay -S astrbot-git
 | Coze | Платформы LLMOps |
 | OpenAI Whisper | Сервисы распознавания речи |
 | SenseVoice | Сервисы распознавания речи |
+| Xiaomi MiMo Omni | Сервисы распознавания речи |
 | OpenAI TTS | Сервисы синтеза речи |
 | Gemini TTS | Сервисы синтеза речи |
 | GPT-Sovits-Inference | Сервисы синтеза речи |
@@ -193,6 +197,7 @@ yay -S astrbot-git
 | Alibaba Cloud Bailian TTS | Сервисы синтеза речи |
 | Azure TTS | Сервисы синтеза речи |
 | Minimax TTS | Сервисы синтеза речи |
+| Xiaomi MiMo TTS | Сервисы синтеза речи |
 | Volcano Engine TTS | Сервисы синтеза речи |

 ## ❤️ Вклад в проект
--- a/README_zh-TW.md
+++ b/README_zh-TW.md
@@ -92,6 +92,9 @@ astrbot run
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> 透過 `uv` 部署的 AstrBot **不支援在 WebUI 中進行版本升級**。如需更新，請透過命令列執行上述命令。
+
 ### Docker 部署

 對於熟悉容器、希望獲得更穩定且更適合正式環境部署方式的使用者，我們推薦使用 Docker / Docker Compose 部署 AstrBot。
@@ -184,6 +187,7 @@ yay -S astrbot-git
 | Coze | LLMOps 平台 |
 | OpenAI Whisper | 語音轉文字服務 |
 | SenseVoice | 語音轉文字服務 |
+| Xiaomi MiMo Omni | 語音轉文字服務 |
 | OpenAI TTS | 文字轉語音服務 |
 | Gemini TTS | 文字轉語音服務 |
 | GPT-Sovits-Inference | 文字轉語音服務 |
@@ -193,6 +197,7 @@ yay -S astrbot-git
 | 阿里雲百煉 TTS | 文字轉語音服務 |
 | Azure TTS | 文字轉語音服務 |
 | Minimax TTS | 文字轉語音服務 |
+| Xiaomi MiMo TTS | 文字轉語音服務 |
 | 火山引擎 TTS | 文字轉語音服務 |

 ## ❤️ 貢獻
--- a/README_zh.md
+++ b/README_zh.md
@@ -92,6 +92,9 @@ astrbot run
 uv tool upgrade astrbot
 ```

+> [!WARNING]
+> 通过 `uv` 部署的 AstrBot **不支持在 WebUI 中进行版本升级**。如需更新，请通过命令行执行上述命令。
+
 ### Docker 部署

 对于熟悉容器、希望获得更稳定且更适合生产环境部署方式的用户，我们推荐使用 Docker / Docker Compose 部署 AstrBot。
@@ -185,6 +188,7 @@ yay -S astrbot-git
 | Coze | LLMOps 平台 |
 | OpenAI Whisper | 语音转文本 |
 | SenseVoice | 语音转文本 |
+| Xiaomi MiMo Omni | 语音转文本 |
 | OpenAI TTS | 文本转语音 |
 | Gemini TTS | 文本转语音 |
 | GPT-Sovits-Inference | 文本转语音 |
@@ -194,6 +198,7 @@ yay -S astrbot-git
 | 阿里云百炼 TTS | 文本转语音 |
 | Azure TTS | 文本转语音 |
 | Minimax TTS | 文本转语音 |
+| Xiaomi MiMo TTS | 文本转语音 |
 | 火山引擎 TTS | 文本转语音 |

 ## ❤️ 贡献
--- a/astrbot/core/agent/handoff.py
+++ b/astrbot/core/agent/handoff.py
@@ -15,7 +15,6 @@ class HandoffTool(FunctionTool, Generic[TContext]):
        tool_description: str | None = None,
        **kwargs,
    ) -> None:
-
        # Avoid passing duplicate `description` to the FunctionTool dataclass.
        # Some call sites (e.g. SubAgentOrchestrator) pass `description` via kwargs
        # to override what the main agent sees, while we also compute a default
--- a/astrbot/core/config/default.py
+++ b/astrbot/core/config/default.py
@@ -4040,9 +4040,9 @@ CONFIG_METADATA_3_SYSTEM = {
                        "hint": "时区设置。请填写 IANA 时区名称, 如 Asia/Shanghai, 为空时使用系统默认时区。所有时区请查看: https://data.iana.org/time-zones/tzdb-2021a/zone1970.tab",
                    },
                    "http_proxy": {
-                        "description": "HTTP 代理",
+                        "description": "代理",
                        "type": "string",
-                        "hint": "启用后，会以添加环境变量的方式设置代理。格式为 `http://ip:port`",
+                        "hint": "启用后，会以添加环境变量的方式设置代理。支持 http://、https://、socks5:// 格式，例如：http://127.0.0.1:7890 或 socks5://127.0.0.1:7891",
                    },
                    "no_proxy": {
                        "description": "直连地址列表",
--- a/astrbot/core/knowledge_base/kb_helper.py
+++ b/astrbot/core/knowledge_base/kb_helper.py
@@ -108,6 +108,7 @@ Text chunk to process:
 class KBHelper:
    vec_db: BaseVecDB
    kb: KnowledgeBase
+    init_error: str | None

    def __init__(
        self,
@@ -122,6 +123,7 @@ class KBHelper:
        self.prov_mgr = provider_manager
        self.kb_root_dir = kb_root_dir
        self.chunker = chunker
+        self.init_error = None

        self.kb_dir = Path(self.kb_root_dir) / self.kb.kb_id
        self.kb_medias_dir = Path(self.kb_dir) / "medias" / self.kb.kb_id
@@ -148,13 +150,14 @@ class KBHelper:
    async def get_rp(self) -> RerankProvider | None:
        if not self.kb.rerank_provider_id:
            return None
-        rp: RerankProvider = await self.prov_mgr.get_provider_by_id(
+        rp: RerankProvider | None = await self.prov_mgr.get_provider_by_id(
            self.kb.rerank_provider_id,
        )  # type: ignore
        if not rp:
-            raise ValueError(
-                f"无法找到 ID 为 {self.kb.rerank_provider_id} 的 Rerank Provider",
+            logger.warning(
+                f"知识库 {self.kb.kb_name}({self.kb.kb_id}) 的 Rerank Provider({self.kb.rerank_provider_id}) 不可用，将跳过重排序。",
            )
+            return None
        return rp

    async def _ensure_vec_db(self) -> FaissVecDB:
@@ -162,7 +165,13 @@ class KBHelper:
            raise ValueError(f"知识库 {self.kb.kb_name} 未配置 Embedding Provider")

        ep = await self.get_ep()
-        rp = await self.get_rp()
+        rp: RerankProvider | None = None
+        try:
+            rp = await self.get_rp()
+        except Exception as e:
+            logger.warning(
+                f"知识库 {self.kb.kb_name}({self.kb.kb_id}) 初始化重排序能力失败，将跳过重排序: {e}",
+            )

        vec_db = FaissVecDB(
            doc_store_path=str(self.kb_dir / "doc.db"),
@@ -172,6 +181,8 @@ class KBHelper:
        )
        await vec_db.initialize()
        self.vec_db = vec_db
+        # Clear stale init_error once initialization succeeds.
+        self.init_error = None
        return vec_db

    async def delete_vec_db(self) -> None:
@@ -183,7 +194,7 @@ class KBHelper:
            shutil.rmtree(self.kb_dir)

    async def terminate(self) -> None:
-        if self.vec_db:
+        if hasattr(self, "vec_db") and self.vec_db:
            await self.vec_db.close()

    async def upload_document(
--- a/astrbot/core/knowledge_base/kb_mgr.py
+++ b/astrbot/core/knowledge_base/kb_mgr.py
@@ -1,4 +1,3 @@
-import traceback
 from pathlib import Path

 from astrbot.core import logger
@@ -56,8 +55,7 @@ class KnowledgeBaseManager:
            logger.error(f"知识库模块导入失败: {e}")
            logger.warning("请确保已安装所需依赖: pypdf, aiofiles, Pillow, rank-bm25")
        except Exception as e:
-            logger.error(f"知识库模块初始化失败: {e}")
-            logger.error(traceback.format_exc())
+            logger.error(f"知识库模块初始化失败: {e}", exc_info=True)

    async def _init_kb_database(self) -> None:
        self.kb_db = KBSQLiteDatabase(DB_PATH.as_posix())
@@ -76,7 +74,14 @@ class KnowledgeBaseManager:
                kb_root_dir=FILES_PATH,
                chunker=CHUNKER,
            )
-            await kb_helper.initialize()
+            try:
+                await kb_helper.initialize()
+            except Exception as e:
+                kb_helper.init_error = str(e)
+                logger.error(
+                    f"知识库 {record.kb_name}({record.kb_id}) 初始化失败: {e}",
+                    exc_info=True,
+                )
            self.kb_insts[record.kb_id] = kb_helper

    async def create_kb(
@@ -179,6 +184,20 @@ class KnowledgeBaseManager:
            return None

        kb = kb_helper.kb
+        previous_state = {
+            "kb_name": kb.kb_name,
+            "description": kb.description,
+            "emoji": kb.emoji,
+            "embedding_provider_id": kb.embedding_provider_id,
+            "rerank_provider_id": kb.rerank_provider_id,
+            "chunk_size": kb.chunk_size,
+            "chunk_overlap": kb.chunk_overlap,
+            "top_k_dense": kb.top_k_dense,
+            "top_k_sparse": kb.top_k_sparse,
+            "top_m_final": kb.top_m_final,
+        }
+        previous_init_error = kb_helper.init_error
+
        if kb_name is not None:
            kb.kb_name = kb_name
        if description is not None:
@@ -198,12 +217,47 @@ class KnowledgeBaseManager:
            kb.top_k_sparse = top_k_sparse
        if top_m_final is not None:
            kb.top_m_final = top_m_final
+
+        # Build a new helper first. Keep current vec_db alive until new init succeeds.
+        new_helper = KBHelper(
+            kb_db=self.kb_db,
+            kb=kb,
+            provider_manager=self.provider_manager,
+            kb_root_dir=FILES_PATH,
+            chunker=CHUNKER,
+        )
+
+        try:
+            await new_helper.initialize()
+        except Exception as e:
+            # Roll back in-memory settings and keep current helper available.
+            kb.kb_name = previous_state["kb_name"]
+            kb.description = previous_state["description"]
+            kb.emoji = previous_state["emoji"]
+            kb.embedding_provider_id = previous_state["embedding_provider_id"]
+            kb.rerank_provider_id = previous_state["rerank_provider_id"]
+            kb.chunk_size = previous_state["chunk_size"]
+            kb.chunk_overlap = previous_state["chunk_overlap"]
+            kb.top_k_dense = previous_state["top_k_dense"]
+            kb.top_k_sparse = previous_state["top_k_sparse"]
+            kb.top_m_final = previous_state["top_m_final"]
+            kb_helper.init_error = previous_init_error
+            logger.error(
+                f"知识库 {kb.kb_name}({kb.kb_id}) 重新初始化失败，继续使用旧实例: {e}",
+                exc_info=True,
+            )
+            return kb_helper
+
        async with self.kb_db.get_db() as session:
            session.add(kb)
            await session.commit()
            await session.refresh(kb)

-        return kb_helper
+        old_helper = kb_helper
+        self.kb_insts[kb_id] = new_helper
+        await old_helper.terminate()
+        new_helper.init_error = None
+        return new_helper

    async def retrieve(
        self,
@@ -215,11 +269,21 @@ class KnowledgeBaseManager:
        """从指定知识库中检索相关内容"""
        kb_ids = []
        kb_id_helper_map = {}
+        unavailable_kbs = []
        for kb_name in kb_names:
            if kb_helper := await self.get_kb_by_name(kb_name):
+                if kb_helper.init_error:
+                    unavailable_kbs.append((kb_name, kb_helper.init_error))
+                    logger.warning(f"知识库 {kb_name} 不可用: {kb_helper.init_error}")
+                    continue
                kb_ids.append(kb_helper.kb.kb_id)
                kb_id_helper_map[kb_helper.kb.kb_id] = kb_helper

+        # all requested KBs are unavailable
+        if not kb_ids and unavailable_kbs:
+            errors = "; ".join(f"{n}: {e}" for n, e in unavailable_kbs)
+            raise ValueError(f"所有请求的知识库均不可用: {errors}")
+
        if not kb_ids:
            return {}

--- a/astrbot/core/knowledge_base/retrieval/manager.py
+++ b/astrbot/core/knowledge_base/retrieval/manager.py
@@ -184,12 +184,15 @@ class RetrievalManager:
                first_rerank = vec_db.rerank_provider
                break
        if first_rerank and retrieval_results:
-            retrieval_results = await self._rerank(
-                query=query,
-                results=retrieval_results,
-                top_k=top_m_final,
-                rerank_provider=first_rerank,
-            )
+            try:
+                retrieval_results = await self._rerank(
+                    query=query,
+                    results=retrieval_results,
+                    top_k=top_m_final,
+                    rerank_provider=first_rerank,
+                )
+            except Exception as e:
+                logger.warning(f"Rerank 执行失败，已跳过重排序并使用融合结果: {e}")

        return retrieval_results[:top_m_final]

@@ -229,10 +232,10 @@ class RetrievalManager:

                all_results.extend(vec_results)
            except Exception as e:
-                from astrbot.core import logger
-
-                logger.warning(f"知识库 {kb_id} 稠密检索失败: {e}")
-                continue
+                logger.error(f"知识库 {kb_id} 稠密检索失败: {e}", exc_info=True)
+                if len(kb_ids) == 1:
+                    raise RuntimeError(f"知识库 {kb_id} 稠密检索失败: {e}") from e
+                # multi-KB: skip the faulty KB and continue

        # 按相似度排序并返回 top_k
        all_results.sort(key=lambda x: x.similarity, reverse=True)
--- a/astrbot/core/platform/sources/discord/client.py
+++ b/astrbot/core/platform/sources/discord/client.py
@@ -35,11 +35,11 @@ class DiscordBotClient(discord.Bot):
    async def on_ready(self) -> None:
        """当机器人成功连接并准备就绪时触发"""
        if self.user is None:
-            logger.error("[Discord] 客户端未正确加载用户信息 (self.user is None)")
+            logger.error("[Discord] Bot user not loaded correctly (self.user is None)")
            return

-        logger.info(f"[Discord] 已作为 {self.user} (ID: {self.user.id}) 登录")
-        logger.info("[Discord] 客户端已准备就绪。")
+        logger.info(f"[Discord] Logged in as {self.user} (ID: {self.user.id})")
+        logger.info("[Discord] Client is ready.")

        if self.on_ready_once_callback and not self._ready_once_fired:
            self._ready_once_fired = True
@@ -47,7 +47,7 @@ class DiscordBotClient(discord.Bot):
                await self.on_ready_once_callback()
            except Exception as e:
                logger.error(
-                    f"[Discord] on_ready_once_callback 执行失败: {e}",
+                    f"[Discord] Failed to execute on_ready_once_callback: {e}",
                    exc_info=True,
                )

@@ -99,7 +99,7 @@ class DiscordBotClient(discord.Bot):
            return

        logger.debug(
-            f"[Discord] 收到原始消息 from {message.author.name}: {message.content}",
+            f"[Discord] Received raw message from {message.author.name}: {message.content}",
        )

        if self.on_message_received:
--- a/astrbot/core/platform/sources/discord/discord_platform_adapter.py
+++ b/astrbot/core/platform/sources/discord/discord_platform_adapter.py
@@ -46,7 +46,7 @@ class DiscordPlatformAdapter(Platform):
    ) -> None:
        super().__init__(platform_config, event_queue)
        self.settings = platform_settings
-        self.client_self_id: str | None = None
+        self.bot_self_id: str | None = None
        self.registered_handlers = []
        # 指令注册相关
        self.enable_command_register = self.config.get("discord_command_register", True)
@@ -64,7 +64,7 @@ class DiscordPlatformAdapter(Platform):
        """通过会话发送消息"""
        if self.client.user is None:
            logger.error(
-                "[Discord] 客户端未就绪 (self.client.user is None)，无法发送消息"
+                "[Discord] Client is not ready (self.client.user is None); message send skipped"
            )
            return

@@ -92,10 +92,10 @@ class DiscordPlatformAdapter(Platform):

        message_obj.message_str = message_chain.get_plain_text()
        message_obj.sender = MessageMember(
-            user_id=str(self.client_self_id),
+            user_id=str(self.bot_self_id),
            nickname=self.client.user.display_name,
        )
-        message_obj.self_id = cast(str, self.client_self_id)
+        message_obj.self_id = cast(str, self.bot_self_id)
        message_obj.session_id = session.session_id
        message_obj.message = message_chain.chain

@@ -115,7 +115,7 @@ class DiscordPlatformAdapter(Platform):
        """返回平台元数据"""
        return PlatformMetadata(
            "discord",
-            "Discord 适配器",
+            "Discord Adapter",
            id=cast(str, self.config.get("id")),
            default_config_tmpl=self.config,
            support_streaming_message=False,
@@ -127,16 +127,18 @@ class DiscordPlatformAdapter(Platform):

        # 初始化回调函数
        async def on_received(message_data) -> None:
-            logger.debug(f"[Discord] 收到消息: {message_data}")
-            if self.client_self_id is None:
-                self.client_self_id = message_data.get("bot_id")
+            logger.debug(f"[Discord] Message received: {message_data}")
+            if self.bot_self_id is None:
+                self.bot_self_id = message_data.get("bot_id")
            abm = await self.convert_message(data=message_data)
            await self.handle_msg(abm)

        # 初始化 Discord 客户端
        token = str(self.config.get("discord_token"))
        if not token:
-            logger.error("[Discord] Bot Token 未配置。请在配置文件中正确设置 token。")
+            logger.error(
+                "[Discord] Bot token is not configured. Please set a valid token in the config file."
+            )
            return

        proxy = self.config.get("discord_proxy") or None
@@ -144,12 +146,17 @@ class DiscordPlatformAdapter(Platform):
        self.client.on_message_received = on_received

        async def callback() -> None:
-            if self.enable_command_register:
-                await self._collect_and_register_commands()
-            if self.activity_name:
-                await self.client.change_presence(
-                    status=discord.Status.online,
-                    activity=discord.CustomActivity(name=self.activity_name),
+            try:
+                if self.enable_command_register:
+                    await self._collect_and_register_commands()
+                if self.activity_name:
+                    await self.client.change_presence(
+                        status=discord.Status.online,
+                        activity=discord.CustomActivity(name=self.activity_name),
+                    )
+            except Exception as e:
+                logger.error(
+                    f"[Discord] on_ready_once_callback err: {e}", exc_info=True
                )

        self.client.on_ready_once_callback = callback
@@ -158,11 +165,16 @@ class DiscordPlatformAdapter(Platform):
            self._polling_task = asyncio.create_task(self.client.start_polling())
            await self.shutdown_event.wait()
        except discord.errors.LoginFailure:
-            logger.error("[Discord] 登录失败。请检查你的 Bot Token 是否正确。")
+            logger.error(
+                "[Discord] Login failed. Please check whether the bot token is correct."
+            )
        except discord.errors.ConnectionClosed:
-            logger.warning("[Discord] 与 Discord 的连接已关闭。")
+            logger.warning("[Discord] Connection with Discord has been closed.")
        except Exception as e:
-            logger.error(f"[Discord] 适配器运行时发生意外错误: {e}", exc_info=True)
+            logger.error(
+                f"[Discord] Unexpected error while adapter is running: {e}",
+                exc_info=True,
+            )

    def _get_message_type(
        self,
@@ -241,7 +253,7 @@ class DiscordPlatformAdapter(Platform):
                    )
        abm.message = message_chain
        abm.raw_message = message
-        abm.self_id = cast(str, self.client_self_id)
+        abm.self_id = cast(str, self.bot_self_id)
        abm.session_id = str(message.channel.id)
        abm.message_id = str(message.id)
        return abm
@@ -264,7 +276,7 @@ class DiscordPlatformAdapter(Platform):

        if self.client.user is None:
            logger.error(
-                "[Discord] 客户端未就绪 (self.client.user is None)，无法处理消息"
+                "[Discord] Client is not ready (self.client.user is None); message handling skipped"
            )
            return

@@ -283,7 +295,7 @@ class DiscordPlatformAdapter(Platform):
        raw_message = message.raw_message
        if not isinstance(raw_message, discord.Message):
            logger.warning(
-                f"[Discord] 收到非 Message 类型的消息: {type(raw_message)}，已忽略。"
+                f"[Discord] Non-Message type received and ignored: {type(raw_message)}"
            )
            return

@@ -324,20 +336,9 @@ class DiscordPlatformAdapter(Platform):

    @override
    async def terminate(self) -> None:
-        """终止适配器"""
-        logger.info("[Discord] 正在终止适配器... (step 1: cancel polling task)")
+        logger.info("[Discord] Shutting down adapter...")
        self.shutdown_event.set()
-        # 优先 cancel polling_task
-        if self._polling_task:
-            self._polling_task.cancel()
-            try:
-                await asyncio.wait_for(self._polling_task, timeout=10)
-            except asyncio.CancelledError:
-                logger.info("[Discord] polling_task 已取消。")
-            except Exception as e:
-                logger.warning(f"[Discord] polling_task 取消异常: {e}")
-        logger.info("[Discord] 正在清理已注册的斜杠指令... (step 2)")
-        # 清理指令
+        logger.info("[Discord] Cleaning up commands...")
        if self.enable_command_register and self.client:
            try:
                await asyncio.wait_for(
@@ -347,16 +348,29 @@ class DiscordPlatformAdapter(Platform):
                    ),
                    timeout=10,
                )
-                logger.info("[Discord] 指令清理完成。")
+                logger.info("[Discord] Commands cleaned up successfully.")
            except Exception as e:
-                logger.error(f"[Discord] 清理指令时发生错误: {e}", exc_info=True)
-        logger.info("[Discord] 正在关闭 Discord 客户端... (step 3)")
+                logger.warning(
+                    f"[Discord] Error occurred while cleaning up commands: {e}"
+                )
+
+        if self._polling_task:
+            self._polling_task.cancel()
+            try:
+                await asyncio.wait_for(self._polling_task, timeout=10)
+            except asyncio.CancelledError:
+                logger.info("[Discord] Polling task cancelled successfully.")
+            except Exception as e:
+                logger.warning(
+                    f"[Discord] Error occurred while cancelling polling task: {e}"
+                )
+        logger.info("[Discord] Closing client connection...")
        if self.client and hasattr(self.client, "close"):
            try:
                await asyncio.wait_for(self.client.close(), timeout=10)
            except Exception as e:
-                logger.warning(f"[Discord] 客户端关闭异常: {e}")
-        logger.info("[Discord] 适配器已终止。")
+                logger.warning(f"[Discord] Error occurred while closing client: {e}")
+        logger.info("[Discord] Adapter shutdown complete.")

    def register_handler(self, handler_info) -> None:
        """注册处理器信息"""
@@ -364,7 +378,7 @@ class DiscordPlatformAdapter(Platform):

    async def _collect_and_register_commands(self) -> None:
        """收集所有指令并注册到Discord"""
-        logger.info("[Discord] 开始收集并注册斜杠指令...")
+        logger.info("[Discord] Collecting and registering slash commands...")
        registered_commands = []

        for handler_md in star_handlers_registry:
@@ -405,15 +419,15 @@ class DiscordPlatformAdapter(Platform):

        if registered_commands:
            logger.info(
-                f"[Discord] 准备同步 {len(registered_commands)} 个指令: {', '.join(registered_commands)}",
+                f"[Discord] Ready to sync {len(registered_commands)} commands: {', '.join(registered_commands)}",
            )
        else:
-            logger.info("[Discord] 没有发现可注册的指令。")
+            logger.info("[Discord] No commands found for registration.")

        # 使用 Pycord 的方法同步指令
        # 注意：这可能需要一些时间，并且有频率限制
        await self.client.sync_commands()
-        logger.info("[Discord] 指令同步完成。")
+        logger.info("[Discord] Command synchronization completed.")

    def _create_dynamic_callback(self, cmd_name: str):
        """为每个指令动态创建一个异步回调函数"""
@@ -422,17 +436,17 @@ class DiscordPlatformAdapter(Platform):
            ctx: discord.ApplicationContext, params: str | None = None
        ) -> None:
            # 将平台特定的前缀'/'剥离，以适配通用的CommandFilter
-            logger.debug(f"[Discord] 回调函数触发: {cmd_name}")
-            logger.debug(f"[Discord] 回调函数参数: {ctx}")
-            logger.debug(f"[Discord] 回调函数参数: {params}")
+            logger.debug(f"[Discord] Callback triggered: {cmd_name}")
+            logger.debug(f"[Discord] Callback context: {ctx}")
+            logger.debug(f"[Discord] Callback params: {params}")
            message_str_for_filter = cmd_name
            if params:
                message_str_for_filter += f" {params}"

            logger.debug(
-                f"[Discord] 斜杠指令 '{cmd_name}' 被触发。 "
-                f"原始参数: '{params}'. "
-                f"构建的指令字符串: '{message_str_for_filter}'",
+                f"[Discord] Slash command '{cmd_name}' triggered. "
+                f"Raw params: '{params}'. "
+                f"Built command string: '{message_str_for_filter}'",
            )

            # 尝试立即响应，防止超时
@@ -441,7 +455,7 @@ class DiscordPlatformAdapter(Platform):
                await ctx.defer()
                followup_webhook = ctx.followup
            except Exception as e:
-                logger.warning(f"[Discord] 指令 '{cmd_name}' defer 失败: {e}")
+                logger.warning(f"[Discord] Failed to defer command '{cmd_name}': {e}")

            # 2. 构建 AstrBotMessage
            channel = ctx.channel
@@ -465,7 +479,7 @@ class DiscordPlatformAdapter(Platform):
            )
            abm.message = [Plain(text=message_str_for_filter)]
            abm.raw_message = ctx.interaction
-            abm.self_id = cast(str, self.client_self_id)
+            abm.self_id = cast(str, self.bot_self_id)
            abm.session_id = str(ctx.channel_id)
            abm.message_id = str(ctx.interaction.id)

@@ -503,10 +517,10 @@ class DiscordPlatformAdapter(Platform):

        # Discord 斜杠指令名称规范
        if not re.match(r"^[a-z0-9_-]{1,32}$", cmd_name):
-            logger.debug(f"[Discord] 跳过不符合规范的指令: {cmd_name}")
+            logger.debug(f"[Discord] Skipping invalid slash command format: {cmd_name}")
            return None

-        description = handler_metadata.desc or f"指令: {cmd_name}"
+        description = handler_metadata.desc or f"Command: {cmd_name}"
        if len(description) > 100:
            description = f"{description[:97]}..."

--- a/astrbot/core/platform/sources/misskey/misskey_adapter.py
+++ b/astrbot/core/platform/sources/misskey/misskey_adapter.py
@@ -93,7 +93,7 @@ class MisskeyPlatformAdapter(Platform):

        self.api: MisskeyAPI | None = None
        self._running = False
-        self.client_self_id = ""
+        self.bot_self_id = ""
        self._bot_username = ""
        self._user_cache = {}

@@ -138,10 +138,10 @@ class MisskeyPlatformAdapter(Platform):

        try:
            user_info = await self.api.get_current_user()
-            self.client_self_id = str(user_info.get("id", ""))
+            self.bot_self_id = str(user_info.get("id", ""))
            self._bot_username = user_info.get("username", "")
            logger.info(
-                f"[Misskey] 已连接用户: {self._bot_username} (ID: {self.client_self_id})",
+                f"[Misskey] 已连接用户: {self._bot_username} (ID: {self.bot_self_id})",
            )
        except Exception as e:
            logger.error(f"[Misskey] 获取用户信息失败: {e}")
@@ -312,9 +312,9 @@ class MisskeyPlatformAdapter(Platform):
            )
            room_id = data.get("toRoomId")
            logger.debug(
-                f"[Misskey] 收到聊天事件: sender_id={sender_id}, room_id={room_id}, is_self={sender_id == self.client_self_id}",
+                f"[Misskey] 收到聊天事件: sender_id={sender_id}, room_id={room_id}, is_self={sender_id == self.bot_self_id}",
            )
-            if sender_id == self.client_self_id:
+            if sender_id == self.bot_self_id:
                return

            if room_id:
@@ -354,13 +354,13 @@ class MisskeyPlatformAdapter(Platform):
        mentions = note.get("mentions", [])
        if self._bot_username and f"@{self._bot_username}" in text:
            return True
-        if self.client_self_id in [str(uid) for uid in mentions]:
+        if self.bot_self_id in [str(uid) for uid in mentions]:
            return True

        reply = note.get("reply")
        if reply and isinstance(reply, dict):
            reply_user_id = str(reply.get("user", {}).get("id", ""))
-            if reply_user_id == self.client_self_id:
+            if reply_user_id == self.bot_self_id:
                return bool(self._bot_username and f"@{self._bot_username}" in text)

        return False
@@ -598,7 +598,7 @@ class MisskeyPlatformAdapter(Platform):
                    visibility, visible_user_ids = resolve_message_visibility(
                        user_id=user_id_for_cache,
                        user_cache=self._user_cache,
-                        self_id=self.client_self_id,
+                        self_id=self.bot_self_id,
                        default_visibility=self.default_visibility,
                    )
                    logger.debug(
@@ -637,14 +637,14 @@ class MisskeyPlatformAdapter(Platform):
        message = create_base_message(
            raw_data,
            sender_info,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=False,
        )
        cache_user_info(
            self._user_cache,
            sender_info,
            raw_data,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=False,
        )

@@ -656,7 +656,7 @@ class MisskeyPlatformAdapter(Platform):
                message,
                raw_text,
                self._bot_username,
-                self.client_self_id,
+                self.bot_self_id,
            )
            message_parts.extend(text_parts)

@@ -685,14 +685,14 @@ class MisskeyPlatformAdapter(Platform):
        message = create_base_message(
            raw_data,
            sender_info,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=True,
        )
        cache_user_info(
            self._user_cache,
            sender_info,
            raw_data,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=True,
        )

@@ -713,7 +713,7 @@ class MisskeyPlatformAdapter(Platform):
        message = create_base_message(
            raw_data,
            sender_info,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=False,
            room_id=room_id,
        )
@@ -722,10 +722,10 @@ class MisskeyPlatformAdapter(Platform):
            self._user_cache,
            sender_info,
            raw_data,
-            self.client_self_id,
+            self.bot_self_id,
            is_chat=False,
        )
-        cache_room_info(self._user_cache, raw_data, self.client_self_id)
+        cache_room_info(self._user_cache, raw_data, self.bot_self_id)

        raw_text = raw_data.get("text", "")
        message_parts = []
@@ -736,7 +736,7 @@ class MisskeyPlatformAdapter(Platform):
                    message,
                    raw_text,
                    self._bot_username,
-                    self.client_self_id,
+                    self.bot_self_id,
                )
                message_parts.extend(text_parts)
            else:
--- a/astrbot/core/platform/sources/misskey/misskey_utils.py
+++ b/astrbot/core/platform/sources/misskey/misskey_utils.py
@@ -335,7 +335,7 @@ def extract_sender_info(
 def create_base_message(
    raw_data: dict[str, Any],
    sender_info: dict[str, Any],
-    client_self_id: str,
+    bot_self_id: str,
    is_chat: bool = False,
    room_id: str | None = None,
 ) -> AstrBotMessage:
@@ -367,7 +367,7 @@ def create_base_message(
        session_id if sender_info["sender_id"] else f"{session_prefix}%unknown"
    )
    message.message_id = str(raw_data.get("id", ""))
-    message.self_id = client_self_id
+    message.self_id = bot_self_id

    return message

@@ -376,7 +376,7 @@ def process_at_mention(
    message: AstrBotMessage,
    raw_text: str,
    bot_username: str,
-    client_self_id: str,
+    bot_self_id: str,
 ) -> tuple[list[str], str]:
    """处理@提及逻辑，返回消息部分列表和处理后的文本"""
    message_parts = []
@@ -386,7 +386,7 @@ def process_at_mention(

    if bot_username and raw_text.startswith(f"@{bot_username}"):
        at_mention = f"@{bot_username}"
-        message.message.append(Comp.At(qq=client_self_id))
+        message.message.append(Comp.At(qq=bot_self_id))
        remaining_text = raw_text[len(at_mention) :].strip()
        if remaining_text:
            message.message.append(Comp.Plain(remaining_text))
@@ -401,7 +401,7 @@ def cache_user_info(
    user_cache: dict[str, Any],
    sender_info: dict[str, Any],
    raw_data: dict[str, Any],
-    client_self_id: str,
+    bot_self_id: str,
    is_chat: bool = False,
 ) -> None:
    """缓存用户信息"""
@@ -410,7 +410,7 @@ def cache_user_info(
            "username": sender_info["username"],
            "nickname": sender_info["nickname"],
            "visibility": "specified",
-            "visible_user_ids": [client_self_id, sender_info["sender_id"]],
+            "visible_user_ids": [bot_self_id, sender_info["sender_id"]],
        }
    else:
        user_cache_data = {
@@ -428,7 +428,7 @@ def cache_user_info(
 def cache_room_info(
    user_cache: dict[str, Any],
    raw_data: dict[str, Any],
-    client_self_id: str,
+    bot_self_id: str,
 ) -> None:
    """缓存房间信息"""
    room_data = raw_data.get("toRoom")
@@ -442,7 +442,7 @@ def cache_room_info(
            "room_description": room_data.get("description", ""),
            "owner_id": room_data.get("ownerId", ""),
            "visibility": "specified",
-            "visible_user_ids": [client_self_id],
+            "visible_user_ids": [bot_self_id],
        }


--- a/astrbot/core/platform/sources/telegram/tg_adapter.py
+++ b/astrbot/core/platform/sources/telegram/tg_adapter.py
@@ -50,7 +50,6 @@ class TelegramPlatformAdapter(Platform):
    ) -> None:
        super().__init__(platform_config, event_queue)
        self.settings = platform_settings
-        self.client_self_id = uuid.uuid4().hex[:8]

        base_url = self.config.get(
            "telegram_api_base_url",
@@ -336,6 +335,8 @@ class TelegramPlatformAdapter(Platform):
            return None

        def _apply_caption() -> None:
+            if not update.message:
+                return
            if update.message.caption:
                message.message_str = update.message.caption
                message.message.append(Comp.Plain(message.message_str))
--- a/astrbot/core/platform/sources/wecom/wecom_adapter.py
+++ b/astrbot/core/platform/sources/wecom/wecom_adapter.py
@@ -148,7 +148,6 @@ class WecomPlatformAdapter(Platform):
    ) -> None:
        super().__init__(platform_config, event_queue)
        self.settingss = platform_settings
-        self.client_self_id = uuid.uuid4().hex[:8]
        self.api_base_url = platform_config.get(
            "api_base_url",
            "https://qyapi.weixin.qq.com/cgi-bin/",
--- a/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_adapter.py
+++ b/astrbot/core/platform/sources/weixin_official_account/weixin_offacc_adapter.py
@@ -2,7 +2,6 @@ import asyncio
 import os
 import sys
 import time
-import uuid
 from collections.abc import Callable, Coroutine
 from typing import Any, cast

@@ -324,7 +323,6 @@ class WeixinOfficialAccountPlatformAdapter(Platform):
    ) -> None:
        super().__init__(platform_config, event_queue)
        self.settingss = platform_settings
-        self.client_self_id = uuid.uuid4().hex[:8]
        self.api_base_url = platform_config.get(
            "api_base_url",
            "https://api.weixin.qq.com/cgi-bin/",
--- a/astrbot/core/provider/sources/bailian_rerank_source.py
+++ b/astrbot/core/provider/sources/bailian_rerank_source.py
@@ -142,7 +142,8 @@ class BailianRerankProvider(RerankProvider):
                f"百炼 API 错误: {data.get('code')} – {data.get('message', '')}"
            )

-        results = data.get("output", {}).get("results", [])
+        # 兼容旧版 API (output.results) 和新版 compatible API (results)
+        results = (data.get("output") or {}).get("results") or data.get("results") or []
        if not results:
            logger.warning(f"百炼 Rerank 返回空结果: {data}")
            return []
--- a/astrbot/core/provider/sources/openai_source.py
+++ b/astrbot/core/provider/sources/openai_source.py
@@ -457,6 +457,27 @@ class ProviderOpenAIOfficial(Provider):

        model = payloads.get("model", "").lower()

+        if "messages" in payloads and isinstance(payloads["messages"], list):
+            cleaned_messages = []
+            for idx, msg in enumerate(payloads["messages"]):
+                # 过滤空的 assistant 消息，防止严格 API（如 Moonshot）返回 400 错误
+                if msg.get("role") == "assistant":
+                    content = msg.get("content")
+                    tool_calls = msg.get("tool_calls")
+
+                    # 情况1: 空/null content 且无 tool_calls -> 过滤掉
+                    if not tool_calls and (content == "" or content is None):
+                        logger.warning(f"过滤第 {idx} 条空 assistant 消息 (无工具调用)")
+                        continue
+
+                    # 情况2: 空 content 但有 tool_calls -> 设为 None (符合 OpenAI 规范)
+                    if content == "" and tool_calls:
+                        msg["content"] = None
+
+                cleaned_messages.append(msg)
+
+            payloads["messages"] = cleaned_messages
+
        completion = await self.client.chat.completions.create(
            **payloads,
            stream=False,
@@ -589,7 +610,10 @@ class ProviderOpenAIOfficial(Provider):
    def _extract_usage(self, usage: CompletionUsage | dict) -> TokenUsage:
        ptd = getattr(usage, "prompt_tokens_details", None)
        cached = getattr(ptd, "cached_tokens", 0) if ptd else 0
-        prompt_tokens = getattr(usage, "prompt_tokens", 0) or 0
+        cached = (
+            cached if isinstance(cached, int) else 0
+        )  # ptd.cached_tokens 可能为None
+        prompt_tokens = getattr(usage, "prompt_tokens", 0) or 0  # 安全
        completion_tokens = getattr(usage, "completion_tokens", 0) or 0
        cached = cached or 0
        prompt_tokens = prompt_tokens or 0
--- a/astrbot/core/utils/requirements_utils.py
+++ b/astrbot/core/utils/requirements_utils.py
@@ -394,7 +394,6 @@ def find_missing_requirements(requirements_path: str) -> set[str] | None:
 def find_missing_requirements_from_lines(
    requirement_lines: Sequence[str],
 ) -> set[str] | None:
-
    required = list(iter_requirements(lines=requirement_lines))
    if not required:
        return set()
--- a/astrbot/dashboard/routes/knowledge_base.py
+++ b/astrbot/dashboard/routes/knowledge_base.py
@@ -314,7 +314,12 @@ class KnowledgeBaseRoute(Route):
            # 转换为字典列表
            kb_list = []
            for kb in kbs:
-                kb_list.append(kb.model_dump())
+                kb_dict = kb.model_dump()
+                # include init_error from KBHelper if present
+                kb_helper = await kb_manager.get_kb(kb.kb_id)
+                if kb_helper and kb_helper.init_error:
+                    kb_dict["init_error"] = kb_helper.init_error
+                kb_list.append(kb_dict)

            return (
                Response()
--- a/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css
+++ b/dashboard/src/assets/mdi-subset/materialdesignicons-subset.css
@@ -1,4 +1,4 @@
-/* Auto-generated MDI subset – 256 icons */
+/* Auto-generated MDI subset – 255 icons */
 /* Do not edit manually. Run: pnpm run subset-icons */

@font-face {
@@ -132,10 +132,6 @@
  content: "\F0B66";
 }

-.mdi-calendar-clock-outline::before {
-  content: "\F16E1";
-}
-
 .mdi-calendar-edit::before {
  content: "\F08A7";
 }
@@ -296,6 +292,10 @@
  content: "\F0193";
 }

+.mdi-content-save-outline::before {
+  content: "\F0818";
+}
+
 .mdi-creation::before {
  content: "\F0674";
 }
@@ -844,10 +844,6 @@
  content: "\F048A";
 }

-.mdi-send-clock-outline::before {
-  content: "\F1164";
-}
-
 .mdi-server::before {
  content: "\F048B";
 }
--- a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff
+++ b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff
--- a/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2
+++ b/dashboard/src/assets/mdi-subset/materialdesignicons-webfont-subset.woff2
--- a/dashboard/src/components/extension/PinnedPluginItem.vue
+++ b/dashboard/src/components/extension/PinnedPluginItem.vue
@@ -65,18 +65,26 @@ const authorDisplay = computed(() => {
  >
    <v-menu offset-y>
      <template #activator="{ props: menuProps }">
-        <v-avatar
-          v-bind="menuProps"
-          size="72"
-          class="pinned-avatar activator-avatar"
-          :title="plugin.display_name || plugin.name"
-        >
-          <img
-            :src="(typeof plugin.logo === 'string' && plugin.logo.trim()) ? plugin.logo : defaultPluginIcon"
-            :alt="plugin.name"
-            @error="handlePinnedImgError"
-          />
-        </v-avatar>
+        <div class="d-flex flex-column align-center" style="cursor: pointer; width: 80px;">
+          <v-avatar
+            v-bind="menuProps"
+            size="72"
+            class="pinned-avatar activator-avatar mb-1"
+            :title="plugin.display_name || plugin.name"
+          >
+            <img
+              :src="(typeof plugin.logo === 'string' && plugin.logo.trim()) ? plugin.logo : defaultPluginIcon"
+              :alt="plugin.name"
+              @error="handlePinnedImgError"
+            />
+          </v-avatar>
+          <span 
+            class="text-caption text-center text-truncate" 
+            style="width: 100%; font-size: 0.75rem; opacity: 0.9; line-height: 1.2;"
+          >
+            {{ plugin.display_name || plugin.name }}
+          </span>
+        </div>
      </template>

      <v-card>
@@ -182,8 +190,7 @@ const authorDisplay = computed(() => {
 .pinned-card-wrapper {
  position: relative;
  display: inline-block;
-  width: 72px;
-  height: 72px;
+  width: 80px;
 }

 .pinned-item {
--- a/dashboard/src/components/provider/ProviderModelsPanel.vue
+++ b/dashboard/src/components/provider/ProviderModelsPanel.vue
@@ -1,8 +1,10 @@
 <template>
-  <div class="mt-4">
-    <div class="d-flex align-center ga-2 mb-2">
-      <h3 class="text-h5 font-weight-bold mb-0">{{ tm('models.configured') }}</h3>
-      <small style="color: grey;" v-if="availableCount">{{ tm('models.available') }} {{ availableCount }}</small>
+  <div class="provider-models-panel">
+    <div class="provider-models-head">
+      <div class="provider-models-title-wrap">
+        <h3 class="provider-models-title">{{ tm('models.configured') }}</h3>
+        <small v-if="availableCount" class="provider-models-subtitle">{{ tm('models.available') }} {{ availableCount }}</small>
+      </div>
      <v-text-field
        v-model="modelSearchProxy"
        density="compact"
@@ -11,37 +13,35 @@
        hide-details
        variant="solo-filled"
        flat
-        class="ml-1"
-        style="max-width: 240px;"
+        class="provider-models-search"
        :placeholder="tm('models.searchPlaceholder')"
      />
-      <v-spacer></v-spacer>
-      <v-btn
-        color="primary"
-        prepend-icon="mdi-download"
-        :loading="loadingModels"
-        @click="emit('fetch-models')"
-        variant="tonal"
-        size="small"
-      >
-        {{ isSourceModified ? tm('providerSources.saveAndFetchModels') : tm('providerSources.fetchModels') }}
-      </v-btn>
-      <v-btn
-        color="primary"
-        prepend-icon="mdi-pencil-plus"
-        variant="text"
-        size="small"
-        class="ml-1"
-        @click="emit('open-manual-model')"
-      >
-        {{ tm('models.manualAddButton') }}
-      </v-btn>
+      <div class="provider-models-actions">
+        <v-btn
+          color="primary"
+          prepend-icon="mdi-download"
+          :loading="loadingModels"
+          @click="emit('fetch-models')"
+          variant="tonal"
+          size="small"
+        >
+          {{ isSourceModified ? tm('providerSources.saveAndFetchModels') : tm('providerSources.fetchModels') }}
+        </v-btn>
+        <v-btn
+          color="primary"
+          prepend-icon="mdi-pencil-plus"
+          variant="text"
+          size="small"
+          @click="emit('open-manual-model')"
+        >
+          {{ tm('models.manualAddButton') }}
+        </v-btn>
+      </div>
    </div>

    <v-list
      density="compact"
-      class="rounded-lg border"
-      style="max-height: 520px; overflow-y: auto; font-family:system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;"
+      class="provider-models-list"
    >
      <template v-if="entries.length > 0">
        <template v-for="entry in entries" :key="entry.type === 'configured' ? `provider-${entry.provider.id}` : `model-${entry.model}`">
@@ -55,7 +55,7 @@
                <v-list-item-title class="font-weight-medium text-truncate">
                  {{ entry.provider.id }}
                </v-list-item-title>
-            <v-list-item-subtitle class="text-caption text-grey d-flex align-center ga-1" style="font-family: monospace;">
+            <v-list-item-subtitle class="provider-model-subtitle d-flex align-center ga-1">
              <span>{{ entry.provider.model }}</span>
              <v-icon v-if="supportsImageInput(entry.metadata)" size="14" color="grey">
                mdi-eye-outline
@@ -124,7 +124,7 @@
            <template #activator="{ props }">
              <v-list-item v-bind="props" class="cursor-pointer" @click="emit('add-model-provider', entry.model)">
                <v-list-item-title>{{ entry.model }}</v-list-item-title>
-            <v-list-item-subtitle class="text-caption text-grey d-flex align-center ga-1">
+            <v-list-item-subtitle class="provider-model-subtitle d-flex align-center ga-1">
              <span>{{ entry.model }}</span>
              <v-icon v-if="supportsImageInput(entry.metadata)" size="14" color="grey">
                mdi-eye-outline
@@ -231,11 +231,87 @@ const isProviderTesting = (providerId) => props.testingProviders.includes(provid
 </script>

 <style scoped>
-.border {
-  border: 1px solid rgba(var(--v-border-color), var(--v-border-opacity));
+.provider-models-panel {
+  display: grid;
+  gap: 14px;
+}
+
+.provider-models-head {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+  flex-wrap: wrap;
+}
+
+.provider-models-title-wrap {
+  min-width: 0;
+}
+
+.provider-models-title {
+  margin: 0;
+  font-size: 18px;
+  line-height: 1.3;
+  font-weight: 650;
+}
+
+.provider-models-subtitle {
+  display: block;
+  margin-top: 6px;
+  color: rgba(var(--v-theme-on-surface), 0.6);
+  font-size: 12px;
+}
+
+.provider-models-search {
+  max-width: 240px;
+}
+
+.provider-models-actions {
+  margin-left: auto;
+  display: flex;
+  align-items: center;
+  gap: 6px;
+  flex-wrap: wrap;
+}
+
+.provider-models-list {
+  max-height: 520px;
+  overflow-y: auto;
+  border: 1px solid rgba(var(--v-theme-on-surface), 0.1);
+  border-radius: 14px;
+  background: rgb(var(--v-theme-surface));
+  font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif;
+}
+
+.provider-compact-item {
+  border-bottom: 1px solid rgba(var(--v-theme-on-surface), 0.08);
+}
+
+.provider-models-list :deep(.v-list-item:last-child) {
+  border-bottom: 0;
+}
+
+.provider-model-subtitle {
+  color: rgba(var(--v-theme-on-surface), 0.62);
+  font-family: ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, 'Liberation Mono', 'Courier New', monospace;
 }

 .cursor-pointer {
  cursor: pointer;
 }
+
+@media (max-width: 900px) {
+  .provider-models-head {
+    align-items: stretch;
+  }
+
+  .provider-models-search {
+    max-width: none;
+    width: 100%;
+  }
+
+  .provider-models-actions {
+    margin-left: 0;
+    width: 100%;
+  }
+}
 </style>
--- a/dashboard/src/components/provider/ProviderSourcesPanel.vue
+++ b/dashboard/src/components/provider/ProviderSourcesPanel.vue
@@ -1,8 +1,13 @@
 <template>
  <v-card class="provider-sources-panel h-100" elevation="0">
-    <div class="d-flex align-center justify-space-between px-4 pt-4 pb-2">
-      <div class="d-flex align-center ga-2">
-        <h3 class="mb-0">{{ tm('providerSources.title') }}</h3>
+    <div class="provider-sources-head">
+      <div class="provider-sources-title-wrap">
+        <div class="provider-sources-title-row">
+          <h3 class="provider-sources-title">{{ tm('providerSources.title') }}</h3>
+          <v-chip size="x-small" variant="tonal" label>
+            {{ displayedProviderSources.length }}
+          </v-chip>
+        </div>
      </div>
      <StyledMenu>
        <template #activator="{ props }">
@@ -11,7 +16,6 @@
            prepend-icon="mdi-plus"
            color="primary"
            variant="tonal"
-            rounded="xl"
            size="small"
          >
            {{ tm('providerSources.add') }}
@@ -34,7 +38,7 @@
      </StyledMenu>
    </div>

-    <div v-if="isMobile && displayedProviderSources.length > 0" class="px-4 pb-3">
+    <div v-if="isMobile && displayedProviderSources.length > 0" class="provider-sources-mobile">
      <div class="d-flex align-center ga-2">
        <v-select
          :model-value="selectedId"
@@ -71,7 +75,7 @@
      </div>
    </div>

-    <div v-else-if="displayedProviderSources.length > 0">
+    <div v-else-if="displayedProviderSources.length > 0" class="provider-sources-list-wrap">
      <v-list class="provider-source-list" nav density="compact" lines="two">
        <v-list-item
          v-for="source in displayedProviderSources"
@@ -83,13 +87,13 @@
          @click="emitSelectSource(source)"
        >
          <template #prepend>
-            <v-avatar size="32" class="bg-grey-lighten-4" rounded="0">
+            <v-avatar size="28" class="provider-source-avatar" rounded="0">
              <v-img v-if="source?.provider" :src="resolveSourceIcon(source)" alt="logo" cover></v-img>
-              <v-icon v-else size="32">mdi-creation</v-icon>
+              <v-icon v-else size="20">mdi-creation</v-icon>
            </v-avatar>
          </template>
-          <v-list-item-title class="font-weight-bold mb-1" style="font-family: Arial, Helvetica, sans-serif; font-size: 16px;">{{ getSourceDisplayName(source) }}</v-list-item-title>
-          <v-list-item-subtitle class="text-truncate">{{ source.api_base || 'N/A' }}</v-list-item-subtitle>
+          <v-list-item-title class="provider-source-title">{{ getSourceDisplayName(source) }}</v-list-item-title>
+          <v-list-item-subtitle class="provider-source-subtitle text-truncate">{{ source.api_base || 'N/A' }}</v-list-item-subtitle>
          <template #append>
            <div class="d-flex align-center ga-1">
              <v-btn
@@ -98,6 +102,7 @@
                variant="text"
                size="x-small"
                color="error"
+                :ripple="false"
                @click.stop="emitDeleteSource(source)"
              ></v-btn>
            </div>
@@ -181,22 +186,98 @@ const emitDeleteSource = (source) => emit('delete-provider-source', source)

 <style scoped>
 .provider-sources-panel {
+  border: 1px solid rgba(var(--v-theme-on-surface), 0.1);
+  border-radius: 16px;
+  background: rgb(var(--v-theme-surface));
  min-height: 320px;
+  overflow: hidden;
+}
+
+.provider-sources-head {
+  display: flex;
+  align-items: flex-start;
+  justify-content: space-between;
+  gap: 8px;
+  padding: 18px 18px 12px;
+  border-bottom: 1px solid rgba(var(--v-theme-on-surface), 0.1);
+}
+
+.provider-sources-title-row {
+  display: flex;
+  align-items: center;
+  gap: 6px;
+}
+
+.provider-sources-title {
+  margin: 0;
+  font-size: 17px;
+  line-height: 1.2;
+  font-weight: 650;
+}
+
+.provider-sources-mobile {
+  padding: 14px 18px 0;
+}
+
+.provider-sources-list-wrap {
+  padding: 8px 8px 10px;
 }

 .provider-source-list {
  max-height: calc(100vh - 335px);
  overflow-y: auto;
-  padding: 6px 8px;
+  padding: 0;
+  background: transparent;
 }

 .provider-source-list-item {
+  margin-bottom: 2px;
+  border: 1px solid transparent;
  transition: background-color 0.15s ease, border-color 0.15s ease;
+  background: transparent;
 }

 .provider-source-list-item--active {
-  background-color: #E8F0FE;
-  border: 1px solid rgba(var(--v-theme-primary), 0.25);
+  background-color: rgba(var(--v-theme-primary), 0.06);
+  border: 1px solid transparent;
+}
+
+.provider-source-avatar {
+  background: transparent !important;
+}
+
+.provider-source-title {
+  font-size: 15px;
+  font-weight: 650;
+  line-height: 1.4;
+}
+
+.provider-source-subtitle {
+  color: rgba(var(--v-theme-on-surface), 0.62);
+  font-size: 12px;
+  line-height: 1.5;
+}
+
+.provider-source-list :deep(.v-list-item__prepend) {
+  margin-inline-end: 10px;
+}
+
+.provider-source-list :deep(.v-list-item__content) {
+  min-width: 0;
+}
+
+.provider-source-list :deep(.v-list-item__append) {
+  opacity: 0;
+  transition: opacity 0.15s ease;
+}
+
+.provider-source-list-item:hover {
+  background-color: rgba(var(--v-theme-on-surface), 0.025);
+}
+
+.provider-source-list-item:hover :deep(.v-list-item__append),
+.provider-source-list-item--active :deep(.v-list-item__append) {
+  opacity: 1;
 }

@media (max-width: 960px) {
@@ -212,7 +293,7 @@ const emitDeleteSource = (source) => emit('delete-provider-source', source)

 <style>
 .v-theme--PurpleThemeDark .provider-source-list-item--active {
-  background-color: #2d2d2d;
-  border: none;
+  background-color: rgba(var(--v-theme-primary), 0.1);
+  border: 1px solid transparent;
 }
 </style>
--- a/dashboard/src/components/shared/ConsoleDisplayer.vue
+++ b/dashboard/src/components/shared/ConsoleDisplayer.vue
@@ -5,7 +5,7 @@ import { EventSourcePolyfill } from 'event-source-polyfill';
 </script>

 <template>
-  <div>
+  <div class="console-displayer-wrapper" id="console-wrapper">
    <div class="filter-controls mb-2" v-if="showLevelBtns">
      <v-chip-group v-model="selectedLevels" column multiple>
        <v-chip v-for="level in logLevels" :key="level" :color="getLevelColor(level)" filter variant="flat" size="small"
@@ -13,6 +13,14 @@ import { EventSourcePolyfill } from 'event-source-polyfill';
          {{ level }}
        </v-chip>
      </v-chip-group>
+      <v-spacer></v-spacer>
+      <v-btn
+        :icon="isFullscreen ? 'mdi-fullscreen-exit' : 'mdi-fullscreen'"
+        variant="text"
+        density="compact"
+        class="me-4 fullscreen-btn"
+        @click="toggleFullscreen"
+      ></v-btn>
    </div>

    <div id="term" style="background-color: #1e1e1e; padding: 16px; border-radius: 8px; overflow-y:auto; height: 100%">
@@ -26,6 +34,7 @@ export default {
  data() {
    return {
      autoScroll: true,
+      isFullscreen: false,
      logColorAnsiMap: {
        '\u001b[1;34m': 'color: #39C5BB; font-weight: bold;',
        '\u001b[1;36m': 'color: #00FFFF; font-weight: bold;',
@@ -80,8 +89,10 @@ export default {
  async mounted() {
    await this.fetchLogHistory();
    this.connectSSE();
+    document.addEventListener('fullscreenchange', this.handleFullscreenChange);
  },
  beforeUnmount() {
+    document.removeEventListener('fullscreenchange', this.handleFullscreenChange);
    if (this.eventSource) {
      this.eventSource.close();
      this.eventSource = null;
@@ -253,6 +264,21 @@ export default {
      this.autoScroll = !this.autoScroll;
    },

+    toggleFullscreen() {
+      const container = document.getElementById('console-wrapper');
+      if (!document.fullscreenElement) {
+        container.requestFullscreen().catch(err => {
+          console.error(`Error attempting to enable full-screen mode: ${err.message}`);
+        });
+      } else {
+        document.exitFullscreen();
+      }
+    },
+
+    handleFullscreenChange() {
+      this.isFullscreen = !!document.fullscreenElement;
+    },
+
    printLog(log) {
      let ele = document.getElementById('term')
      if (!ele) {
@@ -282,14 +308,30 @@ export default {
 </script>

 <style scoped>
+.console-displayer-wrapper {
+  height: 100%;
+  display: flex;
+  flex-direction: column;
+}
+
+#console-wrapper:fullscreen {
+  background-color: #1e1e1e;
+  padding: 20px;
+}
+
 .filter-controls {
  display: flex;
+  align-items: center;
  flex-wrap: wrap;
  gap: 8px;
  margin-bottom: 8px;
  margin-left: 20px;
 }

+.fullscreen-btn {
+    color: rgba(255, 255, 255, 0.7) !important; /* 提高在深色背景下的对比度 */
+}
+
 :deep(.console-log-line) {
  display: block;
  margin-bottom: 2px;
--- a/dashboard/src/i18n/locales/en-US/features/knowledge-base/index.json
+++ b/dashboard/src/i18n/locales/en-US/features/knowledge-base/index.json
@@ -10,7 +10,8 @@
    "loading": "Loading...",
    "documents": "Documents",
    "chunks": "Chunks",
-    "sessionConfig": "Session Config"
+    "sessionConfig": "Session Config",
+    "initError": "Initialization Failed"
  },
  "card": {
    "edit": "Edit",
--- a/dashboard/src/i18n/locales/ru-RU/features/knowledge-base/index.json
+++ b/dashboard/src/i18n/locales/ru-RU/features/knowledge-base/index.json
@@ -10,7 +10,8 @@
        "loading": "Загрузка...",
        "documents": "док.",
        "chunks": "фрагм.",
-        "sessionConfig": "Профиль"
+        "sessionConfig": "Профиль",
+        "initError": "Ошибка инициализации"
    },
    "card": {
        "edit": "Изменить",
--- a/dashboard/src/i18n/locales/zh-CN/features/knowledge-base/index.json
+++ b/dashboard/src/i18n/locales/zh-CN/features/knowledge-base/index.json
@@ -10,7 +10,8 @@
    "loading": "正在加载...",
    "documents": "文档",
    "chunks": "分块",
-    "sessionConfig": "会话配置"
+    "sessionConfig": "会话配置",
+    "initError": "初始化失败"
  },
  "card": {
    "edit": "编辑",
--- a/dashboard/src/main.ts
+++ b/dashboard/src/main.ts
@@ -10,9 +10,33 @@ import VueApexCharts from 'vue3-apexcharts';

 import print from 'vue3-print-nb';
 import { loader } from '@guolao/vue-monaco-editor'
+import * as monaco from 'monaco-editor';
+import editorWorker from 'monaco-editor/esm/vs/editor/editor.worker?worker';
+import jsonWorker from 'monaco-editor/esm/vs/language/json/json.worker?worker';
+import cssWorker from 'monaco-editor/esm/vs/language/css/css.worker?worker';
+import htmlWorker from 'monaco-editor/esm/vs/language/html/html.worker?worker';
+import tsWorker from 'monaco-editor/esm/vs/language/typescript/ts.worker?worker';
 import axios from 'axios';
 import { waitForRouterReadyInBackground } from './utils/routerReadiness.mjs';

+(self as any).MonacoEnvironment = {
+  getWorker(_: string, label: string) {
+    if (label === 'json') {
+      return new jsonWorker();
+    }
+    if (label === 'css' || label === 'scss' || label === 'less') {
+      return new cssWorker();
+    }
+    if (label === 'html' || label === 'handlebars' || label === 'razor') {
+      return new htmlWorker();
+    }
+    if (label === 'typescript' || label === 'javascript') {
+      return new tsWorker();
+    }
+    return new editorWorker();
+  },
+};
+
 // 初始化新的i18n系统，等待完成后再挂载应用
 setupI18n().then(async () => {
  console.log('🌍 新i18n系统初始化完成');
@@ -112,8 +136,4 @@ window.fetch = (input: RequestInfo | URL, init?: RequestInit) => {
  return _origFetch(input, { ...init, headers });
 };

-loader.config({
-  paths: {
-    vs: 'https://cdn.jsdelivr.net/npm/monaco-editor@0.54.0/min/vs',
-  },
-})
+loader.config({ monaco })
--- a/dashboard/src/stores/auth.ts
+++ b/dashboard/src/stores/auth.ts
@@ -25,12 +25,47 @@ export const useAuthStore = defineStore({
        localStorage.setItem('user', this.username);
        localStorage.setItem('token', res.data.data.token);
        localStorage.setItem('change_pwd_hint', res.data.data?.change_pwd_hint);
+        
+        const onboardingCompleted = await this.checkOnboardingCompleted();
        this.returnUrl = null;
-        router.push('/welcome');
+        if (onboardingCompleted) {
+          router.push('/dashboard/default');
+        } else {
+          router.push('/welcome');
+        }
      } catch (error) {
        return Promise.reject(error);
      }
    },
+    async checkOnboardingCompleted(): Promise<boolean> {
+      try {
+        // 1. 检查平台配置
+        const platformRes = await axios.get('/api/config/get');
+        const hasPlatform = (platformRes.data.data.config.platform || []).length > 0;
+        if (!hasPlatform) return false;
+
+        // 2. 检查提供者配置
+        const providerRes = await axios.get('/api/config/provider/template');
+        const providers = providerRes.data.data?.providers || [];
+        const sources = providerRes.data.data?.provider_sources || [];
+        const sourceMap = new Map();
+        sources.forEach((s: any) => sourceMap.set(s.id, s.provider_type));
+        
+        const hasProvider = providers.some((provider: any) => {
+          if (provider.provider_type) return provider.provider_type === 'chat_completion';
+          if (provider.provider_source_id) {
+            const type = sourceMap.get(provider.provider_source_id);
+            if (type === 'chat_completion') return true;
+          }
+          return String(provider.type || '').includes('chat_completion');
+        });
+
+        return hasProvider;
+      } catch (e) {
+        console.error('Failed to check onboarding status:', e);
+        return false;
+      }
+    },
    logout() {
      this.username = '';
      localStorage.removeItem('user');
--- a/dashboard/src/views/ConversationPage.vue
+++ b/dashboard/src/views/ConversationPage.vue
@@ -94,7 +94,21 @@

                        <template v-slot:item.title="{ item }">
                            <div class="conversation-title-cell">
-                                <span class="conversation-title-text">{{ item.title || tm('status.noTitle') }}</span>
+                                <div class="conversation-title-row">
+                                    <span class="conversation-title-text">{{ item.title || tm('status.noTitle') }}</span>
+                                    <v-btn
+                                        icon
+                                        variant="plain"
+                                        size="x-small"
+                                        density="compact"
+                                        :ripple="false"
+                                        class="conversation-inline-edit"
+                                        @click.stop="editConversation(item)"
+                                        :disabled="loading"
+                                    >
+                                        <v-icon size="14">mdi-pencil</v-icon>
+                                    </v-btn>
+                                </div>
                                <span class="conversation-title-meta">{{ item.cid || tm('status.unknown') }}</span>
                            </div>
                        </template>
@@ -141,10 +155,6 @@
                                    @click="viewConversation(item)" :disabled="loading">
                                    <v-icon>mdi-eye</v-icon>
                                </v-btn>
-                                <v-btn icon variant="plain" size="x-small" class="action-button"
-                                    @click="editConversation(item)" :disabled="loading">
-                                    <v-icon>mdi-pencil</v-icon>
-                                </v-btn>
                                <v-btn icon color="error" variant="plain" size="x-small" class="action-button"
                                    @click="confirmDeleteConversation(item)" :disabled="loading">
                                    <v-icon>mdi-delete</v-icon>
@@ -1188,14 +1198,29 @@ export default {
    max-width: 145px;
 }

+.conversation-title-row {
+    display: flex;
+    align-items: center;
+    gap: 2px;
+    min-width: 0;
+}
+
 .conversation-title-text {
    display: inline-block;
-    width: 100%;
+    flex: 1;
+    min-width: 0;
    white-space: nowrap;
    overflow: hidden;
    text-overflow: ellipsis;
 }

+.conversation-inline-edit {
+    width: 18px;
+    height: 18px;
+    min-width: 18px;
+    flex-shrink: 0;
+}
+
 .conversation-title-meta {
    display: block;
    color: rgba(var(--v-theme-on-surface), 0.58);
--- a/dashboard/src/views/ProviderPage.vue
+++ b/dashboard/src/views/ProviderPage.vue
@@ -29,9 +29,9 @@
        </v-tabs>

        <!-- Chat Completion: 左侧列表 + 右侧上下卡片布局 -->
-        <div v-if="selectedProviderType === 'chat_completion'" class="d-flex align-center justify-center">
-          <v-row style="max-width: 1500px; ">
-            <v-col cols="12" md="4" lg="3" class="pr-md-4">
+        <div v-if="selectedProviderType === 'chat_completion'" class="provider-workbench">
+          <v-row class="provider-workbench__shell">
+            <v-col cols="12" md="4" lg="3" class="provider-workbench__sources">
              <ProviderSourcesPanel
                :displayed-provider-sources="displayedProviderSources"
                :selected-provider-source="selectedProviderSource"
@@ -45,66 +45,77 @@
              />
            </v-col>

-            <v-col cols="12" md="8" lg="9">
-              <v-card class="provider-config-card h-100" elevation="0" style="overflow-y: auto;">
-                <v-card-title class="d-flex align-center justify-space-between flex-wrap ga-3 pt-4 pl-5">
-                  <div class="d-flex align-center ga-3" v-if="selectedProviderSource">
-                    <div>
-                      <div class="text-h4 font-weight-bold">{{ selectedProviderSource.id }}</div>
-                      <div class="text-caption text-medium-emphasis">{{ selectedProviderSource.api_base || 'N/A' }}
-                      </div>
+            <v-col cols="12" md="8" lg="9" class="provider-workbench__settings">
+              <v-card class="provider-config-card provider-settings-panel h-100" elevation="0">
+                <div v-if="selectedProviderSource" class="provider-config-header">
+                  <div class="provider-config-headline">
+                    <div class="provider-config-kicker">{{ tm('providers.settings') }}</div>
+                    <div class="provider-config-title">{{ selectedProviderSource.id }}</div>
+                    <div class="provider-config-subtitle">
+                      {{ selectedProviderSource.api_base || 'N/A' }}
                    </div>
                  </div>

-                  <div class="d-flex align-center ga-2" v-if="selectedProviderSource">
-                    <v-btn color="success" prepend-icon="mdi-check" :loading="savingSource"
-                      :disabled="!isSourceModified" @click="saveProviderSource" variant="flat">
+                  <div class="provider-config-actions">
+                    <v-btn
+                      color="primary"
+                      prepend-icon="mdi-content-save-outline"
+                      :loading="savingSource"
+                      :disabled="!isSourceModified"
+                      @click="saveProviderSource"
+                      variant="tonal"
+                    >
                      {{ tm('providerSources.save') }}
                    </v-btn>
                  </div>
-                </v-card-title>
+                </div>

-                <v-card-text>
+                <v-card-text class="provider-config-body">
                  <template v-if="selectedProviderSource">
-                    <div>
+                    <section class="provider-section">
+                      <div class="provider-section-head">
+                        <div class="provider-section-title">{{ tm('providers.settings') }}</div>
+                      </div>
                      <AstrBotConfig v-if="basicSourceConfig" :iterable="basicSourceConfig" :metadata="providerSourceSchema"
                        metadataKey="provider" :is-editing="true" />
-                    </div>
+                    </section>

-                    <v-expansion-panels variant="accordion" class="mb-2">
-                      <v-expansion-panel elevation="0" class="border rounded-lg">
-                        <v-expansion-panel-title>
-                          <span class="font-weight-medium">{{ tm('providerSources.advancedConfig') }}</span>
-                        </v-expansion-panel-title>
-                        <v-expansion-panel-text>
-                          <AstrBotConfig v-if="advancedSourceConfig" :iterable="advancedSourceConfig"
-                            :metadata="providerSourceSchema" metadataKey="provider" :is-editing="true" />
-                        </v-expansion-panel-text>
-                      </v-expansion-panel>
-                    </v-expansion-panels>
+                    <section v-if="advancedSourceConfig" class="provider-section">
+                      <div class="provider-section-head">
+                        <div class="provider-section-title">{{ tm('providerSources.advancedConfig') }}</div>
+                      </div>
+                      <AstrBotConfig
+                        :iterable="advancedSourceConfig"
+                        :metadata="providerSourceSchema"
+                        metadataKey="provider"
+                        :is-editing="true"
+                      />
+                    </section>

-                    <ProviderModelsPanel
-                      :entries="filteredMergedModelEntries"
-                      :available-count="availableModels.length"
-                      v-model:model-search="modelSearch"
-                      :loading-models="loadingModels"
-                      :is-source-modified="isSourceModified"
-                      :supports-image-input="supportsImageInput"
-                      :supports-tool-call="supportsToolCall"
-                      :supports-reasoning="supportsReasoning"
-                      :format-context-limit="formatContextLimit"
-                      :testing-providers="testingProviders"
-                      :tm="tm"
-                      @fetch-models="fetchAvailableModels"
-                      @open-manual-model="openManualModelDialog"
-                      @open-provider-edit="openProviderEdit"
-                      @toggle-provider-enable="toggleProviderEnable"
-                      @test-provider="testProvider"
-                      @delete-provider="deleteProvider"
-                      @add-model-provider="addModelProvider"
-                    />
+                    <section class="provider-section provider-section--models">
+                      <ProviderModelsPanel
+                        :entries="filteredMergedModelEntries"
+                        :available-count="availableModels.length"
+                        v-model:model-search="modelSearch"
+                        :loading-models="loadingModels"
+                        :is-source-modified="isSourceModified"
+                        :supports-image-input="supportsImageInput"
+                        :supports-tool-call="supportsToolCall"
+                        :supports-reasoning="supportsReasoning"
+                        :format-context-limit="formatContextLimit"
+                        :testing-providers="testingProviders"
+                        :tm="tm"
+                        @fetch-models="fetchAvailableModels"
+                        @open-manual-model="openManualModelDialog"
+                        @open-provider-edit="openProviderEdit"
+                        @toggle-provider-enable="toggleProviderEnable"
+                        @test-provider="testProvider"
+                        @delete-provider="deleteProvider"
+                        @add-model-provider="addModelProvider"
+                      />
+                    </section>
                  </template>
-                  <div v-else class="text-center py-8 text-medium-emphasis">
+                  <div v-else class="provider-empty-state">
                    <v-icon size="48" color="grey-lighten-1">mdi-cursor-default-click</v-icon>
                    <p class="mt-2">{{ tm('providerSources.selectHint') }}</p>
                  </div>
@@ -665,18 +676,141 @@ function goToConfigPage() {

 <style scoped>
 .provider-page {
+  --provider-surface: rgb(var(--v-theme-surface));
+  --provider-text: rgb(var(--v-theme-on-surface));
+  --provider-muted: rgba(var(--v-theme-on-surface), 0.68);
+  --provider-subtle: rgba(var(--v-theme-on-surface), 0.56);
+  --provider-border: rgba(var(--v-theme-on-surface), 0.1);
+  --provider-border-strong: rgba(var(--v-theme-on-surface), 0.14);
+  --provider-soft: rgba(var(--v-theme-primary), 0.08);
  padding: 20px;
  padding-top: 8px;
  padding-bottom: 40px;
 }

+.provider-workbench {
+  display: flex;
+  justify-content: center;
+}
+
+.provider-workbench__shell {
+  width: 100%;
+  max-width: 1500px;
+}
+
+.provider-workbench__sources,
+.provider-workbench__settings {
+  min-width: 0;
+}
+
 .provider-config-card {
  min-height: 280px;
+  border: 1px solid var(--provider-border);
+  border-radius: 16px;
+  background: var(--provider-surface);
+  overflow: hidden;
+}
+
+.provider-settings-panel {
+  display: flex;
+  flex-direction: column;
+}
+
+.provider-config-header {
+  display: flex;
+  justify-content: space-between;
+  align-items: flex-start;
+  gap: 12px;
+  padding: 20px 20px 16px;
+  border-bottom: 1px solid var(--provider-border);
+}
+
+.provider-config-headline {
+  min-width: 0;
+}
+
+.provider-config-kicker {
+  color: var(--provider-subtle);
+  font-size: 12px;
+  font-weight: 600;
+  letter-spacing: 0.08em;
+  text-transform: uppercase;
+}
+
+.provider-config-title {
+  margin-top: 8px;
+  font-size: 22px;
+  line-height: 1.1;
+  font-weight: 650;
+  letter-spacing: -0.03em;
+  overflow-wrap: anywhere;
+  color: var(--provider-text);
+}
+
+.provider-config-subtitle {
+  margin-top: 8px;
+  color: var(--provider-muted);
+  font-size: 13px;
+  line-height: 1.6;
+  overflow-wrap: anywhere;
+}
+
+.provider-config-actions {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  flex-shrink: 0;
+}
+
+.provider-config-body {
+  display: grid;
+  gap: 14px;
+  padding: 18px 20px 20px;
+}
+
+.provider-section {
+  border: 1px solid var(--provider-border);
+  border-radius: 14px;
+  background: rgba(var(--v-theme-primary), 0.02);
+  padding: 16px;
+}
+
+.provider-section--models {
+  padding: 18px;
+}
+
+.provider-section-head {
+  margin-bottom: 10px;
+}
+
+.provider-section-title {
+  font-size: 16px;
+  font-weight: 650;
+  line-height: 1.4;
+  color: var(--provider-text);
+}
+
+.provider-empty-state {
+  min-height: 420px;
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  justify-content: center;
+  color: var(--provider-muted);
 }

@media (max-width: 960px) {
  .provider-config-card {
    min-height: auto;
  }
+
+  .provider-config-header {
+    flex-direction: column;
+    align-items: flex-start;
+  }
+
+  .provider-config-body {
+    padding: 18px;
+  }
 }
 </style>
--- a/dashboard/src/views/authentication/auth/LoginPage.vue
+++ b/dashboard/src/views/authentication/auth/LoginPage.vue
@@ -22,10 +22,15 @@ function toggleTheme() {
  theme.global.name.value = newTheme;
 }

-onMounted(() => {
+onMounted(async () => {
  // 检查用户是否已登录，如果已登录则重定向
  if (authStore.has_token()) {
-    router.push('/welcome');
+    const onboardingCompleted = await authStore.checkOnboardingCompleted();
+    if (onboardingCompleted) {
+      router.push('/dashboard/default');
+    } else {
+      router.push('/welcome');
+    }
    return;
  }

--- a/dashboard/src/views/knowledge-base/KBList.vue
+++ b/dashboard/src/views/knowledge-base/KBList.vue
@@ -27,14 +27,27 @@
    </div>

    <div v-else-if="kbList.length > 0" class="kb-grid">
-      <v-card v-for="kb in kbList" :key="kb.kb_id" class="kb-card" elevation="2" hover
-        @click="navigateToDetail(kb.kb_id)">
-        <div class="kb-card-content">
+      <v-card v-for="kb in kbList" :key="kb.kb_id" class="kb-card" elevation="2" :hover="!kb.init_error"
+        :class="{ 'kb-card-error': kb.init_error }"
+        @click="!kb.init_error && navigateToDetail(kb.kb_id)">
+        <!-- Error badge -->
+        <v-badge v-if="kb.init_error" color="error" icon="mdi-alert-circle"
+          class="kb-error-badge position-absolute" style="top: 0; right: 0; transform: translate(34%, -34%);" />
+        <div class="kb-card-content" :class="{ 'kb-card-content-error': kb.init_error }">
          <div class="kb-emoji">{{ kb.emoji || '📚' }}</div>
          <h3 class="kb-name">{{ kb.kb_name }}</h3>
-          <p class="kb-description text-medium-emphasis">{{ kb.description || '暂无描述' }}</p>
+          <p v-if="!kb.init_error" class="kb-description text-medium-emphasis">{{ kb.description || '暂无描述' }}</p>

-          <div class="kb-stats mt-4">
+          <!-- Error message display -->
+          <div v-if="kb.init_error" class="kb-error-panel mt-3 mb-2">
+            <div class="kb-error-title">
+              <v-icon size="16" color="error">mdi-close-circle</v-icon>
+              <span>{{ t('list.initError') }}</span>
+            </div>
+            <div class="kb-error-detail" :title="kb.init_error">{{ kb.init_error }}</div>
+          </div>
+
+          <div class="kb-stats mt-4" v-if="!kb.init_error">
            <div class="stat-item">
              <v-icon size="small" color="primary">mdi-file-document</v-icon>
              <span>{{ kb.doc_count || 0 }} {{ t('list.documents') }}</span>
@@ -45,8 +58,8 @@
            </div>
          </div>

-          <div class="kb-actions">
-            <v-btn icon="mdi-pencil" size="small" variant="text" color="info" @click.stop="editKB(kb)" />
+          <div class="kb-actions" :class="{ 'error-actions': kb.init_error }">
+            <v-btn v-if="!kb.init_error" icon="mdi-pencil" size="small" variant="text" color="info" @click.stop="editKB(kb)" />
            <v-btn icon="mdi-delete" size="small" variant="text" color="error" @click.stop="confirmDelete(kb)" />
          </div>
        </div>
@@ -478,6 +491,34 @@ onMounted(() => {
  box-shadow: 0 12px 24px rgba(0, 0, 0, 0.15) !important;
 }

+/* Error state card styles */
+.kb-card-error {
+  cursor: not-allowed;
+  border: 1px solid rgba(var(--v-theme-error), 0.3);
+  background-color: rgba(var(--v-theme-error), 0.02) !important;
+  overflow: visible; /* Allow badge to overflow */
+}
+
+.kb-card-error:hover {
+  transform: none;
+  box-shadow: 0 4px 12px rgba(var(--v-theme-error), 0.1) !important;
+  border-color: rgba(var(--v-theme-error), 0.5);
+}
+
+.kb-card-error .kb-emoji {
+  opacity: 0.7;
+  filter: grayscale(0.5);
+}
+
+.kb-card-error .kb-name {
+  color: rgba(var(--v-theme-on-surface), 0.7);
+}
+
+.kb-error-badge {
+  z-index: 10;
+  opacity: 0.9;
+}
+
 .kb-card-content {
  padding: 24px;
  display: flex;
@@ -488,6 +529,11 @@ onMounted(() => {
  position: relative;
 }

+.kb-card-content-error {
+  justify-content: center;
+  gap: 8px;
+}
+
 .kb-emoji {
  font-size: 56px;
  margin-bottom: 8px;
@@ -518,6 +564,36 @@ onMounted(() => {
  justify-content: center;
 }

+.kb-error-panel {
+  width: 100%;
+  text-align: left;
+  background: rgba(var(--v-theme-error), 0.08);
+  border: 1px solid rgba(var(--v-theme-error), 0.18);
+  border-radius: 10px;
+  padding: 10px 12px;
+}
+
+.kb-error-title {
+  display: flex;
+  align-items: center;
+  gap: 8px;
+  font-size: 0.8rem;
+  font-weight: 600;
+  color: rgb(var(--v-theme-error));
+  margin-bottom: 4px;
+}
+
+.kb-error-detail {
+  font-size: 0.78rem;
+  line-height: 1.35;
+  color: rgba(var(--v-theme-on-surface), 0.82);
+  word-break: break-word;
+  display: -webkit-box;
+  -webkit-line-clamp: 3;
+  -webkit-box-orient: vertical;
+  overflow: hidden;
+}
+
 .stat-item {
  display: flex;
  align-items: center;
--- a/docs/en/deploy/astrbot/package.md
+++ b/docs/en/deploy/astrbot/package.md
@@ -9,6 +9,11 @@ If `uv` is not installed, install it first by following the official guide:

 `uv` supports Linux, Windows, and macOS.

+## Important Notes
+
+> [!WARNING]
+> AstrBot deployed via `uv` **does not support upgrading through the WebUI**. To update, run `uv tool upgrade astrbot` from the command line.
+
 ## Install and Start

 ```bash
--- a/docs/zh/deploy/astrbot/package.md
+++ b/docs/zh/deploy/astrbot/package.md
@@ -8,6 +8,11 @@

 `uv` 支持 Linux、Windows、macOS。

+## 注意事项
+
+> [!WARNING]
+> 通过 `uv` 部署的 AstrBot **不支持在 WebUI 中进行版本升级**。如需更新，请在命令行中执行 `uv tool upgrade astrbot`。
+
 ## 安装并启动

 ```bash
--- a/docs/zh/platform/qqofficial/websockets.md
+++ b/docs/zh/platform/qqofficial/websockets.md
@@ -87,4 +87,4 @@

 ## 🎉 大功告成

-此时，你的 AstrBot 和 NapCatQQ 应该已经连接成功。使用 `私聊` 的方式在 QQ 对机器人发送 `/help` 以检查是否连接成功。
+此时，你的 AstrBot 应该已经成功连接 QQ 官方接口。使用 `私聊` 的方式在 QQ 对机器人发送 `/help` 以检查是否连接成功。
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -66,6 +66,7 @@ dependencies = [
  "shipyard-python-sdk>=0.2.4",
  "shipyard-neo-sdk>=0.2.0",
  "python-socks>=2.8.0",
+  "pysocks>=1.7.1",
  "packaging>=24.2",
 ]

--- a/requirements.txt
+++ b/requirements.txt
@@ -32,6 +32,7 @@ pydub>=0.25.1
 pyjwt>=2.10.1
 python-telegram-bot>=22.6
 qq-botpy>=1.2.1
+python-socks>=2.8.0
 quart>=0.20.0
 readability-lxml>=0.8.4.1
 silk-python>=0.2.6
@@ -45,6 +46,7 @@ wechatpy>=1.8.18
 audioop-lts ; python_full_version >= '3.13'
 click>=8.2.1
 pypdf>=6.1.1
+pysocks>=1.7.1
 aiofiles>=25.1.0
 rank-bm25>=0.2.2
 jieba>=0.42.1
@@ -54,3 +56,4 @@ tenacity>=9.1.2
 shipyard-python-sdk>=0.2.4
 shipyard-neo-sdk>=0.2.0
 packaging>=24.2
+qrcode>=8.2
--- a/tests/test_openai_source.py
+++ b/tests/test_openai_source.py
@@ -1173,3 +1173,360 @@ async def test_parse_openai_completion_raises_empty_model_output_error():
            await provider._parse_openai_completion(completion, tools=None)
    finally:
        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_filters_empty_assistant_message_without_tool_calls(monkeypatch):
+    """Test that empty assistant messages without tool_calls are filtered out."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "user", "content": "hello"},
+                {"role": "assistant", "content": ""},  # Should be filtered
+                {"role": "user", "content": "world"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # The empty assistant message should be filtered out
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 2
+        assert messages[0] == {"role": "user", "content": "hello"}
+        assert messages[1] == {"role": "user", "content": "world"}
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_filters_null_content_assistant_message_without_tool_calls(
+    monkeypatch,
+):
+    """Test that assistant messages with null content and no tool_calls are filtered."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "user", "content": "hello"},
+                {"role": "assistant", "content": None},  # Should be filtered
+                {"role": "user", "content": "world"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # The null content assistant message should be filtered out
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 2
+        assert messages[0] == {"role": "user", "content": "hello"}
+        assert messages[1] == {"role": "user", "content": "world"}
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_converts_empty_content_to_none_with_tool_calls(monkeypatch):
+    """Test that empty content with tool_calls is converted to None (OpenAI spec)."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "user", "content": "hello"},
+                {
+                    "role": "assistant",
+                    "content": "",
+                    "tool_calls": [
+                        {
+                            "id": "call-123",
+                            "type": "function",
+                            "function": {"name": "test", "arguments": "{}"},
+                        }
+                    ],
+                },
+                {"role": "user", "content": "world"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # The assistant message with tool_calls should be kept but content set to None
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 3
+        assert messages[1]["role"] == "assistant"
+        assert messages[1]["content"] is None
+        assert messages[1]["tool_calls"] is not None
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_keeps_valid_assistant_message_with_content(monkeypatch):
+    """Test that valid assistant messages with content are kept."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "user", "content": "hello"},
+                {"role": "assistant", "content": "response"},
+                {"role": "user", "content": "world"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # All messages should be kept
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 3
+        assert messages[1] == {"role": "assistant", "content": "response"}
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_keeps_assistant_message_with_tool_calls_and_none_content(
+    monkeypatch,
+):
+    """Test that assistant messages with tool_calls and None content are kept."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "user", "content": "hello"},
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call-123",
+                            "type": "function",
+                            "function": {"name": "test", "arguments": "{}"},
+                        }
+                    ],
+                },
+                {"role": "user", "content": "world"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # The assistant message with tool_calls should be kept
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 3
+        assert messages[1]["role"] == "assistant"
+        assert messages[1]["content"] is None
+        assert messages[1]["tool_calls"] is not None
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_query_does_not_filter_user_or_system_messages(monkeypatch):
+    """Test that user and system messages are not affected by the filter."""
+    provider = _make_provider()
+    try:
+        captured_kwargs = {}
+
+        async def fake_create(**kwargs):
+            captured_kwargs.update(kwargs)
+            return ChatCompletion.model_validate(
+                {
+                    "id": "chatcmpl-test",
+                    "object": "chat.completion",
+                    "created": 0,
+                    "model": "gpt-4o-mini",
+                    "choices": [
+                        {
+                            "index": 0,
+                            "message": {
+                                "role": "assistant",
+                                "content": "ok",
+                            },
+                            "finish_reason": "stop",
+                        }
+                    ],
+                    "usage": {
+                        "prompt_tokens": 1,
+                        "completion_tokens": 1,
+                        "total_tokens": 2,
+                    },
+                }
+            )
+
+        monkeypatch.setattr(provider.client.chat.completions, "create", fake_create)
+
+        payloads = {
+            "model": "gpt-4o-mini",
+            "messages": [
+                {"role": "system", "content": ""},  # Empty system message
+                {"role": "user", "content": ""},  # Empty user message
+                {"role": "assistant", "content": ""},  # Should be filtered
+                {"role": "user", "content": "hello"},
+            ],
+        }
+
+        await provider._query(payloads=payloads, tools=None)
+
+        # Only assistant message should be filtered
+        messages = captured_kwargs["messages"]
+        assert len(messages) == 3
+        assert messages[0] == {"role": "system", "content": ""}
+        assert messages[1] == {"role": "user", "content": ""}
+        assert messages[2] == {"role": "user", "content": "hello"}
+    finally:
+        await provider.terminate()
--- a/tests/unit/test_kb_manager_resilience.py
+++ b/tests/unit/test_kb_manager_resilience.py
@@ -0,0 +1,305 @@
+"""
+Unit tests for knowledge base manager resilience behavior.
+
+Tests the following scenarios:
+1. update_kb preserves old instance when re-initialization fails
+2. update_kb switches instance only after new instance initializes successfully
+3. _ensure_vec_db clears stale init_error after successful initialization
+
+These tests use lazy imports and mocks to avoid circular import issues
+in the astrbot core module chain.
+"""
+
+import sys
+import types
+from pathlib import Path
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+
+@pytest.fixture
+def stub_provider_manager_module():
+    """Stub provider manager module to avoid circular imports in unit tests."""
+    original_module = sys.modules.get("astrbot.core.provider.manager")
+    stub_module = types.ModuleType("astrbot.core.provider.manager")
+
+    class ProviderManager: ...
+
+    setattr(stub_module, "ProviderManager", ProviderManager)
+    sys.modules["astrbot.core.provider.manager"] = stub_module
+
+    try:
+        yield
+    finally:
+        if original_module is not None:
+            sys.modules["astrbot.core.provider.manager"] = original_module
+        else:
+            sys.modules.pop("astrbot.core.provider.manager", None)
+
+
+@pytest.fixture
+def mock_provider_manager():
+    """Create a mock ProviderManager."""
+    manager = MagicMock()
+    manager.get_provider_by_id = AsyncMock()
+    manager.acm = MagicMock()
+    manager.acm.default_conf = {}
+    return manager
+
+
+@pytest.fixture
+def mock_kb_db():
+    """Create a mock KBSQLiteDatabase."""
+    db = MagicMock()
+    db.get_db = MagicMock()
+    db.list_kbs = AsyncMock(return_value=[])
+    db.get_kb_by_id = AsyncMock()
+    return db
+
+
+@pytest.fixture
+def mock_knowledge_base():
+    """Create a mock KnowledgeBase instance."""
+    # Use lazy import to avoid circular import
+    from astrbot.core.knowledge_base.models import KnowledgeBase
+
+    kb = KnowledgeBase(
+        kb_name="test_kb",
+        description="Test knowledge base",
+        emoji="📚",
+        embedding_provider_id="test-embedding-provider",
+        rerank_provider_id=None,
+        chunk_size=512,
+        chunk_overlap=50,
+        top_k_dense=50,
+        top_k_sparse=50,
+        top_m_final=5,
+    )
+    return kb
+
+
+@pytest.fixture
+def mock_embedding_provider():
+    """Create a mock EmbeddingProvider."""
+    provider = MagicMock()
+    provider.get_embeddings_batch = AsyncMock(return_value=[[0.1, 0.2, 0.3]])
+    return provider
+
+
+@pytest.mark.asyncio
+async def test_update_kb_preserves_old_instance_when_reinit_fails(
+    stub_provider_manager_module,
+    mock_provider_manager,
+    mock_kb_db,
+    mock_knowledge_base,
+    mock_embedding_provider,
+):
+    """
+    Test that update_kb preserves the old KBHelper instance when
+    re-initialization fails, ensuring the knowledge base remains available.
+    """
+    # Lazy import to avoid circular import
+    from astrbot.core.knowledge_base.kb_helper import KBHelper
+    from astrbot.core.knowledge_base.kb_mgr import KnowledgeBaseManager
+
+    # Setup: create an existing KBHelper with working vec_db
+    mock_provider_manager.get_provider_by_id.return_value = mock_embedding_provider
+
+    # Create KBHelper using __new__ to avoid __init__ side effects
+    old_helper = KBHelper.__new__(KBHelper)
+    old_helper.kb = mock_knowledge_base
+    old_helper.prov_mgr = mock_provider_manager
+    old_helper.kb_db = mock_kb_db
+    old_helper.kb_root_dir = "/tmp/test_kb"
+    old_helper.chunker = MagicMock()
+    old_helper.init_error = None
+    old_helper.vec_db = MagicMock()  # Simulate existing working vec_db
+    old_helper.terminate = AsyncMock()
+
+    # Create KBManager and inject the existing helper
+    kb_mgr = KnowledgeBaseManager.__new__(KnowledgeBaseManager)
+    kb_mgr.provider_manager = mock_provider_manager
+    kb_mgr.kb_db = mock_kb_db
+    kb_mgr.kb_insts = {mock_knowledge_base.kb_id: old_helper}
+    kb_mgr.retrieval_manager = MagicMock()
+
+    # Mock KBHelper creation to simulate initialization failure
+    with patch.object(KBHelper, "initialize", new_callable=AsyncMock) as mock_init:
+        # First call (for new_helper) should fail
+        mock_init.side_effect = Exception("Embedding provider unavailable")
+
+        # Execute update_kb with a different embedding provider
+        result = await kb_mgr.update_kb(
+            kb_id=mock_knowledge_base.kb_id,
+            kb_name="updated_kb",
+            embedding_provider_id="new-embedding-provider",
+        )
+
+        # Verify: the old helper should be returned, not a new one
+        assert result is not None
+        assert result is old_helper
+        assert kb_mgr.kb_insts[mock_knowledge_base.kb_id] is old_helper
+
+        # Verify: old helper's vec_db should still be available
+        assert hasattr(result, "vec_db")
+        assert result.vec_db is not None
+
+        # Verify: failure does not replace the existing helper state
+        assert result.init_error is None
+        assert result.kb.kb_name == "test_kb"
+        assert result.kb.embedding_provider_id == "test-embedding-provider"
+
+
+@pytest.mark.asyncio
+async def test_update_kb_switches_instance_only_after_new_reinit_success(
+    stub_provider_manager_module,
+    mock_provider_manager,
+    mock_kb_db,
+    mock_knowledge_base,
+    mock_embedding_provider,
+):
+    """
+    Test that update_kb only switches to the new KBHelper instance
+    after the new instance successfully initializes.
+    """
+    # Lazy import to avoid circular import
+    from astrbot.core.knowledge_base.kb_helper import KBHelper
+    from astrbot.core.knowledge_base.kb_mgr import KnowledgeBaseManager
+
+    # Setup: create an existing KBHelper
+    mock_provider_manager.get_provider_by_id.return_value = mock_embedding_provider
+
+    old_helper = KBHelper.__new__(KBHelper)
+    old_helper.kb = mock_knowledge_base
+    old_helper.prov_mgr = mock_provider_manager
+    old_helper.kb_db = mock_kb_db
+    old_helper.kb_root_dir = "/tmp/test_kb"
+    old_helper.chunker = MagicMock()
+    old_helper.init_error = None
+    old_helper.vec_db = MagicMock()
+    old_helper.terminate = AsyncMock()
+
+    kb_mgr = KnowledgeBaseManager.__new__(KnowledgeBaseManager)
+    kb_mgr.provider_manager = mock_provider_manager
+    kb_mgr.kb_db = mock_kb_db
+    kb_mgr.kb_insts = {mock_knowledge_base.kb_id: old_helper}
+    kb_mgr.retrieval_manager = MagicMock()
+
+    # Mock session context for database operations
+    mock_session = MagicMock()
+    mock_session.add = MagicMock()
+    mock_session.commit = AsyncMock()
+    mock_session.refresh = AsyncMock()
+
+    mock_db_context = MagicMock()
+    mock_db_context.__aenter__ = AsyncMock(return_value=mock_session)
+    mock_db_context.__aexit__ = AsyncMock()
+    mock_kb_db.get_db.return_value = mock_db_context
+
+    # Mock KBHelper.initialize to succeed
+    with patch.object(KBHelper, "initialize", new_callable=AsyncMock) as mock_init:
+        mock_init.return_value = None
+
+        # Execute update_kb
+        result = await kb_mgr.update_kb(
+            kb_id=mock_knowledge_base.kb_id,
+            kb_name="updated_kb",
+            embedding_provider_id="new-embedding-provider",
+        )
+
+        # Verify: a new helper should be returned
+        assert result is not None
+        assert result is not old_helper
+        assert result.init_error is None
+        assert kb_mgr.kb_insts[mock_knowledge_base.kb_id] is result
+
+        # Verify: old helper should be terminated
+        old_helper.terminate.assert_called_once()
+
+
+@pytest.mark.asyncio
+async def test_ensure_vec_db_clears_stale_init_error(
+    stub_provider_manager_module,
+    mock_provider_manager,
+    mock_kb_db,
+    mock_knowledge_base,
+    mock_embedding_provider,
+):
+    """
+    Test that _ensure_vec_db clears the init_error attribute
+    after successful initialization, removing stale error state.
+    """
+    # Lazy import to avoid circular import
+    from astrbot.core.knowledge_base.kb_helper import KBHelper
+
+    # Setup: create KBHelper with stale init_error
+    mock_provider_manager.get_provider_by_id.return_value = mock_embedding_provider
+
+    helper = KBHelper.__new__(KBHelper)
+    helper.kb = mock_knowledge_base
+    helper.prov_mgr = mock_provider_manager
+    helper.kb_db = mock_kb_db
+    helper.kb_root_dir = "/tmp/test_kb"
+    helper.chunker = MagicMock()
+    helper.init_error = "Previous initialization failed"
+    helper.kb_dir = Path("/tmp/test_kb") / mock_knowledge_base.kb_id
+    helper.kb_medias_dir = helper.kb_dir / "medias" / mock_knowledge_base.kb_id
+    helper.kb_files_dir = helper.kb_dir / "files" / mock_knowledge_base.kb_id
+
+    # Mock FaissVecDB initialization
+    mock_vec_db = MagicMock()
+    mock_vec_db.initialize = AsyncMock()
+    mock_vec_db.close = AsyncMock()
+
+    with patch(
+        "astrbot.core.knowledge_base.kb_helper.FaissVecDB",
+        return_value=mock_vec_db,
+    ):
+        # Execute _ensure_vec_db
+        await helper._ensure_vec_db()
+
+        # Verify: init_error should be cleared
+        assert helper.init_error is None
+        assert helper.vec_db is mock_vec_db
+
+
+@pytest.mark.asyncio
+async def test_ensure_vec_db_sets_init_error_on_failure(
+    stub_provider_manager_module,
+    mock_provider_manager,
+    mock_kb_db,
+    mock_knowledge_base,
+):
+    """
+    Test that _ensure_vec_db does NOT clear init_error when
+    initialization fails, preserving the error state.
+    """
+    # Lazy import to avoid circular import
+    from astrbot.core.knowledge_base.kb_helper import KBHelper
+
+    # Setup: provider unavailable
+    mock_provider_manager.get_provider_by_id.return_value = None
+
+    helper = KBHelper.__new__(KBHelper)
+    helper.kb = mock_knowledge_base
+    helper.prov_mgr = mock_provider_manager
+    helper.kb_db = mock_kb_db
+    helper.kb_root_dir = "/tmp/test_kb"
+    helper.chunker = MagicMock()
+    helper.init_error = "Previous initialization failed"
+    helper.kb_dir = Path("/tmp/test_kb") / mock_knowledge_base.kb_id
+    helper.kb_medias_dir = helper.kb_dir / "medias" / mock_knowledge_base.kb_id
+    helper.kb_files_dir = helper.kb_dir / "files" / mock_knowledge_base.kb_id
+
+    # Execute _ensure_vec_db - should raise exception
+    try:
+        await helper._ensure_vec_db()
+        pytest.fail("Expected exception but none was raised")
+    except ValueError as e:
+        # Verify: exception should be raised
+        assert "无法找到" in str(e) or "未配置" in str(e)
+
+        # Verify: init_error should NOT be cleared (still has previous error)
+        # Note: _ensure_vec_db doesn't set init_error; that's done by the caller
+        assert helper.init_error is not None
Author	SHA1	Message	Date
Soulter	d612c9eed4	fix: english logging	2026-04-03 14:01:11 +08:00
Soulter	12039fe7d0	fix: resolve Discord/Misskey hot reload issue by fixing client_self_id misuse fixes: #7187 closes: #7188	2026-04-03 13:41:56 +08:00
Soulter	5886c43752	fix: add qrcode package for QR code generation support closes: #7327	2026-04-03 13:15:04 +08:00
氕氙	88d70a8013	docs: 在 uv 部署文档中添加不支持 WebUI 升级的说明 (#7298 ) * docs: 在 uv 部署文档中添加不支持 WebUI 升级的说明通过 astrbot run（CLI 模式）启动时，会设置 ASTRBOT_CLI 环境变量， updator 会拒绝 WebUI 触发的升级操作以避免版本管理混乱。用户需要通过命令行执行 uv tool upgrade astrbot 来更新。 Closes #7291 * Update README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update README_fr.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update README_ja.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update README_ru.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update README_zh-TW.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * Update README_zh.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --------- Co-authored-by: LIghtJUNction <lightjunction.me@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-04-03 09:03:29 +08:00
氕氙	9d4472cb2d	fix: 改进知识库的初始化错误处理 (#7243 ) * fix: 改进 KnowledgeBaseManager 和 KBHelper 中的初始化错误处理 * fix: 改进知识库初始化和重排序错误处理，增强日志记录 * fix: 改进知识库模块初始化和检索错误处理 * fix(ui): handle kb init errors in list cards display a dedicated error state for knowledge base cards that fail initialization, including a visible badge and error details prevent navigation and edit actions for failed cards while keeping delete available, and hide normal stats/description for error items add list.initError locale strings for en-US, ru-RU, and zh-CN * fix(kb): avoid replacing helper on init failure Initialize a new KB helper before swapping instances so a failed re-init does not break the active knowledge base service. If initialization fails, restore in-memory KB settings and keep the existing helper and previous init error state. Also clear stale init_error after successful vector DB initialization to prevent outdated error reporting. * test(kb): add kb manager resilience tests cover initialization failure and recovery scenarios to guard against regressions in kb error handling include reference assets under refs for test validation --------- Co-authored-by: RC-CHN <1051989940@qq.com>	2026-04-02 16:16:22 +08:00
M1LKT	e8d6938d31	Feat(webui): dashboard and console qol improvements (#7215 ) * feat: support native fullscreen for log console * feat: skip welcome page for configured users * feat: display plugin names under pinned icons * fix: refine container styles	2026-04-02 13:40:21 +08:00
RichardLiu	206973e8ad	Docs/update mimo provider readme (#7207 ) * feat: add mimo tts provider support * fix: handle empty mimo tts choices * feat: add mimo stt provider support * fix: align mimo tts style payload with official docs * docs: add Xiaomi MiMo Omni and TTS services to multiple language READMEs	2026-04-02 10:25:19 +08:00
kaixinyujue	0ecddb4c06	修复：过滤空助手消息，以防止在严格API上出现400错误（fix: filter empty assistant messages to prevent 400 error on strict APIs） (#7202 ) * fix: filter empty assistant messages to prevent 400 error on strict APIs Some OpenAI-compatible APIs (e.g., Moonshot) reject requests with empty content in assistant messages when no tool_calls are present. This fix cleans up the messages payload before sending to avoid 'message at position X must not be empty' errors. Closes related issue with fallback provider behavior. * test(openai): add tests for empty assistant message filtering * refactor(openai): simplify empty assistant message filtering logic * style: format code --------- Co-authored-by: RC-CHN <1051989940@qq.com>	2026-04-02 09:10:06 +08:00
Thelia	2de23184d0	Update connection success message for AstrBot (#7279 )	2026-04-02 08:49:48 +08:00
Yufeng He	4d2791aa9a	fix: support both old and new Bailian Rerank API response formats (#7217 ) * fix: support both old and new Bailian Rerank API response formats The new compatible API (compatible-api/v1/reranks) returns results at the top level as data.results, while the old API returns them nested under data.output.results. The parser only checked the old path, causing qwen3-rerank to always report empty results. Fixes #7161 * Update astrbot/core/provider/sources/bailian_rerank_source.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --------- Co-authored-by: Ruochen Pan <badbatch0x01@gmail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-04-01 11:55:54 +08:00
Chang Lee	3dd7799f27	fix(Docker): add amr encoder (#7247 ) - Modified Dockerfile to add amr encoder (use libavcodec-extra)	2026-04-01 11:55:16 +08:00
NekoYukari	deedf85360	fix: add pysocks dependency to support SOCKS5 proxy for pip install (#7221 ) * fix: add pysocks dependency to support SOCKS5 proxy for pip install * docs: update proxy description to include https:// support * fix: add python-socks and pysocks to requirements.txt for consistency --------- Co-authored-by: root <root@localhost.localdomain>	2026-04-01 09:05:02 +08:00
Soulter	4d9dce184f	feat: integrate Monaco Editor workers for enhanced code editing support (#7249 ) fixes: #5587	2026-04-01 01:18:18 +08:00
Soulter	788d103a36	refactor: update provider panels for improved layout and styling (#7248 )	2026-04-01 01:12:35 +08:00
LIghtJUNction	328748bd63	Fix cached_tokens handling in _extract_usage method (#6719 ) * Fix cached_tokens handling in _extract_usage method Ensure cached_tokens is an integer and handle None safely. * ruuf format	2026-03-31 17:14:52 +08:00