feat: enhance Live Mode with text input functionality and UI improvements

- Added a text input panel to allow users to send plain text messages while in Live Mode.
- Updated the LiveMode.vue component to handle text input and integrate it with WebSocket communication.
- Improved the layout and styling of the Live Mode interface for better user experience.
- Documented the new `text_input` message type in the Live API README.

.github/PULL_REQUEST_TEMPLATE.md

@@ -21,7 +21,23 @@
 <!--If merged, your code will serve tens of thousands of users! Please double-check the following items before submitting.-->
 <!--如果分支被合并，您的代码将服务于数万名用户！在提交前，请核查一下几点内容。-->
 
-- [ ] 😊 如果 PR 中有新加入的功能，已经通过 Issue / 邮件等方式和作者讨论过。/ If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
-- [ ] 👀 我的更改经过了良好的测试，**并已在上方提供了“验证步骤”和“运行截图”**。/ My changes have been well-tested, **and "Verification Steps" and "Screenshots" have been provided above**.
-- [ ] 🤓 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到了 `requirements.txt` 和 `pyproject.toml` 文件相应位置。/ I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in `requirements.txt` and `pyproject.toml`.
-- [ ] 😮 我的更改没有引入恶意代码。/ My changes do not introduce malicious code.
+- [ ] 😊 如果 PR 中有新加入的功能，已经通过 Issue / 邮件等方式和作者讨论过。
+  / If there are new features added in the PR, I have discussed it with the authors through issues/emails, etc.
+
+- [ ] 👀 我的更改经过了良好的测试，**并已在上方提供了“验证步骤”和“运行截图”**。
+  / My changes have been well-tested, **and "Verification Steps" and "Screenshots" have been provided above**.
+
+- [ ] 🤓 我确保没有引入新依赖库，或者引入了新依赖库的同时将其添加到 `requirements.txt` 和 `pyproject.toml` 文件相应位置。
+  / I have ensured that no new dependencies are introduced, OR if new dependencies are introduced, they have been added to the appropriate locations in `requirements.txt` and `pyproject.toml`.
+
+- [ ] 😮 我的更改没有引入恶意代码。
+  / My changes do not introduce malicious code.
+
+- [ ] ⚠️ 我已认真阅读并理解以上所有内容，确保本次提交符合规范。
+  / I have read and understood all the above and confirm this PR follows the rules.
+
+- [ ] 🚀 我确保本次开发**基于 dev 分支**，并将代码合并至**开发分支**（除非极其紧急，才允许合并到主分支）。
+   / I confirm that this development is **based on the dev branch** and will be merged into the **development branch**, unless it is extremely urgent to merge into the main branch.
+
+- [ ] ⚠️ 我**没有**认真阅读以上内容，直接提交。
+  / I **did not** read the above carefully before submitting.

.github/workflows/pr-checklist-check.yml

@@ -0,0 +1,45 @@
+name: PR Checklist Check
+
+on:
+  pull_request_target:
+    types: [opened, edited, reopened, synchronize]
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+
+    permissions:
+      pull-requests: write
+      issues: write
+
+    steps:
+      - name: Check checklist
+        id: check
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const body = context.payload.pull_request.body || "";
+            const regex = /-\s*\[\s*x\s*\].*没有.*认真阅读/i;
+            const bad = regex.test(body);
+            core.setOutput("bad", bad);
+
+      - name: Close PR
+        if: steps.check.outputs.bad == 'true'
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const pr = context.payload.pull_request;
+
+            await github.rest.issues.createComment({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              issue_number: pr.number,
+              body: `检测到你勾选了“我没有认真阅读”，PR 已关闭。`
+            });
+
+            await github.rest.pulls.update({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              pull_number: pr.number,
+              state: "closed"
+            });

.github/workflows/release.yml

@@ -50,7 +50,7 @@ jobs:
           echo "tag=$tag" >> "$GITHUB_OUTPUT"
 
       - name: Setup pnpm
-        uses: pnpm/action-setup@v4.3.0
+        uses: pnpm/action-setup@v4.4.0
         with:
           version: 10.28.2
 

README.md

@@ -78,7 +78,7 @@ For users who want to quickly experience AstrBot, are familiar with command-line
 ```bash
 uv tool install astrbot
 astrbot init # Only execute this command for the first time to initialize the environment
-astrbot
+astrbot run
 ```
 
 > Requires [uv](https://docs.astral.sh/uv/) to be installed.

README_fr.md

@@ -78,7 +78,7 @@ Pour les utilisateurs qui veulent découvrir AstrBot rapidement, qui sont famili
 ```bash
 uv tool install astrbot
 astrbot init # Exécutez cette commande uniquement la première fois pour initialiser l'environnement
-astrbot
+astrbot run
 ```
 
 > [uv](https://docs.astral.sh/uv/) doit être installé.

README_ja.md

@@ -78,7 +78,7 @@ AstrBot を素早く試したいユーザーで、コマンドラインに慣れ
 ```bash
 uv tool install astrbot
 astrbot init # 初回のみ実行して環境を初期化します
-astrbot
+astrbot run
 ```
 
 > [uv](https://docs.astral.sh/uv/) のインストールが必要です。

README_ru.md

@@ -78,7 +78,7 @@ AstrBot — это универсальная платформа Agent-чатб
 ```bash
 uv tool install astrbot
 astrbot init # Выполните эту команду только при первом запуске для инициализации окружения
-astrbot
+astrbot run
 ```
 
 > Требуется установленный [uv](https://docs.astral.sh/uv/).

README_zh-TW.md

@@ -78,7 +78,7 @@ AstrBot 是一個開源的一站式 Agent 聊天機器人平台，可接入主
 ```bash
 uv tool install astrbot
 astrbot init # 僅首次執行此命令以初始化環境
-astrbot
+astrbot run
 ```
 
 > 需要安裝 [uv](https://docs.astral.sh/uv/)。

README_zh.md

@@ -78,7 +78,7 @@ AstrBot 是一个开源的一站式 Agentic 个人和群聊助手，可在 QQ、
 ```bash
 uv tool install astrbot
 astrbot init # 仅首次执行此命令以初始化环境
-astrbot
+astrbot run
 ```
 
 > 需要安装 [uv](https://docs.astral.sh/uv/)。

astrbot/core/astr_agent_run_util.py

@@ -326,6 +326,7 @@ async def run_live_agent(
 
     # 创建队列
     text_queue: asyncio.Queue[str | None] = asyncio.Queue()
+    delta_queue: asyncio.Queue[str | None] = asyncio.Queue()
     # audio_queue stored bytes or (text, bytes)
     audio_queue: asyncio.Queue[bytes | tuple[str, bytes] | None] = asyncio.Queue()
 
@@ -334,6 +335,7 @@ async def run_live_agent(
         _run_agent_feeder(
             agent_runner,
             text_queue,
+            delta_queue,
             max_step,
             show_tool_use,
             show_tool_call_result,
@@ -353,32 +355,63 @@ async def run_live_agent(
 
     # 3. 主循环：从 audio_queue 读取音频并 yield
     try:
-        while True:
-            queue_item = await audio_queue.get()
+        delta_done = False
+        audio_done = False
+        while not (delta_done and audio_done):
+            task_sources: dict[asyncio.Task, str] = {}
+            if not delta_done:
+                task = asyncio.create_task(delta_queue.get())
+                task_sources[task] = "delta"
+            if not audio_done:
+                task = asyncio.create_task(audio_queue.get())
+                task_sources[task] = "audio"
 
-            if queue_item is None:
-                break
+            done, pending = await asyncio.wait(
+                list(task_sources),
+                return_when=asyncio.FIRST_COMPLETED,
+            )
 
-            text = None
-            if isinstance(queue_item, tuple):
-                text, audio_data = queue_item
-            else:
-                audio_data = queue_item
+            for task in pending:
+                task.cancel()
+            if pending:
+                await asyncio.gather(*pending, return_exceptions=True)
 
-            if not first_chunk_received:
-                # 记录首帧延迟（从开始处理到收到第一个音频块）
-                tts_first_frame_time = time.time() - tts_start_time
-                first_chunk_received = True
+            for task in done:
+                source = task_sources[task]
+                queue_item = task.result()
+                if source == "delta":
+                    if queue_item is None:
+                        delta_done = True
+                        continue
+                    yield MessageChain(
+                        chain=[Plain(queue_item)], type="live_text_delta"
+                    )
+                    continue
 
-            # 将音频数据封装为 MessageChain
-            import base64
+                if queue_item is None:
+                    audio_done = True
+                    continue
 
-            audio_b64 = base64.b64encode(audio_data).decode("utf-8")
-            comps: list[BaseMessageComponent] = [Plain(audio_b64)]
-            if text:
-                comps.append(Json(data={"text": text}))
-            chain = MessageChain(chain=comps, type="audio_chunk")
-            yield chain
+                text = None
+                if isinstance(queue_item, tuple):
+                    text, audio_data = queue_item
+                else:
+                    audio_data = queue_item
+
+                if not first_chunk_received:
+                    # 记录首帧延迟（从开始处理到收到第一个音频块）
+                    tts_first_frame_time = time.time() - tts_start_time
+                    first_chunk_received = True
+
+                # 将音频数据封装为 MessageChain
+                import base64
+
+                audio_b64 = base64.b64encode(audio_data).decode("utf-8")
+                comps: list[BaseMessageComponent] = [Plain(audio_b64)]
+                if text:
+                    comps.append(Json(data={"text": text}))
+                chain = MessageChain(chain=comps, type="audio_chunk")
+                yield chain
 
     except Exception as e:
         logger.error(f"[Live Agent] 运行时发生错误: {e}", exc_info=True)
@@ -421,6 +454,7 @@ async def run_live_agent(
 async def _run_agent_feeder(
     agent_runner: AgentRunner,
     text_queue: asyncio.Queue,
+    delta_queue: asyncio.Queue,
     max_step: int,
     show_tool_use: bool,
     show_tool_call_result: bool,
@@ -440,9 +474,13 @@ async def _run_agent_feeder(
             if chain is None:
                 continue
 
+            if chain.type == "reasoning":
+                continue
+
             # 提取文本
             text = chain.get_plain_text()
             if text:
+                await delta_queue.put(text)
                 buffer += text
 
                 # 分句逻辑：匹配标点符号
@@ -477,6 +515,7 @@ async def _run_agent_feeder(
     finally:
         # 发送结束信号
         await text_queue.put(None)
+        await delta_queue.put(None)
 
 
 async def _safe_tts_stream_wrapper(

astrbot/core/astr_main_agent.py

@@ -778,9 +778,14 @@ def _plugin_tool_fix(event: AstrMessageEvent, req: ProviderRequest) -> None:
                 continue
             mp = tool.handler_module_path
             if not mp:
+                # 没有 plugin 归属信息的工具（如 subagent transfer_to_*）
+                # 不应受到会话插件过滤影响。
+                new_tool_set.add_tool(tool)
                 continue
             plugin = star_map.get(mp)
             if not plugin:
+                # 无法解析插件归属时，保守保留工具，避免误过滤。
+                new_tool_set.add_tool(tool)
                 continue
             if plugin.name in event.plugins_name or plugin.reserved:
                 new_tool_set.add_tool(tool)

astrbot/core/astr_main_agent_resources.py

@@ -188,7 +188,12 @@ class KnowledgeBaseQueryTool(FunctionTool[AstrAgentContext]):
 @dataclass
 class SendMessageToUserTool(FunctionTool[AstrAgentContext]):
     name: str = "send_message_to_user"
-    description: str = "Directly send message to the user. Only use this tool when you need to proactively message the user. Otherwise you can directly output the reply in the conversation."
+    description: str = (
+        "Send message to the user. "
+        "Supports various message types including `plain`, `image`, `record`, `video`, `file`, and `mention_user`. "
+        "Use this tool to send media files (`image`, `record`, `video`, `file`), "
+        "or when you need to proactively message the user(such as cron job). For normal text replies, you can output directly."
+    )
 
     parameters: dict = Field(
         default_factory=lambda: {

astrbot/core/computer/tools/neo_skills.py

@@ -164,7 +164,10 @@ class CreateSkillPayloadTool(NeoSkillToolBase):
             "type": "object",
             "properties": {
                 "payload": {
-                    "anyOf": [{"type": "object"}, {"type": "array"}],
+                    "anyOf": [
+                        {"type": "object"},
+                        {"type": "array", "items": {"type": "object"}},
+                    ],
                     "description": (
                         "Skill payload JSON. Typical schema: {skill_markdown, inputs, outputs, meta}. "
                         "This only stores content and returns payload_ref; it does not create a candidate or release."

astrbot/core/config/default.py

@@ -1132,6 +1132,18 @@ CONFIG_METADATA_2 = {
                         "proxy": "",
                         "custom_headers": {},
                     },
+                    "MiniMax": {
+                        "id": "minimax",
+                        "provider": "minimax",
+                        "type": "openai_chat_completion",
+                        "provider_type": "chat_completion",
+                        "enable": True,
+                        "key": [],
+                        "api_base": "https://api.minimaxi.com/v1",
+                        "timeout": 120,
+                        "proxy": "",
+                        "custom_headers": {},
+                    },
                     "xAI": {
                         "id": "xai",
                         "provider": "xai",

astrbot/core/cron/manager.py

@@ -332,9 +332,9 @@ class CronJobManager:
             cron_job=cron_job_str
         )
         req.prompt = (
-            "You are now responding to a scheduled task"
+            "You are now responding to a scheduled task. "
             "Proceed according to your system instructions. "
-            "Output using same language as previous conversation."
+            "Output using same language as previous conversation. "
             "After completing your task, summarize and output your actions and results."
         )
         if not req.func_tool:

astrbot/core/db/__init__.py

@@ -647,6 +647,13 @@ class BaseDatabase(abc.ABC):
         """Get a Platform session by its ID."""
         ...
 
+    @abc.abstractmethod
+    async def get_platform_sessions_by_ids(
+        self, session_ids: list[str]
+    ) -> list[PlatformSession]:
+        """Get platform sessions by IDs."""
+        ...
+
     @abc.abstractmethod
     async def get_platform_sessions_by_creator(
         self,

astrbot/core/db/sqlite.py

@@ -1417,6 +1417,21 @@ class SQLiteDatabase(BaseDatabase):
             result = await session.execute(query)
             return result.scalar_one_or_none()
 
+    async def get_platform_sessions_by_ids(
+        self, session_ids: list[str]
+    ) -> list[PlatformSession]:
+        """Get platform sessions by IDs."""
+        if not session_ids:
+            return []
+
+        async with self.get_db() as session:
+            session: AsyncSession
+            query = select(PlatformSession).where(
+                col(PlatformSession.session_id).in_(session_ids)
+            )
+            result = await session.execute(query)
+            return list(result.scalars().all())
+
     async def get_platform_sessions_by_creator(
         self,
         creator: str,

astrbot/core/message/components.py

@@ -96,10 +96,10 @@ class Plain(BaseMessageComponent):
     def __init__(self, text: str, convert: bool = True, **_) -> None:
         super().__init__(text=text, convert=convert, **_)
 
-    def toDict(self):
-        return {"type": "text", "data": {"text": self.text.strip()}}
+    def toDict(self) -> dict:
+        return {"type": "text", "data": {"text": self.text}}
 
-    async def to_dict(self):
+    async def to_dict(self) -> dict:
         return {"type": "text", "data": {"text": self.text}}
 
 

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

@@ -6,6 +6,7 @@ from aiocqhttp import CQHttp, Event
 
 from astrbot.api.event import AstrMessageEvent, MessageChain
 from astrbot.api.message_components import (
+    At,
     BaseMessageComponent,
     File,
     Image,
@@ -70,11 +71,19 @@ class AiocqhttpMessageEvent(AstrMessageEvent):
         """解析成 OneBot json 格式"""
         ret = []
         for segment in message_chain.chain:
-            if isinstance(segment, Plain):
+            if isinstance(segment, At):
+                # At 组件后插入一个空格，避免与后续文本粘连
+                d = await AiocqhttpMessageEvent._from_segment_to_dict(segment)
+                ret.append(d)
+                ret.append({"type": "text", "data": {"text": " "}})
+            elif isinstance(segment, Plain):
                 if not segment.text.strip():
                     continue
-            d = await AiocqhttpMessageEvent._from_segment_to_dict(segment)
-            ret.append(d)
+                d = await AiocqhttpMessageEvent._from_segment_to_dict(segment)
+                ret.append(d)
+            else:
+                d = await AiocqhttpMessageEvent._from_segment_to_dict(segment)
+                ret.append(d)
         return ret
 
     @classmethod

astrbot/core/platform/sources/qqofficial/qqofficial_platform_adapter.py

@@ -391,6 +391,47 @@ class QQOfficialPlatformAdapter(Platform):
                 else:
                     msg.append(File(name=filename, file=url, url=url))
 
+    @staticmethod
+    def _parse_face_message(content: str) -> str:
+        """Parse QQ official face message format and convert to readable text.
+
+        QQ official face message format:
+        <faceType=4,faceId="",ext="eyJ0ZXh0IjoiW+a7oeWktOmXruWPt10ifQ==">
+
+        The ext field contains base64-encoded JSON with a 'text' field
+        describing the emoji (e.g., '[满头问号]').
+
+        Args:
+            content: The message content that may contain face tags.
+
+        Returns:
+            Content with face tags replaced by readable emoji descriptions.
+        """
+        import base64
+        import json
+        import re
+
+        def replace_face(match):
+            face_tag = match.group(0)
+            # Extract ext field from the face tag
+            ext_match = re.search(r'ext="([^"]*)"', face_tag)
+            if ext_match:
+                try:
+                    ext_encoded = ext_match.group(1)
+                    # Decode base64 and parse JSON
+                    ext_decoded = base64.b64decode(ext_encoded).decode("utf-8")
+                    ext_data = json.loads(ext_decoded)
+                    emoji_text = ext_data.get("text", "")
+                    if emoji_text:
+                        return f"[表情:{emoji_text}]"
+                except Exception:
+                    pass
+            # Fallback if parsing fails
+            return "[表情]"
+
+        # Match face tags: <faceType=...>
+        return re.sub(r"<faceType=\d+[^>]*>", replace_face, content)
+
     @staticmethod
     def _parse_from_qqofficial(
         message: botpy.message.Message
@@ -416,7 +457,10 @@ class QQOfficialPlatformAdapter(Platform):
                 abm.group_id = message.group_openid
             else:
                 abm.sender = MessageMember(message.author.user_openid, "")
-            abm.message_str = message.content.strip()
+            # Parse face messages to readable text
+            abm.message_str = QQOfficialPlatformAdapter._parse_face_message(
+                message.content.strip()
+            )
             abm.self_id = "unknown_selfid"
             msg.append(At(qq="qq_official"))
             msg.append(Plain(abm.message_str))
@@ -432,10 +476,12 @@ class QQOfficialPlatformAdapter(Platform):
             else:
                 abm.self_id = ""
 
-            plain_content = message.content.replace(
-                "<@!" + str(abm.self_id) + ">",
-                "",
-            ).strip()
+            plain_content = QQOfficialPlatformAdapter._parse_face_message(
+                message.content.replace(
+                    "<@!" + str(abm.self_id) + ">",
+                    "",
+                ).strip()
+            )
 
             QQOfficialPlatformAdapter._append_attachments(msg, message.attachments)
             abm.message = msg

astrbot/core/platform/sources/qqofficial_webhook/qo_webhook_server.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import time
 from typing import cast
 
 import quart
@@ -39,6 +40,9 @@ class QQOfficialWebhook:
         self.client = botpy_client
         self.event_queue = event_queue
         self.shutdown_event = asyncio.Event()
+        # Deduplication cache for webhook retry callbacks.
+        self._seen_event_ids: dict[str, float] = {}
+        self._dedup_ttl: int = 60  # seconds
 
     async def initialize(self) -> None:
         logger.info("正在登录到 QQ 官方机器人...")
@@ -106,6 +110,22 @@ class QQOfficialWebhook:
             print(signed)
             return signed
 
+        event_id = msg.get("id")
+        if event_id:
+            now = time.monotonic()
+            # Lazily evict expired entries to prevent unbounded growth.
+            expired = [
+                k
+                for k, ts in self._seen_event_ids.items()
+                if now - ts > self._dedup_ttl
+            ]
+            for k in expired:
+                del self._seen_event_ids[k]
+            if event_id in self._seen_event_ids:
+                logger.debug(f"Duplicate webhook event {event_id!r}, skipping.")
+                return {"opcode": 12}
+            self._seen_event_ids[event_id] = now
+
         if event and opcode == BotWebSocket.WS_DISPATCH_EVENT:
             event = msg["t"].lower()
             try:

astrbot/core/platform/sources/telegram/tg_adapter.py

@@ -289,8 +289,8 @@ class TelegramPlatformAdapter(Platform):
         else:
             message.type = MessageType.GROUP_MESSAGE
             message.group_id = str(update.message.chat.id)
-            if update.message.message_thread_id:
-                # Topic Group
+            if update.message.is_topic_message and update.message.message_thread_id:
+                # Telegram Topic Group: include thread id to isolate per-topic sessions.
                 message.group_id += "#" + str(update.message.message_thread_id)
                 message.session_id = message.group_id
         message.message_id = str(update.message.message_id)

astrbot/core/platform/sources/telegram/tg_event.py

@@ -25,6 +25,16 @@ from astrbot.api.platform import AstrBotMessage, MessageType, PlatformMetadata
 from astrbot.core.utils.metrics import Metric
 
 
+def _is_gif(path: str) -> bool:
+    if path.lower().endswith(".gif"):
+        return True
+    try:
+        with open(path, "rb") as f:
+            return f.read(6) in (b"GIF87a", b"GIF89a")
+    except OSError:
+        return False
+
+
 class TelegramPlatformEvent(AstrMessageEvent):
     # Telegram 的最大消息长度限制
     MAX_MESSAGE_LENGTH = 4096
@@ -291,7 +301,13 @@ class TelegramPlatformEvent(AstrMessageEvent):
                         await client.send_message(text=chunk, **cast(Any, payload))
             elif isinstance(i, Image):
                 image_path = await i.convert_to_file_path()
-                await client.send_photo(photo=image_path, **cast(Any, payload))
+                if _is_gif(image_path):
+                    send_coro = client.send_animation
+                    media_kwarg = {"animation": image_path}
+                else:
+                    send_coro = client.send_photo
+                    media_kwarg = {"photo": image_path}
+                await send_coro(**media_kwarg, **cast(Any, payload))
             elif isinstance(i, File):
                 path = await i.get_file()
                 name = i.name or os.path.basename(path)
@@ -406,12 +422,20 @@ class TelegramPlatformEvent(AstrMessageEvent):
                 on_text(i.text)
             elif isinstance(i, Image):
                 image_path = await i.convert_to_file_path()
+                if _is_gif(image_path):
+                    action = ChatAction.UPLOAD_VIDEO
+                    send_coro = self.client.send_animation
+                    media_kwarg = {"animation": image_path}
+                else:
+                    action = ChatAction.UPLOAD_PHOTO
+                    send_coro = self.client.send_photo
+                    media_kwarg = {"photo": image_path}
                 await self._send_media_with_action(
                     self.client,
-                    ChatAction.UPLOAD_PHOTO,
-                    self.client.send_photo,
+                    action,
+                    send_coro,
                     user_name=user_name,
-                    photo=image_path,
+                    **media_kwarg,
                     **cast(Any, payload),
                 )
             elif isinstance(i, File):

astrbot/core/platform/sources/wecom_ai_bot/wecomai_adapter.py

@@ -440,9 +440,16 @@ class WecomAIBotAdapter(Platform):
         )
 
     def _extract_session_id(self, message_data: dict[str, Any]) -> str:
-        """从消息数据中提取会话ID"""
-        user_id = message_data.get("from", {}).get("userid", "default_user")
-        return format_session_id("wecomai", user_id)
+        """从消息数据中提取会话ID
+        群聊使用 chatid，单聊使用 userid
+        """
+        chattype = message_data.get("chattype", "single")
+        if chattype == "group":
+            chat_id = message_data.get("chatid", "default_group")
+            return format_session_id("wecomai", chat_id)
+        else:
+            user_id = message_data.get("from", {}).get("userid", "default_user")
+            return format_session_id("wecomai", user_id)
 
     async def _enqueue_message(
         self,

astrbot/core/provider/manager.py

@@ -808,6 +808,8 @@ class ProviderManager:
             config.save_config()
             # load instance
             await self.load_provider(new_config)
+            # sync in-memory config for API queries (e.g., embedding provider list)
+            self.providers_config = astrbot_config["provider"]
 
     async def terminate(self) -> None:
         if self._mcp_init_task and not self._mcp_init_task.done():

astrbot/core/provider/sources/groq_source.py

@@ -13,3 +13,11 @@ class ProviderGroq(ProviderOpenAIOfficial):
     ) -> None:
         super().__init__(provider_config, provider_settings)
         self.reasoning_key = "reasoning"
+
+    def _finally_convert_payload(self, payloads: dict) -> None:
+        """Groq rejects assistant history items that include reasoning_content."""
+        super()._finally_convert_payload(payloads)
+        for message in payloads.get("messages", []):
+            if message.get("role") == "assistant":
+                message.pop("reasoning_content", None)
+                message.pop("reasoning", None)

astrbot/core/provider/sources/openai_source.py

@@ -311,7 +311,7 @@ class ProviderOpenAIOfficial(Provider):
                 state.handle_chunk(chunk)
             except Exception as e:
                 logger.warning("Saving chunk state error: " + str(e))
-            if len(chunk.choices) == 0:
+            if not chunk.choices:
                 continue
             delta = chunk.choices[0].delta
             # logger.debug(f"chunk delta: {delta}")
@@ -322,7 +322,7 @@ class ProviderOpenAIOfficial(Provider):
             if reasoning:
                 llm_response.reasoning_content = reasoning
                 _y = True
-            if delta.content:
+            if delta and delta.content:
                 # Don't strip streaming chunks to preserve spaces between words
                 completion_text = self._normalize_content(delta.content, strip=False)
                 llm_response.result_chain = MessageChain(
@@ -345,7 +345,7 @@ class ProviderOpenAIOfficial(Provider):
     ) -> str:
         """Extract reasoning content from OpenAI ChatCompletion if available."""
         reasoning_text = ""
-        if len(completion.choices) == 0:
+        if not completion.choices:
             return reasoning_text
         if isinstance(completion, ChatCompletion):
             choice = completion.choices[0]
@@ -468,7 +468,7 @@ class ProviderOpenAIOfficial(Provider):
         """Parse OpenAI ChatCompletion into LLMResponse"""
         llm_response = LLMResponse("assistant")
 
-        if len(completion.choices) == 0:
+        if not completion.choices:
             raise Exception("API 返回的 completion 为空。")
         choice = completion.choices[0]
 
@@ -629,7 +629,8 @@ class ProviderOpenAIOfficial(Provider):
             # 最后一次不等待
             if retry_cnt < max_retries - 1:
                 await asyncio.sleep(1)
-            available_api_keys.remove(chosen_key)
+            if chosen_key in available_api_keys:
+                available_api_keys.remove(chosen_key)
             if len(available_api_keys) > 0:
                 chosen_key = random.choice(available_api_keys)
                 return (

astrbot/core/provider/sources/openrouter_source.py

@@ -16,4 +16,7 @@ class ProviderOpenRouter(ProviderOpenAIOfficial):
         self.client._custom_headers["HTTP-Referer"] = (  # type: ignore
             "https://github.com/AstrBotDevs/AstrBot"
         )
-        self.client._custom_headers["X-TITLE"] = "AstrBot"  # type: ignore
+        self.client._custom_headers["X-OpenRouter-Title"] = "AstrBot"  # type: ignore
+        self.client._custom_headers["X-OpenRouter-Categories"] = (
+            "general-chat,personal-agent"  # type: ignore
+        )

astrbot/core/umop_config_router.py

@@ -25,12 +25,22 @@ class UmopConfigRouter:
         )
         self.umop_to_conf_id = sp_data
 
+    @staticmethod
+    def _split_umo(umo: str) -> tuple[str, str, str] | None:
+        """将 UMO 拆分为 3 个部分，同时保留 session_id 中的 ':'"""
+        if not isinstance(umo, str):
+            return None
+        parts = umo.split(":", 2)
+        if len(parts) != 3:
+            return None
+        return parts[0], parts[1], parts[2]
+
     def _is_umo_match(self, p1: str, p2: str) -> bool:
         """判断 p2 umo 是否逻辑包含于 p1 umo"""
-        p1_ls = p1.split(":")
-        p2_ls = p2.split(":")
+        p1_ls = self._split_umo(p1)
+        p2_ls = self._split_umo(p2)
 
-        if len(p1_ls) != 3 or len(p2_ls) != 3:
+        if p1_ls is None or p2_ls is None:
             return False  # 非法格式
 
         return all(p == "" or fnmatch.fnmatchcase(t, p) for p, t in zip(p1_ls, p2_ls))
@@ -62,7 +72,7 @@ class UmopConfigRouter:
 
         """
         for part in new_routing:
-            if not isinstance(part, str) or len(part.split(":")) != 3:
+            if self._split_umo(part) is None:
                 raise ValueError(
                     "umop keys must be strings in the format [platform_id]:[message_type]:[session_id], with optional wildcards * or empty for all",
                 )
@@ -81,7 +91,7 @@ class UmopConfigRouter:
             ValueError: 如果 umo 格式不正确
 
         """
-        if not isinstance(umo, str) or len(umo.split(":")) != 3:
+        if self._split_umo(umo) is None:
             raise ValueError(
                 "umop must be a string in the format [platform_id]:[message_type]:[session_id], with optional wildcards * or empty for all",
             )
@@ -99,7 +109,7 @@ class UmopConfigRouter:
             ValueError: 当 umo 格式不正确时抛出
         """
 
-        if not isinstance(umo, str) or len(umo.split(":")) != 3:
+        if self._split_umo(umo) is None:
             raise ValueError(
                 "umop must be a string in the format [platform_id]:[message_type]:[session_id], with optional wildcards * or empty for all",
             )

astrbot/dashboard/routes/auth.py

@@ -82,7 +82,8 @@ class AuthRoute(Route):
     def generate_jwt(self, username):
         payload = {
             "username": username,
-            "exp": datetime.datetime.utcnow() + datetime.timedelta(days=7),
+            "exp": datetime.datetime.now(datetime.timezone.utc)
+            + datetime.timedelta(days=7),
         }
         jwt_token = self.config["dashboard"].get("jwt_secret", None)
         if not jwt_token:

astrbot/dashboard/routes/chat.py

@@ -36,6 +36,20 @@ async def track_conversation(convs: dict, conv_id: str):
         convs.pop(conv_id, None)
 
 
+async def _poll_webchat_stream_result(back_queue, username: str):
+    try:
+        result = await asyncio.wait_for(back_queue.get(), timeout=1)
+    except asyncio.TimeoutError:
+        return None, False
+    except asyncio.CancelledError:
+        logger.debug(f"[WebChat] 用户 {username} 断开聊天长连接。")
+        return None, True
+    except Exception as e:
+        logger.error(f"WebChat stream error: {e}")
+        return None, False
+    return result, False
+
+
 class ChatRoute(Route):
     def __init__(
         self,
@@ -51,6 +65,7 @@ class ChatRoute(Route):
             "/chat/get_session": ("GET", self.get_session),
             "/chat/stop": ("POST", self.stop_session),
             "/chat/delete_session": ("GET", self.delete_webchat_session),
+            "/chat/batch_delete_sessions": ("POST", self.batch_delete_sessions),
             "/chat/update_session_display_name": (
                 "POST",
                 self.update_session_display_name,
@@ -342,16 +357,12 @@ class ChatRoute(Route):
 
                 async with track_conversation(self.running_convs, webchat_conv_id):
                     while True:
-                        try:
-                            result = await asyncio.wait_for(back_queue.get(), timeout=1)
-                        except asyncio.TimeoutError:
-                            continue
-                        except asyncio.CancelledError:
-                            logger.debug(f"[WebChat] 用户 {username} 断开聊天长连接。")
+                        result, should_break = await _poll_webchat_stream_result(
+                            back_queue, username
+                        )
+                        if should_break:
                             client_disconnected = True
-                        except Exception as e:
-                            logger.error(f"WebChat stream error: {e}")
-
+                            break
                         if not result:
                             continue
 
@@ -578,19 +589,9 @@ class ChatRoute(Route):
 
         return Response().ok(data={"stopped_count": stopped_count}).__dict__
 
-    async def delete_webchat_session(self):
-        """Delete a Platform session and all its related data."""
-        session_id = request.args.get("session_id")
-        if not session_id:
-            return Response().error("Missing key: session_id").__dict__
-        username = g.get("username", "guest")
-
-        # 验证会话是否存在且属于当前用户
-        session = await self.db.get_platform_session_by_id(session_id)
-        if not session:
-            return Response().error(f"Session {session_id} not found").__dict__
-        if session.creator != username:
-            return Response().error("Permission denied").__dict__
+    async def _delete_session_internal(self, session, username: str) -> None:
+        """Delete a single session and all its related data."""
+        session_id = session.session_id
 
         # 删除该会话下的所有对话
         message_type = "GroupMessage" if session.is_group else "FriendMessage"
@@ -632,8 +633,70 @@ class ChatRoute(Route):
         # 删除会话
         await self.db.delete_platform_session(session_id)
 
+    async def delete_webchat_session(self):
+        """Delete a Platform session and all its related data."""
+        session_id = request.args.get("session_id")
+        if not session_id:
+            return Response().error("Missing key: session_id").__dict__
+        username = g.get("username", "guest")
+
+        session = await self.db.get_platform_session_by_id(session_id)
+        if not session:
+            return Response().error(f"Session {session_id} not found").__dict__
+        if session.creator != username:
+            return Response().error("Permission denied").__dict__
+
+        await self._delete_session_internal(session, username)
+
         return Response().ok().__dict__
 
+    async def batch_delete_sessions(self):
+        """Batch delete multiple Platform sessions."""
+        post_data = await request.json
+        if post_data is None:
+            return Response().error("Missing JSON body").__dict__
+        if not isinstance(post_data, dict):
+            return Response().error("Invalid JSON body: expected object").__dict__
+
+        session_ids = post_data.get("session_ids")
+        if not session_ids or not isinstance(session_ids, list):
+            return Response().error("Missing or invalid key: session_ids").__dict__
+
+        username = g.get("username", "guest")
+        sessions = await self.db.get_platform_sessions_by_ids(session_ids)
+        sessions_by_id = {session.session_id: session for session in sessions}
+        deleted_count = 0
+        failed_items = []
+
+        for sid in session_ids:
+            session = sessions_by_id.get(sid)
+            if not session:
+                failed_items.append({"session_id": sid, "reason": "not found"})
+                continue
+            if session.creator != username:
+                failed_items.append({"session_id": sid, "reason": "permission denied"})
+                continue
+
+            try:
+                await self._delete_session_internal(session, username)
+                deleted_count += 1
+                sessions_by_id.pop(sid, None)
+            except Exception:
+                logger.warning("Failed to delete session %s", sid)
+                failed_items.append({"session_id": sid, "reason": "internal_error"})
+
+        return (
+            Response()
+            .ok(
+                data={
+                    "deleted_count": deleted_count,
+                    "failed_count": len(failed_items),
+                    "failed_items": failed_items,
+                }
+            )
+            .__dict__
+        )
+
     def _extract_attachment_ids(self, history_list) -> list[str]:
         """从消息历史中提取所有 attachment_id"""
         attachment_ids = []

astrbot/dashboard/routes/live_chat.py

@@ -130,16 +130,6 @@ class LiveChatRoute(Route):
 
     async def live_chat_ws(self) -> None:
         """Legacy Live Chat WebSocket 处理器（默认 ct=live）"""
-        await self._unified_ws_loop(force_ct="live")
-
-    async def unified_chat_ws(self) -> None:
-        """Unified Chat WebSocket 处理器（支持 ct=live/chat）"""
-        await self._unified_ws_loop(force_ct=None)
-
-    async def _unified_ws_loop(self, force_ct: str | None = None) -> None:
-        """统一 WebSocket 循环"""
-        # WebSocket 不能通过 header 传递 token，需要从 query 参数获取
-        # 注意：WebSocket 上下文使用 websocket.args 而不是 request.args
         token = websocket.args.get("token")
         if not token:
             await websocket.close(1008, "Missing authentication token")
@@ -156,6 +146,49 @@ class LiveChatRoute(Route):
             await websocket.close(1008, "Invalid token")
             return
 
+        await self.run_ws_session(username=username, force_ct="live")
+
+    async def unified_chat_ws(self) -> None:
+        """Unified Chat WebSocket 处理器（支持 ct=live/chat）"""
+        token = websocket.args.get("token")
+        if not token:
+            await websocket.close(1008, "Missing authentication token")
+            return
+
+        try:
+            jwt_secret = self.config["dashboard"].get("jwt_secret")
+            payload = jwt.decode(token, jwt_secret, algorithms=["HS256"])
+            username = payload["username"]
+        except jwt.ExpiredSignatureError:
+            await websocket.close(1008, "Token expired")
+            return
+        except jwt.InvalidTokenError:
+            await websocket.close(1008, "Invalid token")
+            return
+
+        await self.run_ws_session(username=username, force_ct=None)
+
+    async def _unified_ws_loop(self, force_ct: str | None = None) -> None:
+        """统一 WebSocket 循环"""
+        # Keep the legacy entry point for internal call sites.
+        token = websocket.args.get("token")
+        if not token:
+            await websocket.close(1008, "Missing authentication token")
+            return
+        try:
+            jwt_secret = self.config["dashboard"].get("jwt_secret")
+            payload = jwt.decode(token, jwt_secret, algorithms=["HS256"])
+            username = payload["username"]
+        except jwt.ExpiredSignatureError:
+            await websocket.close(1008, "Token expired")
+            return
+        except jwt.InvalidTokenError:
+            await websocket.close(1008, "Invalid token")
+            return
+        await self.run_ws_session(username=username, force_ct=force_ct)
+
+    async def run_ws_session(self, username: str, force_ct: str | None = None) -> None:
+        """Run a live/unified websocket session for an authenticated username."""
         session_id = f"webchat_live!{username}!{uuid.uuid4()}"
         live_session = LiveChatSession(session_id, username)
         self.sessions[session_id] = live_session
@@ -690,6 +723,16 @@ class LiveChatRoute(Route):
 
         elif msg_type == "end_speaking":
             # 结束说话
+            if session.is_processing:
+                await websocket.send_json(
+                    {
+                        "t": "error",
+                        "data": "Session is busy",
+                        "code": "PROCESSING_ERROR",
+                    }
+                )
+                return
+
             stamp = message.get("stamp")
             if not stamp:
                 logger.warning("[Live Chat] end_speaking 缺少 stamp")
@@ -703,45 +746,59 @@ class LiveChatRoute(Route):
             # 处理音频：STT -> LLM -> TTS
             await self._process_audio(session, audio_path, assemble_duration)
 
+        elif msg_type == "text_input":
+            if session.is_processing:
+                await websocket.send_json(
+                    {
+                        "t": "error",
+                        "data": "Session is busy",
+                        "code": "PROCESSING_ERROR",
+                    }
+                )
+                return
+
+            user_text = message.get("text")
+            if not isinstance(user_text, str):
+                user_text = message.get("message")
+
+            if not isinstance(user_text, str) or not user_text.strip():
+                await websocket.send_json(
+                    {
+                        "t": "error",
+                        "data": "message must be non-empty text",
+                        "code": "INVALID_MESSAGE_FORMAT",
+                    }
+                )
+                return
+
+            await self._process_live_user_text(
+                session,
+                user_text=user_text.strip(),
+                initial_metrics={"input_type": "text"},
+                processing_start_time=time.time(),
+            )
+
         elif msg_type == "interrupt":
             # 用户打断
             session.should_interrupt = True
             logger.info(f"[Live Chat] 用户打断: {session.username}")
 
-    async def _process_audio(
-        self, session: LiveChatSession, audio_path: str, assemble_duration: float
+    async def _process_live_user_text(
+        self,
+        session: LiveChatSession,
+        user_text: str,
+        initial_metrics: dict[str, Any] | None = None,
+        processing_start_time: float | None = None,
     ) -> None:
-        """处理音频：STT -> LLM -> 流式 TTS"""
+        """处理 Live 用户文本：走 run_live_agent pipeline 并回传流式 TTS."""
         try:
-            # 发送 WAV 组装耗时
-            await websocket.send_json(
-                {"t": "metrics", "data": {"wav_assemble_time": assemble_duration}}
-            )
-            wav_assembly_finish_time = time.time()
+            if initial_metrics:
+                await websocket.send_json({"t": "metrics", "data": initial_metrics})
 
+            processing_start = processing_start_time or time.time()
             session.is_processing = True
             session.should_interrupt = False
 
-            # 1. STT - 语音转文字
-            ctx = self.plugin_manager.context
-            stt_provider = ctx.provider_manager.stt_provider_insts[0]
-
-            if not stt_provider:
-                logger.error("[Live Chat] STT Provider 未配置")
-                await websocket.send_json({"t": "error", "data": "语音识别服务未配置"})
-                return
-
-            await websocket.send_json(
-                {"t": "metrics", "data": {"stt": stt_provider.meta().type}}
-            )
-
-            user_text = await stt_provider.get_text(audio_path)
-            if not user_text:
-                logger.warning("[Live Chat] STT 识别结果为空")
-                return
-
-            logger.info(f"[Live Chat] STT 结果: {user_text}")
-
             await websocket.send_json(
                 {
                     "t": "user_msg",
@@ -761,7 +818,6 @@ class LiveChatRoute(Route):
                 "action_type": "live",  # 标记为 live mode
             }
 
-            # 将消息放入队列
             await queue.put((session.username, cid, payload))
 
             # 3. 等待响应并流式发送 TTS 音频
@@ -776,11 +832,9 @@ class LiveChatRoute(Route):
                         # 用户打断，停止处理
                         logger.info("[Live Chat] 检测到用户打断")
                         await websocket.send_json({"t": "stop_play"})
-                        # 保存消息并标记为被打断
                         await self._save_interrupted_message(
                             session, user_text, bot_text
                         )
-                        # 清空队列中未处理的消息
                         while not back_queue.empty():
                             try:
                                 back_queue.get_nowait()
@@ -805,6 +859,7 @@ class LiveChatRoute(Route):
 
                     result_type = result.get("type")
                     result_chain_type = result.get("chain_type")
+                    result_streaming = bool(result.get("streaming", False))
                     data = result.get("data", "")
 
                     if result_chain_type == "agent_stats":
@@ -827,29 +882,41 @@ class LiveChatRoute(Route):
                     if result_chain_type == "tts_stats":
                         try:
                             stats = json.loads(data)
-                            await websocket.send_json(
-                                {
-                                    "t": "metrics",
-                                    "data": stats,
-                                }
-                            )
+                            await websocket.send_json({"t": "metrics", "data": stats})
                         except Exception as e:
                             logger.error(f"[Live Chat] 解析 TTSStats 失败: {e}")
                         continue
 
+                    if result_chain_type == "live_text_delta":
+                        if data:
+                            await websocket.send_json(
+                                {
+                                    "t": "bot_delta_chunk",
+                                    "data": {"text": data},
+                                }
+                            )
+                        continue
+
                     if result_type == "plain":
-                        # 普通文本消息
+                        if (
+                            result_streaming
+                            and data
+                            and result_chain_type != "reasoning"
+                        ):
+                            await websocket.send_json(
+                                {
+                                    "t": "bot_delta_chunk",
+                                    "data": {"text": data},
+                                }
+                            )
                         bot_text += data
 
                     elif result_type == "audio_chunk":
-                        # 流式音频数据
                         if not audio_playing:
                             audio_playing = True
                             logger.debug("[Live Chat] 开始播放音频流")
-
-                            # Calculate latency from wav assembly finish to first audio chunk
                             speak_to_first_frame_latency = (
-                                time.time() - wav_assembly_finish_time
+                                time.time() - processing_start
                             )
                             await websocket.send_json(
                                 {
@@ -869,19 +936,15 @@ class LiveChatRoute(Route):
                                 }
                             )
 
-                        # 发送音频数据给前端
                         await websocket.send_json(
                             {
                                 "t": "response",
-                                "data": data,  # base64 编码的音频数据
+                                "data": data,
                             }
                         )
 
                     elif result_type in ["complete", "end"]:
-                        # 处理完成
                         logger.info(f"[Live Chat] Bot 回复完成: {bot_text}")
-
-                        # 如果没有音频流，发送 bot 消息文本
                         if not audio_playing:
                             await websocket.send_json(
                                 {
@@ -893,11 +956,8 @@ class LiveChatRoute(Route):
                                 }
                             )
 
-                        # 发送结束标记
                         await websocket.send_json({"t": "end"})
-
-                        # 发送总耗时
-                        wav_to_tts_duration = time.time() - wav_assembly_finish_time
+                        wav_to_tts_duration = time.time() - processing_start
                         await websocket.send_json(
                             {
                                 "t": "metrics",
@@ -909,13 +969,65 @@ class LiveChatRoute(Route):
                 webchat_queue_mgr.remove_back_queue(message_id)
 
         except Exception as e:
-            logger.error(f"[Live Chat] 处理音频失败: {e}", exc_info=True)
+            logger.error(f"[Live Chat] 处理文本失败: {e}", exc_info=True)
             await websocket.send_json({"t": "error", "data": f"处理失败: {str(e)}"})
 
         finally:
             session.is_processing = False
             session.should_interrupt = False
 
+    async def _process_audio(
+        self, session: LiveChatSession, audio_path: str, assemble_duration: float
+    ) -> None:
+        """处理音频：STT -> LLM -> 流式 TTS"""
+        try:
+            await websocket.send_json(
+                {
+                    "t": "metrics",
+                    "data": {
+                        "wav_assemble_time": assemble_duration,
+                        "input_type": "audio",
+                    },
+                }
+            )
+            wav_assembly_finish_time = time.time()
+
+            # 1. STT - 语音转文字
+            ctx = self.plugin_manager.context
+            stt_provider = ctx.provider_manager.stt_provider_insts[0]
+
+            if not stt_provider:
+                logger.error("[Live Chat] STT Provider 未配置")
+                await websocket.send_json({"t": "error", "data": "语音识别服务未配置"})
+                return
+
+            await websocket.send_json(
+                {
+                    "t": "metrics",
+                    "data": {
+                        "stt": stt_provider.meta().type,
+                    },
+                }
+            )
+
+            user_text = await stt_provider.get_text(audio_path)
+            if not user_text:
+                logger.warning("[Live Chat] STT 识别结果为空")
+                return
+
+            logger.info(f"[Live Chat] STT 结果: {user_text}")
+
+            await self._process_live_user_text(
+                session,
+                user_text=user_text,
+                initial_metrics=None,
+                processing_start_time=wav_assembly_finish_time,
+            )
+
+        except Exception as e:
+            logger.error(f"[Live Chat] 处理音频失败: {e}", exc_info=True)
+            await websocket.send_json({"t": "error", "data": f"处理失败: {str(e)}"})
+
     async def _save_interrupted_message(
         self, session: LiveChatSession, user_text: str, bot_text: str
     ) -> None:

astrbot/dashboard/routes/open_api.py

@@ -19,6 +19,7 @@ from astrbot.core.utils.datetime_utils import to_utc_isoformat
 
 from .api_key import ALL_OPEN_API_SCOPES
 from .chat import ChatRoute
+from .live_chat import LiveChatRoute
 from .route import Response, Route, RouteContext
 
 
@@ -29,12 +30,14 @@ class OpenApiRoute(Route):
         db: BaseDatabase,
         core_lifecycle: AstrBotCoreLifecycle,
         chat_route: ChatRoute,
+        live_chat_route: LiveChatRoute,
     ) -> None:
         super().__init__(context)
         self.db = db
         self.core_lifecycle = core_lifecycle
         self.platform_manager = core_lifecycle.platform_manager
         self.chat_route = chat_route
+        self.live_chat_route = live_chat_route
 
         self.routes = {
             "/v1/chat": ("POST", self.chat_send),
@@ -46,6 +49,7 @@ class OpenApiRoute(Route):
         }
         self.register_routes()
         self.app.websocket("/api/v1/chat/ws")(self.chat_ws)
+        self.app.websocket("/api/v1/live/ws")(self.live_ws)
 
     @staticmethod
     def _resolve_open_username(
@@ -534,6 +538,39 @@ class OpenApiRoute(Route):
         except Exception as e:
             logger.debug("Open API WS connection closed: %s", e)
 
+    async def live_ws(self) -> None:
+        authed, auth_err = await self._authenticate_chat_ws_api_key()
+        if not authed:
+            await self._send_chat_ws_error(auth_err or "Unauthorized", "UNAUTHORIZED")
+            await websocket.close(1008, auth_err or "Unauthorized")
+            return
+
+        username, username_err = self._resolve_open_username(
+            websocket.args.get("username")
+        )
+        if username_err or not username:
+            await self._send_chat_ws_error(
+                username_err or "Invalid username",
+                "BAD_USER",
+            )
+            await websocket.close(1008, username_err or "Invalid username")
+            return
+
+        ct = websocket.args.get("ct")
+        force_ct = ct.strip() if isinstance(ct, str) and ct.strip() else "live"
+        if force_ct not in {"live", "chat"}:
+            await self._send_chat_ws_error(
+                "ct must be 'live' or 'chat'",
+                "INVALID_MESSAGE",
+            )
+            await websocket.close(1008, "Invalid ct")
+            return
+
+        await self.live_chat_route.run_ws_session(
+            username=username,
+            force_ct=force_ct,
+        )
+
     async def upload_file(self):
         return await self.chat_route.post_file()
 

astrbot/dashboard/server.py

@@ -115,11 +115,13 @@ class AstrBotDashboard:
         self.ar = AuthRoute(self.context)
         self.api_key_route = ApiKeyRoute(self.context, db)
         self.chat_route = ChatRoute(self.context, db, core_lifecycle)
+        self.live_chat_route = LiveChatRoute(self.context, db, core_lifecycle)
         self.open_api_route = OpenApiRoute(
             self.context,
             db,
             core_lifecycle,
             self.chat_route,
+            self.live_chat_route,
         )
         self.chatui_project_route = ChatUIProjectRoute(self.context, db)
         self.tools_root = ToolsRoute(self.context, core_lifecycle)
@@ -138,7 +140,6 @@ class AstrBotDashboard:
         self.kb_route = KnowledgeBaseRoute(self.context, core_lifecycle)
         self.platform_route = PlatformRoute(self.context, core_lifecycle)
         self.backup_route = BackupRoute(self.context, db, core_lifecycle)
-        self.live_chat_route = LiveChatRoute(self.context, db, core_lifecycle)
 
         self.app.add_url_rule(
             "/api/plug/<path:subpath>",
@@ -244,6 +245,7 @@ class AstrBotDashboard:
         scope_map = {
             "/api/v1/chat": "chat",
             "/api/v1/chat/ws": "chat",
+            "/api/v1/live/ws": "chat",
             "/api/v1/chat/sessions": "chat",
             "/api/v1/configs": "config",
             "/api/v1/file": "file",

compose-with-shipyard.yml

@@ -37,6 +37,7 @@ services:
       - DEFAULT_SHIP_MEMORY=512m
     volumes:
       - ${PWD}/data/shipyard/bay_data:/app/data
+      - ${PWD}/data/temp:/AstrBot/data/temp           # Bind the local temp directory to the sandbox so that the uploaded file can be accessed in the sandbox
       - /var/run/docker.sock:/var/run/docker.sock:ro
     networks:
       - astrbot_network

dashboard/package.json

@@ -36,7 +36,6 @@
     "remixicon": "3.5.0",
     "shiki": "^3.20.0",
     "stream-markdown": "^0.0.13",
-    "stream-monaco": "^0.0.17",
     "vee-validate": "4.11.3",
     "vite-plugin-vuetify": "2.1.3",
     "vue": "3.3.4",

dashboard/pnpm-lock.yaml

@@ -81,9 +81,6 @@ importers:
       stream-markdown:
         specifier: ^0.0.13
         version: 0.0.13(shiki@3.22.0)
-      stream-monaco:
-        specifier: ^0.0.17
-        version: 0.0.17(monaco-editor@0.52.2)
       vee-validate:
         specifier: 4.11.3
         version: 4.11.3(vue@3.3.4)
@@ -3300,6 +3297,7 @@ snapshots:
       '@shikijs/core': 3.22.0
       '@shikijs/types': 3.22.0
       '@shikijs/vscode-textmate': 10.0.2
+    optional: true
 
   '@shikijs/themes@3.22.0':
     dependencies:
@@ -3992,7 +3990,8 @@ snapshots:
       json-schema-traverse: 1.0.0
       require-from-string: 2.0.2
 
-  alien-signals@2.0.8: {}
+  alien-signals@2.0.8:
+    optional: true
 
   ansi-regex@5.0.1: {}
 
@@ -5443,6 +5442,7 @@ snapshots:
       alien-signals: 2.0.8
       monaco-editor: 0.52.2
       shiki: 3.22.0
+    optional: true
 
   stringify-entities@4.0.4:
     dependencies:

dashboard/src/components/chat/Chat.vue

@@ -11,6 +11,7 @@
                     :currSessionId="currSessionId"
                     :selectedProjectId="selectedProjectId"
                     :transportMode="transportMode"
+                    :sendShortcut="sendShortcut"
                     :isDark="isDark"
                     :chatboxMode="chatboxMode"
                     :isMobile="isMobile"
@@ -20,6 +21,7 @@
                     @selectConversation="handleSelectConversation"
                     @editTitle="showEditTitleDialog"
                     @deleteConversation="handleDeleteConversation"
+                    @batchDeleteConversations="handleBatchDeleteConversations"
                     @closeMobileSidebar="closeMobileSidebar"
                     @toggleTheme="toggleTheme"
                     @toggleFullscreen="toggleFullscreen"
@@ -28,6 +30,7 @@
                     @editProject="showEditProjectDialog"
                     @deleteProject="handleDeleteProject"
                     @updateTransportMode="setTransportMode"
+                    @updateSendShortcut="setSendShortcut"
                 />
 
                 <!-- 右侧聊天内容区域 -->
@@ -71,13 +74,14 @@
                                 :stagedImagesUrl="stagedImagesUrl"
                                 :stagedAudioUrl="stagedAudioUrl"
                                 :stagedFiles="stagedNonImageFiles"
-                                :disabled="isStreaming"
+                                :disabled="false"
                                 :is-running="isStreaming || isConvRunning"
                                 :enableStreaming="enableStreaming"
                                 :isRecording="isRecording"
                                 :session-id="currSessionId || null"
                                 :current-session="getCurrentSession"
                                 :replyTo="replyTo"
+                                :send-shortcut="sendShortcut"
                                 @send="handleSendMessage"
                                 @stop="handleStopMessage"
                                 @toggleStreaming="toggleStreaming"
@@ -102,13 +106,14 @@
                                 :stagedImagesUrl="stagedImagesUrl"
                                 :stagedAudioUrl="stagedAudioUrl"
                                 :stagedFiles="stagedNonImageFiles"
-                                :disabled="isStreaming"
+                                :disabled="false"
                                 :is-running="isStreaming || isConvRunning"
                                 :enableStreaming="enableStreaming"
                                 :isRecording="isRecording"
                                 :session-id="currSessionId || null"
                                 :current-session="getCurrentSession"
                                 :replyTo="replyTo"
+                                :send-shortcut="sendShortcut"
                                 @send="handleSendMessage"
                                 @stop="handleStopMessage"
                                 @toggleStreaming="toggleStreaming"
@@ -132,13 +137,14 @@
                             :stagedImagesUrl="stagedImagesUrl"
                             :stagedAudioUrl="stagedAudioUrl"
                             :stagedFiles="stagedNonImageFiles"
-                            :disabled="isStreaming"
+                            :disabled="false"
                             :is-running="isStreaming || isConvRunning"
                             :enableStreaming="enableStreaming"
                             :isRecording="isRecording"
                             :session-id="currSessionId || null"
                             :current-session="getCurrentSession"
                             :replyTo="replyTo"
+                            :send-shortcut="sendShortcut"
                             @send="handleSendMessage"
                             @stop="handleStopMessage"
                             @toggleStreaming="toggleStreaming"
@@ -220,10 +226,13 @@ import { useMediaHandling } from '@/composables/useMediaHandling';
 import { useProjects } from '@/composables/useProjects';
 import type { Project } from '@/components/chat/ProjectList.vue';
 import { useRecording } from '@/composables/useRecording';
+import { useToast } from '@/utils/toast';
 
 interface Props {
     chatboxMode?: boolean;
 }
+type SendShortcut = 'enter' | 'shift_enter';
+const SEND_SHORTCUT_STORAGE_KEY = 'chat_send_shortcut';
 
 const props = withDefaults(defineProps<Props>(), {
     chatboxMode: false
@@ -233,6 +242,7 @@ const router = useRouter();
 const route = useRoute();
 const { t } = useI18n();
 const { tm } = useModuleI18n('features/chat');
+const { warning: toastWarning } = useToast();
 const theme = useTheme();
 const customizer = useCustomizerStore();
 
@@ -257,6 +267,7 @@ const {
     getSessions,
     newSession,
     deleteSession: deleteSessionFn,
+    batchDeleteSessions,
     showEditTitleDialog,
     saveTitle,
     updateSessionTitle,
@@ -330,6 +341,18 @@ interface ReplyInfo {
 const replyTo = ref<ReplyInfo | null>(null);
 
 const isDark = computed(() => useCustomizerStore().uiTheme === 'PurpleThemeDark');
+const sendShortcut = ref<SendShortcut>('shift_enter');
+
+function setSendShortcut(mode: SendShortcut) {
+    sendShortcut.value = mode;
+    localStorage.setItem(SEND_SHORTCUT_STORAGE_KEY, mode);
+}
+
+function focusChatInput() {
+    nextTick(() => {
+        chatInputRef.value?.focusInput?.();
+    });
+}
 
 // 检测是否为手机端
 function checkMobile() {
@@ -488,6 +511,7 @@ async function handleSelectConversation(sessionIds: string[]) {
     nextTick(() => {
         messageList.value?.scrollToBottom();
     });
+    focusChatInput();
 }
 
 function handleNewChat() {
@@ -497,6 +521,7 @@ function handleNewChat() {
     // 退出项目视图
     selectedProjectId.value = null;
     projectSessions.value = [];
+    focusChatInput();
 }
 
 async function handleDeleteConversation(sessionId: string) {
@@ -510,6 +535,33 @@ async function handleDeleteConversation(sessionId: string) {
     }
 }
 
+async function handleBatchDeleteConversations(sessionIds: string[]) {
+    try {
+        const result = await batchDeleteSessions(sessionIds);
+
+        // 仅在当前会话成功删除时清除信息
+        if (result.currentSessionDeleted) {
+            messages.value = [];
+        }
+
+        // 失败处理
+        if (result.failed_count > 0) {
+            toastWarning(
+                tm('batch.partialFailure', { failed: result.failed_count, total: sessionIds.length })
+            );
+        }
+
+        // 如果在项目视图中，刷新项目会话列表
+        if (selectedProjectId.value) {
+            const sessions = await getProjectSessions(selectedProjectId.value);
+            projectSessions.value = sessions;
+        }
+    } catch (err) {
+        console.error('Batch delete sessions failed:', err);
+        toastWarning(tm('batch.requestFailed'));
+    }
+}
+
 async function handleSelectProject(projectId: string) {
     selectedProjectId.value = projectId;
     const sessions = await getProjectSessions(projectId);
@@ -627,6 +679,11 @@ async function handleSendMessage() {
     const selectedProviderId = selection?.providerId || '';
     const selectedModelName = selection?.modelName || '';
 
+    // 点击发送后立即将消息区滚到底部，确保用户看到最新消息
+    nextTick(() => {
+        messageList.value?.scrollToBottom();
+    });
+
     await sendMsg(
         promptToSend,
         filesToSend,
@@ -636,6 +693,11 @@ async function handleSendMessage() {
         replyToSend
     );
 
+    // 发送流程结束后再兜底一次，处理异步渲染场景
+    nextTick(() => {
+        messageList.value?.scrollToBottom();
+    });
+
     // 如果在项目中创建了新会话，将其添加到项目
     if (isCreatingNewSession && currentProjectId && currSessionId.value) {
         await addSessionToProject(currSessionId.value, currentProjectId);
@@ -694,6 +756,10 @@ watch(sessions, (newSessions) => {
 });
 
 onMounted(() => {
+    const storedShortcut = localStorage.getItem(SEND_SHORTCUT_STORAGE_KEY);
+    if (storedShortcut === 'enter' || storedShortcut === 'shift_enter') {
+        sendShortcut.value = storedShortcut;
+    }
     checkMobile();
     window.addEventListener('resize', checkMobile);
     getSessions();

dashboard/src/components/chat/ChatInput.vue

@@ -15,7 +15,7 @@
             <transition name="fade">
                 <div v-if="isDragging" class="drop-overlay">
                     <div class="drop-overlay-content">
-                        <v-icon size="48" color="deep-purple">mdi-cloud-upload</v-icon>
+                        <v-icon size="48" color="primary">mdi-cloud-upload</v-icon>
                         <span class="drop-text">{{ tm('input.dropToUpload') }}</span>
                     </div>
                 </div>
@@ -41,7 +41,7 @@
                     <!-- Settings Menu -->
                     <StyledMenu offset="8" location="top start" :close-on-content-click="false">
                         <template v-slot:activator="{ props: activatorProps }">
-                            <v-btn v-bind="activatorProps" icon="mdi-plus" variant="text" color="deep-purple" />
+                            <v-btn v-bind="activatorProps" icon="mdi-plus" variant="text" color="primary" />
                         </template>
 
                         <!-- Upload Files -->
@@ -87,7 +87,7 @@
                             {{ tm('voice.liveMode') }}
                         </v-tooltip>
                     </v-btn> -->
-                    <v-btn @click="handleRecordClick" icon variant="text" :color="isRecording ? 'error' : 'deep-purple'"
+                    <v-btn @click="handleRecordClick" icon variant="text" :color="isRecording ? 'error' : 'primary'"
                         class="record-btn">
                         <v-icon :icon="isRecording ? 'mdi-stop-circle' : 'mdi-microphone'" variant="text"
                             plain></v-icon>
@@ -95,13 +95,13 @@
                             {{ isRecording ? tm('voice.speaking') : tm('voice.startRecording') }}
                         </v-tooltip>
                     </v-btn>
-                    <v-btn icon v-if="isRunning" @click="$emit('stop')" variant="tonal" color="deep-purple" class="send-btn">
+                    <v-btn icon v-if="isRunning && !canSend" @click="$emit('stop')" variant="tonal" color="primary" class="send-btn">
                         <v-icon icon="mdi-stop" variant="text" plain></v-icon>
                         <v-tooltip activator="parent" location="top">
                             {{ tm('input.stopGenerating') }}
                         </v-tooltip>
                     </v-btn>
-                    <v-btn v-else @click="$emit('send')" icon="mdi-send" variant="tonal" color="deep-purple"
+                    <v-btn v-else @click="$emit('send')" icon="mdi-send" variant="tonal" color="primary"
                         :disabled="!canSend" class="send-btn" />
                 </div>
             </div>
@@ -117,7 +117,7 @@
             </div>
 
             <div v-if="stagedAudioUrl" class="audio-preview">
-                <v-chip color="deep-purple-lighten-4" class="audio-chip">
+                <v-chip color="primary" variant="tonal" class="audio-chip">
                     <v-icon start icon="mdi-microphone" size="small"></v-icon>
                     {{ tm('voice.recording') }}
                 </v-chip>
@@ -126,7 +126,7 @@
             </div>
 
             <div v-for="(file, index) in stagedFiles" :key="'file-' + index" class="file-preview">
-                <v-chip color="blue-grey-lighten-4" class="file-chip">
+                <v-chip color="primary" variant="tonal" class="file-chip">
                     <v-icon start icon="mdi-file-document-outline" size="small"></v-icon>
                     <span class="file-name-preview">{{ file.original_name }}</span>
                 </v-chip>
@@ -173,6 +173,7 @@ interface Props {
     currentSession?: Session | null;
     configId?: string | null;
     replyTo?: ReplyInfo | null;
+    sendShortcut?: 'enter' | 'shift_enter';
 }
 
 const props = withDefaults(defineProps<Props>(), {
@@ -180,7 +181,8 @@ const props = withDefaults(defineProps<Props>(), {
     currentSession: null,
     configId: null,
     stagedFiles: () => [],
-    replyTo: null
+    replyTo: null,
+    sendShortcut: 'shift_enter'
 });
 
 const emit = defineEmits<{
@@ -253,9 +255,29 @@ watch(localPrompt, () => {
 });
 
 function handleKeyDown(e: KeyboardEvent) {
-    // Enter 插入换行（桌面和手机端均如此，发送通过右下角发送按鈕）
-    // Shift+Enter 发送（Ctrl+Enter / Cmd+Enter 也保留）
-    if (e.keyCode === 13 && (e.shiftKey || e.ctrlKey || e.metaKey)) {
+    const isEnter = e.key === 'Enter';
+    if (!isEnter) {
+        // Ctrl+B 录音
+        if (e.ctrlKey && e.keyCode === 66) {
+            e.preventDefault();
+            if (ctrlKeyDown.value) return;
+
+            ctrlKeyDown.value = true;
+            ctrlKeyTimer.value = window.setTimeout(() => {
+                if (ctrlKeyDown.value && !props.isRecording) {
+                    emit('startRecording');
+                }
+            }, ctrlKeyLongPressThreshold);
+        }
+        return;
+    }
+
+    const isSendHotkey =
+        e.ctrlKey ||
+        e.metaKey ||
+        (props.sendShortcut === 'enter' ? !e.shiftKey : e.shiftKey);
+
+    if (isSendHotkey) {
         e.preventDefault();
         if (localPrompt.value.trim() === '/astr_live_dev') {
             emit('openLiveMode');
@@ -267,19 +289,6 @@ function handleKeyDown(e: KeyboardEvent) {
         }
         return;
     }
-
-    // Ctrl+B 录音
-    if (e.ctrlKey && e.keyCode === 66) {
-        e.preventDefault();
-        if (ctrlKeyDown.value) return;
-
-        ctrlKeyDown.value = true;
-        ctrlKeyTimer.value = window.setTimeout(() => {
-            if (ctrlKeyDown.value && !props.isRecording) {
-                emit('startRecording');
-            }
-        }, ctrlKeyLongPressThreshold);
-    }
 }
 
 function handleKeyUp(e: KeyboardEvent) {
@@ -364,6 +373,11 @@ function getCurrentSelection() {
     return providerModelMenuRef.value?.getCurrentSelection();
 }
 
+function focusInput() {
+    if (!inputField.value) return;
+    inputField.value.focus();
+}
+
 onMounted(() => {
     if (inputField.value) {
         inputField.value.addEventListener('paste', handlePaste);
@@ -379,7 +393,8 @@ onBeforeUnmount(() => {
 });
 
 defineExpose({
-    getCurrentSelection
+    getCurrentSelection,
+    focusInput
 });
 </script>
 
@@ -399,8 +414,8 @@ defineExpose({
     left: 0;
     right: 0;
     bottom: 0;
-    background-color: rgba(103, 58, 183, 0.15);
-    border: 2px dashed rgba(103, 58, 183, 0.5);
+    background-color: rgba(var(--v-theme-primary), 0.12);
+    border: 2px dashed rgba(var(--v-theme-primary), 0.45);
     border-radius: 24px;
     display: flex;
     align-items: center;
@@ -419,7 +434,7 @@ defineExpose({
 .drop-text {
     font-size: 16px;
     font-weight: 500;
-    color: #673ab7;
+    color: rgb(var(--v-theme-primary));
 }
 
 /* Fade transition for drop overlay */
@@ -439,7 +454,7 @@ defineExpose({
     justify-content: space-between;
     padding: 8px 16px;
     margin: 8px 8px 0 8px;
-    background-color: rgba(103, 58, 183, 0.06);
+    background-color: rgba(var(--v-theme-primary), 0.06);
     border-radius: 12px;
     gap: 8px;
     max-height: 500px;

dashboard/src/components/chat/ConversationSidebar.vue

@@ -5,7 +5,7 @@
             'mobile-sidebar-open': isMobile && mobileMenuOpen,
             'mobile-sidebar': isMobile
         }"
-        :style="{ 'background-color': isDark ? sidebarCollapsed ? '#1e1e1e' : '#2d2d2d' : sidebarCollapsed ? '#ffffff' : '#f1f4f9' }">
+        :style="{ backgroundColor: sidebarCollapsed && !isMobile ? 'rgb(var(--v-theme-surface))' : 'rgb(var(--v-theme-mcpCardBg))' }">
 
         <div class="sidebar-collapse-btn-container" v-if="!isMobile">
             <v-btn icon class="sidebar-collapse-btn" @click="toggleSidebar" variant="text" color="deep-purple">
@@ -21,12 +21,31 @@
         </div>
 
         <div style="padding: 8px; opacity: 0.6;">
-            <v-btn block variant="text" class="new-chat-btn" @click="$emit('newChat')" :disabled="!currSessionId && !selectedProjectId"
-                v-if="!sidebarCollapsed || isMobile" prepend-icon="mdi-square-edit-outline">{{ tm('actions.newChat') }}</v-btn>
-            <v-btn icon="mdi-square-edit-outline" rounded="xl" @click="$emit('newChat')" :disabled="!currSessionId && !selectedProjectId" 
+            <div class="new-chat-row" v-if="!sidebarCollapsed || isMobile">
+                <v-btn block variant="text" class="new-chat-btn" @click="$emit('newChat')" :disabled="!currSessionId && !selectedProjectId"
+                    prepend-icon="mdi-square-edit-outline">{{ tm('actions.newChat') }}</v-btn>
+                <v-btn v-if="sessions.length > 0" icon size="small" variant="text" @click="toggleBatchMode"
+                    :color="batchMode ? 'primary' : undefined">
+                    <v-icon>mdi-checkbox-multiple-marked-outline</v-icon>
+                </v-btn>
+            </div>
+            <v-btn icon="mdi-square-edit-outline" rounded="xl" @click="$emit('newChat')" :disabled="!currSessionId && !selectedProjectId"
                 v-if="sidebarCollapsed && !isMobile" elevation="0"></v-btn>
         </div>
 
+        <!-- Batch action bar -->
+        <div v-if="batchMode && (!sidebarCollapsed || isMobile)" class="batch-action-bar">
+            <v-btn size="x-small" variant="text" @click="toggleSelectAll">
+                {{ isAllSelected ? tm('batch.deselectAll') : tm('batch.selectAll') }}
+            </v-btn>
+            <span class="batch-selected-count">{{ tm('batch.selected', { count: batchSelected.length }) }}</span>
+            <v-spacer />
+            <v-btn size="x-small" variant="text" color="error" :disabled="batchSelected.length === 0"
+                @click="handleBatchDelete">
+                {{ tm('batch.delete') }}
+            </v-btn>
+        </div>
+
         <!-- 项目列表组件 -->
         <ProjectList
             v-if="!sidebarCollapsed || isMobile"
@@ -41,19 +60,34 @@
             v-if="!sidebarCollapsed || isMobile">
             <v-card v-if="sessions.length > 0" flat style="background-color: transparent;">
                 <v-list density="compact" nav class="conversation-list"
-                    style="background-color: transparent;" :selected="selectedSessions"
-                    @update:selected="$emit('selectConversation', $event)">
+                    style="background-color: transparent;" :selected="batchMode ? [] : selectedSessions"
+                    @update:selected="handleListSelect">
                     <v-list-item v-for="item in sessions" :key="item.session_id" :value="item.session_id"
-                        rounded="lg" class="conversation-item" active-color="secondary">
+                        rounded="lg" class="conversation-item" active-color="secondary"
+                        @click="batchMode ? toggleBatchItem(item.session_id) : undefined">
+
+                        <template v-slot:prepend>
+                            <div class="batch-checkbox-slot" :class="{ 'batch-checkbox-slot--active': batchMode }">
+                                <v-checkbox-btn
+                                    :model-value="batchSelected.includes(item.session_id)"
+                                    @update:model-value="toggleBatchItem(item.session_id)"
+                                    @click.stop
+                                    density="compact"
+                                    hide-details
+                                    class="batch-checkbox"
+                                />
+                            </div>
+                        </template>
+
                         <v-list-item-title v-if="!sidebarCollapsed || isMobile" class="conversation-title"
-                            :style="{ color: isDark ? '#ffffff' : '#000000' }">
+                            :style="{ color: 'rgb(var(--v-theme-primaryText))' }">
                             {{ item.display_name || tm('conversation.newConversation') }}
                         </v-list-item-title>
                         <!-- <v-list-item-subtitle v-if="!sidebarCollapsed || isMobile" class="timestamp">
                             {{ new Date(item.updated_at).toLocaleString() }}
                         </v-list-item-subtitle> -->
 
-                        <template v-if="!sidebarCollapsed || isMobile" v-slot:append>
+                        <template v-if="!batchMode && (!sidebarCollapsed || isMobile)" v-slot:append>
                             <div class="conversation-actions">
                                 <v-btn icon="mdi-pencil" size="x-small" variant="text"
                                     class="edit-title-btn"
@@ -98,16 +132,52 @@
                     </v-btn>
                 </template>
                 
-                <!-- 语言切换 -->
-                <v-list-item class="styled-menu-item">
-                    <template v-slot:prepend>
-                        <v-icon>mdi-translate</v-icon>
+                <!-- 语言切换（分组） -->
+                <v-menu
+                    :open-on-hover="!isMobile"
+                    :open-on-click="isMobile"
+                    :open-delay="!isMobile ? 60 : 0"
+                    :close-delay="!isMobile ? 120 : 0"
+                    :location="isMobile ? 'bottom' : 'end center'"
+                    offset="8"
+                    close-on-content-click
+                >
+                    <template v-slot:activator="{ props: languageMenuProps }">
+                        <v-list-item
+                            v-bind="languageMenuProps"
+                            class="styled-menu-item chat-settings-group-trigger"
+                            rounded="md"
+                        >
+                            <template v-slot:prepend>
+                                <v-icon>mdi-translate</v-icon>
+                            </template>
+                            <v-list-item-title>{{ t('core.common.language') }}</v-list-item-title>
+                            <template v-slot:append>
+                                <span class="chat-settings-group-current">{{ currentLanguage?.flag }}</span>
+                                <v-icon size="18" class="chat-settings-group-arrow">mdi-chevron-right</v-icon>
+                            </template>
+                        </v-list-item>
                     </template>
-                    <v-list-item-title>{{ t('core.common.language') }}</v-list-item-title>
-                    <template v-slot:append>
-                        <LanguageSwitcher variant="chatbox" />
-                    </template>
-                </v-list-item>
+
+                    <v-card class="styled-menu-card" style="min-width: 180px;" elevation="8" rounded="lg">
+                        <v-list density="compact" class="styled-menu-list pa-1">
+                            <v-list-item
+                                v-for="lang in languages"
+                                :key="lang.code"
+                                :value="lang.code"
+                                @click="changeLanguage(lang.code)"
+                                :class="{ 'styled-menu-item-active': currentLocale === lang.code }"
+                                class="styled-menu-item"
+                                rounded="md"
+                            >
+                                <template v-slot:prepend>
+                                    <span class="language-flag">{{ lang.flag }}</span>
+                                </template>
+                                <v-list-item-title>{{ lang.name }}</v-list-item-title>
+                            </v-list-item>
+                        </v-list>
+                    </v-card>
+                </v-menu>
                 
                 <!-- 主题切换 -->
                 <v-list-item class="styled-menu-item" @click="$emit('toggleTheme')">
@@ -117,26 +187,93 @@
                     <v-list-item-title>{{ isDark ? tm('modes.lightMode') : tm('modes.darkMode') }}</v-list-item-title>
                 </v-list-item>
 
-                <!-- 通信传输模式 -->
-                <v-list-item class="styled-menu-item">
-                    <template v-slot:prepend>
-                        <v-icon>mdi-lan-connect</v-icon>
+                <!-- 通信传输模式（分组） -->
+                <v-menu
+                    :open-on-hover="!isMobile"
+                    :open-on-click="isMobile"
+                    :open-delay="!isMobile ? 60 : 0"
+                    :close-delay="!isMobile ? 120 : 0"
+                    :location="isMobile ? 'bottom' : 'end center'"
+                    offset="8"
+                    close-on-content-click
+                >
+                    <template v-slot:activator="{ props: transportMenuProps }">
+                        <v-list-item
+                            v-bind="transportMenuProps"
+                            class="styled-menu-item chat-settings-group-trigger"
+                            rounded="md"
+                        >
+                            <template v-slot:prepend>
+                                <v-icon>mdi-lan-connect</v-icon>
+                            </template>
+                            <v-list-item-title>{{ tm('transport.title') }}</v-list-item-title>
+                            <template v-slot:append>
+                                <span class="chat-settings-group-current chat-settings-transport-current">{{ currentTransportLabel }}</span>
+                                <v-icon size="18" class="chat-settings-group-arrow">mdi-chevron-right</v-icon>
+                            </template>
+                        </v-list-item>
                     </template>
-                    <v-list-item-title>{{ tm('transport.title') }}</v-list-item-title>
-                    <template v-slot:append>
-                        <v-select
-                            :model-value="transportMode"
-                            :items="transportOptions"
-                            item-title="label"
-                            item-value="value"
-                            density="compact"
-                            variant="underlined"
-                            hide-details
-                            class="transport-mode-select"
-                            @update:model-value="handleTransportModeChange"
-                        />
+
+                    <v-card class="styled-menu-card" style="min-width: 220px;" elevation="8" rounded="lg">
+                        <v-list density="compact" class="styled-menu-list pa-1">
+                            <v-list-item
+                                v-for="opt in transportOptions"
+                                :key="opt.value"
+                                :value="opt.value"
+                                @click="handleTransportModeChange(opt.value)"
+                                :class="{ 'styled-menu-item-active': transportMode === opt.value }"
+                                class="styled-menu-item"
+                                rounded="md"
+                            >
+                                <v-list-item-title>{{ opt.label }}</v-list-item-title>
+                            </v-list-item>
+                        </v-list>
+                    </v-card>
+                </v-menu>
+
+                <!-- 发送快捷键（分组） -->
+                <v-menu
+                    :open-on-hover="!isMobile"
+                    :open-on-click="isMobile"
+                    :open-delay="!isMobile ? 60 : 0"
+                    :close-delay="!isMobile ? 120 : 0"
+                    :location="isMobile ? 'bottom' : 'end center'"
+                    offset="8"
+                    close-on-content-click
+                >
+                    <template v-slot:activator="{ props: sendShortcutMenuProps }">
+                        <v-list-item
+                            v-bind="sendShortcutMenuProps"
+                            class="styled-menu-item chat-settings-group-trigger"
+                            rounded="md"
+                        >
+                            <template v-slot:prepend>
+                                <v-icon>mdi-keyboard-outline</v-icon>
+                            </template>
+                            <v-list-item-title>{{ tm('shortcuts.sendKey.title') }}</v-list-item-title>
+                            <template v-slot:append>
+                                <span class="chat-settings-group-current chat-settings-transport-current">{{ currentSendShortcutLabel }}</span>
+                                <v-icon size="18" class="chat-settings-group-arrow">mdi-chevron-right</v-icon>
+                            </template>
+                        </v-list-item>
                     </template>
-                </v-list-item>
+
+                    <v-card class="styled-menu-card" style="min-width: 220px;" elevation="8" rounded="lg">
+                        <v-list density="compact" class="styled-menu-list pa-1">
+                            <v-list-item
+                                v-for="opt in sendShortcutOptions"
+                                :key="opt.value"
+                                :value="opt.value"
+                                @click="handleSendShortcutChange(opt.value)"
+                                :class="{ 'styled-menu-item-active': props.sendShortcut === opt.value }"
+                                class="styled-menu-item"
+                                rounded="md"
+                            >
+                                <v-list-item-title>{{ opt.label }}</v-list-item-title>
+                            </v-list-item>
+                        </v-list>
+                    </v-card>
+                </v-menu>
 
                 <!-- 全屏/退出全屏 -->
                 <v-list-item class="styled-menu-item" @click="$emit('toggleFullscreen')">
@@ -162,15 +299,16 @@
 </template>
 
 <script setup lang="ts">
-import { ref } from 'vue';
+import { ref, computed } from 'vue';
 import { useI18n, useModuleI18n } from '@/i18n/composables';
 import type { Session } from '@/composables/useSessions';
 import { askForConfirmation, useConfirmDialog } from '@/utils/confirmDialog';
-import LanguageSwitcher from '@/components/shared/LanguageSwitcher.vue';
 import StyledMenu from '@/components/shared/StyledMenu.vue';
 import ProviderConfigDialog from '@/components/chat/ProviderConfigDialog.vue';
 import ProjectList from '@/components/chat/ProjectList.vue';
 import type { Project } from '@/components/chat/ProjectList.vue';
+import { useLanguageSwitcher } from '@/i18n/composables';
+import type { Locale } from '@/i18n/types';
 
 interface Props {
     sessions: Session[];
@@ -183,6 +321,7 @@ interface Props {
     isMobile: boolean;
     mobileMenuOpen: boolean;
     projects?: Project[];
+    sendShortcut: 'enter' | 'shift_enter';
 }
 
 const props = withDefaults(defineProps<Props>(), {
@@ -194,6 +333,7 @@ const emit = defineEmits<{
     selectConversation: [sessionIds: string[]];
     editTitle: [sessionId: string, title: string];
     deleteConversation: [sessionId: string];
+    batchDeleteConversations: [sessionIds: string[]];
     closeMobileSidebar: [];
     toggleTheme: [];
     toggleFullscreen: [];
@@ -202,6 +342,7 @@ const emit = defineEmits<{
     editProject: [project: Project];
     deleteProject: [projectId: string];
     updateTransportMode: [mode: 'sse' | 'websocket'];
+    updateSendShortcut: [mode: 'enter' | 'shift_enter'];
 }>();
 
 const { t } = useI18n();
@@ -211,10 +352,84 @@ const confirmDialog = useConfirmDialog();
 
 const sidebarCollapsed = ref(true);
 const showProviderConfigDialog = ref(false);
+
+// Batch mode state
+const batchMode = ref(false);
+const batchSelected = ref<string[]>([]);
+
+const isAllSelected = computed(() =>
+    props.sessions.length > 0 && batchSelected.value.length === props.sessions.length
+);
+
+function toggleBatchMode() {
+    batchMode.value = !batchMode.value;
+    batchSelected.value = [];
+}
+
+function toggleBatchItem(sessionId: string) {
+    const idx = batchSelected.value.indexOf(sessionId);
+    if (idx >= 0) {
+        batchSelected.value.splice(idx, 1);
+    } else {
+        batchSelected.value.push(sessionId);
+    }
+}
+
+function toggleSelectAll() {
+    if (isAllSelected.value) {
+        batchSelected.value = [];
+    } else {
+        batchSelected.value = props.sessions.map(s => s.session_id);
+    }
+}
+
+async function handleBatchDelete() {
+    const count = batchSelected.value.length;
+    if (count === 0) return;
+    const message = tm('batch.confirmDelete', { count });
+    if (await askForConfirmation(message, confirmDialog)) {
+        emit('batchDeleteConversations', [...batchSelected.value]);
+        batchSelected.value = [];
+        batchMode.value = false;
+    }
+}
+
+function handleListSelect(sessionIds: string[]) {
+    if (!batchMode.value) {
+        emit('selectConversation', sessionIds);
+    }
+}
 const transportOptions = [
     { label: tm('transport.sse'), value: 'sse' as const },
     { label: tm('transport.websocket'), value: 'websocket' as const }
 ];
+const sendShortcutOptions = [
+    { label: tm('shortcuts.sendKey.enterToSend'), value: 'enter' as const },
+    { label: tm('shortcuts.sendKey.shiftEnterToSend'), value: 'shift_enter' as const }
+];
+
+// Language switcher
+const { languageOptions, currentLanguage, switchLanguage, locale } = useLanguageSwitcher();
+const languages = computed(() =>
+    languageOptions.value.map(lang => ({
+        code: lang.value,
+        name: lang.label,
+        flag: lang.flag
+    }))
+);
+const currentLocale = computed(() => locale.value);
+const changeLanguage = async (langCode: string) => {
+    await switchLanguage(langCode as Locale);
+};
+
+const currentTransportLabel = computed(() => {
+    const found = transportOptions.find(opt => opt.value === props.transportMode);
+    return found?.label ?? '';
+});
+const currentSendShortcutLabel = computed(() => {
+    const found = sendShortcutOptions.find(opt => opt.value === props.sendShortcut);
+    return found?.label ?? '';
+});
 
 // 从 localStorage 读取侧边栏折叠状态
 const savedCollapsedState = localStorage.getItem('sidebarCollapsed');
@@ -242,6 +457,12 @@ function handleTransportModeChange(mode: string | null) {
         emit('updateTransportMode', mode);
     }
 }
+
+function handleSendShortcutChange(mode: string | null) {
+    if (mode === 'enter' || mode === 'shift_enter') {
+        emit('updateSendShortcut', mode);
+    }
+}
 </script>
 
 <style scoped>
@@ -310,7 +531,7 @@ function handleTransportModeChange(mode: string | null) {
 }
 
 .conversation-item:hover {
-    background-color: rgba(103, 58, 183, 0.05);
+    background-color: rgba(var(--v-theme-primary), 0.05);
 }
 
 .conversation-item:hover .conversation-actions {
@@ -402,7 +623,74 @@ function handleTransportModeChange(mode: string | null) {
     justify-content: center;
 }
 
-.transport-mode-select {
-    min-width: 120px;
+.chat-settings-group-trigger :deep(.v-list-item__append) {
+    display: flex;
+    align-items: center;
+    gap: 6px;
+}
+
+.chat-settings-group-current {
+    font-size: 14px;
+    line-height: 1;
+    opacity: 0.8;
+}
+
+.chat-settings-transport-current {
+    font-size: 12px;
+}
+
+.chat-settings-group-arrow {
+    opacity: 0.7;
+}
+
+.language-flag {
+    font-size: 16px;
+    margin-right: 8px;
+}
+
+.new-chat-row {
+    display: flex;
+    align-items: center;
+    gap: 4px;
+}
+
+.new-chat-row .new-chat-btn {
+    flex: 1;
+    min-width: 0;
+}
+
+.batch-action-bar {
+    display: flex;
+    align-items: center;
+    padding: 4px 12px;
+    gap: 4px;
+    flex-shrink: 0;
+}
+
+.batch-selected-count {
+    font-size: 12px;
+    opacity: 0.7;
+    white-space: nowrap;
+}
+
+.batch-checkbox {
+    flex: none;
+    transition: opacity 0.2s ease, transform 0.2s ease;
+}
+
+.batch-checkbox-slot {
+    width: 0;
+    opacity: 0;
+    overflow: hidden;
+    pointer-events: none;
+    transform: translateX(-8px);
+    transition: width 0.2s ease, opacity 0.2s ease, transform 0.2s ease;
+}
+
+.batch-checkbox-slot--active {
+    width: 28px;
+    opacity: 1;
+    pointer-events: auto;
+    transform: translateX(0);
 }
 </style>

dashboard/src/components/chat/MessageList.vue

@@ -180,7 +180,7 @@
 
 <script>
 import { useI18n, useModuleI18n } from '@/i18n/composables';
-import { enableKatex, enableMermaid, setCustomComponents } from 'markstream-vue'
+import { enableKatex, enableMermaid, MarkdownCodeBlockNode, setCustomComponents } from 'markstream-vue'
 import 'markstream-vue/index.css'
 import 'katex/dist/katex.min.css'
 import 'highlight.js/styles/github.css';
@@ -194,8 +194,11 @@ import ActionRef from './message_list_comps/ActionRef.vue';
 enableKatex();
 enableMermaid();
 
-// 注册自定义 ref 组件
-setCustomComponents('message-list', { ref: RefNode });
+// 注册 message-list 专用组件：引用节点 + Shiki 代码块渲染
+setCustomComponents('message-list', {
+    ref: RefNode,
+    code_block: MarkdownCodeBlockNode
+});
 
 export default {
     name: 'MessageList',

dashboard/src/components/chat/StandaloneChat.vue

@@ -22,7 +22,7 @@
                         v-model:prompt="prompt"
                         :stagedImagesUrl="stagedImagesUrl"
                         :stagedAudioUrl="stagedAudioUrl"
-                        :disabled="isStreaming"
+                        :disabled="false"
                         :is-running="isStreaming || isConvRunning"
                         :enableStreaming="enableStreaming"
                         :isRecording="isRecording"

dashboard/src/components/chat/message_list_comps/MessagePartsRenderer.vue

@@ -63,8 +63,9 @@
         <!-- Text (Markdown) -->
         <MarkdownRender
             v-else-if="renderPart.part.type === 'plain' && renderPart.part.text && renderPart.part.text.trim()"
+            :key="`${renderPart.key}-${isDark ? 'dark' : 'light'}`"
             custom-id="message-list" :custom-html-tags="['ref']" :content="renderPart.part.text" :typewriter="false"
-            class="markdown-content" :is-dark="isDark" :monacoOptions="{ theme: isDark ? 'vs-dark' : 'vs-light' }" />
+            class="markdown-content" :is-dark="isDark" />
 
         <!-- Image -->
         <div v-else-if="renderPart.part.type === 'image' && renderPart.part.embedded_url" class="embedded-images">

dashboard/src/components/chat/message_list_comps/ReasoningBlock.vue

@@ -9,7 +9,7 @@
             </span>
         </div>
         <div v-if="isExpanded" class="reasoning-content animate-fade-in">
-            <MarkdownRender :content="reasoning" class="reasoning-text markdown-content"
+            <MarkdownRender :key="`reasoning-${isDark ? 'dark' : 'light'}`" :content="reasoning" class="reasoning-text markdown-content"
                 :typewriter="false" :is-dark="isDark" :style="isDark ? { opacity: '0.85' } : {}" />
         </div>
     </div>

dashboard/src/components/chat/message_list_comps/RefNode.vue

@@ -1,12 +1,12 @@
 <template>
     <v-chip v-if="domain" class="ref-chip" size="x-small" variant="flat"
-        :style="{ backgroundColor: isDark ? '#303030' : '#f4f4f4', color: isDark ? '#999' : '#666' }" :href="url"
+        :style="chipStyle" :href="url"
         target="_blank" clickable>
         <v-icon start size="x-small" color>mdi-link-variant</v-icon>
         <span>{{ domain }}</span>
 
     </v-chip>
-    <span v-else class="ref-fallback" :style="{ color: isDark ? '#999' : '#666' }">{{ 'site' }}</span>
+    <span v-else class="ref-fallback" :style="fallbackStyle">{{ 'site' }}</span>
 </template>
 
 <script setup>
@@ -46,6 +46,15 @@ const domain = computed(() => {
         return ''
     }
 })
+
+const chipStyle = computed(() => ({
+    backgroundColor: isDark ? 'rgba(var(--v-theme-on-surface), 0.08)' : 'rgba(var(--v-theme-on-surface), 0.04)',
+    color: isDark ? 'rgba(var(--v-theme-on-surface), 0.62)' : 'rgba(var(--v-theme-on-surface), 0.72)'
+}))
+
+const fallbackStyle = computed(() => ({
+    color: isDark ? 'rgba(var(--v-theme-on-surface), 0.62)' : 'rgba(var(--v-theme-on-surface), 0.72)'
+}))
 </script>
 
 <style scoped>

dashboard/src/components/shared/LanguageSwitcher.vue

@@ -12,7 +12,7 @@
       >
         <v-icon 
           size="18"
-          :color="props.variant === 'default' ? (useCustomizerStore().uiTheme === 'PurpleTheme' ? '#5e35b1' : '#d7c5fa') : undefined"
+          :color="props.variant === 'default' ? 'rgb(var(--v-theme-primary))' : undefined"
         >
           mdi-translate
         </v-icon>
@@ -42,7 +42,6 @@
 <script setup lang="ts">
 import { computed } from 'vue'
 import { useI18n, useLanguageSwitcher } from '@/i18n/composables'
-import { useCustomizerStore } from '@/stores/customizer'
 import type { Locale } from '@/i18n/types'
 import StyledMenu from '@/components/shared/StyledMenu.vue'
 
@@ -90,7 +89,7 @@ const changeLanguage = async (langCode: string) => {
 
 .language-switcher--default:hover {
   transform: scale(1.05);
-  background: rgba(94, 53, 177, 0.08) !important;
+  background: rgba(var(--v-theme-primary), 0.08) !important;
 }
 
 /* Header变体样式 - 完全继承Vuetify和action-btn的默认样式 */
@@ -103,8 +102,4 @@ const changeLanguage = async (langCode: string) => {
   /* 继承action-btn样式，与工具栏主题按钮保持一致 */
 }
 
-/* 深色模式下的悬停效果（仅对default变体） */
-:deep(.v-theme--PurpleThemeDark) .language-switcher--default:hover {
-  background: rgba(114, 46, 209, 0.12) !important;
-}
 </style> 

dashboard/src/components/shared/Logo.vue

@@ -6,11 +6,11 @@
       </div>
       <div class="logo-text">
         <h2 
-          :style="{color: useCustomizerStore().uiTheme === 'PurpleTheme' ? '#5e35b1' : '#d7c5fa'}"
+          :style="{ color: 'rgb(var(--v-theme-primary))' }"
           v-html="formatTitle(title || t('core.header.logoTitle'))"
         ></h2>
         <!-- 父子组件传递css变量可能会出错，暂时使用十六进制颜色值 -->
-        <h4 :style="{color: useCustomizerStore().uiTheme === 'PurpleTheme' ? '#000000aa' : '#ffffffcc'}"
+        <h4 :style="{ color: 'rgba(var(--v-theme-on-surface), 0.72)' }"
             class="hint-text">{{ subtitle || t('core.header.accountDialog.title') }}</h4>
       </div>
     </div>
@@ -18,7 +18,6 @@
 </template>
 
 <script setup lang="ts">
-import { useCustomizerStore } from "@/stores/customizer";
 import { useI18n } from '@/i18n/composables';
 
 const { t } = useI18n();

dashboard/src/components/shared/StyledMenu.vue

@@ -24,12 +24,12 @@ withDefaults(defineProps<{
 })
 </script>
 
-<style scoped>
+<style>
 .styled-menu-card {
   min-width: 100px;
   width: fit-content;
-  border: 1px solid rgba(94, 53, 177, 0.15) !important;
-  background: #f8f6fc !important;
+  border: 1px solid rgba(var(--v-theme-primary), 0.15) !important;
+  background: rgba(var(--v-theme-surface), 0.98) !important;
   backdrop-filter: blur(10px);
 }
 
@@ -37,43 +37,41 @@ withDefaults(defineProps<{
   background: transparent !important;
 }
 
-:deep(.styled-menu-item) {
+.styled-menu-item {
   margin: 2px 0;
   transition: all 0.2s ease;
   border-radius: 6px;
 }
 
-:deep(.styled-menu-item:hover) {
-  background: rgba(94, 53, 177, 0.08) !important;
+.styled-menu-item:hover {
+  background: rgba(var(--v-theme-primary), 0.08) !important;
 }
 
-:deep(.styled-menu-item-active) {
-  background: rgba(94, 53, 177, 0.15) !important;
+.styled-menu-item-active {
+  background: rgba(var(--v-theme-primary), 0.15) !important;
   font-weight: 500;
 }
 
-:deep(.styled-menu-item-active:hover) {
-  background: rgba(94, 53, 177, 0.2) !important;
+.styled-menu-item-active:hover {
+  background: rgba(var(--v-theme-primary), 0.2) !important;
 }
-</style>
 
-<style>
 /* 深色模式下的下拉框样式 - 需要全局样式才能检测主题 */
 .v-theme--PurpleThemeDark .styled-menu-card {
-  background: #2a2733 !important;
-  border: 1px solid rgba(110, 60, 180, 0.692) !important;
+  background: rgba(var(--v-theme-surface), 0.98) !important;
+  border: 1px solid rgba(var(--v-theme-primary), 0.2) !important;
 }
 
 /* 深色模式下的列表项悬停效果 */
 .v-theme--PurpleThemeDark .styled-menu-item:hover {
-  background: rgba(114, 46, 209, 0.12) !important;
+  background: rgba(var(--v-theme-primary), 0.12) !important;
 }
 
 .v-theme--PurpleThemeDark .styled-menu-item-active {
-  background: rgba(114, 46, 209, 0.2) !important;
+  background: rgba(var(--v-theme-primary), 0.2) !important;
 }
 
 .v-theme--PurpleThemeDark .styled-menu-item-active:hover {
-  background: rgba(114, 46, 209, 0.25) !important;
+  background: rgba(var(--v-theme-primary), 0.25) !important;
 }
 </style>

dashboard/src/composables/useProviderSources.ts

@@ -590,9 +590,11 @@ export function useProviderSources(options: UseProviderSourcesOptions) {
   async function testProvider(provider: any) {
     testingProviders.value.push(provider.id)
     try {
+      const startTime = performance.now()
       const response = await axios.get('/api/config/provider/check_one', { params: { id: provider.id } })
       if (response.data.status === 'ok' && response.data.data.error === null) {
-        showMessage(tm('models.testSuccess', { id: provider.id }))
+        const latency = Math.max(0, Math.round(performance.now() - startTime))
+        showMessage(tm('models.testSuccessWithLatency', { id: provider.id, latency }))
       } else {
         throw new Error(response.data.data.error || tm('models.testError'))
       }

dashboard/src/composables/useSessions.ts

@@ -109,6 +109,73 @@ export function useSessions(chatboxMode: boolean = false) {
         }
     }
 
+    interface BatchDeleteFailedItem {
+        session_id: string;
+        reason: string;
+    }
+
+    interface BatchDeleteResult {
+        deleted_count: number;
+        failed_count: number;
+        failed_items: BatchDeleteFailedItem[];
+        currentSessionDeleted: boolean;
+    }
+
+    function isBatchDeleteResponseData(data: unknown): data is {
+        deleted_count: number;
+        failed_count: number;
+        failed_items: BatchDeleteFailedItem[];
+    } {
+        if (!data || typeof data !== 'object') {
+            return false;
+        }
+        const payload = data as Record<string, unknown>;
+        return (
+            typeof payload.deleted_count === 'number' &&
+            typeof payload.failed_count === 'number' &&
+            Array.isArray(payload.failed_items)
+        );
+    }
+
+    async function batchDeleteSessions(sessionIds: string[]): Promise<BatchDeleteResult> {
+        try {
+            const currentSessionId = currSessionId.value;
+            const response = await axios.post('/api/chat/batch_delete_sessions', { session_ids: sessionIds });
+            if (response.data?.status !== 'ok') {
+                throw new Error(response.data?.message || 'Failed to batch delete sessions');
+            }
+
+            const data = response.data?.data;
+            if (!isBatchDeleteResponseData(data)) {
+                throw new Error('Invalid batch delete response payload');
+            }
+
+            const failedItems = data.failed_items;
+            const failedSessionIds = new Set(failedItems.map(item => item.session_id));
+            const currentSessionDeleted = Boolean(
+                currentSessionId &&
+                sessionIds.includes(currentSessionId) &&
+                !failedSessionIds.has(currentSessionId)
+            );
+
+            if (currentSessionDeleted) {
+                currSessionId.value = '';
+                selectedSessions.value = [];
+            }
+            await getSessions();
+
+            return {
+                deleted_count: data.deleted_count,
+                failed_count: data.failed_count,
+                failed_items: failedItems,
+                currentSessionDeleted,
+            };
+        } catch (err) {
+            console.error(err);
+            throw err;
+        }
+    }
+
     function showEditTitleDialog(sessionId: string, title: string) {
         editingSessionId.value = sessionId;
         editingTitle.value = title || '';
@@ -167,6 +234,7 @@ export function useSessions(chatboxMode: boolean = false) {
         getSessions,
         newSession,
         deleteSession,
+        batchDeleteSessions,
         showEditTitleDialog,
         saveTitle,
         updateSessionTitle,

dashboard/src/i18n/locales/en-US/core/shared.json

@@ -96,6 +96,7 @@
     "save": "Save",
     "livePreview": "Live Preview (may differ)",
     "refreshPreview": "Refresh Preview",
+    "previewText": "This is a sample text used to preview the template output.\n\nIt can contain multiple lines and various formatting.",
     "syntaxHint": "Supports jinja2 syntax. Available variables: text | safe (text to render), version (AstrBot version)",
     "saveAndApply": "Save and Apply Current Template",
     "confirmReset": "Confirm Reset",

dashboard/src/i18n/locales/en-US/features/chat.json

@@ -71,10 +71,16 @@
   "modes": {
     "darkMode": "Switch to Dark Mode",
     "lightMode": "Switch to Light Mode"
-  },  "shortcuts": {
+  },
+  "shortcuts": {
     "help": "Get Help",
     "voiceRecord": "Record Voice",
-    "pasteImage": "Paste Image"
+    "pasteImage": "Paste Image",
+    "sendKey": {
+      "title": "Send Shortcut",
+      "enterToSend": "Enter to send",
+      "shiftEnterToSend": "Shift+Enter to send"
+    }
   },
   "streaming": {
     "enabled": "Streaming enabled",
@@ -141,5 +147,15 @@
   "errors": {
     "sendMessageFailed": "Failed to send message, please try again",
     "createSessionFailed": "Failed to create session, please refresh the page"
+  },
+  "batch": {
+    "selected": "{count} selected",
+    "confirmDelete": "Are you sure you want to delete {count} conversation(s)? This action cannot be undone.",
+    "selectAll": "Select All",
+    "deselectAll": "Deselect All",
+    "delete": "Delete",
+    "exit": "Exit",
+    "partialFailure": "{failed} of {total} conversations failed to delete",
+    "requestFailed": "Failed to delete conversations. Please try again."
   }
 } 

dashboard/src/i18n/locales/en-US/features/provider.json

@@ -132,6 +132,7 @@
     "deleteSuccess": "Model deleted successfully",
     "deleteError": "Failed to delete model",
     "testSuccess": "Model {id} test passed",
+    "testSuccessWithLatency": "Model {id} test passed, latency {latency} ms",
     "testError": "Model test failed",
     "searchPlaceholder": "Search models or ID",
     "manualAddButton": "Custom Model",

dashboard/src/i18n/locales/ru-RU/core/shared.json

@@ -97,6 +97,7 @@
         "save": "Сохранить",
         "livePreview": "Предпросмотр (может отличаться)",
         "refreshPreview": "Обновить",
+        "previewText": "Это пример текста для предпросмотра результата шаблона.\n\nОн может содержать несколько строк и различные форматы.",
         "syntaxHint": "Поддерживается синтаксис jinja2. Переменные: text | safe (текст для рендеринга), version (версия AstrBot)",
         "saveAndApply": "Сохранить и применить текущий шаблон",
         "confirmReset": "Подтверждение сброса",

dashboard/src/i18n/locales/ru-RU/features/chat.json

@@ -75,7 +75,12 @@
     "shortcuts": {
         "help": "Справка",
         "voiceRecord": "Запись голоса",
-        "pasteImage": "Вставить изображение"
+        "pasteImage": "Вставить изображение",
+        "sendKey": {
+            "title": "Клавиша отправки",
+            "enterToSend": "Enter для отправки",
+            "shiftEnterToSend": "Shift+Enter для отправки"
+        }
     },
     "streaming": {
         "enabled": "Потоковый ответ включен",
@@ -143,4 +148,4 @@
         "sendMessageFailed": "Ошибка отправки сообщения, попробуйте еще раз",
         "createSessionFailed": "Ошибка создания сессии, обновите страницу"
     }
-}
+}

dashboard/src/i18n/locales/zh-CN/core/shared.json

@@ -96,6 +96,7 @@
     "save": "保存",
     "livePreview": "实时预览(可能有差异)",
     "refreshPreview": "刷新预览",
+    "previewText": "这是一个示例文本，用于预览模板效果。\n\n这里可以包含多行文本，支持换行和各种格式。",
     "syntaxHint": "支持 jinja2 语法。可用变量：text | safe（要渲染的文本）, version（AstrBot 版本）",
     "saveAndApply": "保存应用当前编辑模板",
     "confirmReset": "确认重置",

dashboard/src/i18n/locales/zh-CN/features/chat.json

@@ -71,10 +71,16 @@
   "modes": {
     "darkMode": "切换到夜间模式",
     "lightMode": "切换到日间模式"
-  },  "shortcuts": {
+  },
+  "shortcuts": {
     "help": "获取帮助",
     "voiceRecord": "录制语音",
-    "pasteImage": "粘贴图片"
+    "pasteImage": "粘贴图片",
+    "sendKey": {
+      "title": "发送快捷键",
+      "enterToSend": "Enter 发送",
+      "shiftEnterToSend": "Shift+Enter 发送"
+    }
   },
   "streaming": {
     "enabled": "流式响应已开启",
@@ -141,5 +147,15 @@
   "errors": {
     "sendMessageFailed": "发送消息失败，请重试",
     "createSessionFailed": "创建会话失败，请刷新页面重试"
+  },
+  "batch": {
+    "selected": "已选择 {count} 个",
+    "confirmDelete": "确定要删除 {count} 个对话吗？此操作无法撤销。",
+    "selectAll": "全选",
+    "deselectAll": "取消全选",
+    "delete": "删除",
+    "exit": "退出",
+    "partialFailure": "{total} 个对话中有 {failed} 个删除失败",
+    "requestFailed": "删除对话失败，请重试。"
   }
 } 

dashboard/src/i18n/locales/zh-CN/features/provider.json

@@ -133,6 +133,7 @@
     "deleteSuccess": "模型删除成功",
     "deleteError": "模型删除失败",
     "testSuccess": "模型 {id} 测试通过",
+    "testSuccessWithLatency": "模型 {id} 测试通过，延迟 {latency} ms",
     "testError": "模型测试失败",
     "searchPlaceholder": "搜索模型或 ID",
     "manualAddButton": "自定义模型",

dashboard/src/layouts/full/vertical-header/VerticalHeader.vue

@@ -465,23 +465,14 @@ onMounted(async () => {
   <v-app-bar elevation="0" height="50" class="top-header">
 
     <!-- 桌面端 menu 按钮 - 仅在 bot 模式下显示 -->
-    <v-btn v-if="customizer.viewMode === 'bot' && useCustomizerStore().uiTheme === 'PurpleTheme'" style="margin-left: 16px;"
-      class="hidden-md-and-down"  icon rounded="sm" variant="flat"
-      @click.stop="customizer.SET_MINI_SIDEBAR(!customizer.mini_sidebar)">
-      <v-icon>mdi-menu</v-icon>
-    </v-btn>
-    <v-btn v-else-if="customizer.viewMode === 'bot'"
-      style="margin-left: 22px;"
+    <v-btn v-if="customizer.viewMode === 'bot'"
+      style="margin-left: 16px;"
       class="hidden-md-and-down" icon rounded="sm" variant="flat"
       @click.stop="customizer.SET_MINI_SIDEBAR(!customizer.mini_sidebar)">
       <v-icon>mdi-menu</v-icon>
     </v-btn>
     <!-- 移动端 menu 按钮 - 仅在 bot 模式下显示 -->
-    <v-btn v-if="customizer.viewMode === 'bot' && useCustomizerStore().uiTheme === 'PurpleTheme'" class="hidden-lg-and-up ms-3"
-      icon rounded="sm" variant="flat" @click.stop="customizer.SET_SIDEBAR_DRAWER">
-      <v-icon>mdi-menu</v-icon>
-    </v-btn>
-    <v-btn v-else-if="customizer.viewMode === 'bot'" class="hidden-lg-and-up ms-3" icon rounded="sm" variant="flat"
+    <v-btn v-if="customizer.viewMode === 'bot'" class="hidden-lg-and-up ms-3" icon rounded="sm" variant="flat"
       @click.stop="customizer.SET_SIDEBAR_DRAWER">
       <v-icon>mdi-menu</v-icon>
     </v-btn>
@@ -572,21 +563,51 @@ onMounted(async () => {
         <v-divider class="my-1" />
       </template>
 
-      <!-- 语言切换 -->
-      <v-list-item
-        v-for="lang in languages"
-        :key="lang.code"
-        :value="lang.code"
-        @click="changeLanguage(lang.code)"
-        :class="{ 'styled-menu-item-active': currentLocale === lang.code }"
-        class="styled-menu-item"
-        rounded="md"
+      <!-- 语言切换分组 -->
+      <v-menu
+        :open-on-hover="!$vuetify.display.xs"
+        :open-on-click="$vuetify.display.xs"
+        :open-delay="!$vuetify.display.xs ? 60 : 0"
+        :close-delay="!$vuetify.display.xs ? 120 : 0"
+        :location="$vuetify.display.xs ? 'bottom' : 'start center'"
+        offset="8"
       >
-        <template v-slot:prepend>
-          <span class="language-flag">{{ lang.flag }}</span>
+        <template v-slot:activator="{ props: languageMenuProps }">
+          <v-list-item
+            v-bind="languageMenuProps"
+            class="styled-menu-item language-group-trigger"
+            rounded="md"
+          >
+            <template v-slot:prepend>
+              <v-icon>mdi-translate</v-icon>
+            </template>
+            <v-list-item-title>{{ t('core.common.language') }}</v-list-item-title>
+            <template v-slot:append>
+              <span class="language-group-current">{{ currentLanguage?.flag }}</span>
+              <v-icon size="18" class="language-group-arrow">mdi-chevron-right</v-icon>
+            </template>
+          </v-list-item>
         </template>
-        <v-list-item-title>{{ lang.name }}</v-list-item-title>
-      </v-list-item>
+
+        <v-card class="styled-menu-card" style="min-width: 180px;" elevation="8" rounded="lg">
+          <v-list density="compact" class="styled-menu-list pa-1">
+            <v-list-item
+              v-for="lang in languages"
+              :key="lang.code"
+              :value="lang.code"
+              @click="changeLanguage(lang.code)"
+              :class="{ 'styled-menu-item-active': currentLocale === lang.code }"
+              class="styled-menu-item"
+              rounded="md"
+            >
+              <template v-slot:prepend>
+                <span class="language-flag">{{ lang.flag }}</span>
+              </template>
+              <v-list-item-title>{{ lang.name }}</v-list-item-title>
+            </v-list-item>
+          </v-list>
+        </v-card>
+      </v-menu>
 
       <!-- 主题切换 -->
       <v-list-item
@@ -978,6 +999,25 @@ onMounted(async () => {
   margin-right: 8px;
 }
 
+.language-group-trigger :deep(.v-list-item__append) {
+  display: flex;
+  align-items: center;
+  gap: 6px;
+}
+
+.language-group-current {
+  font-size: 16px;
+  line-height: 1;
+}
+
+.language-group-arrow {
+  opacity: 0.7;
+}
+
+.language-submenu-card {
+  min-width: 180px;
+}
+
 .mobile-mode-toggle-wrapper {
   display: flex;
   justify-content: center;

dashboard/src/layouts/full/vertical-sidebar/VerticalSidebar.vue

@@ -288,7 +288,7 @@ function openChangelogDialog() {
     :rail="customizer.mini_sidebar"
   >
     <div class="sidebar-container">
-      <v-list class="pa-4 listitem flex-grow-1" v-model:opened="openedItems" :open-strategy="'multiple'">
+      <v-list :class="['pa-4', 'listitem', 'flex-grow-1', { 'hidden-scrollbar': customizer.mini_sidebar }]" v-model:opened="openedItems" :open-strategy="'multiple'">
         <template v-for="(item, i) in sidebarMenu" :key="item.title || item.to || `sidebar-item-${i}`">
           <NavItem :item="item" class="leftPadding" />
         </template>

dashboard/src/main.ts

@@ -11,19 +11,21 @@ import VueApexCharts from 'vue3-apexcharts';
 import print from 'vue3-print-nb';
 import { loader } from '@guolao/vue-monaco-editor'
 import axios from 'axios';
+import { waitForRouterReadyInBackground } from './utils/routerReadiness.mjs';
 
 // 初始化新的i18n系统，等待完成后再挂载应用
-setupI18n().then(() => {
+setupI18n().then(async () => {
   console.log('🌍 新i18n系统初始化完成');
   
   const app = createApp(App);
-  app.use(router);
   const pinia = createPinia();
   app.use(pinia);
+  app.use(router);
   app.use(print);
   app.use(VueApexCharts);
   app.use(vuetify);
   app.use(confirmPlugin);
+  await router.isReady();
   app.mount('#app');
   
   // 挂载后同步 Vuetify 主题
@@ -49,14 +51,15 @@ setupI18n().then(() => {
   
   // 即使i18n初始化失败，也要挂载应用（使用回退机制）
   const app = createApp(App);
-  app.use(router);
   const pinia = createPinia();
   app.use(pinia);
+  app.use(router);
   app.use(print);
   app.use(VueApexCharts);
   app.use(vuetify);
   app.use(confirmPlugin);
   app.mount('#app');
+  waitForRouterReadyInBackground(router);
   
   // 挂载后同步 Vuetify 主题
   import('./stores/customizer').then(({ useCustomizerStore }) => {
@@ -95,14 +98,28 @@ axios.interceptors.request.use((config) => {
 // Some parts of the UI use fetch directly; without this, those requests will 401.
 const _origFetch = window.fetch.bind(window);
 window.fetch = (input: RequestInfo | URL, init?: RequestInit) => {
+  const requestUrl = (() => {
+    if (typeof input === 'string') return input;
+    if (input instanceof URL) return input.toString();
+    return input.url;
+  })();
+
+  let shouldAttachAuth = false;
+  try {
+    const resolvedUrl = new URL(requestUrl, window.location.origin);
+    shouldAttachAuth = resolvedUrl.origin === window.location.origin;
+  } catch (_) {
+    shouldAttachAuth = requestUrl.startsWith('/');
+  }
+
   const token = localStorage.getItem('token');
-  if (!token) return _origFetch(input, init);
+  const locale = localStorage.getItem('astrbot-locale');
+  if (!token && !locale) return _origFetch(input, init);
 
   const headers = new Headers(init?.headers || (typeof input !== 'string' && 'headers' in input ? (input as Request).headers : undefined));
-  if (!headers.has('Authorization')) {
+  if (shouldAttachAuth && token && !headers.has('Authorization')) {
     headers.set('Authorization', `Bearer ${token}`);
   }
-  const locale = localStorage.getItem('astrbot-locale');
   if (locale && !headers.has('Accept-Language')) {
     headers.set('Accept-Language', locale);
   }

dashboard/src/router/MainRoutes.ts

@@ -1,3 +1,5 @@
+import { EXTENSION_ROUTE_NAME } from './routeConstants.mjs';
+
 const MainRoutes = {
   path: '/main',
   meta: {
@@ -17,7 +19,7 @@ const MainRoutes = {
       component: () => import('@/views/WelcomePage.vue')
     },
     {
-      name: 'Extensions',
+      name: EXTENSION_ROUTE_NAME,
       path: '/extension',
       component: () => import('@/views/ExtensionPage.vue')
     },

dashboard/src/router/routeConstants.mjs

@@ -0,0 +1 @@
+export const EXTENSION_ROUTE_NAME = 'Extensions';

dashboard/src/scss/components/_VScrollbar.scss

@@ -1,4 +1,13 @@
-/* 自定义滚动条样式 - 紫色主题 */
+/* 自定义滚动条样式 - 跟随主题 */
+
+:root {
+  --astrbot-scrollbar-track: rgba(var(--v-theme-primary), 0.08);
+  --astrbot-scrollbar-thumb: rgba(var(--v-theme-primary), 0.72);
+  --astrbot-scrollbar-thumb-hover: rgba(var(--v-theme-primary), 0.84);
+  --astrbot-scrollbar-thumb-active: rgba(var(--v-theme-primary), 0.94);
+  --astrbot-scrollbar-thumb-border: rgba(var(--v-theme-surface), 0.5);
+  --astrbot-scrollbar-thumb-shadow: rgba(var(--v-theme-primary), 0.32);
+}
 
 /* 全局滚动条样式 */
 ::-webkit-scrollbar {
@@ -7,52 +16,31 @@
 }
 
 ::-webkit-scrollbar-track {
-  background: rgba(0, 0, 0, 0.05);
+  background: var(--astrbot-scrollbar-track);
   border-radius: 5px;
 }
 
 ::-webkit-scrollbar-thumb {
-  background: rgba(160, 60, 254, 0.75);
+  background: var(--astrbot-scrollbar-thumb);
   border-radius: 5px;
   transition: all 0.3s ease;
-  border: 1px solid rgba(255, 255, 255, 0.2);
+  border: 1px solid var(--astrbot-scrollbar-thumb-border);
 }
 
 ::-webkit-scrollbar-thumb:hover {
-  background: rgba(147, 51, 234, 0.85);
+  background: var(--astrbot-scrollbar-thumb-hover);
   transform: scale(1.05);
-  box-shadow: 0 2px 8px rgba(147, 51, 234, 0.3);
+  box-shadow: 0 2px 8px var(--astrbot-scrollbar-thumb-shadow);
 }
 
 ::-webkit-scrollbar-thumb:active {
-  background: rgba(147, 51, 234, 0.95);
+  background: var(--astrbot-scrollbar-thumb-active);
 }
 
 ::-webkit-scrollbar-corner {
   background: transparent;
 }
 
-/* 深色主题滚动条样式 */
-.v-theme--PurpleThemeDark {
-  ::-webkit-scrollbar-track {
-    background: rgba(255, 255, 255, 0.05);
-  }
-
-  ::-webkit-scrollbar-thumb {
-    background: rgba(192, 132, 252, 0.75);
-    border: 1px solid rgba(0, 0, 0, 0.2);
-  }
-
-  ::-webkit-scrollbar-thumb:hover {
-    background: rgba(192, 132, 252, 0.85);
-    box-shadow: 0 2px 8px rgba(192, 132, 252, 0.4);
-  }
-
-  ::-webkit-scrollbar-thumb:active {
-    background: rgba(192, 132, 252, 0.95);
-  }
-}
-
 /* 细滚动条变体 */
 .thin-scrollbar {
   ::-webkit-scrollbar {
@@ -61,17 +49,11 @@
   }
 
   ::-webkit-scrollbar-thumb {
-    background: rgba(147, 51, 234, 0.75);
+    background: var(--astrbot-scrollbar-thumb);
     border: none;
   }
 }
 
-.v-theme--PurpleThemeDark .thin-scrollbar {
-  ::-webkit-scrollbar-thumb {
-    background: rgba(192, 132, 252, 0.75);
-  }
-}
-
 /* 聊天区域滚动条 */
 .chat-scrollbar {
   ::-webkit-scrollbar {
@@ -79,33 +61,18 @@
   }
 
   ::-webkit-scrollbar-track {
-    background: rgba(147, 51, 234, 0.08);
+    background: var(--astrbot-scrollbar-track);
     border-radius: 4px;
   }
 
   ::-webkit-scrollbar-thumb {
-    background: rgba(147, 51, 234, 0.75);
+    background: var(--astrbot-scrollbar-thumb);
     border-radius: 4px;
-    border: 1px solid rgba(255, 255, 255, 0.1);
+    border: 1px solid var(--astrbot-scrollbar-thumb-border);
   }
 
   ::-webkit-scrollbar-thumb:hover {
-    background: rgba(147, 51, 234, 0.85);
-  }
-}
-
-.v-theme--PurpleThemeDark .chat-scrollbar {
-  ::-webkit-scrollbar-track {
-    background: rgba(192, 132, 252, 0.08);
-  }
-
-  ::-webkit-scrollbar-thumb {
-    background: rgba(192, 132, 252, 0.75);
-    border: 1px solid rgba(0, 0, 0, 0.1);
-  }
-
-  ::-webkit-scrollbar-thumb:hover {
-    background: rgba(192, 132, 252, 0.85);
+    background: var(--astrbot-scrollbar-thumb-hover);
   }
 }
 
@@ -123,11 +90,7 @@
 /* Firefox 兼容性 */
 * {
   scrollbar-width: thin;
-  scrollbar-color: rgba(147, 51, 234, 0.75) rgba(0, 0, 0, 0.05);
-}
-
-.v-theme--PurpleThemeDark * {
-  scrollbar-color: rgba(192, 132, 252, 0.75) rgba(255, 255, 255, 0.05);
+  scrollbar-color: var(--astrbot-scrollbar-thumb) var(--astrbot-scrollbar-track);
 }
 
 /* 平滑滚动 */

dashboard/src/scss/layout/_sidebar.scss

@@ -28,27 +28,27 @@
     .v-list-group__items .v-list-item,
     .v-list-item {
       &:hover {
-        color: #b794f6 !important;
+        color: rgb(var(--v-theme-primary)) !important;
         
         .v-list-item-title {
-          color: #b794f6 !important;
+          color: rgb(var(--v-theme-primary)) !important;
         }
         
         .v-icon {
-          color: #b794f6 !important;
+          color: rgb(var(--v-theme-primary)) !important;
         }
       }
       
       // 选中状态的样式
       &.v-list-item--active {
-        color: #b794f6 !important;
+        color: rgb(var(--v-theme-primary)) !important;
         
         .v-list-item-title {
-          color: #b794f6 !important;
+          color: rgb(var(--v-theme-primary)) !important;
         }
         
         .v-icon {
-          color: #b794f6 !important;
+          color: rgb(var(--v-theme-primary)) !important;
         }
       }
     }
@@ -56,9 +56,6 @@
   .v-list-item--density-default.v-list-item--one-line {
     min-height: 40px;
   }
-  .leftPadding {
-    margin-left: 4px;
-  }
 }
 .v-navigation-drawer--rail {
   .scrollnavbar .v-list .v-list-group__items,

dashboard/src/theme/DarkTheme.ts

@@ -4,26 +4,26 @@ const PurpleThemeDark: ThemeTypes = {
   name: 'PurpleThemeDark',
   dark: true,
   variables: {
-    'border-color': '#1677ff',
+    'border-color': '#3c96ca',
     'carousel-control-size': 10
   },
   colors: {
-    primary: '#1677ff',
-    secondary: '#722ed1',
+    primary: '#3c96ca',
+    secondary: '#4ea4d8',
     info: '#03c9d7',
     success: '#52c41a',
     accent: '#FFAB91',
     warning: '#faad14',
     error: '#ff4d4f',
-    lightprimary: '#eef2f6',
-    lightsecondary: '#ede7f6',
+    lightprimary: '#e8f3fa',
+    lightsecondary: '#e8f3fa',
     lightsuccess: '#b9f6ca',
     lighterror: '#f9d8d8',
     lightwarning: '#fff8e1',
     primaryText: '#ffffff',
     secondaryText: '#ffffffcc',
-    darkprimary: '#1565c0',
-    darksecondary: '#4527a0',
+    darkprimary: '#2f86bd',
+    darksecondary: '#2f86bd',
     borderLight: '#d0d0d0',
     border: '#333333ee',
     inputBorder: '#787878',
@@ -34,8 +34,8 @@ const PurpleThemeDark: ThemeTypes = {
     twitter: '#1da1f2',
     linkedin: '#0e76a8',
     gray100: '#cccccccc',
-    primary200: '#90caf9',
-    secondary200: '#b39ddb',
+    primary200: '#84c9ea',
+    secondary200: '#8cc4e1',
     background: '#1d1d1d',
     overlay: '#111111aa',
     codeBg: '#282833',

dashboard/src/theme/LightTheme.ts

@@ -9,21 +9,21 @@ const PurpleTheme: ThemeTypes = {
   },
   colors: {
     primary: '#3c96ca',
-    secondary: '#2288b7',
+    secondary: '#2f86bd',
     info: '#03c9d7',
     success: '#00c853',
     accent: '#FFAB91',
     warning: '#ffc107',
     error: '#f44336',
     lightprimary: '#eef2f6',
-    lightsecondary: '#ede7f6',
+    lightsecondary: '#e8f3fa',
     lightsuccess: '#b9f6ca',
     lighterror: '#f9d8d8',
     lightwarning: '#fff8e1',
     primaryText: '#1b1c1d',
     secondaryText: '#000000aa',
     darkprimary: '#1565c0',
-    darksecondary: '#4527a0',
+    darksecondary: '#236b99',
     borderLight: '#d0d0d0',
     border: '#d0d0d0',
     inputBorder: '#787878',
@@ -35,7 +35,7 @@ const PurpleTheme: ThemeTypes = {
     linkedin: '#0e76a8',
     gray100: '#fafafacc',
     primary200: '#90caf9',
-    secondary200: '#b39ddb',
+    secondary200: '#8cc4e1',
     background: '#ffffff',
     overlay: '#ffffffaa',
     codeBg: '#ececec',

dashboard/src/utils/hashRouteTabs.mjs

@@ -0,0 +1,46 @@
+import { EXTENSION_ROUTE_NAME } from '../router/routeConstants.mjs';
+
+export function getValidHashTab(routeHash, validTabs) {
+  const hash = String(routeHash || '');
+  const tab = hash.includes('#') ? hash.slice(hash.lastIndexOf('#') + 1) : hash;
+  return validTabs.includes(tab) ? tab : null;
+}
+
+export function createTabRouteLocation(route, tab, fallbackRouteName = EXTENSION_ROUTE_NAME) {
+  const query = route?.query ? { ...route.query } : {};
+  const params = route?.params ? { ...route.params } : undefined;
+
+  if (route?.name) {
+    return {
+      name: route.name,
+      ...(params ? { params } : {}),
+      query,
+      hash: `#${tab}`,
+    };
+  }
+
+  if (route?.path) {
+    return {
+      path: route.path,
+      query,
+      hash: `#${tab}`,
+    };
+  }
+
+  return {
+    name: fallbackRouteName,
+    ...(params ? { params } : {}),
+    query,
+    hash: `#${tab}`,
+  };
+}
+
+export async function replaceTabRoute(router, route, tab, logger = console) {
+  try {
+    await router.replace(createTabRouteLocation(route, tab));
+    return true;
+  } catch (error) {
+    logger.warn?.('Failed to update extension tab route:', error);
+    return false;
+  }
+}

dashboard/src/utils/providerUtils.js

@@ -9,33 +9,33 @@
  */
 export function getProviderIcon(type) {
   const icons = {
-    'openai': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openai.svg',
-    'azure': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/azure.svg',
-    'xai': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/xai.svg',
-    'anthropic': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/anthropic.svg',
-    'ollama': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/ollama.svg',
-    'google': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/gemini-color.svg',
-    'deepseek': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/deepseek.svg',
-    'modelscope': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/modelscope.svg',
-    'zhipu': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/zhipu.svg',
-    'nvidia': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/nvidia-color.svg',
-    'siliconflow': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/siliconcloud.svg',
-    'moonshot': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/kimi.svg',
-    'ppio': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/ppio.svg',
-    'dify': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/dify-color.svg',
-    "coze": "https://registry.npmmirror.com/@lobehub/icons-static-svg/1.66.0/files/icons/coze.svg",
-    'dashscope': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/alibabacloud-color.svg',
+    'openai': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/openai.svg',
+    'azure': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/azure.svg',
+    'xai': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/xai.svg',
+    'anthropic': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/anthropic.svg',
+    'ollama': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/ollama.svg',
+    'google': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/gemini-color.svg',
+    'deepseek': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/deepseek.svg',
+    'modelscope': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/modelscope.svg',
+    'zhipu': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/zhipu.svg',
+    'nvidia': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/nvidia-color.svg',
+    'siliconflow': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/siliconcloud.svg',
+    'moonshot': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/kimi.svg',
+    'ppio': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/ppio.svg',
+    'dify': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/dify-color.svg',
+    "coze": "https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.66.0/icons/coze.svg",
+    'dashscope': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/alibabacloud-color.svg',
     'deerflow': 'https://cdn.jsdelivr.net/gh/bytedance/deer-flow@main/frontend/public/images/deer.svg',
-    'fastgpt': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/fastgpt-color.svg',
-    'lm_studio': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/lmstudio.svg',
-    'fishaudio': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/fishaudio.svg',
-    'minimax': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/minimax.svg',
-    '302ai': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/1.53.0/files/icons/ai302-color.svg',
-    'microsoft': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/microsoft.svg',
-    'vllm': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/vllm.svg',
-    'groq': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/groq.svg',
-    'aihubmix': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/aihubmix-color.svg',
-    'openrouter': 'https://registry.npmmirror.com/@lobehub/icons-static-svg/latest/files/icons/openrouter.svg',
+    'fastgpt': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/fastgpt-color.svg',
+    'lm_studio': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/lmstudio.svg',
+    'fishaudio': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/fishaudio.svg',
+    'minimax': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/minimax.svg',
+    '302ai': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@1.53.0/icons/ai302-color.svg',
+    'microsoft': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/microsoft.svg',
+    'vllm': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/vllm.svg',
+    'groq': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/groq.svg',
+    'aihubmix': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/aihubmix-color.svg',
+    'openrouter': 'https://cdn.jsdelivr.net/npm/@lobehub/icons-static-svg@latest/icons/openrouter.svg',
     "tokenpony": "https://tokenpony.cn/tokenpony-web/logo.png",
     "compshare": "https://compshare.cn/favicon.ico"
   };

dashboard/src/utils/routerReadiness.mjs

@@ -0,0 +1,5 @@
+export function waitForRouterReadyInBackground(router, logger = console) {
+  router.isReady().catch((error) => {
+    logger.warn?.('Router did not become ready after fallback mount:', error);
+  });
+}

dashboard/src/views/ProviderPage.vue

@@ -602,12 +602,15 @@ async function testSingleProvider(provider) {
       return
     }
 
+    const startTime = performance.now()
     const res = await axios.get(`/api/config/provider/check_one?id=${provider.id}`)
     if (res.data && res.data.status === 'ok') {
       const index = providerStatuses.value.findIndex(s => s.id === provider.id)
       if (index !== -1) {
         providerStatuses.value.splice(index, 1, res.data.data)
       }
+      const latency = Math.max(0, Math.round(performance.now() - startTime))
+      showMessage(tm('models.testSuccessWithLatency', { id: provider.id, latency }))
     } else {
       throw new Error(res.data?.message || `Failed to check status for ${provider.id}`)
     }

dashboard/src/views/authentication/auth/LoginPage.vue

@@ -45,9 +45,9 @@ onMounted(() => {
           <div class="d-flex align-center gap-1">
             <LanguageSwitcher />
             <v-divider vertical class="mx-1"
-              style="height: 24px !important; opacity: 0.9 !important; align-self: center !important; border-color: rgba(180, 148, 246, 0.8) !important;"></v-divider>
+              style="height: 24px !important; opacity: 0.9 !important; align-self: center !important; border-color: rgba(var(--v-theme-primary), 0.45) !important;"></v-divider>
             <v-btn @click="toggleTheme" class="theme-toggle-btn" icon variant="text" size="small">
-              <v-icon size="18" :color="useCustomizerStore().uiTheme === 'PurpleTheme' ? '#5e35b1' : '#d7c5fa'">
+              <v-icon size="18" :color="'rgb(var(--v-theme-primary))'">
                 mdi-white-balance-sunny
               </v-icon>
               <v-tooltip activator="parent" location="top">

dashboard/src/views/extension/useExtensionPage.js

@@ -10,6 +10,10 @@ import {
   toInitials,
   toPinyinText,
 } from "@/utils/pluginSearch";
+import {
+  getValidHashTab,
+  replaceTabRoute,
+} from "@/utils/hashRouteTabs.mjs";
 import { ref, computed, onMounted, onUnmounted, reactive, watch } from "vue";
 import { useRoute, useRouter } from "vue-router";
 import { useDisplay } from "vuetify";
@@ -103,16 +107,11 @@ export const useExtensionPage = () => {
   const activeTab = ref("installed");
   const validTabs = ["installed", "market", "mcp", "skills", "components"];
   const isValidTab = (tab) => validTabs.includes(tab);
-  const getLocationHash = () =>
-    typeof window !== "undefined" ? window.location.hash : "";
-  const extractTabFromHash = (hash) => {
-    const lastHashIndex = (hash || "").lastIndexOf("#");
-    if (lastHashIndex === -1) return "";
-    return hash.slice(lastHashIndex + 1);
-  };
+  const getLocationHash = () => route.hash || "";
+  const extractTabFromHash = (hash) => getValidHashTab(hash, validTabs);
   const syncTabFromHash = (hash) => {
     const tab = extractTabFromHash(hash);
-    if (isValidTab(tab)) {
+    if (tab) {
       activeTab.value = tab;
       return true;
     }
@@ -1436,9 +1435,7 @@ export const useExtensionPage = () => {
   // 生命周期
   onMounted(async () => {
     if (!syncTabFromHash(getLocationHash())) {
-      if (typeof window !== "undefined") {
-        window.location.hash = `#${activeTab.value}`;
-      }
+      await replaceTabRoute(router, route, activeTab.value);
     }
     await getExtensions();
   
@@ -1446,17 +1443,9 @@ export const useExtensionPage = () => {
     loadCustomSources();
   
     // 检查是否有 open_config 参数
-    let urlParams;
-    if (window.location.hash) {
-      // For hash mode (#/path?param=value)
-      const hashQuery = window.location.hash.split("?")[1] || "";
-      urlParams = new URLSearchParams(hashQuery);
-    } else {
-      // For history mode (/path?param=value)
-      urlParams = new URLSearchParams(window.location.search);
-    }
-    console.log("URL Parameters:", urlParams.toString());
-    const plugin_name = urlParams.get("open_config");
+    const plugin_name = Array.isArray(route.query.open_config)
+      ? route.query.open_config[0]
+      : route.query.open_config;
     if (plugin_name) {
       console.log(`Opening config for plugin: ${plugin_name}`);
       openExtensionConfig(plugin_name);
@@ -1528,10 +1517,10 @@ export const useExtensionPage = () => {
   );
   
   watch(
-    () => route.fullPath,
-    () => {
-      const tab = extractTabFromHash(getLocationHash());
-      if (isValidTab(tab) && tab !== activeTab.value) {
+    () => route.hash,
+    (newHash) => {
+      const tab = extractTabFromHash(newHash);
+      if (tab && tab !== activeTab.value) {
         activeTab.value = tab;
       }
     },
@@ -1539,15 +1528,8 @@ export const useExtensionPage = () => {
   
   watch(activeTab, (newTab) => {
     if (!isValidTab(newTab)) return;
-    const currentTab = extractTabFromHash(getLocationHash());
-    if (currentTab === newTab) return;
-    const hash = getLocationHash();
-    const lastHashIndex = hash.lastIndexOf("#");
-    const nextHash =
-      lastHashIndex > 0 ? `${hash.slice(0, lastHashIndex)}#${newTab}` : `#${newTab}`;
-    if (typeof window !== "undefined") {
-      window.location.hash = nextHash;
-    }
+    if (route.hash === `#${newTab}`) return;
+    void replaceTabRoute(router, route, newTab);
   });
 
   return {

dashboard/tests/hashRouteTabs.test.mjs

@@ -0,0 +1,123 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+
+import * as hashRouteTabs from '../src/utils/hashRouteTabs.mjs';
+import { EXTENSION_ROUTE_NAME } from '../src/router/routeConstants.mjs';
+
+const { createTabRouteLocation, getValidHashTab } = hashRouteTabs;
+
+test('getValidHashTab returns the tab name for a valid route hash', () => {
+  const validTabs = ['installed', 'market', 'mcp'];
+
+  assert.equal(getValidHashTab('#market', validTabs), 'market');
+});
+
+test('getValidHashTab rejects empty and unknown hashes', () => {
+  const validTabs = ['installed', 'market', 'mcp'];
+
+  assert.equal(getValidHashTab('', validTabs), null);
+  assert.equal(getValidHashTab('#unknown', validTabs), null);
+});
+
+test('getValidHashTab uses the last hash segment when multiple hashes are present', () => {
+  const validTabs = ['installed', 'market', 'mcp'];
+
+  assert.equal(getValidHashTab('#/extension#foo#installed', validTabs), 'installed');
+});
+
+test('createTabRouteLocation preserves the current path and query', () => {
+  const query = { open_config: 'sample-plugin', page: '2' };
+  const location = createTabRouteLocation(
+    {
+      path: '/extension',
+      query,
+    },
+    'market',
+  );
+
+  assert.deepEqual(location, {
+    path: '/extension',
+    query: { open_config: 'sample-plugin', page: '2' },
+    hash: '#market',
+  });
+  assert.notEqual(location.query, query);
+});
+
+test('createTabRouteLocation falls back to the extension route name', () => {
+  const location = createTabRouteLocation(undefined, 'installed');
+
+  assert.deepEqual(location, {
+    name: EXTENSION_ROUTE_NAME,
+    query: {},
+    hash: '#installed',
+  });
+});
+
+test('createTabRouteLocation prefers route name and preserves params', () => {
+  const params = { pluginId: 'demo-plugin' };
+  const location = createTabRouteLocation(
+    {
+      name: 'ExtensionDetails',
+      path: '/extension/demo-plugin',
+      params,
+      query: { tab: 'details' },
+    },
+    'market',
+  );
+
+  assert.deepEqual(location, {
+    name: 'ExtensionDetails',
+    params: { pluginId: 'demo-plugin' },
+    query: { tab: 'details' },
+    hash: '#market',
+  });
+  assert.notEqual(location.params, params);
+});
+
+test('createTabRouteLocation omits params for path-based routes', () => {
+  const params = { pluginId: 'demo-plugin' };
+  const location = createTabRouteLocation(
+    {
+      path: '/extension/demo-plugin',
+      params,
+    },
+    'installed',
+  );
+
+  assert.deepEqual(location, {
+    path: '/extension/demo-plugin',
+    query: {},
+    hash: '#installed',
+  });
+  assert.equal(location.params, undefined);
+});
+
+test('replaceTabRoute catches rejected router updates', async () => {
+  assert.equal(typeof hashRouteTabs.replaceTabRoute, 'function');
+
+  const error = new Error('blocked');
+  let logged;
+  const router = {
+    replace: async () => {
+      throw error;
+    },
+  };
+  const logger = {
+    warn: (message, cause) => {
+      logged = { message, cause };
+    },
+  };
+
+  const result = await hashRouteTabs.replaceTabRoute(
+    router,
+    { name: EXTENSION_ROUTE_NAME, query: { page: '1' } },
+    'installed',
+    logger,
+  );
+
+  assert.equal(result, false);
+  assert.deepEqual(logged, {
+    message: 'Failed to update extension tab route:',
+    cause: error,
+  });
+});

dashboard/tests/routerReadiness.test.mjs

@@ -0,0 +1,29 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+
+test('waitForRouterReadyInBackground returns immediately and logs failures', async () => {
+  const module = await import('../src/utils/routerReadiness.mjs').catch(() => null);
+
+  assert.ok(module?.waitForRouterReadyInBackground);
+
+  const error = new Error('router blocked');
+  let warned;
+  const readyPromise = Promise.reject(error);
+  const logger = {
+    warn: (message, cause) => {
+      warned = { message, cause };
+    },
+  };
+
+  const result = module.waitForRouterReadyInBackground(
+    { isReady: () => readyPromise },
+    logger,
+  );
+
+  assert.equal(result, undefined);
+  await Promise.resolve();
+  assert.deepEqual(warned, {
+    message: 'Router did not become ready after fallback mount:',
+    cause: error,
+  });
+});

docs/en/community.md

@@ -6,7 +6,7 @@ This documentation may not cover all features comprehensively. If you have any q
 
 ### Discord
 
-<https://discord.gg/PxgzhmxJ>
+<https://discord.gg/hAVk6tgV36>
 
 ### GitHub
 

docs/en/dev/openapi.md

@@ -29,6 +29,7 @@ X-API-Key: abk_xxx
 ## Common Endpoints
 
 - `POST /api/v1/chat`: send chat message (SSE stream, server generates UUID when `session_id` is omitted)
+- `GET /api/v1/live/ws`: Live API WebSocket (API Key auth, requires `username` query parameter, optional `ct=live|chat`)
 - `GET /api/v1/chat/sessions`: list sessions for a specific `username` with pagination
 - `GET /api/v1/configs`: list available config files
 - `POST /api/v1/file`: upload attachment
@@ -49,3 +50,7 @@ curl -N 'http://localhost:6185/api/v1/chat' \
 Use the interactive docs:
 
 - https://docs.astrbot.app/scalar.html
+
+For the full Live API wire protocol, see:
+
+- `docs/live-api/README.md`

docs/live-api/README.md

@@ -0,0 +1,434 @@
+# AstrBot Live API Protocol
+
+This document describes the current WebSocket protocol for AstrBot Live API.
+
+## Endpoint
+
+- Legacy JWT endpoint: `/api/live_chat/ws`
+- Legacy unified JWT endpoint: `/api/unified_chat/ws`
+- Open API endpoint: `/api/v1/live/ws`
+
+## Authentication
+
+### Legacy dashboard endpoints
+
+Pass a dashboard JWT in the `token` query parameter.
+
+Example:
+
+```text
+ws://localhost:6185/api/live_chat/ws?token=<dashboard_jwt>
+```
+
+### Open API endpoint
+
+Use an API key and provide `username` in the query string.
+
+Examples:
+
+```text
+ws://localhost:6185/api/v1/live/ws?api_key=<api_key>&username=alice
+ws://localhost:6185/api/v1/live/ws?api_key=<api_key>&username=alice&ct=chat
+```
+
+`ct` values:
+
+- `live`: voice conversation mode
+- `chat`: unified chat mode over the same WebSocket transport
+
+The Open API endpoint reuses the `chat` API key scope.
+
+## Transport
+
+- Protocol: WebSocket
+- Payload format: UTF-8 JSON text frames
+- Audio upload format in `live` mode:
+  - client sends raw PCM frames encoded as Base64
+  - sample rate: `16000`
+  - channels: `1`
+  - sample width: `16-bit`
+
+## Top-Level Envelope
+
+### Client to server
+
+```json
+{
+  "t": "message_type",
+  "...": "message specific fields"
+}
+```
+
+When using the unified socket, the client can also include:
+
+```json
+{
+  "ct": "live|chat",
+  "t": "message_type"
+}
+```
+
+### Server to client
+
+Legacy `live` mode uses:
+
+```json
+{
+  "t": "message_type",
+  "data": {}
+}
+```
+
+Unified `chat` mode uses:
+
+```json
+{
+  "ct": "chat",
+  "type": "message_type",
+  "data": {}
+}
+```
+
+Some forwarded `chat` frames may also contain `t`, `streaming`, `chain_type`, `message_id`, or `session_id`.
+
+## Live Mode
+
+### Client messages
+
+#### `start_speaking`
+
+Start a voice capture segment.
+
+```json
+{
+  "t": "start_speaking",
+  "stamp": "seg_001"
+}
+```
+
+#### `speaking_part`
+
+Send one audio frame.
+
+```json
+{
+  "t": "speaking_part",
+  "data": "<base64_pcm_bytes>"
+}
+```
+
+#### `end_speaking`
+
+Finish the current voice capture segment.
+
+```json
+{
+  "t": "end_speaking",
+  "stamp": "seg_001"
+}
+```
+
+#### `text_input`
+
+Send a plain text input directly while using `ct=live`. The server will still route through Live mode with TTS and interrupt handling.
+
+```json
+{
+  "t": "text_input",
+  "text": "Hello, what is the weather today?"
+}
+```
+
+#### `interrupt`
+
+Interrupt the current model or TTS response.
+
+```json
+{
+  "t": "interrupt"
+}
+```
+
+### Server messages
+
+#### `metrics`
+
+Performance and provider metadata.
+
+Example:
+
+```json
+{
+  "t": "metrics",
+  "data": {
+    "wav_assemble_time": 0.12,
+    "stt": "whisper_api",
+    "llm_ttft": 0.84,
+    "tts_total_time": 1.72
+  }
+}
+```
+
+#### `user_msg`
+
+STT result from the uploaded audio.
+
+```json
+{
+  "t": "user_msg",
+  "data": {
+    "text": "Hello there",
+    "ts": 1710000000000
+  }
+}
+```
+
+#### `bot_delta_chunk`
+
+Raw model text delta. This is the token or chunk level stream and is not sentence segmented.
+
+```json
+{
+  "t": "bot_delta_chunk",
+  "data": {
+    "text": "Hel"
+  }
+}
+```
+
+Notes:
+
+- This event is generated directly from the model streaming path.
+- It is independent from TTS chunking.
+- Consumers should append `data.text` to a local buffer.
+
+#### `bot_text_chunk`
+
+Text associated with the current TTS chunk. This is usually sentence or phrase segmented.
+
+```json
+{
+  "t": "bot_text_chunk",
+  "data": {
+    "text": "Hello there."
+  }
+}
+```
+
+Notes:
+
+- This event is aligned to TTS output, not raw token streaming.
+- It may be coarser than `bot_delta_chunk`.
+
+#### `response`
+
+One TTS audio chunk, Base64 encoded.
+
+```json
+{
+  "t": "response",
+  "data": "<base64_audio_bytes>"
+}
+```
+
+#### `bot_msg`
+
+Final bot text when the response completed without audio streaming.
+
+```json
+{
+  "t": "bot_msg",
+  "data": {
+    "text": "Final reply text",
+    "ts": 1710000001234
+  }
+}
+```
+
+#### `stop_play`
+
+Stop client-side audio playback because the response was interrupted.
+
+```json
+{
+  "t": "stop_play"
+}
+```
+
+#### `end`
+
+Marks the end of the current response turn.
+
+```json
+{
+  "t": "end"
+}
+```
+
+#### `error`
+
+Recoverable or terminal processing error.
+
+```json
+{
+  "t": "error",
+  "data": "error message"
+}
+```
+
+## Unified Chat Mode
+
+Set `ct=chat` on the Open API endpoint or include `"ct": "chat"` in each client frame when using `/api/unified_chat/ws`.
+
+### Client messages
+
+#### `bind`
+
+Subscribe to an existing webchat session.
+
+```json
+{
+  "ct": "chat",
+  "t": "bind",
+  "session_id": "session_001"
+}
+```
+
+#### `send`
+
+Send a chat request.
+
+```json
+{
+  "ct": "chat",
+  "t": "send",
+  "username": "alice",
+  "session_id": "session_001",
+  "message_id": "msg_001",
+  "message": [
+    {
+      "type": "plain",
+      "text": "Please summarize this"
+    }
+  ],
+  "selected_provider": "openai_chat_completion",
+  "selected_model": "gpt-4.1-mini",
+  "enable_streaming": true
+}
+```
+
+`message` uses the same message-part schema as `POST /api/v1/chat`.
+
+#### `interrupt`
+
+Interrupt the current chat response.
+
+```json
+{
+  "ct": "chat",
+  "t": "interrupt"
+}
+```
+
+### Server messages
+
+#### `session_bound`
+
+Acknowledges a successful `bind`.
+
+```json
+{
+  "ct": "chat",
+  "type": "session_bound",
+  "session_id": "session_001",
+  "message_id": "ws_sub_xxx"
+}
+```
+
+#### Forwarded streaming events
+
+The server forwards the normal webchat queue payloads. Common examples:
+
+```json
+{
+  "ct": "chat",
+  "type": "plain",
+  "data": "Hello",
+  "streaming": true,
+  "chain_type": null,
+  "message_id": "msg_001"
+}
+```
+
+```json
+{
+  "ct": "chat",
+  "type": "image",
+  "data": "[IMAGE]file.jpg",
+  "streaming": false,
+  "message_id": "msg_001"
+}
+```
+
+```json
+{
+  "ct": "chat",
+  "type": "agent_stats",
+  "data": {
+    "time_to_first_token": 0.8
+  }
+}
+```
+
+```json
+{
+  "ct": "chat",
+  "type": "message_saved",
+  "data": {
+    "id": 123,
+    "created_at": "2026-03-16T10:00:00Z"
+  }
+}
+```
+
+```json
+{
+  "ct": "chat",
+  "type": "end",
+  "data": "",
+  "streaming": false,
+  "message_id": "msg_001"
+}
+```
+
+#### Chat errors
+
+```json
+{
+  "ct": "chat",
+  "t": "error",
+  "code": "INVALID_MESSAGE_FORMAT",
+  "data": "message must be list"
+}
+```
+
+## Recommended Client Strategy
+
+For `live` mode:
+
+1. Append every `bot_delta_chunk.data.text` into a raw transcript buffer.
+2. Use `bot_text_chunk` only when you need text aligned with audio playback.
+3. Decode and play each `response` audio chunk in arrival order.
+4. Reset per-turn buffers after `end`.
+
+For `chat` mode:
+
+1. Treat `plain + streaming=true` as incremental text.
+2. Treat `complete` or `end` as the end of a response turn.
+3. Persist `message_saved` metadata if you need server-side history IDs.
+
+## Compatibility Notes
+
+- `bot_text_chunk` remains sentence or phrase segmented for TTS compatibility.
+- `bot_delta_chunk` is the new delta-level text event for real-time rendering.
+- The legacy JWT endpoints and the new Open API endpoint share the same runtime behavior after authentication.

docs/public/openapi.json

@@ -257,6 +257,56 @@
         }
       }
     },
+    "/api/v1/live/ws": {
+      "get": {
+        "tags": [
+          "Open API"
+        ],
+        "summary": "Live API WebSocket",
+        "description": "WebSocket endpoint for Live API. Authenticate with API Key using query parameter `api_key` or header `Authorization: Bearer <api_key>`, and pass `username` as a query parameter. Use `ct=live` for voice mode or `ct=chat` for unified chat mode. See docs/live-api/README.md for the full frame-level protocol.",
+        "security": [
+          {
+            "ApiKeyHeader": []
+          }
+        ],
+        "parameters": [
+          {
+            "name": "username",
+            "in": "query",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "Target username for the live session."
+          },
+          {
+            "name": "ct",
+            "in": "query",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "live",
+                "chat"
+              ],
+              "default": "live"
+            },
+            "description": "Session mode. `live` for voice conversation, `ct=chat` for the unified chat WebSocket."
+          }
+        ],
+        "responses": {
+          "101": {
+            "description": "WebSocket protocol switch"
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "403": {
+            "$ref": "#/components/responses/Forbidden"
+          }
+        },
+        "x-websocket": true
+      }
+    },
     "/api/v1/im/message": {
       "post": {
         "tags": [

docs/zh/community.md

@@ -21,7 +21,7 @@
 
 ### Discord
 
-https://discord.gg/PxgzhmxJ
+https://discord.gg/hAVk6tgV36
 
 ### Astrbook
 

docs/zh/deploy/astrbot/package.md

@@ -13,5 +13,5 @@
 ```bash
 uv tool install astrbot
 astrbot init # 只需要在第一次部署时执行，后续启动不需要执行
-astrbot
+astrbot run
 ```

docs/zh/deploy/astrbot/rainyun.md

@@ -41,4 +41,4 @@ AstrBot 已经上架至雨云的预装软件列表，支持**一键安装** Astr
 
 ![创建NAT端口映射规则](https://files.astrbot.app/docs/source/images/rainyun/image-2.png)
 
-然后，内网端口填写 `6185`，点击 `创建映射规则`，这样就可以通过 `http://IP:上面设置好的外网端口` 访问 AstrBot 的管理面板了。
+然后，内网端口填写 `6185`，点击 `创建映射规则`，这样就可以通过 `http://IP:上面设置好的外网端口` 访问 AstrBot 的管理面板了。如果无法打开，请点击`备用地址`，通过备用地址访问管理面板。

docs/zh/dev/openapi.md

@@ -46,6 +46,7 @@ X-API-Key: abk_xxx
 调用 AstrBot 内建的 Agent 进行对话交互。支持插件调用、工具调用等能力，与 IM 端对话能力一致。
 
 - `POST /api/v1/chat`：发送对话消息（SSE 流式返回，不传 `session_id` 会自动创建 UUID）
+- `GET /api/v1/live/ws`：Live API WebSocket（API Key 鉴权，查询参数必须包含 `username`，可选 `ct=live|chat`）
 - `GET /api/v1/chat/sessions`：分页获取指定 `username` 的会话
 - `GET /api/v1/configs`：获取可用配置文件列表
 
@@ -148,3 +149,7 @@ curl -N 'http://localhost:6185/api/v1/chat' \
 交互式 API 文档请查看：
 
 - https://docs.astrbot.app/scalar.html
+
+Live API 协议说明请查看：
+
+- `docs/live-api/README.md`

docs/zh/platform/matrix.md

@@ -7,7 +7,7 @@
 
 进入 AstrBot WebUI 的插件市场，搜索 `astrbot_plugin_matrix_adapter`，点击安装。
 
-安装完成后，前往 消息平台 → 新增适配器 → 选择 Matrix（若选项缺失，尝试重启 AstrBot 或检查插件安装状态）。
+安装完成后，前往 机器人（旧版本为 `消息平台`） → 新增适配器 → 选择 Matrix（若选项缺失，尝试重启 AstrBot 或检查插件安装状态）。
 
 在弹出的配置对话框中点击 `启用`。
 

docs/zh/platform/wecom_ai_bot.md

@@ -30,7 +30,7 @@
 
 ## 配置 AstrBot
 
-1. 进入 AstrBot 的管理面板，点击左侧栏 `消息平台`，然后在右侧的界面中，点击 `+ 新增适配器`，选择 `企业微信智能机器人`，进入配置页面。
+1. 进入 AstrBot 的管理面板，点击左侧栏 `机器人`（旧版本为 `消息平台`），然后在右侧的界面中，点击 `+ 新增适配器`，选择 `企业微信智能机器人`，进入配置页面。
 
 ![新增适配器](https://files.astrbot.app/docs/source/images/wecom_ai_bot/image-2.png)
 

docs/zh/what-is-astrbot.md

@@ -23,7 +23,7 @@ AstrBot 是一个开源的一站式 Agentic 个人和群聊助手，可在 QQ、
 
 - 部署 AstrBot：阅读部署指南，快速在本地机器或云服务器上部署 AstrBot。
 - 连接 IM 平台：按照说明将 AstrBot 连接到您喜欢的 IM 平台，如 Discord、Telegram、Slack 等。
-- 配置 AI 模型：AstrBot 支持各种 AI 模型。请参阅 [连接模型服务](/config/providers/start)
+- 配置 AI 模型：AstrBot 支持各种 AI 模型。请参阅 [连接模型服务](/providers/start)
 
 ## 它是如何实现的？
 

openapi.json

@@ -257,6 +257,56 @@
         }
       }
     },
+    "/api/v1/live/ws": {
+      "get": {
+        "tags": [
+          "Open API"
+        ],
+        "summary": "Live API WebSocket",
+        "description": "WebSocket endpoint for Live API. Authenticate with API Key using query parameter `api_key` or header `Authorization: Bearer <api_key>`, and pass `username` as a query parameter. Use `ct=live` for voice mode or `ct=chat` for unified chat mode. See docs/live-api/README.md for the full frame-level protocol.",
+        "security": [
+          {
+            "ApiKeyHeader": []
+          }
+        ],
+        "parameters": [
+          {
+            "name": "username",
+            "in": "query",
+            "required": true,
+            "schema": {
+              "type": "string"
+            },
+            "description": "Target username for the live session."
+          },
+          {
+            "name": "ct",
+            "in": "query",
+            "schema": {
+              "type": "string",
+              "enum": [
+                "live",
+                "chat"
+              ],
+              "default": "live"
+            },
+            "description": "Session mode. `live` for voice conversation, `chat` for the unified chat WebSocket."
+          }
+        ],
+        "responses": {
+          "101": {
+            "description": "WebSocket protocol switch"
+          },
+          "401": {
+            "$ref": "#/components/responses/Unauthorized"
+          },
+          "403": {
+            "$ref": "#/components/responses/Forbidden"
+          }
+        },
+        "x-websocket": true
+      }
+    },
     "/api/v1/im/message": {
       "post": {
         "tags": [

requirements.txt

@@ -1,9 +1,6 @@
 aiocqhttp>=1.4.4
 aiodocker>=0.24.0
 aiohttp>=3.11.18
-aiocqhttp>=1.4.4
-aiodocker>=0.24.0
-aiohttp>=3.11.18
 aiosqlite>=0.21.0
 anthropic>=0.51.0
 apscheduler>=3.11.0

scripts/astrbot.service

@@ -1,5 +1,7 @@
+# user service
 [Unit]
 Description=AstrBot Service
+Documentation=https://github.com/AstrBotDevs/AstrBot
 After=network-online.target
 Wants=network-online.target
 
@@ -9,6 +11,9 @@ WorkingDirectory=%h/.local/share/astrbot
 ExecStart=/usr/bin/sh -c '/usr/bin/astrbot run || { /usr/bin/astrbot init && /usr/bin/astrbot run; }'
 Restart=on-failure
 RestartSec=5
+StandardOutput=journal
+StandardError=journal
+SyslogIdentifier=astrbot-%u
 Environment=PYTHONUNBUFFERED=1
 
 [Install]

scripts/generate_changelog.py

@@ -1,253 +0,0 @@
-#!/usr/bin/env python3
-"""
-Auto-generate changelog from git commits using LLM.
-Usage: python scripts/generate_changelog.py [--version VERSION]
-"""
-
-import argparse
-import os
-import re
-import subprocess
-import sys
-from pathlib import Path
-
-
-def get_latest_tag():
-    """Get the latest git tag."""
-    result = subprocess.run(
-        ["git", "describe", "--tags", "--abbrev=0"],
-        capture_output=True,
-        text=True,
-        check=True,
-    )
-    return result.stdout.strip()
-
-
-def get_commits_since_tag(tag):
-    """Get all commit messages since the specified tag."""
-    result = subprocess.run(
-        ["git", "log", f"{tag}..HEAD", "--pretty=format:%H|%s|%b"],
-        capture_output=True,
-        text=True,
-        check=True,
-    )
-    commits = []
-    for line in result.stdout.strip().split("\n"):
-        if not line:
-            continue
-        parts = line.split("|", 2)
-        if len(parts) >= 2:
-            commit_hash = parts[0]
-            subject = parts[1]
-            body = parts[2] if len(parts) > 2 else ""
-            commits.append({"hash": commit_hash[:7], "subject": subject, "body": body})
-    return commits
-
-
-def extract_issue_number(text):
-    """Extract issue number from commit message."""
-    # Match #1234 or (#1234)
-    match = re.search(r"#(\d+)", text)
-    return match.group(1) if match else None
-
-
-def call_llm_for_changelog(commits, version):
-    """Call LLM to generate changelog from commits."""
-    try:
-        # Try to use OpenAI API or other LLM providers
-        import openai
-
-        # Build prompt
-        commits_text = "\n".join([f"- {c['subject']}" for c in commits])
-
-        prompt = f"""Based on the following git commit messages, generate a changelog document in BOTH Chinese and English.
-
-Commit messages:
-{commits_text}
-
-Please organize the changes into these categories:
-- 新增 (New Features)
-- 修复 (Bug Fixes)
-- 优化 (Improvements)
-- 其他 (Others)
-
-Format requirements:
-1. Start with Chinese version under "## What's Changed"
-2. Follow with English version under "## What's Changed (EN)"
-3. Use markdown format with proper bullet points
-4. Keep descriptions concise and user-friendly
-5. If a commit mentions an issue number (#1234), include it in the format ([#1234](https://github.com/AstrBotDevs/AstrBot/issues/1234))
-
-Example format:
-## What's Changed
-
-### 新增
-- 支持某某功能 ([#1234](https://github.com/AstrBotDevs/AstrBot/issues/1234))
-
-### 修复
-- 修复某某问题
-
-## What's Changed (EN)
-
-### New Features
-- Add support for something ([#1234](https://github.com/AstrBotDevs/AstrBot/issues/1234))
-
-### Bug Fixes
-- Fix something
-"""
-
-        client = openai.OpenAI(
-            api_key=os.getenv("OPENAI_API_KEY"),
-            base_url=os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1"),
-        )
-
-        response = client.chat.completions.create(
-            model=os.getenv("OPENAI_MODEL", "gpt-4"),
-            messages=[
-                {
-                    "role": "system",
-                    "content": "You are a helpful assistant that generates well-structured changelogs.",
-                },
-                {"role": "user", "content": prompt},
-            ],
-            temperature=0.3,
-        )
-
-        return response.choices[0].message.content
-
-    except ImportError:
-        print(
-            "Warning: openai package not installed. Install it with: pip install openai"
-        )
-        return generate_simple_changelog(commits)
-    except Exception as e:
-        print(f"Warning: Failed to call LLM API: {e}")
-        print("Falling back to simple changelog generation...")
-        return generate_simple_changelog(commits)
-
-
-def generate_simple_changelog(commits):
-    """Generate a simple changelog without LLM."""
-    sections = {
-        "feat": ("新增", "New Features", []),
-        "fix": ("修复", "Bug Fixes", []),
-        "perf": ("优化", "Improvements", []),
-        "docs": ("文档", "Documentation", []),
-        "refactor": ("重构", "Refactoring", []),
-        "test": ("测试", "Tests", []),
-        "chore": ("其他", "Chore", []),
-        "other": ("其他", "Others", []),
-    }
-
-    # Categorize commits by conventional commit type
-    for commit in commits:
-        subject = commit["subject"]
-        issue_num = extract_issue_number(subject)
-        issue_link = (
-            f" ([#{issue_num}](https://github.com/AstrBotDevs/AstrBot/issues/{issue_num}))"
-            if issue_num
-            else ""
-        )
-
-        # Detect conventional commit type
-        matched = False
-        for prefix in ["feat", "fix", "perf", "docs", "refactor", "test", "chore"]:
-            if subject.lower().startswith(f"{prefix}:") or subject.lower().startswith(
-                f"{prefix}("
-            ):
-                # Remove prefix for display
-                clean_subject = re.sub(
-                    r"^[a-z]+(\([^)]+\))?:\s*", "", subject, flags=re.IGNORECASE
-                )
-                sections[prefix][2].append(f"- {clean_subject}{issue_link}")
-                matched = True
-                break
-
-        if not matched:
-            sections["other"][2].append(f"- {subject}{issue_link}")
-
-    # Build Chinese version
-    changelog_zh = "## What's Changed\n\n"
-    for section_key in ["feat", "fix", "perf", "docs", "refactor", "test", "other"]:
-        zh_title, _, items = sections[section_key]
-        if items:
-            changelog_zh += f"### {zh_title}\n\n"
-            changelog_zh += "\n".join(items) + "\n\n"
-
-    # Build English version
-    changelog_en = "## What's Changed (EN)\n\n"
-    for section_key in ["feat", "fix", "perf", "docs", "refactor", "test", "other"]:
-        _, en_title, items = sections[section_key]
-        if items:
-            changelog_en += f"### {en_title}\n\n"
-            changelog_en += "\n".join(items) + "\n\n"
-
-    return changelog_zh + changelog_en
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description="Generate changelog from git commits")
-    parser.add_argument(
-        "--version", help="Version number for the changelog (e.g., v4.13.3)"
-    )
-    parser.add_argument(
-        "--use-llm",
-        action="store_true",
-        help="Use LLM to generate changelog (requires OpenAI API key)",
-    )
-    args = parser.parse_args()
-
-    # Get latest tag
-    try:
-        latest_tag = get_latest_tag()
-        print(f"Latest tag: {latest_tag}")
-    except subprocess.CalledProcessError:
-        print("Error: No tags found in repository")
-        sys.exit(1)
-
-    # Get commits since tag
-    commits = get_commits_since_tag(latest_tag)
-    if not commits:
-        print(f"No commits found since {latest_tag}")
-        sys.exit(0)
-
-    print(f"Found {len(commits)} commits since {latest_tag}")
-
-    # Determine version
-    if args.version:
-        version = args.version
-    else:
-        # Auto-increment patch version
-        match = re.match(r"v(\d+)\.(\d+)\.(\d+)", latest_tag)
-        if match:
-            major, minor, patch = map(int, match.groups())
-            version = f"v{major}.{minor}.{patch + 1}"
-        else:
-            print(f"Warning: Could not parse version from tag {latest_tag}")
-            version = "vX.X.X"
-
-    print(f"Generating changelog for {version}...")
-
-    # Generate changelog
-    if args.use_llm:
-        changelog_content = call_llm_for_changelog(commits, version)
-    else:
-        changelog_content = generate_simple_changelog(commits)
-
-    # Save to file
-    changelog_dir = Path(__file__).parent.parent / "changelogs"
-    changelog_dir.mkdir(exist_ok=True)
-    changelog_file = changelog_dir / f"{version}.md"
-
-    with open(changelog_file, "w", encoding="utf-8") as f:
-        f.write(changelog_content)
-
-    print(f"\n✓ Changelog generated: {changelog_file}")
-    print("\nPreview:")
-    print("=" * 80)
-    print(changelog_content)
-    print("=" * 80)
-
-
-if __name__ == "__main__":
-    main()

tests/test_chat_route.py

@@ -0,0 +1,56 @@
+import asyncio
+
+import pytest
+
+from astrbot.dashboard.routes.chat import _poll_webchat_stream_result
+
+
+class _QueueThatRaises:
+    def __init__(self, exc: BaseException):
+        self._exc = exc
+
+    async def get(self):
+        raise self._exc
+
+
+class _QueueWithResult:
+    def __init__(self, result):
+        self._result = result
+
+    async def get(self):
+        return self._result
+
+
+@pytest.mark.asyncio
+async def test_poll_webchat_stream_result_breaks_on_cancelled_error():
+    result, should_break = await _poll_webchat_stream_result(
+        _QueueThatRaises(asyncio.CancelledError()),
+        "alice",
+    )
+
+    assert result is None
+    assert should_break is True
+
+
+@pytest.mark.asyncio
+async def test_poll_webchat_stream_result_continues_on_generic_exception():
+    result, should_break = await _poll_webchat_stream_result(
+        _QueueThatRaises(RuntimeError("boom")),
+        "alice",
+    )
+
+    assert result is None
+    assert should_break is False
+
+
+@pytest.mark.asyncio
+async def test_poll_webchat_stream_result_returns_queue_payload():
+    payload = {"type": "end", "data": ""}
+
+    result, should_break = await _poll_webchat_stream_result(
+        _QueueWithResult(payload),
+        "alice",
+    )
+
+    assert result == payload
+    assert should_break is False

tests/test_dashboard.py

@@ -106,6 +106,109 @@ async def test_get_stat(app: Quart, authenticated_header: dict):
     assert data["status"] == "ok" and "platform" in data["data"]
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("payload", [[], "x"])
+async def test_batch_delete_sessions_rejects_non_object_payload(
+    app: Quart, authenticated_header: dict, payload
+):
+    test_client = app.test_client()
+    response = await test_client.post(
+        "/api/chat/batch_delete_sessions",
+        json=payload,
+        headers=authenticated_header,
+    )
+
+    assert response.status_code == 200
+    data = await response.get_json()
+    assert data["status"] == "error"
+    assert data["message"] == "Invalid JSON body: expected object"
+
+
+@pytest.mark.asyncio
+async def test_batch_delete_sessions_masks_internal_error(
+    app: Quart, authenticated_header: dict, monkeypatch
+):
+    test_client = app.test_client()
+
+    create_session_response = await test_client.get(
+        "/api/chat/new_session", headers=authenticated_header
+    )
+    assert create_session_response.status_code == 200
+    create_session_data = await create_session_response.get_json()
+    session_id = create_session_data["data"]["session_id"]
+
+    async def _raise_error(*args, **kwargs):
+        raise RuntimeError("secret-internal-error")
+
+    monkeypatch.setattr(
+        "astrbot.dashboard.routes.chat.ChatRoute._delete_session_internal",
+        _raise_error,
+    )
+
+    response = await test_client.post(
+        "/api/chat/batch_delete_sessions",
+        json={"session_ids": [session_id]},
+        headers=authenticated_header,
+    )
+
+    assert response.status_code == 200
+    data = await response.get_json()
+    assert data["status"] == "ok"
+    assert data["data"]["deleted_count"] == 0
+    assert data["data"]["failed_count"] == 1
+    assert data["data"]["failed_items"][0]["session_id"] == session_id
+    assert data["data"]["failed_items"][0]["reason"] == "internal_error"
+
+
+@pytest.mark.asyncio
+async def test_batch_delete_sessions_uses_batch_lookup(
+    app: Quart,
+    authenticated_header: dict,
+    core_lifecycle_td: AstrBotCoreLifecycle,
+    monkeypatch,
+):
+    test_client = app.test_client()
+    db = core_lifecycle_td.db
+
+    create_session_response = await test_client.get(
+        "/api/chat/new_session", headers=authenticated_header
+    )
+    assert create_session_response.status_code == 200
+    create_session_data = await create_session_response.get_json()
+    session_id = create_session_data["data"]["session_id"]
+
+    original_batch_lookup = db.get_platform_sessions_by_ids
+    called = {"batch_lookup_count": 0}
+
+    async def _wrapped_batch_lookup(session_ids: list[str]):
+        called["batch_lookup_count"] += 1
+        return await original_batch_lookup(session_ids)
+
+    # 不应单个查询
+    async def _should_not_call_single_lookup(session_id: str):
+        raise AssertionError(
+            f"single-session lookup should not be called: {session_id}"
+        )
+
+    monkeypatch.setattr(db, "get_platform_sessions_by_ids", _wrapped_batch_lookup)
+    monkeypatch.setattr(
+        db, "get_platform_session_by_id", _should_not_call_single_lookup
+    )
+
+    response = await test_client.post(
+        "/api/chat/batch_delete_sessions",
+        json={"session_ids": [session_id]},
+        headers=authenticated_header,
+    )
+
+    assert response.status_code == 200
+    data = await response.get_json()
+    assert data["status"] == "ok"
+    assert data["data"]["deleted_count"] == 1
+    assert data["data"]["failed_count"] == 0
+    assert called["batch_lookup_count"] == 1
+
+
 @pytest.mark.asyncio
 async def test_plugins(
     app: Quart,

tests/test_openai_source.py

@@ -2,6 +2,7 @@ from types import SimpleNamespace
 
 import pytest
 
+from astrbot.core.provider.sources.groq_source import ProviderGroq
 from astrbot.core.provider.sources.openai_source import ProviderOpenAIOfficial
 
 
@@ -32,6 +33,21 @@ def _make_provider(overrides: dict | None = None) -> ProviderOpenAIOfficial:
     )
 
 
+def _make_groq_provider(overrides: dict | None = None) -> ProviderGroq:
+    provider_config = {
+        "id": "test-groq",
+        "type": "groq_chat_completion",
+        "model": "qwen/qwen3-32b",
+        "key": ["test-key"],
+    }
+    if overrides:
+        provider_config.update(overrides)
+    return ProviderGroq(
+        provider_config=provider_config,
+        provider_settings={},
+    )
+
+
 @pytest.mark.asyncio
 async def test_handle_api_error_content_moderated_removes_images():
     provider = _make_provider(
@@ -198,6 +214,57 @@ def test_extract_error_text_candidates_truncates_long_response_text():
     )
 
 
+@pytest.mark.asyncio
+async def test_openai_payload_keeps_reasoning_content_in_assistant_history():
+    provider = _make_provider()
+    try:
+        payloads = {
+            "messages": [
+                {
+                    "role": "assistant",
+                    "content": [
+                        {"type": "think", "think": "step 1"},
+                        {"type": "text", "text": "final answer"},
+                    ],
+                }
+            ]
+        }
+
+        provider._finally_convert_payload(payloads)
+
+        assistant_message = payloads["messages"][0]
+        assert assistant_message["content"] == [{"type": "text", "text": "final answer"}]
+        assert assistant_message["reasoning_content"] == "step 1"
+    finally:
+        await provider.terminate()
+
+
+@pytest.mark.asyncio
+async def test_groq_payload_drops_reasoning_content_from_assistant_history():
+    provider = _make_groq_provider()
+    try:
+        payloads = {
+            "messages": [
+                {
+                    "role": "assistant",
+                    "content": [
+                        {"type": "think", "think": "step 1"},
+                        {"type": "text", "text": "final answer"},
+                    ],
+                }
+            ]
+        }
+
+        provider._finally_convert_payload(payloads)
+
+        assistant_message = payloads["messages"][0]
+        assert assistant_message["content"] == [{"type": "text", "text": "final answer"}]
+        assert "reasoning_content" not in assistant_message
+        assert "reasoning" not in assistant_message
+    finally:
+        await provider.terminate()
+
+
 @pytest.mark.asyncio
 async def test_handle_api_error_content_moderated_without_images_raises():
     provider = _make_provider(

tests/unit/test_astr_main_agent.py

@@ -804,6 +804,28 @@ class TestPluginToolFix:
 
         assert "mcp_tool" in req.func_tool.names()
 
+    def test_plugin_tool_fix_preserves_tools_without_plugin_origin(self, mock_event):
+        """Tools without handler_module_path should not be filtered out."""
+        module = ama
+        handoff_tool = FunctionTool(
+            name="transfer_to_demo_agent",
+            description="Delegate to demo agent",
+            parameters={"type": "object", "properties": {}},
+            handler_module_path=None,
+            active=True,
+        )
+
+        tool_set = ToolSet()
+        tool_set.add_tool(handoff_tool)
+
+        req = ProviderRequest(func_tool=tool_set)
+        mock_event.plugins_name = ["other_plugin"]
+
+        with patch("astrbot.core.astr_main_agent.star_map"):
+            module._plugin_tool_fix(mock_event, req)
+
+        assert "transfer_to_demo_agent" in req.func_tool.names()
+
 
 class TestBuildMainAgent:
     """Tests for build_main_agent function."""