feat: add note for remove_think & remove dify remove cot code

Fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages (#1624 )
* fix: update invoke_embedding to return only embeddings from client.embed * fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages
2025-11-25 19:37:36 +08:00 · 2025-08-21 21:38:58 +08:00 · 2025-08-21 20:46:26 +08:00 · 2025-08-21 14:14:25 +08:00 · 2025-08-21 12:03:04 +08:00 · 2025-08-21 11:47:40 +08:00
130 changed files with 5299 additions and 1160 deletions
--- a/README.md
+++ b/README.md
@@ -6,7 +6,9 @@

 <div align="center">

-简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)
+<a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+[English](README_EN.md) / 简体中文 / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)

 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
 [![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
@@ -67,7 +69,7 @@ docker compose up -d

 ## ✨ 特性

- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
+- 💬 大模型对话、Agent：支持多种大模型，适配群聊和私聊；具有多轮对话、工具调用、多模态、流式输出能力，自带 RAG（知识库）实现，并深度适配 [Dify](https://dify.ai)。
 - 🤖 多平台支持：目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
 - 🛠️ 高稳定性、功能完备：原生支持访问控制、限速、敏感词过滤等机制；配置简单，支持多种部署方式。支持多流水线配置，不同机器人用于不同应用场景。
 - 🧩 插件扩展、活跃社区：支持事件驱动、组件扩展等插件机制；适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/)；目前已有数百个插件。
@@ -85,8 +87,9 @@ docker compose up -d
 | --- | --- | --- |
 | QQ 个人号 | ✅ | QQ 个人号私聊、群聊 |
 | QQ 官方机器人 | ✅ | QQ 官方机器人，支持频道、私聊、群聊 |
-| 微信 | ✅ |  |
+| 企业微信 | ✅ |  |
 | 企微对外客服 | ✅ |  |
+| 个人微信 | ✅ |  |
 | 微信公众号 | ✅ |  |
 | 飞书 | ✅ |  |
 | 钉钉 | ✅ |  |
@@ -106,6 +109,7 @@ docker compose up -d
 | [智谱AI](https://open.bigmodel.cn/) | ✅ |  |
 | [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 资源平台 |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 资源平台 |
+| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 资源平台 |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
--- a/README_EN.md
+++ b/README_EN.md
@@ -5,7 +5,7 @@

 <div align="center">

-[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
+English / [简体中文](README.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)

 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
@@ -63,7 +63,7 @@ Click the Star and Watch button in the upper right corner of the repository to g

 ## ✨ Features

- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
+- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
 - 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
 - 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
 - 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
@@ -103,6 +103,7 @@ Or visit the demo environment: https://demo.langbot.dev/
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | LLM and GPU resource platform |
 | [Dify](https://dify.ai) | ✅ | LLMOps platform |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM and GPU resource platform |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |
--- a/README_JP.md
+++ b/README_JP.md
@@ -5,7 +5,7 @@

 <div align="center">

-[简体中文](README.md) / [English](README_EN.md) / 日本語 / (PR for your language)
+[English](README_EN.md) / [简体中文](README.md) / [繁體中文](README_TW.md) / 日本語 / (PR for your language)

 [![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
 [![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
@@ -63,7 +63,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール

 ## ✨ 機能

- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
+- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル、ストリーミング出力機能をサポート、RAG（知識ベース）を組み込み、[Dify](https://dify.ai) と深く統合。
 - 🤖 多プラットフォーム対応: 現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
 - 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
 - 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/)；豊富なエコシステム、現在数百のプラグインが存在。
@@ -102,6 +102,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
 | [Zhipu AI](https://open.bigmodel.cn/) | ✅ |  |
 | [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
 | [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
+| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLMとGPUリソースプラットフォーム |
 | [302.AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
 | [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
 | [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |
--- a/README_TW.md
+++ b/README_TW.md
@@ -0,0 +1,140 @@
+<p align="center">
+<a href="https://langbot.app">
+<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
+</a>
+
+<div align="center"><a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="Featured｜HelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
+
+[English](README_EN.md) / [简体中文](README.md) / 繁體中文 / [日本語](README_JP.md) / (PR for your language)
+
+[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
+[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
+[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
+<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
+[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
+
+<a href="https://langbot.app">主頁</a> ｜
+<a href="https://docs.langbot.app/zh/insight/guide.html">部署文件</a> ｜
+<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">外掛介紹</a> ｜
+<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交外掛</a>
+
+</div>
+
+</p>
+
+LangBot 是一個開源的大語言模型原生即時通訊機器人開發平台，旨在提供開箱即用的 IM 機器人開發體驗，具有 Agent、RAG、MCP 等多種 LLM 應用功能，適配全球主流即時通訊平台，並提供豐富的 API 介面，支援自定義開發。
+
+## 📦 開始使用
+
+#### Docker Compose 部署
+
+```bash
+git clone https://github.com/langbot-app/LangBot
+cd LangBot
+docker compose up -d
+```
+
+訪問 http://localhost:5300 即可開始使用。
+
+詳細文件[Docker 部署](https://docs.langbot.app/zh/deploy/langbot/docker.html)。
+
+#### 寶塔面板部署
+
+已上架寶塔面板，若您已安裝寶塔面板，可以根據[文件](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html)使用。
+
+#### Zeabur 雲端部署
+
+社群貢獻的 Zeabur 模板。
+
+[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
+
+#### Railway 雲端部署
+
+[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
+
+#### 手動部署
+
+直接使用發行版運行，查看文件[手動部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。
+
+## 😎 保持更新
+
+點擊倉庫右上角 Star 和 Watch 按鈕，獲取最新動態。
+
+![star gif](https://docs.langbot.app/star.gif)
+
+## ✨ 特性
+
+- 💬 大模型對話、Agent：支援多種大模型，適配群聊和私聊；具有多輪對話、工具調用、多模態、流式輸出能力，自帶 RAG（知識庫）實現，並深度適配 [Dify](https://dify.ai)。
+- 🤖 多平台支援：目前支援 QQ、QQ頻道、企業微信、個人微信、飛書、Discord、Telegram 等平台。
+- 🛠️ 高穩定性、功能完備：原生支援訪問控制、限速、敏感詞過濾等機制；配置簡單，支援多種部署方式。支援多流水線配置，不同機器人用於不同應用場景。
+- 🧩 外掛擴展、活躍社群：支援事件驅動、組件擴展等外掛機制；適配 Anthropic [MCP 協議](https://modelcontextprotocol.io/)；目前已有數百個外掛。
+- 😻 Web 管理面板：支援通過瀏覽器管理 LangBot 實例，不再需要手動編寫配置文件。
+
+詳細規格特性請訪問[文件](https://docs.langbot.app/zh/insight/features.html)。
+
+或訪問 demo 環境：https://demo.langbot.dev/  
+  - 登入資訊：郵箱：`demo@langbot.app` 密碼：`langbot123456`
+  - 注意：僅展示 WebUI 效果，公開環境，請不要在其中填入您的任何敏感資訊。
+
+### 訊息平台
+
+| 平台 | 狀態 | 備註 |
+| --- | --- | --- |
+| QQ 個人號 | ✅ | QQ 個人號私聊、群聊 |
+| QQ 官方機器人 | ✅ | QQ 官方機器人，支援頻道、私聊、群聊 |
+| 微信 | ✅ |  |
+| 企微對外客服 | ✅ |  |
+| 微信公眾號 | ✅ |  |
+| Lark | ✅ |  |
+| DingTalk | ✅ |  |
+| Discord | ✅ |  |
+| Telegram | ✅ |  |
+| Slack | ✅ |  |
+
+### 大模型能力
+
+| 模型 | 狀態 | 備註 |
+| --- | --- | --- |
+| [OpenAI](https://platform.openai.com/) | ✅ | 可接入任何 OpenAI 介面格式模型 |
+| [DeepSeek](https://www.deepseek.com/) | ✅ |  |
+| [Moonshot](https://www.moonshot.cn/) | ✅ |  |
+| [Anthropic](https://www.anthropic.com/) | ✅ |  |
+| [xAI](https://x.ai/) | ✅ |  |
+| [智譜AI](https://open.bigmodel.cn/) | ✅ |  |
+| [勝算雲](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 資源平台 |
+| [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 資源平台 |
+| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 資源平台 |
+| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
+| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
+| [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
+| [Ollama](https://ollama.com/) | ✅ | 本地大模型運行平台 |
+| [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型運行平台 |
+| [GiteeAI](https://ai.gitee.com/) | ✅ | 大模型介面聚合平台 |
+| [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
+| [阿里雲百煉](https://bailian.console.aliyun.com/) | ✅ | 大模型聚合平台, LLMOps 平台 |
+| [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | 大模型聚合平台, LLMOps 平台 |
+| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | 大模型聚合平台 |
+| [MCP](https://modelcontextprotocol.io/) | ✅ | 支援通過 MCP 協議獲取工具 |
+
+### TTS
+
+| 平台/模型 | 備註 |
+| --- | --- |
+| [FishAudio](https://fish.audio/zh-CN/discovery/) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
+| [海豚 AI](https://www.ttson.cn/?source=thelazy) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
+| [AzureTTS](https://portal.azure.com/) | [外掛](https://github.com/Ingnaryk/LangBot_AzureTTS) |
+
+### 文生圖
+
+| 平台/模型 | 備註 |
+| --- | --- |
+| 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
+
+## 😘 社群貢獻
+
+感謝以下[程式碼貢獻者](https://github.com/langbot-app/LangBot/graphs/contributors)和社群裡其他成員對 LangBot 的貢獻：
+
+<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
+</a> 
--- a/libs/dingtalk_api/api.py
+++ b/libs/dingtalk_api/api.py
@@ -253,6 +253,43 @@ class DingTalkClient:
            await self.logger.error(f'failed to send proactive massage to group: {traceback.format_exc()}')
            raise Exception(f'failed to send proactive massage to group: {traceback.format_exc()}')

+    async def create_and_card(
+        self, temp_card_id: str, incoming_message: dingtalk_stream.ChatbotMessage, quote_origin: bool = False
+    ):
+        content_key = 'content'
+        card_data = {content_key: ''}
+
+        card_instance = dingtalk_stream.AICardReplier(self.client, incoming_message)
+        # print(card_instance)
+        # 先投放卡片: https://open.dingtalk.com/document/orgapp/create-and-deliver-cards
+        card_instance_id = await card_instance.async_create_and_deliver_card(
+            temp_card_id,
+            card_data,
+        )
+        return card_instance, card_instance_id
+
+    async def send_card_message(self, card_instance, card_instance_id: str, content: str, is_final: bool):
+        content_key = 'content'
+        try:
+            await card_instance.async_streaming(
+                card_instance_id,
+                content_key=content_key,
+                content_value=content,
+                append=False,
+                finished=is_final,
+                failed=False,
+            )
+        except Exception as e:
+            self.logger.exception(e)
+            await card_instance.async_streaming(
+                card_instance_id,
+                content_key=content_key,
+                content_value='',
+                append=False,
+                finished=is_final,
+                failed=True,
+            )
+
    async def start(self):
        """启动 WebSocket 连接，监听消息"""
        await self.client.start()
--- a/libs/qq_official_api/api.py
+++ b/libs/qq_official_api/api.py
@@ -104,7 +104,7 @@ class QQOfficialClient:
            return {'code': 0, 'message': 'success'}

        except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
            return {'error': str(e)}, 400

    async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -168,7 +168,6 @@ class QQOfficialClient:
        if not await self.check_access_token():
            await self.get_access_token()

-
        url = self.base_url + '/v2/users/' + user_openid + '/messages'
        async with httpx.AsyncClient() as client:
            headers = {
@@ -193,7 +192,6 @@ class QQOfficialClient:
        if not await self.check_access_token():
            await self.get_access_token()

-
        url = self.base_url + '/v2/groups/' + group_openid + '/messages'
        async with httpx.AsyncClient() as client:
            headers = {
@@ -209,7 +207,7 @@ class QQOfficialClient:
            if response.status_code == 200:
                return
            else:
-                await self.logger.error(f"发送群聊消息失败:{response.json()}")
+                await self.logger.error(f'发送群聊消息失败:{response.json()}')
                raise Exception(response.read().decode())

    async def send_channle_group_text_msg(self, channel_id: str, content: str, msg_id: str):
@@ -217,7 +215,6 @@ class QQOfficialClient:
        if not await self.check_access_token():
            await self.get_access_token()

-
        url = self.base_url + '/channels/' + channel_id + '/messages'
        async with httpx.AsyncClient() as client:
            headers = {
@@ -240,7 +237,6 @@ class QQOfficialClient:
        """发送频道私聊消息"""
        if not await self.check_access_token():
            await self.get_access_token()
-        

        url = self.base_url + '/dms/' + guild_id + '/messages'
        async with httpx.AsyncClient() as client:
--- a/libs/slack_api/api.py
+++ b/libs/slack_api/api.py
@@ -34,7 +34,6 @@ class SlackClient:

            if self.bot_user_id and bot_user_id == self.bot_user_id:
                return jsonify({'status': 'ok'})
-            

            # 处理私信
            if data and data.get('event', {}).get('channel_type') in ['im']:
@@ -52,7 +51,7 @@ class SlackClient:
            return jsonify({'status': 'ok'})

        except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
            raise (e)

    async def _handle_message(self, event: SlackEvent):
@@ -82,7 +81,7 @@ class SlackClient:
                self.bot_user_id = response['message']['bot_id']
            return
        except Exception as e:
-            await self.logger.error(f"Error in send_message: {e}")
+            await self.logger.error(f'Error in send_message: {e}')
            raise e

    async def send_message_to_one(self, text: str, user_id: str):
@@ -93,7 +92,7 @@ class SlackClient:

            return
        except Exception as e:
-            await self.logger.error(f"Error in send_message: {traceback.format_exc()}")
+            await self.logger.error(f'Error in send_message: {traceback.format_exc()}')
            raise e

    async def run_task(self, host: str, port: int, *args, **kwargs):
--- a/libs/wechatpad_api/api/user.py
+++ b/libs/wechatpad_api/api/user.py
@@ -12,12 +12,9 @@ class UserApi:

        return get_json(base_url=url, token=self.token)

-    def get_qr_code(self, recover:bool=True, style:int=8):
+    def get_qr_code(self, recover: bool = True, style: int = 8):
        """获取自己的二维码"""
-        param = {
-              "Recover": recover,
-              "Style": style
-            }
+        param = {'Recover': recover, 'Style': style}
        url = f'{self.base_url}/user/GetMyQRCode'
        return post_json(base_url=url, token=self.token, data=param)

@@ -26,12 +23,8 @@ class UserApi:
        url = f'{self.base_url}/equipment/GetSafetyInfo'
        return post_json(base_url=url, token=self.token)

-
-
-    async def update_head_img(self,  head_img_base64):
+    async def update_head_img(self, head_img_base64):
        """修改头像"""
-        param = {
-              "Base64": head_img_base64
-            }
+        param = {'Base64': head_img_base64}
        url = f'{self.base_url}/user/UploadHeadImage'
-        return await async_request(base_url=url, token_key=self.token, json=param)
+        return await async_request(base_url=url, token_key=self.token, json=param)
--- a/libs/wechatpad_api/client.py
+++ b/libs/wechatpad_api/client.py
@@ -1,4 +1,3 @@
-
 from libs.wechatpad_api.api.login import LoginApi
 from libs.wechatpad_api.api.friend import FriendApi
 from libs.wechatpad_api.api.message import MessageApi
@@ -7,9 +6,6 @@ from libs.wechatpad_api.api.downloadpai import DownloadApi
 from libs.wechatpad_api.api.chatroom import ChatRoomApi


-
-
-
 class WeChatPadClient:
    def __init__(self, base_url, token, logger=None):
        self._login_api = LoginApi(base_url, token)
@@ -20,16 +16,16 @@ class WeChatPadClient:
        self._chatroom_api = ChatRoomApi(base_url, token)
        self.logger = logger

-    def get_token(self,admin_key, day: int):
-        '''获取token'''
+    def get_token(self, admin_key, day: int):
+        """获取token"""
        return self._login_api.get_token(admin_key, day)

-    def get_login_qr(self, Proxy:str=""):
+    def get_login_qr(self, Proxy: str = ''):
        """登录二维码"""
        return self._login_api.get_login_qr(Proxy=Proxy)

-    def awaken_login(self, Proxy:str=""):
-        '''唤醒登录'''
+    def awaken_login(self, Proxy: str = ''):
+        """唤醒登录"""
        return self._login_api.wake_up_login(Proxy=Proxy)

    def log_out(self):
@@ -40,59 +36,57 @@ class WeChatPadClient:
        """获取登录状态"""
        return self._login_api.get_login_status()

-    def send_text_message(self, to_wxid, message, ats: list=[]):
+    def send_text_message(self, to_wxid, message, ats: list = []):
        """发送文本消息"""
-        return  self._message_api.post_text(to_wxid, message, ats)
+        return self._message_api.post_text(to_wxid, message, ats)

-    def send_image_message(self, to_wxid, img_url, ats: list=[]):
+    def send_image_message(self, to_wxid, img_url, ats: list = []):
        """发送图片消息"""
-        return  self._message_api.post_image(to_wxid, img_url, ats)
+        return self._message_api.post_image(to_wxid, img_url, ats)

    def send_voice_message(self, to_wxid, voice_data, voice_forma, voice_duration):
        """发送音频消息"""
-        return  self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)
+        return self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)

    def send_app_message(self, to_wxid, app_message, type):
        """发送app消息"""
-        return  self._message_api.post_app_msg(to_wxid, app_message, type)
+        return self._message_api.post_app_msg(to_wxid, app_message, type)

    def send_emoji_message(self, to_wxid, emoji_md5, emoji_size):
        """发送emoji消息"""
-        return  self._message_api.post_emoji(to_wxid,emoji_md5,emoji_size)
+        return self._message_api.post_emoji(to_wxid, emoji_md5, emoji_size)

    def revoke_msg(self, to_wxid, msg_id, new_msg_id, create_time):
        """撤回消息"""
-        return  self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)
+        return self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)

    def get_profile(self):
        """获取用户信息"""
        return self._user_api.get_profile()

-    def get_qr_code(self, recover:bool=True, style:int=8):
+    def get_qr_code(self, recover: bool = True, style: int = 8):
        """获取用户二维码"""
-        return  self._user_api.get_qr_code(recover=recover, style=style)
+        return self._user_api.get_qr_code(recover=recover, style=style)

    def get_safety_info(self):
        """获取设备信息"""
-        return  self._user_api.get_safety_info()
+        return self._user_api.get_safety_info()

-    def update_head_img(self,  head_img_base64):
+    def update_head_img(self, head_img_base64):
        """上传用户头像"""
-        return  self._user_api.update_head_img(head_img_base64)
+        return self._user_api.update_head_img(head_img_base64)

    def cdn_download(self, aeskey, file_type, file_url):
        """cdn下载"""
-        return self._download_api.send_download( aeskey, file_type, file_url)
+        return self._download_api.send_download(aeskey, file_type, file_url)

-    def get_msg_voice(self,buf_id, length, msgid):
+    def get_msg_voice(self, buf_id, length, msgid):
        """下载语音"""
        return self._download_api.get_msg_voice(buf_id, length, msgid)

-    async def download_base64(self,url):
+    async def download_base64(self, url):
        return await self._download_api.download_url_to_base64(download_url=url)

    def get_chatroom_member_detail(self, chatroom_name):
        """查看群成员详情"""
        return self._chatroom_api.get_chatroom_member_detail(chatroom_name)
-
-
--- a/libs/wechatpad_api/util/terminal_printer.py
+++ b/libs/wechatpad_api/util/terminal_printer.py
@@ -1,31 +1,34 @@
 import qrcode

+
 def print_green(text):
-    print(f"\033[32m{text}\033[0m")
+    print(f'\033[32m{text}\033[0m')
+

 def print_yellow(text):
-    print(f"\033[33m{text}\033[0m")
+    print(f'\033[33m{text}\033[0m')
+

 def print_red(text):
-    print(f"\033[31m{text}\033[0m")
+    print(f'\033[31m{text}\033[0m')
+

 def make_and_print_qr(url):
    """生成并打印二维码
-    
+
    Args:
        url: 需要生成二维码的URL字符串
-        
+
    Returns:
        None
-        
+
    功能:
        1. 在终端打印二维码的ASCII图形
        2. 同时提供在线二维码生成链接作为备选
    """
-    print_green("请扫描下方二维码登录")
+    print_green('请扫描下方二维码登录')
    qr = qrcode.QRCode()
    qr.add_data(url)
    qr.make()
    qr.print_ascii(invert=True)
-    print_green(f"也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}")
-
+    print_green(f'也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}')
--- a/libs/wecom_api/api.py
+++ b/libs/wecom_api/api.py
@@ -57,7 +57,7 @@ class WecomClient:
            if 'access_token' in data:
                return data['access_token']
            else:
-                await self.logger.error(f"获取accesstoken失败:{response.json()}")
+                await self.logger.error(f'获取accesstoken失败:{response.json()}')
                raise Exception(f'未获取access token: {data}')

    async def get_users(self):
@@ -129,7 +129,7 @@ class WecomClient:
                response = await client.post(url, json=params)
                data = response.json()
            except Exception as e:
-                await self.logger.error(f"发送图片失败:{data}")
+                await self.logger.error(f'发送图片失败:{data}')
                raise Exception('Failed to send image: ' + str(e))

            # 企业微信错误码40014和42001，代表accesstoken问题
@@ -164,7 +164,7 @@ class WecomClient:
                self.access_token = await self.get_access_token(self.secret)
                return await self.send_private_msg(user_id, agent_id, content)
            if data['errcode'] != 0:
-                await self.logger.error(f"发送消息失败:{data}")
+                await self.logger.error(f'发送消息失败:{data}')
                raise Exception('Failed to send message: ' + str(data))

    async def handle_callback_request(self):
@@ -181,7 +181,7 @@ class WecomClient:
                echostr = request.args.get('echostr')
                ret, reply_echo_str = wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
                if ret != 0:
-                    await self.logger.error("验证失败")
+                    await self.logger.error('验证失败')
                    raise Exception(f'验证失败，错误码: {ret}')
                return reply_echo_str

@@ -189,9 +189,8 @@ class WecomClient:
                encrypt_msg = await request.data
                ret, xml_msg = wxcpt.DecryptMsg(encrypt_msg, msg_signature, timestamp, nonce)
                if ret != 0:
-                    await self.logger.error("消息解密失败")
+                    await self.logger.error('消息解密失败')
                    raise Exception(f'消息解密失败，错误码: {ret}')
-                

                # 解析消息并处理
                message_data = await self.get_message(xml_msg)
@@ -202,7 +201,7 @@ class WecomClient:

                return 'success'
        except Exception as e:
-            await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+            await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
            return f'Error processing request: {str(e)}', 400

    async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -301,7 +300,7 @@ class WecomClient:
            except binascii.Error as e:
                raise ValueError(f'Invalid base64 string: {str(e)}')
        else:
-            await self.logger.error("Image对象出错")
+            await self.logger.error('Image对象出错')
            raise ValueError('image对象出错')

        # 设置 multipart/form-data 格式的文件
@@ -325,7 +324,7 @@ class WecomClient:
                self.access_token = await self.get_access_token(self.secret)
                media_id = await self.upload_to_work(image)
            if data.get('errcode', 0) != 0:
-                await self.logger.error(f"上传图片失败:{data}")
+                await self.logger.error(f'上传图片失败:{data}')
                raise Exception('failed to upload file')

            media_id = data.get('media_id')
--- a/libs/wecom_customer_service_api/api.py
+++ b/libs/wecom_customer_service_api/api.py
@@ -187,7 +187,7 @@ class WecomCSClient:
                self.access_token = await self.get_access_token(self.secret)
                return await self.send_text_msg(open_kfid, external_userid, msgid, content)
            if data['errcode'] != 0:
-                await self.logger.error(f"发送消息失败：{data}")
+                await self.logger.error(f'发送消息失败：{data}')
                raise Exception('Failed to send message')
            return data

@@ -227,7 +227,7 @@ class WecomCSClient:
                return 'success'
        except Exception as e:
            if self.logger:
-                await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
+                await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
            else:
                traceback.print_exc()
            return f'Error processing request: {str(e)}', 400
--- a/pkg/api/http/controller/group.py
+++ b/pkg/api/http/controller/group.py
@@ -123,4 +123,4 @@ class RouterGroup(abc.ABC):

    def http_status(self, status: int, code: int, msg: str) -> typing.Tuple[quart.Response, int]:
        """返回一个指定状态码的响应"""
-        return (self.fail(code, msg), status)
+        return (self.fail(code, msg), status)
--- a/pkg/api/http/controller/groups/pipelines/pipelines.py
+++ b/pkg/api/http/controller/groups/pipelines/pipelines.py
@@ -13,7 +13,9 @@ class PipelinesRouterGroup(group.RouterGroup):
            if quart.request.method == 'GET':
                sort_by = quart.request.args.get('sort_by', 'created_at')
                sort_order = quart.request.args.get('sort_order', 'DESC')
-                return self.success(data={'pipelines': await self.ap.pipeline_service.get_pipelines(sort_by, sort_order)})
+                return self.success(
+                    data={'pipelines': await self.ap.pipeline_service.get_pipelines(sort_by, sort_order)}
+                )
            elif quart.request.method == 'POST':
                json_data = await quart.request.json

--- a/pkg/api/http/controller/groups/pipelines/webchat.py
+++ b/pkg/api/http/controller/groups/pipelines/webchat.py
@@ -1,3 +1,5 @@
+import json
+
 import quart

 from ... import group
@@ -9,10 +11,18 @@ class WebChatDebugRouterGroup(group.RouterGroup):
        @self.route('/send', methods=['POST'])
        async def send_message(pipeline_uuid: str) -> str:
            """Send a message to the pipeline for debugging"""
+
+            async def stream_generator(generator):
+                yield 'data: {"type": "start"}\n\n'
+                async for message in generator:
+                    yield f'data: {json.dumps({"message": message})}\n\n'
+                yield 'data: {"type": "end"}\n\n'
+
            try:
                data = await quart.request.get_json()
                session_type = data.get('session_type', 'person')
                message_chain_obj = data.get('message', [])
+                is_stream = data.get('is_stream', False)

                if not message_chain_obj:
                    return self.http_status(400, -1, 'message is required')
@@ -25,13 +35,33 @@ class WebChatDebugRouterGroup(group.RouterGroup):
                if not webchat_adapter:
                    return self.http_status(404, -1, 'WebChat adapter not found')

-                result = await webchat_adapter.send_webchat_message(pipeline_uuid, session_type, message_chain_obj)
-
-                return self.success(
-                    data={
-                        'message': result,
+                if is_stream:
+                    generator = webchat_adapter.send_webchat_message(
+                        pipeline_uuid, session_type, message_chain_obj, is_stream
+                    )
+                    # 设置正确的响应头
+                    headers = {
+                        'Content-Type': 'text/event-stream',
+                        'Transfer-Encoding': 'chunked',
+                        'Cache-Control': 'no-cache',
+                        'Connection': 'keep-alive'
                    }
-                )
+                    return quart.Response(stream_generator(generator), mimetype='text/event-stream',headers=headers)
+
+                else:  # non-stream
+                    result = None
+                    async for message in webchat_adapter.send_webchat_message(
+                        pipeline_uuid, session_type, message_chain_obj
+                    ):
+                        result = message
+                    if result is not None:
+                        return self.success(
+                            data={
+                                'message': result,
+                            }
+                        )
+                    else:
+                        return self.http_status(400, -1, 'message is required')

            except Exception as e:
                return self.http_status(500, -1, f'Internal server error: {str(e)}')
--- a/pkg/api/http/controller/groups/user.py
+++ b/pkg/api/http/controller/groups/user.py
@@ -67,3 +67,19 @@ class UserRouterGroup(group.RouterGroup):
            await self.ap.user_service.reset_password(user_email, new_password)

            return self.success(data={'user': user_email})
+
+        @self.route('/change-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
+        async def _(user_email: str) -> str:
+            json_data = await quart.request.json
+            
+            current_password = json_data['current_password']
+            new_password = json_data['new_password']
+            
+            try:
+                await self.ap.user_service.change_password(user_email, current_password, new_password)
+            except argon2.exceptions.VerifyMismatchError:
+                return self.http_status(400, -1, 'Current password is incorrect')
+            except ValueError as e:
+                return self.http_status(400, -1, str(e))
+            
+            return self.success(data={'user': user_email})
--- a/pkg/api/http/service/knowledge.py
+++ b/pkg/api/http/service/knowledge.py
@@ -78,7 +78,9 @@ class KnowledgeService:
        runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
        if runtime_kb is None:
            raise Exception('Knowledge base not found')
-        return [result.model_dump() for result in await runtime_kb.retrieve(query)]
+        return [
+            result.model_dump() for result in await runtime_kb.retrieve(query, runtime_kb.knowledge_base_entity.top_k)
+        ]

    async def get_files_by_knowledge_base(self, kb_uuid: str) -> list[dict]:
        """获取知识库文件"""
--- a/pkg/api/http/service/model.py
+++ b/pkg/api/http/service/model.py
@@ -101,7 +101,7 @@ class LLMModelsService:
            model=runtime_llm_model,
            messages=[llm_entities.Message(role='user', content='Hello, world!')],
            funcs=[],
-            extra_args={},
+            extra_args=model_data.get('extra_args', {}),
        )


--- a/pkg/api/http/service/pipeline.py
+++ b/pkg/api/http/service/pipeline.py
@@ -40,7 +40,7 @@ class PipelineService:

    async def get_pipelines(self, sort_by: str = 'created_at', sort_order: str = 'DESC') -> list[dict]:
        query = sqlalchemy.select(persistence_pipeline.LegacyPipeline)
-        
+
        if sort_by == 'created_at':
            if sort_order == 'DESC':
                query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.desc())
@@ -51,7 +51,7 @@ class PipelineService:
                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.desc())
            else:
                query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.asc())
-        
+
        result = await self.ap.persistence_mgr.execute_async(query)
        pipelines = result.all()
        return [
--- a/pkg/api/http/service/user.py
+++ b/pkg/api/http/service/user.py
@@ -82,3 +82,18 @@ class UserService:
        await self.ap.persistence_mgr.execute_async(
            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
        )
+
+    async def change_password(self, user_email: str, current_password: str, new_password: str) -> None:
+        ph = argon2.PasswordHasher()
+        
+        user_obj = await self.get_user_by_email(user_email)
+        if user_obj is None:
+            raise ValueError('User not found')
+        
+        ph.verify(user_obj.password, current_password)
+        
+        hashed_password = ph.hash(new_password)
+        
+        await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
+        )
--- a/pkg/core/entities.py
+++ b/pkg/core/entities.py
@@ -19,7 +19,7 @@ class LifecycleControlScope(enum.Enum):
    APPLICATION = 'application'
    PLATFORM = 'platform'
    PLUGIN = 'plugin'
-    PROVIDER = 'provider'  
+    PROVIDER = 'provider'


 class LauncherTypes(enum.Enum):
@@ -87,7 +87,9 @@ class Query(pydantic.BaseModel):
    """使用的函数，由前置处理器阶段设置"""

    resp_messages: (
-        typing.Optional[list[llm_entities.Message]] | typing.Optional[list[platform_message.MessageChain]]
+        typing.Optional[list[llm_entities.Message]]
+        | typing.Optional[list[platform_message.MessageChain]]
+        | typing.Optional[list[llm_entities.MessageChunk]]
    ) = []
    """由Process阶段生成的回复消息对象列表"""

--- a/pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py
+++ b/pkg/persistence/migrations/dbm005_pipeline_remove_cot_config.py
@@ -0,0 +1,38 @@
+from .. import migration
+
+import sqlalchemy
+
+from ...entity.persistence import pipeline as persistence_pipeline
+
+
+@migration.migration_class(5)
+class DBMigratePipelineRemoveCotConfig(migration.DBMigration):
+    """Pipeline remove cot config"""
+
+    async def upgrade(self):
+        """Upgrade"""
+        # read all pipelines
+        pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
+
+        for pipeline in pipelines:
+            serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
+
+            config = serialized_pipeline['config']
+
+            if 'remove-think' not in config['output']['misc']:
+                config['output']['misc']['remove-think'] = False
+
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.update(persistence_pipeline.LegacyPipeline)
+                .where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
+                .values(
+                    {
+                        'config': config,
+                        'for_version': self.ap.ver_mgr.get_current_version(),
+                    }
+                )
+            )
+
+    async def downgrade(self):
+        """Downgrade"""
+        pass
--- a/pkg/pipeline/cntfilter/cntfilter.py
+++ b/pkg/pipeline/cntfilter/cntfilter.py
@@ -67,7 +67,7 @@ class ContentFilterStage(stage.PipelineStage):
        if query.pipeline_config['safety']['content-filter']['scope'] == 'output-msg':
            return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
        if not message.strip():
-            return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)    
+            return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
        else:
            for filter in self.filter_chain:
                if filter_entities.EnableStage.PRE in filter.enable_stages:
--- a/pkg/pipeline/pipelinemgr.py
+++ b/pkg/pipeline/pipelinemgr.py
@@ -93,12 +93,20 @@ class RuntimePipeline:
                query.message_event, platform_events.GroupMessage
            ):
                result.user_notice.insert(0, platform_message.At(query.message_event.sender.id))
-
-            await query.adapter.reply_message(
-                message_source=query.message_event,
-                message=result.user_notice,
-                quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
-            )
+            if await query.adapter.is_stream_output_supported():
+                await query.adapter.reply_message_chunk(
+                    message_source=query.message_event,
+                    bot_message=query.resp_messages[-1],
+                    message=result.user_notice,
+                    quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
+                    is_final=[msg.is_final for msg in query.resp_messages][0]
+                )
+            else:
+                await query.adapter.reply_message(
+                    message_source=query.message_event,
+                    message=result.user_notice,
+                    quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
+                )
        if result.debug_notice:
            self.ap.logger.debug(result.debug_notice)
        if result.console_notice:
--- a/pkg/pipeline/process/handlers/chat.py
+++ b/pkg/pipeline/process/handlers/chat.py
@@ -1,5 +1,6 @@
 from __future__ import annotations

+import uuid
 import typing
 import traceback

@@ -22,11 +23,11 @@ class ChatMessageHandler(handler.MessageHandler):
        self,
        query: core_entities.Query,
    ) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
-        """Process"""
-        # Call API
-        #   generator
+        """处理"""
+        # 调API
+        #   生成器

-        # Trigger plugin event
+        # 触发插件事件
        event_class = (
            events.PersonNormalMessageReceived
            if query.launcher_type == core_entities.LauncherTypes.PERSON
@@ -46,7 +47,6 @@ class ChatMessageHandler(handler.MessageHandler):
        if event_ctx.is_prevented_default():
            if event_ctx.event.reply is not None:
                mc = platform_message.MessageChain(event_ctx.event.reply)
-
                query.resp_messages.append(mc)

                yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
@@ -54,10 +54,14 @@ class ChatMessageHandler(handler.MessageHandler):
                yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
        else:
            if event_ctx.event.alter is not None:
-                # if isinstance(event_ctx.event, str):  # Currently not considering multi-modal alter
+                # if isinstance(event_ctx.event, str):  # 现在暂时不考虑多模态alter
                query.user_message.content = event_ctx.event.alter

            text_length = 0
+            try:
+                is_stream = await query.adapter.is_stream_output_supported()
+            except AttributeError:
+                is_stream = False

            try:
                for r in runner_module.preregistered_runners:
@@ -65,22 +69,42 @@ class ChatMessageHandler(handler.MessageHandler):
                        runner = r(self.ap, query.pipeline_config)
                        break
                else:
-                    raise ValueError(f'Request runner not found: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                    raise ValueError(f'未找到请求运行器: {query.pipeline_config["ai"]["runner"]["runner"]}')
+                if is_stream:
+                    resp_message_id = uuid.uuid4()
+                    await query.adapter.create_message_card(str(resp_message_id), query.message_event)
+                    async for result in runner.run(query):
+                        result.resp_message_id = str(resp_message_id)
+                        if query.resp_messages:
+                            query.resp_messages.pop()
+                        if query.resp_message_chain:
+                            query.resp_message_chain.pop()

-                async for result in runner.run(query):
-                    query.resp_messages.append(result)
+                        query.resp_messages.append(result)
+                        self.ap.logger.info(f'对话({query.query_id})流式响应: {self.cut_str(result.readable_str())}')

-                    self.ap.logger.info(f'Response({query.query_id}): {self.cut_str(result.readable_str())}')
+                        if result.content is not None:
+                            text_length += len(result.content)

-                    if result.content is not None:
-                        text_length += len(result.content)
+                        yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

-                    yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
+                else:
+                    async for result in runner.run(query):
+                        query.resp_messages.append(result)
+
+                        self.ap.logger.info(f'对话({query.query_id})响应: {self.cut_str(result.readable_str())}')
+
+                        if result.content is not None:
+                            text_length += len(result.content)
+
+                        yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

                query.session.using_conversation.messages.append(query.user_message)
+
                query.session.using_conversation.messages.extend(query.resp_messages)
            except Exception as e:
-                self.ap.logger.error(f'Request failed({query.query_id}): {type(e).__name__} {str(e)}')
+                self.ap.logger.error(f'对话({query.query_id})请求失败: {type(e).__name__} {str(e)}')
+                traceback.print_exc()

                hide_exception_info = query.pipeline_config['output']['misc']['hide-exception']

@@ -93,4 +117,4 @@ class ChatMessageHandler(handler.MessageHandler):
                )
            finally:
                # TODO statistics
-                pass
+                pass
--- a/pkg/pipeline/respback/respback.py
+++ b/pkg/pipeline/respback/respback.py
@@ -7,6 +7,10 @@ import asyncio
 from ...platform.types import events as platform_events
 from ...platform.types import message as platform_message

+from ...provider import entities as llm_entities
+
+
+
 from .. import stage, entities
 from ...core import entities as core_entities

@@ -36,10 +40,22 @@ class SendResponseBackStage(stage.PipelineStage):

        quote_origin = query.pipeline_config['output']['misc']['quote-origin']

-        await query.adapter.reply_message(
-            message_source=query.message_event,
-            message=query.resp_message_chain[-1],
-            quote_origin=quote_origin,
-        )
+        has_chunks = any(isinstance(msg, llm_entities.MessageChunk) for msg in query.resp_messages)
+        # TODO 命令与流式的兼容性问题
+        if await query.adapter.is_stream_output_supported() and has_chunks:
+            is_final = [msg.is_final for msg in query.resp_messages][0]
+            await query.adapter.reply_message_chunk(
+                message_source=query.message_event,
+                bot_message=query.resp_messages[-1],
+                message=query.resp_message_chain[-1],
+                quote_origin=quote_origin,
+                is_final=is_final,
+            )
+        else:
+            await query.adapter.reply_message(
+                message_source=query.message_event,
+                message=query.resp_message_chain[-1],
+                quote_origin=quote_origin,
+            )

        return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
--- a/pkg/platform/adapter.py
+++ b/pkg/platform/adapter.py
@@ -61,14 +61,40 @@ class MessagePlatformAdapter(metaclass=abc.ABCMeta):
        """
        raise NotImplementedError

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message: dict,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        """回复消息（流式输出）
+        Args:
+            message_source (platform.types.MessageEvent): 消息源事件
+            message_id (int): 消息ID
+            message (platform.types.MessageChain): 消息链
+            quote_origin (bool, optional): 是否引用原消息. Defaults to False.
+            is_final (bool, optional): 流式是否结束. Defaults to False.
+        """
+        raise NotImplementedError
+
+    async def create_message_card(self, message_id: typing.Type[str, int], event: platform_events.MessageEvent) -> bool:
+        """创建卡片消息
+        Args:
+            message_id (str): 消息ID
+            event (platform_events.MessageEvent): 消息源事件
+        """
+        return False
+
    async def is_muted(self, group_id: int) -> bool:
        """获取账号是否在指定群被禁言"""
        raise NotImplementedError

    def register_listener(
        self,
-        event_type: typing.Type[platform_message.Event],
-        callback: typing.Callable[[platform_message.Event, MessagePlatformAdapter], None],
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[[platform_events.Event, MessagePlatformAdapter], None],
    ):
        """注册事件监听器

@@ -80,8 +106,8 @@ class MessagePlatformAdapter(metaclass=abc.ABCMeta):

    def unregister_listener(
        self,
-        event_type: typing.Type[platform_message.Event],
-        callback: typing.Callable[[platform_message.Event, MessagePlatformAdapter], None],
+        event_type: typing.Type[platform_events.Event],
+        callback: typing.Callable[[platform_events.Event, MessagePlatformAdapter], None],
    ):
        """注销事件监听器

@@ -95,6 +121,10 @@ class MessagePlatformAdapter(metaclass=abc.ABCMeta):
        """异步运行"""
        raise NotImplementedError

+    async def is_stream_output_supported(self) -> bool:
+        """是否支持流式输出"""
+        return False
+
    async def kill(self) -> bool:
        """关闭适配器

@@ -136,7 +166,7 @@ class EventConverter:
    """事件转换器基类"""

    @staticmethod
-    def yiri2target(event: typing.Type[platform_message.Event]):
+    def yiri2target(event: typing.Type[platform_events.Event]):
        """将源平台事件转换为目标平台事件

        Args:
@@ -148,7 +178,7 @@ class EventConverter:
        raise NotImplementedError

    @staticmethod
-    def target2yiri(event: typing.Any) -> platform_message.Event:
+    def target2yiri(event: typing.Any) -> platform_events.Event:
        """将目标平台事件的调用参数转换为源平台的事件参数对象

        Args:
--- a/pkg/platform/botmgr.py
+++ b/pkg/platform/botmgr.py
@@ -120,8 +120,10 @@ class RuntimeBot:
                if isinstance(e, asyncio.CancelledError):
                    self.task_context.set_current_action('Exited.')
                    return
+
+                traceback_str = traceback.format_exc()
                self.task_context.set_current_action('Exited with error.')
-                await self.logger.error(f'平台适配器运行出错:\n{e}\n{traceback.format_exc()}')
+                await self.logger.error(f'平台适配器运行出错:\n{e}\n{traceback_str}')

        self.task_wrapper = self.ap.task_mgr.create_task(
            exception_wrapper(),
--- a/pkg/platform/sources/aiocqhttp.py
+++ b/pkg/platform/sources/aiocqhttp.py
@@ -266,7 +266,7 @@ class AiocqhttpMessageConverter(adapter.MessageConverter):
                    await process_message_data(msg_data, reply_list)

                reply_msg = platform_message.Quote(
-                    message_id=msg.data['id'], sender_id=msg_datas['user_id'], origin=reply_list
+                    message_id=msg.data['id'], sender_id=msg_datas['sender']['user_id'], origin=reply_list
                )
                yiri_msg_list.append(reply_msg)

--- a/pkg/platform/sources/dingtalk.py
+++ b/pkg/platform/sources/dingtalk.py
@@ -1,3 +1,4 @@
+from re import S
 import traceback
 import typing
 from libs.dingtalk_api.dingtalkevent import DingTalkEvent
@@ -99,11 +100,15 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):
    message_converter: DingTalkMessageConverter = DingTalkMessageConverter()
    event_converter: DingTalkEventConverter = DingTalkEventConverter()
    config: dict
+    card_instance_id_dict: dict  # 回复卡片消息字典，key为消息id，value为回复卡片实例id，用于在流式消息时判断是否发送到指定卡片
+    seq: int  # 消息顺序，直接以seq作为标识

    def __init__(self, config: dict, ap: app.Application, logger: EventLogger):
        self.config = config
        self.ap = ap
        self.logger = logger
+        self.card_instance_id_dict = {}
+        # self.seq = 1
        required_keys = [
            'client_id',
            'client_secret',
@@ -139,6 +144,34 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):
        content, at = await DingTalkMessageConverter.yiri2target(message)
        await self.bot.send_message(content, incoming_message, at)

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        # event = await DingTalkEventConverter.yiri2target(
+        #     message_source,
+        # )
+        # incoming_message = event.incoming_message
+
+        # msg_id = incoming_message.message_id
+        message_id = bot_message.resp_message_id
+        msg_seq = bot_message.msg_sequence
+
+        if (msg_seq - 1) % 8 == 0 or is_final:
+
+            content, at = await DingTalkMessageConverter.yiri2target(message)
+
+            card_instance, card_instance_id = self.card_instance_id_dict[message_id]
+            # print(card_instance_id)
+            await self.bot.send_card_message(card_instance, card_instance_id, content, is_final)
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.card_instance_id_dict.pop(message_id)  # 消息回复结束之后删除卡片实例id
+
    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
        content = await DingTalkMessageConverter.yiri2target(message)
        if target_type == 'person':
@@ -146,6 +179,20 @@ class DingTalkAdapter(adapter.MessagePlatformAdapter):
        if target_type == 'group':
            await self.bot.send_proactive_message_to_group(target_id, content)

+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
+    async def create_message_card(self, message_id, event):
+        card_template_id = self.config['card_template_id']
+        incoming_message = event.source_platform_object.incoming_message
+        # message_id = incoming_message.message_id
+        card_instance, card_instance_id = await self.bot.create_and_card(card_template_id, incoming_message)
+        self.card_instance_id_dict[message_id] = (card_instance, card_instance_id)
+        return True
+
    def register_listener(
        self,
        event_type: typing.Type[platform_events.Event],
--- a/pkg/platform/sources/dingtalk.yaml
+++ b/pkg/platform/sources/dingtalk.yaml
@@ -46,6 +46,23 @@ spec:
      type: boolean
      required: false
      default: true
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用钉钉卡片流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of lark reply mode
+        zh_Hans: 如果启用，将使用钉钉卡片流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
+    - name: card_template_id
+      label:
+        en_US: card template id
+        zh_Hans: 卡片模板ID
+      type: string
+      required: true
+      default: "填写你的卡片template_id"
 execution:
  python:
    path: ./dingtalk.py
--- a/pkg/platform/sources/discord.py
+++ b/pkg/platform/sources/discord.py
@@ -8,7 +8,6 @@ import base64
 import uuid
 import os
 import datetime
-import io
 import asyncio
 from enum import Enum

@@ -21,9 +20,11 @@ from ..types import message as platform_message
 from ..types import events as platform_events
 from ..types import entities as platform_entities

+
 # 语音功能相关异常定义
 class VoiceConnectionError(Exception):
    """语音连接基础异常"""
+
    def __init__(self, message: str, error_code: str = None, guild_id: int = None):
        super().__init__(message)
        self.error_code = error_code
@@ -33,8 +34,9 @@ class VoiceConnectionError(Exception):

 class VoicePermissionError(VoiceConnectionError):
    """语音权限异常"""
+
    def __init__(self, message: str, missing_permissions: list = None, user_id: int = None, channel_id: int = None):
-        super().__init__(message, "PERMISSION_ERROR")
+        super().__init__(message, 'PERMISSION_ERROR')
        self.missing_permissions = missing_permissions or []
        self.user_id = user_id
        self.channel_id = channel_id
@@ -42,40 +44,42 @@ class VoicePermissionError(VoiceConnectionError):

 class VoiceNetworkError(VoiceConnectionError):
    """语音网络异常"""
+
    def __init__(self, message: str, retry_count: int = 0):
-        super().__init__(message, "NETWORK_ERROR")
+        super().__init__(message, 'NETWORK_ERROR')
        self.retry_count = retry_count
        self.last_attempt = datetime.datetime.now()


 class VoiceConnectionStatus(Enum):
    """语音连接状态枚举"""
-    IDLE = "idle"
-    CONNECTING = "connecting"
-    CONNECTED = "connected"
-    PLAYING = "playing"
-    RECONNECTING = "reconnecting"
-    FAILED = "failed"
+
+    IDLE = 'idle'
+    CONNECTING = 'connecting'
+    CONNECTED = 'connected'
+    PLAYING = 'playing'
+    RECONNECTING = 'reconnecting'
+    FAILED = 'failed'


 class VoiceConnectionInfo:
    """
    语音连接信息类
-    
+
    用于存储和管理单个语音连接的详细信息，包括连接状态、时间戳、
    频道信息等。提供连接信息的标准化数据结构。
-    
+
    @author: @ydzat
    @version: 1.0
    @since: 2025-07-04
    """
-    
+
    def __init__(self, guild_id: int, channel_id: int, channel_name: str = None):
        """
        初始化语音连接信息
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
            channel_id (int): 语音频道ID
@@ -83,28 +87,28 @@ class VoiceConnectionInfo:
        """
        self.guild_id = guild_id
        self.channel_id = channel_id
-        self.channel_name = channel_name or f"Channel-{channel_id}"
+        self.channel_name = channel_name or f'Channel-{channel_id}'
        self.connected = False
        self.connection_time: datetime.datetime = None
        self.last_activity = datetime.datetime.now()
        self.status = VoiceConnectionStatus.IDLE
        self.user_count = 0
        self.latency = 0.0
-        self.connection_health = "unknown"
+        self.connection_health = 'unknown'
        self.voice_client = None
-        
+
    def update_status(self, status: VoiceConnectionStatus):
        """
        更新连接状态
-        
+
        @author: @ydzat
-        
+
        Args:
            status (VoiceConnectionStatus): 新的连接状态
        """
        self.status = status
        self.last_activity = datetime.datetime.now()
-        
+
        if status == VoiceConnectionStatus.CONNECTED:
            self.connected = True
            if self.connection_time is None:
@@ -113,48 +117,48 @@ class VoiceConnectionInfo:
            self.connected = False
            self.connection_time = None
            self.voice_client = None
-    
+
    def to_dict(self) -> dict:
        """
        转换为字典格式
-        
+
        @author: @ydzat
-        
+
        Returns:
            dict: 连接信息的字典表示
        """
        return {
-            "guild_id": self.guild_id,
-            "channel_id": self.channel_id,
-            "channel_name": self.channel_name,
-            "connected": self.connected,
-            "connection_time": self.connection_time.isoformat() if self.connection_time else None,
-            "last_activity": self.last_activity.isoformat(),
-            "status": self.status.value,
-            "user_count": self.user_count,
-            "latency": self.latency,
-            "connection_health": self.connection_health
+            'guild_id': self.guild_id,
+            'channel_id': self.channel_id,
+            'channel_name': self.channel_name,
+            'connected': self.connected,
+            'connection_time': self.connection_time.isoformat() if self.connection_time else None,
+            'last_activity': self.last_activity.isoformat(),
+            'status': self.status.value,
+            'user_count': self.user_count,
+            'latency': self.latency,
+            'connection_health': self.connection_health,
        }


 class VoiceConnectionManager:
    """
    语音连接管理器
-    
+
    负责管理多个服务器的语音连接，提供连接建立、断开、状态查询等功能。
    采用单例模式确保全局只有一个连接管理器实例。
-    
+
    @author: @ydzat
    @version: 1.0
    @since: 2025-07-04
    """
-    
+
    def __init__(self, bot: discord.Client, logger: EventLogger):
        """
        初始化语音连接管理器
-        
+
        @author: @ydzat
-        
+
        Args:
            bot (discord.Client): Discord 客户端实例
            logger (EventLogger): 事件日志记录器
@@ -165,25 +169,24 @@ class VoiceConnectionManager:
        self._connection_lock = asyncio.Lock()
        self._cleanup_task = None
        self._monitoring_enabled = True
-        
-    async def join_voice_channel(self, guild_id: int, channel_id: int, 
-                                user_id: int = None) -> discord.VoiceClient:
+
+    async def join_voice_channel(self, guild_id: int, channel_id: int, user_id: int = None) -> discord.VoiceClient:
        """
        加入语音频道
-        
+
        验证用户权限和频道状态后，建立到指定语音频道的连接。
        支持连接复用和自动重连机制。
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
            channel_id (int): 语音频道ID
            user_id (int, optional): 请求用户ID，用于权限验证
-            
+
        Returns:
            discord.VoiceClient: 语音客户端实例
-            
+
        Raises:
            VoicePermissionError: 权限不足时抛出
            VoiceNetworkError: 网络连接失败时抛出
@@ -194,370 +197,353 @@ class VoiceConnectionManager:
                # 获取服务器和频道对象
                guild = self.bot.get_guild(guild_id)
                if not guild:
-                    raise VoiceConnectionError(
-                        f"无法找到服务器 {guild_id}",
-                        "GUILD_NOT_FOUND",
-                        guild_id
-                    )
-                
+                    raise VoiceConnectionError(f'无法找到服务器 {guild_id}', 'GUILD_NOT_FOUND', guild_id)
+
                channel = guild.get_channel(channel_id)
                if not channel or not isinstance(channel, discord.VoiceChannel):
-                    raise VoiceConnectionError(
-                        f"无法找到语音频道 {channel_id}",
-                        "CHANNEL_NOT_FOUND",
-                        guild_id
-                    )
-                
+                    raise VoiceConnectionError(f'无法找到语音频道 {channel_id}', 'CHANNEL_NOT_FOUND', guild_id)
+
                # 验证用户是否在语音频道中（如果提供了用户ID）
                if user_id:
                    await self._validate_user_in_channel(guild, channel, user_id)
-                
+
                # 验证机器人权限
                await self._validate_bot_permissions(channel)
-                
+
                # 检查是否已有连接
                if guild_id in self.connections:
                    existing_conn = self.connections[guild_id]
                    if existing_conn.connected and existing_conn.voice_client:
                        if existing_conn.channel_id == channel_id:
                            # 已连接到相同频道，返回现有连接
-                            await self.logger.info(f"复用现有语音连接: {guild.name} -> {channel.name}")
+                            await self.logger.info(f'复用现有语音连接: {guild.name} -> {channel.name}')
                            return existing_conn.voice_client
                        else:
                            # 连接到不同频道，先断开旧连接
                            await self._disconnect_internal(guild_id)
-                
+
                # 建立新连接
                voice_client = await channel.connect()
-                
+
                # 更新连接信息
                conn_info = VoiceConnectionInfo(guild_id, channel_id, channel.name)
                conn_info.voice_client = voice_client
                conn_info.update_status(VoiceConnectionStatus.CONNECTED)
                conn_info.user_count = len(channel.members)
                self.connections[guild_id] = conn_info
-                
-                await self.logger.info(f"成功连接到语音频道: {guild.name} -> {channel.name}")
+
+                await self.logger.info(f'成功连接到语音频道: {guild.name} -> {channel.name}')
                return voice_client
-                
+
            except discord.ClientException as e:
-                raise VoiceNetworkError(f"Discord 客户端错误: {str(e)}")
+                raise VoiceNetworkError(f'Discord 客户端错误: {str(e)}')
            except discord.opus.OpusNotLoaded as e:
-                raise VoiceConnectionError(f"Opus 编码器未加载: {str(e)}", "OPUS_NOT_LOADED", guild_id)
+                raise VoiceConnectionError(f'Opus 编码器未加载: {str(e)}', 'OPUS_NOT_LOADED', guild_id)
            except Exception as e:
-                await self.logger.error(f"连接语音频道时发生未知错误: {str(e)}")
-                raise VoiceConnectionError(f"连接失败: {str(e)}", "UNKNOWN_ERROR", guild_id)
-    
+                await self.logger.error(f'连接语音频道时发生未知错误: {str(e)}')
+                raise VoiceConnectionError(f'连接失败: {str(e)}', 'UNKNOWN_ERROR', guild_id)
+
    async def leave_voice_channel(self, guild_id: int) -> bool:
        """
        离开语音频道
-        
+
        断开指定服务器的语音连接，清理相关资源和状态信息。
        确保音频播放停止后再断开连接。
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
-            
+
        Returns:
            bool: 断开是否成功
        """
        async with self._connection_lock:
            return await self._disconnect_internal(guild_id)
-    
+
    async def _disconnect_internal(self, guild_id: int) -> bool:
        """
        内部断开连接方法
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
-            
+
        Returns:
            bool: 断开是否成功
        """
        if guild_id not in self.connections:
            return True
-        
+
        conn_info = self.connections[guild_id]
-        
+
        try:
            if conn_info.voice_client and conn_info.voice_client.is_connected():
                # 停止当前播放
                if conn_info.voice_client.is_playing():
                    conn_info.voice_client.stop()
-                
+
                # 等待播放完全停止
                await asyncio.sleep(0.1)
-                
+
                # 断开连接
                await conn_info.voice_client.disconnect()
-                
+
            conn_info.update_status(VoiceConnectionStatus.IDLE)
            del self.connections[guild_id]
-            
-            await self.logger.info(f"已断开语音连接: Guild {guild_id}")
+
+            await self.logger.info(f'已断开语音连接: Guild {guild_id}')
            return True
-            
+
        except Exception as e:
-            await self.logger.error(f"断开语音连接时发生错误: {str(e)}")
+            await self.logger.error(f'断开语音连接时发生错误: {str(e)}')
            # 即使出错也要清理连接记录
            conn_info.update_status(VoiceConnectionStatus.FAILED)
            if guild_id in self.connections:
                del self.connections[guild_id]
            return False
-    
+
    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
        """
        获取语音客户端
-        
+
        返回指定服务器的语音客户端实例，如果未连接则返回 None。
        会验证连接的有效性，自动清理无效连接。
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
-            
+
        Returns:
            Optional[discord.VoiceClient]: 语音客户端实例或 None
        """
        if guild_id not in self.connections:
            return None
-        
+
        conn_info = self.connections[guild_id]
-        
+
        # 验证连接是否仍然有效
        if conn_info.voice_client and not conn_info.voice_client.is_connected():
            # 连接已失效，清理状态
            await self._disconnect_internal(guild_id)
            return None
-        
+
        return conn_info.voice_client if conn_info.connected else None
-    
+
    async def is_connected_to_voice(self, guild_id: int) -> bool:
        """
        检查是否连接到语音频道
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
-            
+
        Returns:
            bool: 是否已连接
        """
        if guild_id not in self.connections:
            return False
-        
+
        conn_info = self.connections[guild_id]
-        
+
        # 检查实际连接状态
        if conn_info.voice_client and not conn_info.voice_client.is_connected():
            # 连接已失效，清理状态
            await self._disconnect_internal(guild_id)
            return False
-        
+
        return conn_info.connected
-    
+
    async def get_connection_status(self, guild_id: int) -> typing.Optional[dict]:
        """
        获取连接状态信息
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
-            
+
        Returns:
            Optional[dict]: 连接状态信息字典或 None
        """
        if guild_id not in self.connections:
            return None
-        
+
        conn_info = self.connections[guild_id]
-        
+
        # 更新实时信息
        if conn_info.voice_client and conn_info.voice_client.is_connected():
            conn_info.latency = conn_info.voice_client.latency * 1000  # 转换为毫秒
-            conn_info.connection_health = "good" if conn_info.latency < 100 else "poor"
-            
+            conn_info.connection_health = 'good' if conn_info.latency < 100 else 'poor'
+
            # 更新频道用户数
            guild = self.bot.get_guild(guild_id)
            if guild:
                channel = guild.get_channel(conn_info.channel_id)
                if channel and isinstance(channel, discord.VoiceChannel):
                    conn_info.user_count = len(channel.members)
-        
+
        return conn_info.to_dict()
-    
+
    async def list_active_connections(self) -> typing.List[dict]:
        """
        列出所有活跃连接
-        
+
        @author: @ydzat
-        
+
        Returns:
            List[dict]: 活跃连接列表
        """
        active_connections = []
-        
+
        for guild_id, conn_info in self.connections.items():
            if conn_info.connected:
                status = await self.get_connection_status(guild_id)
                if status:
                    active_connections.append(status)
-        
+
        return active_connections
-    
+
    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
        """
        获取语音频道信息
-        
+
        @author: @ydzat
-        
+
        Args:
            guild_id (int): 服务器ID
            channel_id (int): 频道ID
-            
+
        Returns:
            Optional[dict]: 频道信息字典或 None
        """
        guild = self.bot.get_guild(guild_id)
        if not guild:
            return None
-        
+
        channel = guild.get_channel(channel_id)
        if not channel or not isinstance(channel, discord.VoiceChannel):
            return None
-        
+
        # 获取用户信息
        users = []
        for member in channel.members:
-            users.append({
-                "id": member.id,
-                "name": member.display_name,
-                "status": str(member.status),
-                "is_bot": member.bot
-            })
-        
+            users.append(
+                {'id': member.id, 'name': member.display_name, 'status': str(member.status), 'is_bot': member.bot}
+            )
+
        # 获取权限信息
        bot_member = guild.me
        permissions = channel.permissions_for(bot_member)
-        
+
        return {
-            "channel_id": channel_id,
-            "channel_name": channel.name,
-            "guild_id": guild_id,
-            "guild_name": guild.name,
-            "user_limit": channel.user_limit,
-            "current_users": users,
-            "user_count": len(users),
-            "bitrate": channel.bitrate,
-            "permissions": {
-                "connect": permissions.connect,
-                "speak": permissions.speak,
-                "use_voice_activation": permissions.use_voice_activation,
-                "priority_speaker": permissions.priority_speaker
-            }
+            'channel_id': channel_id,
+            'channel_name': channel.name,
+            'guild_id': guild_id,
+            'guild_name': guild.name,
+            'user_limit': channel.user_limit,
+            'current_users': users,
+            'user_count': len(users),
+            'bitrate': channel.bitrate,
+            'permissions': {
+                'connect': permissions.connect,
+                'speak': permissions.speak,
+                'use_voice_activation': permissions.use_voice_activation,
+                'priority_speaker': permissions.priority_speaker,
+            },
        }
-    
-    async def _validate_user_in_channel(self, guild: discord.Guild, 
-                                       channel: discord.VoiceChannel, user_id: int):
+
+    async def _validate_user_in_channel(self, guild: discord.Guild, channel: discord.VoiceChannel, user_id: int):
        """
        验证用户是否在语音频道中
-        
+
        @author: @ydzat
-        
+
        Args:
            guild: Discord 服务器对象
            channel: 语音频道对象
            user_id: 用户ID
-            
+
        Raises:
            VoicePermissionError: 用户不在频道中时抛出
        """
        member = guild.get_member(user_id)
        if not member:
-            raise VoicePermissionError(
-                f"无法找到用户 {user_id}",
-                ["member_not_found"],
-                user_id,
-                channel.id
-            )
-        
+            raise VoicePermissionError(f'无法找到用户 {user_id}', ['member_not_found'], user_id, channel.id)
+
        if not member.voice or member.voice.channel != channel:
            raise VoicePermissionError(
-                f"用户 {member.display_name} 不在语音频道 {channel.name} 中",
-                ["user_not_in_channel"],
+                f'用户 {member.display_name} 不在语音频道 {channel.name} 中',
+                ['user_not_in_channel'],
                user_id,
-                channel.id
+                channel.id,
            )
-    
+
    async def _validate_bot_permissions(self, channel: discord.VoiceChannel):
        """
        验证机器人权限
-        
+
        @author: @ydzat
-        
+
        Args:
            channel: 语音频道对象
-            
+
        Raises:
            VoicePermissionError: 权限不足时抛出
        """
        bot_member = channel.guild.me
        permissions = channel.permissions_for(bot_member)
-        
+
        missing_permissions = []
-        
+
        if not permissions.connect:
-            missing_permissions.append("connect")
+            missing_permissions.append('connect')
        if not permissions.speak:
-            missing_permissions.append("speak")
-        
+            missing_permissions.append('speak')
+
        if missing_permissions:
            raise VoicePermissionError(
-                f"机器人在频道 {channel.name} 中缺少权限: {', '.join(missing_permissions)}",
+                f'机器人在频道 {channel.name} 中缺少权限: {", ".join(missing_permissions)}',
                missing_permissions,
-                channel_id=channel.id
+                channel_id=channel.id,
            )
-    
+
    async def cleanup_inactive_connections(self):
        """
        清理无效连接
-        
+
        定期检查并清理已断开或无效的语音连接，释放资源。
-        
+
        @author: @ydzat
        """
        cleanup_guilds = []
-        
+
        for guild_id, conn_info in self.connections.items():
            if not conn_info.voice_client or not conn_info.voice_client.is_connected():
                cleanup_guilds.append(guild_id)
-        
+
        for guild_id in cleanup_guilds:
            await self._disconnect_internal(guild_id)
-        
+
        if cleanup_guilds:
-            await self.logger.info(f"清理了 {len(cleanup_guilds)} 个无效的语音连接")
-    
+            await self.logger.info(f'清理了 {len(cleanup_guilds)} 个无效的语音连接')
+
    async def start_monitoring(self):
        """
        开始连接监控
-        
+
        @author: @ydzat
        """
        if self._cleanup_task is None and self._monitoring_enabled:
            self._cleanup_task = asyncio.create_task(self._monitoring_loop())
-    
+
    async def stop_monitoring(self):
        """
        停止连接监控
-        
+
        @author: @ydzat
        """
        self._monitoring_enabled = False
@@ -568,11 +554,11 @@ class VoiceConnectionManager:
            except asyncio.CancelledError:
                pass
            self._cleanup_task = None
-    
+
    async def _monitoring_loop(self):
        """
        监控循环
-        
+
        @author: @ydzat
        """
        try:
@@ -581,18 +567,18 @@ class VoiceConnectionManager:
                await self.cleanup_inactive_connections()
        except asyncio.CancelledError:
            pass
-    
+
    async def disconnect_all(self):
        """
        断开所有连接
-        
+
        @author: @ydzat
        """
        async with self._connection_lock:
            guild_ids = list(self.connections.keys())
            for guild_id in guild_ids:
                await self._disconnect_internal(guild_id)
-        
+
        await self.stop_monitoring()


@@ -815,7 +801,7 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
        self.logger = logger

        self.bot_account_id = self.config['client_id']
-        
+
        # 初始化语音连接管理器
        self.voice_manager: VoiceConnectionManager = None

@@ -838,163 +824,162 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
            args['proxy'] = os.getenv('http_proxy')

        self.bot = MyClient(intents=intents, **args)
-    
+
    # Voice functionality methods
-    async def join_voice_channel(self, guild_id: int, channel_id: int, 
-                                user_id: int = None) -> discord.VoiceClient:
+    async def join_voice_channel(self, guild_id: int, channel_id: int, user_id: int = None) -> discord.VoiceClient:
        """
        加入语音频道
-        
+
        为指定服务器的语音频道建立连接，支持用户权限验证和连接复用。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
            channel_id (int): 语音频道ID
            user_id (int, optional): 请求用户ID，用于权限验证
-            
+
        Returns:
            discord.VoiceClient: 语音客户端实例
-            
+
        Raises:
            VoicePermissionError: 权限不足
            VoiceNetworkError: 网络连接失败
            VoiceConnectionError: 其他连接错误
        """
        if not self.voice_manager:
-            raise VoiceConnectionError("语音管理器未初始化", "MANAGER_NOT_READY")
-        
+            raise VoiceConnectionError('语音管理器未初始化', 'MANAGER_NOT_READY')
+
        return await self.voice_manager.join_voice_channel(guild_id, channel_id, user_id)
-    
+
    async def leave_voice_channel(self, guild_id: int) -> bool:
        """
        离开语音频道
-        
+
        断开指定服务器的语音连接，清理相关资源。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
-            
+
        Returns:
            bool: 是否成功断开连接
        """
        if not self.voice_manager:
            return False
-        
+
        return await self.voice_manager.leave_voice_channel(guild_id)
-    
+
    async def get_voice_client(self, guild_id: int) -> typing.Optional[discord.VoiceClient]:
        """
        获取语音客户端
-        
+
        返回指定服务器的语音客户端实例，用于音频播放控制。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
-            
+
        Returns:
            Optional[discord.VoiceClient]: 语音客户端实例或 None
        """
        if not self.voice_manager:
            return None
-        
+
        return await self.voice_manager.get_voice_client(guild_id)
-    
+
    async def is_connected_to_voice(self, guild_id: int) -> bool:
        """
        检查语音连接状态
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
-            
+
        Returns:
            bool: 是否已连接到语音频道
        """
        if not self.voice_manager:
            return False
-        
+
        return await self.voice_manager.is_connected_to_voice(guild_id)
-    
+
    async def get_voice_connection_status(self, guild_id: int) -> typing.Optional[dict]:
        """
        获取语音连接详细状态
-        
+
        返回包含连接时间、延迟、用户数等详细信息的状态字典。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
-            
+
        Returns:
            Optional[dict]: 连接状态信息或 None
        """
        if not self.voice_manager:
            return None
-        
+
        return await self.voice_manager.get_connection_status(guild_id)
-    
+
    async def list_active_voice_connections(self) -> typing.List[dict]:
        """
        列出所有活跃的语音连接
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Returns:
            List[dict]: 活跃语音连接列表
        """
        if not self.voice_manager:
            return []
-        
+
        return await self.voice_manager.list_active_connections()
-    
+
    async def get_voice_channel_info(self, guild_id: int, channel_id: int) -> typing.Optional[dict]:
        """
        获取语音频道详细信息
-        
+
        包括频道名称、用户列表、权限信息等。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
-        
+
        Args:
            guild_id (int): Discord 服务器ID
            channel_id (int): 语音频道ID
-            
+
        Returns:
            Optional[dict]: 频道信息字典或 None
        """
        if not self.voice_manager:
            return None
-        
+
        return await self.voice_manager.get_voice_channel_info(guild_id, channel_id)
-    
+
    async def cleanup_voice_connections(self):
        """
        清理无效的语音连接
-        
+
        手动触发语音连接清理，移除已断开或无效的连接。
-        
+
        @author: @ydzat
        @version: 1.0
        @since: 2025-07-04
@@ -1069,30 +1054,29 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
    async def run_async(self):
        """
        启动 Discord 适配器
-        
+
        初始化语音管理器并启动 Discord 客户端连接。
-        
+
        @author: @ydzat (修改)
        """
        async with self.bot:
            # 初始化语音管理器
            self.voice_manager = VoiceConnectionManager(self.bot, self.logger)
            await self.voice_manager.start_monitoring()
-            
-            await self.logger.info("Discord 适配器语音功能已启用")
+
+            await self.logger.info('Discord 适配器语音功能已启用')
            await self.bot.start(self.config['token'], reconnect=True)

    async def kill(self) -> bool:
        """
        关闭 Discord 适配器
-        
+
        清理语音连接并关闭 Discord 客户端。
-        
+
        @author: @ydzat (修改)
        """
        if self.voice_manager:
            await self.voice_manager.disconnect_all()
-        
+
        await self.bot.close()
        return True
-
--- a/pkg/platform/sources/lark.py
+++ b/pkg/platform/sources/lark.py
@@ -17,6 +17,7 @@ import aiohttp
 import lark_oapi.ws.exception
 import quart
 from lark_oapi.api.im.v1 import *
+from lark_oapi.api.cardkit.v1 import *

 from .. import adapter
 from ...core import app
@@ -320,6 +321,10 @@ class LarkEventConverter(adapter.EventConverter):
            )


+CARD_ID_CACHE_SIZE = 500
+CARD_ID_CACHE_MAX_LIFETIME = 20 * 60  # 20分钟
+
+
 class LarkAdapter(adapter.MessagePlatformAdapter):
    bot: lark_oapi.ws.Client
    api_client: lark_oapi.Client
@@ -339,12 +344,20 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
    quart_app: quart.Quart
    ap: app.Application

+
+    card_id_dict: dict[str, str]  # 消息id到卡片id的映射，便于创建卡片后的发送消息到指定卡片
+
+    seq: int  # 用于在发送卡片消息中识别消息顺序，直接以seq作为标识
+
    def __init__(self, config: dict, ap: app.Application, logger: EventLogger):
        self.config = config
        self.ap = ap
        self.logger = logger
        self.quart_app = quart.Quart(__name__)
        self.listeners = {}
+        self.card_id_dict = {}
+        self.seq = 1
+

        @self.quart_app.route('/lark/callback', methods=['POST'])
        async def lark_callback():
@@ -409,6 +422,216 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
    async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
        pass

+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
+    async def create_card_id(self, message_id):
+        try:
+            self.ap.logger.debug('飞书支持stream输出,创建卡片......')
+
+            card_data = {"schema": "2.0", "config": {"update_multi": True, "streaming_mode": True,
+                                                     "streaming_config": {"print_step": {"default": 1},
+                                                                          "print_frequency_ms": {"default": 70},
+                                                                          "print_strategy": "fast"}},
+                         "body": {"direction": "vertical", "padding": "12px 12px 12px 12px", "elements": [{"tag": "div",
+                                                                                                           "text": {
+                                                                                                               "tag": "plain_text",
+                                                                                                               "content": "LangBot",
+                                                                                                               "text_size": "normal",
+                                                                                                               "text_align": "left",
+                                                                                                               "text_color": "default"},
+                                                                                                           "icon": {
+                                                                                                               "tag": "custom_icon",
+                                                                                                               "img_key": "img_v3_02p3_05c65d5d-9bad-440a-a2fb-c89571bfd5bg"}},
+                                                                                                          {
+                                                                                                              "tag": "markdown",
+                                                                                                              "content": "",
+                                                                                                              "text_align": "left",
+                                                                                                              "text_size": "normal",
+                                                                                                              "margin": "0px 0px 0px 0px",
+                                                                                                              "element_id": "streaming_txt"},
+                                                                                                          {
+                                                                                                              "tag": "markdown",
+                                                                                                              "content": "",
+                                                                                                              "text_align": "left",
+                                                                                                              "text_size": "normal",
+                                                                                                              "margin": "0px 0px 0px 0px"},
+                                                                                                          {
+                                                                                                              "tag": "column_set",
+                                                                                                              "horizontal_spacing": "8px",
+                                                                                                              "horizontal_align": "left",
+                                                                                                              "columns": [
+                                                                                                                  {
+                                                                                                                      "tag": "column",
+                                                                                                                      "width": "weighted",
+                                                                                                                      "elements": [
+                                                                                                                          {
+                                                                                                                              "tag": "markdown",
+                                                                                                                              "content": "",
+                                                                                                                              "text_align": "left",
+                                                                                                                              "text_size": "normal",
+                                                                                                                              "margin": "0px 0px 0px 0px"},
+                                                                                                                          {
+                                                                                                                              "tag": "markdown",
+                                                                                                                              "content": "",
+                                                                                                                              "text_align": "left",
+                                                                                                                              "text_size": "normal",
+                                                                                                                              "margin": "0px 0px 0px 0px"},
+                                                                                                                          {
+                                                                                                                              "tag": "markdown",
+                                                                                                                              "content": "",
+                                                                                                                              "text_align": "left",
+                                                                                                                              "text_size": "normal",
+                                                                                                                              "margin": "0px 0px 0px 0px"}],
+                                                                                                                      "padding": "0px 0px 0px 0px",
+                                                                                                                      "direction": "vertical",
+                                                                                                                      "horizontal_spacing": "8px",
+                                                                                                                      "vertical_spacing": "2px",
+                                                                                                                      "horizontal_align": "left",
+                                                                                                                      "vertical_align": "top",
+                                                                                                                      "margin": "0px 0px 0px 0px",
+                                                                                                                      "weight": 1}],
+                                                                                                              "margin": "0px 0px 0px 0px"},
+                                                                                                          {"tag": "hr",
+                                                                                                           "margin": "0px 0px 0px 0px"},
+                                                                                                          {
+                                                                                                              "tag": "column_set",
+                                                                                                              "horizontal_spacing": "12px",
+                                                                                                              "horizontal_align": "right",
+                                                                                                              "columns": [
+                                                                                                                  {
+                                                                                                                      "tag": "column",
+                                                                                                                      "width": "weighted",
+                                                                                                                      "elements": [
+                                                                                                                          {
+                                                                                                                              "tag": "markdown",
+                                                                                                                              "content": "<font color=\"grey-600\">以上内容由 AI 生成，仅供参考。更多详细、准确信息可点击引用链接查看</font>",
+                                                                                                                              "text_align": "left",
+                                                                                                                              "text_size": "notation",
+                                                                                                                              "margin": "4px 0px 0px 0px",
+                                                                                                                              "icon": {
+                                                                                                                                  "tag": "standard_icon",
+                                                                                                                                  "token": "robot_outlined",
+                                                                                                                                  "color": "grey"}}],
+                                                                                                                      "padding": "0px 0px 0px 0px",
+                                                                                                                      "direction": "vertical",
+                                                                                                                      "horizontal_spacing": "8px",
+                                                                                                                      "vertical_spacing": "8px",
+                                                                                                                      "horizontal_align": "left",
+                                                                                                                      "vertical_align": "top",
+                                                                                                                      "margin": "0px 0px 0px 0px",
+                                                                                                                      "weight": 1},
+                                                                                                                  {
+                                                                                                                      "tag": "column",
+                                                                                                                      "width": "20px",
+                                                                                                                      "elements": [
+                                                                                                                          {
+                                                                                                                              "tag": "button",
+                                                                                                                              "text": {
+                                                                                                                                  "tag": "plain_text",
+                                                                                                                                  "content": ""},
+                                                                                                                              "type": "text",
+                                                                                                                              "width": "fill",
+                                                                                                                              "size": "medium",
+                                                                                                                              "icon": {
+                                                                                                                                  "tag": "standard_icon",
+                                                                                                                                  "token": "thumbsup_outlined"},
+                                                                                                                              "hover_tips": {
+                                                                                                                                  "tag": "plain_text",
+                                                                                                                                  "content": "有帮助"},
+                                                                                                                              "margin": "0px 0px 0px 0px"}],
+                                                                                                                      "padding": "0px 0px 0px 0px",
+                                                                                                                      "direction": "vertical",
+                                                                                                                      "horizontal_spacing": "8px",
+                                                                                                                      "vertical_spacing": "8px",
+                                                                                                                      "horizontal_align": "left",
+                                                                                                                      "vertical_align": "top",
+                                                                                                                      "margin": "0px 0px 0px 0px"},
+                                                                                                                  {
+                                                                                                                      "tag": "column",
+                                                                                                                      "width": "30px",
+                                                                                                                      "elements": [
+                                                                                                                          {
+                                                                                                                              "tag": "button",
+                                                                                                                              "text": {
+                                                                                                                                  "tag": "plain_text",
+                                                                                                                                  "content": ""},
+                                                                                                                              "type": "text",
+                                                                                                                              "width": "default",
+                                                                                                                              "size": "medium",
+                                                                                                                              "icon": {
+                                                                                                                                  "tag": "standard_icon",
+                                                                                                                                  "token": "thumbdown_outlined"},
+                                                                                                                              "hover_tips": {
+                                                                                                                                  "tag": "plain_text",
+                                                                                                                                  "content": "无帮助"},
+                                                                                                                              "margin": "0px 0px 0px 0px"}],
+                                                                                                                      "padding": "0px 0px 0px 0px",
+                                                                                                                      "vertical_spacing": "8px",
+                                                                                                                      "horizontal_align": "left",
+                                                                                                                      "vertical_align": "top",
+                                                                                                                      "margin": "0px 0px 0px 0px"}],
+                                                                                                              "margin": "0px 0px 4px 0px"}]}}
+            # delay / fast 创建卡片模板，delay 延迟打印，fast 实时打印，可以自定义更好看的消息模板
+
+            request: CreateCardRequest = (
+                CreateCardRequest.builder()
+                .request_body(CreateCardRequestBody.builder().type('card_json').data(json.dumps(card_data)).build())
+                .build()
+            )
+
+            # 发起请求
+            response: CreateCardResponse = self.api_client.cardkit.v1.card.create(request)
+
+            # 处理失败返回
+            if not response.success():
+                raise Exception(
+                    f'client.cardkit.v1.card.create failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+                )
+
+            self.ap.logger.debug(f'飞书卡片创建成功,卡片ID: {response.data.card_id}')
+            self.card_id_dict[message_id] = response.data.card_id
+
+            card_id = response.data.card_id
+            return card_id
+
+        except Exception as e:
+            self.ap.logger.error(f'飞书卡片创建失败,错误信息: {e}')
+
+    async def create_message_card(self, message_id, event) -> str:
+        """
+        创建卡片消息。
+        使用卡片消息是因为普通消息更新次数有限制，而大模型流式返回结果可能很多而超过限制，而飞书卡片没有这个限制（api免费次数有限）
+        """
+        # message_id = event.message_chain.message_id
+
+        card_id = await self.create_card_id(message_id)
+        content = {
+            'type': 'card',
+            'data': {'card_id': card_id, 'template_variable': {'content': 'Thinking...'}},
+        }   # 当收到消息时发送消息模板，可添加模板变量，详情查看飞书中接口文档
+        request: ReplyMessageRequest = (
+            ReplyMessageRequest.builder()
+            .message_id(event.message_chain.message_id)
+            .request_body(
+                ReplyMessageRequestBody.builder().content(json.dumps(content)).msg_type('interactive').build()
+            )
+            .build()
+        )
+
+        # 发起请求
+        response: ReplyMessageResponse = await self.api_client.im.v1.message.areply(request)
+
+        # 处理失败返回
+        if not response.success():
+            raise Exception(
+                f'client.im.v1.message.reply failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+            )
+        return True
+
    async def reply_message(
        self,
        message_source: platform_events.MessageEvent,
@@ -447,6 +670,64 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
                f'client.im.v1.message.reply failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
            )

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        """
+        回复消息变成更新卡片消息
+        """
+        # self.seq += 1
+        message_id = bot_message.resp_message_id
+        msg_seq = bot_message.msg_sequence
+        if msg_seq % 8 == 0 or is_final:
+
+            lark_message = await self.message_converter.yiri2target(message, self.api_client)
+
+
+            text_message = ''
+            for ele in lark_message[0]:
+                if ele['tag'] == 'text':
+                    text_message += ele['text']
+                elif ele['tag'] == 'md':
+                    text_message += ele['text']
+
+            # content = {
+            #     'type': 'card_json',
+            #     'data': {'card_id': self.card_id_dict[message_id], 'elements': {'content': text_message}},
+            # }
+
+            request: ContentCardElementRequest = (
+                ContentCardElementRequest.builder()
+                .card_id(self.card_id_dict[message_id])
+                .element_id('streaming_txt')
+                .request_body(
+                    ContentCardElementRequestBody.builder()
+                    # .uuid("a0d69e20-1dd1-458b-k525-dfeca4015204")
+                    .content(text_message)
+                    .sequence(msg_seq)
+                    .build()
+                )
+                .build()
+            )
+
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.card_id_dict.pop(message_id)  # 清理已经使用过的卡片
+            # 发起请求
+            response: ContentCardElementResponse = self.api_client.cardkit.v1.card_element.content(request)
+
+            # 处理失败返回
+            if not response.success():
+                raise Exception(
+                    f'client.im.v1.message.patch failed, code: {response.code}, msg: {response.msg}, log_id: {response.get_log_id()}, resp: \n{json.dumps(json.loads(response.raw.content), indent=4, ensure_ascii=False)}'
+                )
+                return
+
    async def is_muted(self, group_id: int) -> bool:
        return False

@@ -492,4 +773,9 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
            )

    async def kill(self) -> bool:
-        return False
+        # 需要断开连接，不然旧的连接会继续运行，导致飞书消息来时会随机选择一个连接
+        # 断开时lark.ws.Client的_receive_message_loop会打印error日志: receive message loop exit。然后进行重连，
+        # 所以要设置_auto_reconnect=False,让其不重连。
+        self.bot._auto_reconnect = False
+        await self.bot._disconnect()
+        return False
--- a/pkg/platform/sources/lark.yaml
+++ b/pkg/platform/sources/lark.yaml
@@ -65,6 +65,16 @@ spec:
      type: string
      required: true
      default: ""
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用飞书流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of lark reply mode
+        zh_Hans: 如果启用，将使用飞书流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
 execution:
  python:
    path: ./lark.py
--- a/pkg/platform/sources/qqbotpy.py
+++ b/pkg/platform/sources/qqbotpy.py
@@ -501,7 +501,7 @@ class OfficialAdapter(adapter_model.MessagePlatformAdapter):
            for event_handler in event_handler_mapping[event_type]:
                setattr(self.bot, event_handler, wrapper)
        except Exception as e:
-            self.logger.error(f"Error in qqbotpy callback: {traceback.format_exc()}")
+            self.logger.error(f'Error in qqbotpy callback: {traceback.format_exc()}')
            raise e

    def unregister_listener(
--- a/pkg/platform/sources/telegram.py
+++ b/pkg/platform/sources/telegram.py
@@ -1,5 +1,6 @@
 from __future__ import annotations

+
 import telegram
 import telegram.ext
 from telegram import Update
@@ -143,6 +144,10 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
    config: dict
    ap: app.Application

+    msg_stream_id: dict  # 流式消息id字典，key为流式消息id，value为首次消息源id，用于在流式消息时判断编辑那条消息
+
+    seq: int  # 消息中识别消息顺序，直接以seq作为标识
+
    listeners: typing.Dict[
        typing.Type[platform_events.Event],
        typing.Callable[[platform_events.Event, adapter.MessagePlatformAdapter], None],
@@ -152,6 +157,8 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
        self.config = config
        self.ap = ap
        self.logger = logger
+        self.msg_stream_id = {}
+        # self.seq = 1

        async def telegram_callback(update: Update, context: ContextTypes.DEFAULT_TYPE):
            if update.message.from_user.is_bot:
@@ -160,6 +167,7 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
            try:
                lb_event = await self.event_converter.target2yiri(update, self.bot, self.bot_account_id)
                await self.listeners[type(lb_event)](lb_event, self)
+                await self.is_stream_output_supported()
            except Exception:
                await self.logger.error(f'Error in telegram callback: {traceback.format_exc()}')

@@ -200,6 +208,70 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):

        await self.bot.send_message(**args)

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ):
+        msg_seq = bot_message.msg_sequence
+        if (msg_seq - 1) % 8 == 0 or is_final:
+            assert isinstance(message_source.source_platform_object, Update)
+            components = await TelegramMessageConverter.yiri2target(message, self.bot)
+            args = {}
+            message_id = message_source.source_platform_object.message.id
+            if quote_origin:
+                args['reply_to_message_id'] = message_source.source_platform_object.message.id
+
+            component = components[0]
+            if message_id not in self.msg_stream_id:  # 当消息回复第一次时，发送新消息
+                # time.sleep(0.6)
+                if component['type'] == 'text':
+                    if self.config['markdown_card'] is True:
+                        content = telegramify_markdown.markdownify(
+                            content=component['text'],
+                        )
+                    else:
+                        content = component['text']
+                    args = {
+                        'chat_id': message_source.source_platform_object.effective_chat.id,
+                        'text': content,
+                    }
+                    if self.config['markdown_card'] is True:
+                        args['parse_mode'] = 'MarkdownV2'
+
+                send_msg = await self.bot.send_message(**args)
+                send_msg_id = send_msg.message_id
+                self.msg_stream_id[message_id] = send_msg_id
+            else:  # 存在消息的时候直接编辑消息1
+                if component['type'] == 'text':
+                    if self.config['markdown_card'] is True:
+                        content = telegramify_markdown.markdownify(
+                            content=component['text'],
+                        )
+                    else:
+                        content = component['text']
+                    args = {
+                        'message_id': self.msg_stream_id[message_id],
+                        'chat_id': message_source.source_platform_object.effective_chat.id,
+                        'text': content,
+                    }
+                    if self.config['markdown_card'] is True:
+                        args['parse_mode'] = 'MarkdownV2'
+
+                await self.bot.edit_message_text(**args)
+            if is_final and bot_message.tool_calls is None:
+                # self.seq = 1  # 消息回复结束之后重置seq
+                self.msg_stream_id.pop(message_id)  # 消息回复结束之后删除流式消息id
+
+    async def is_stream_output_supported(self) -> bool:
+        is_stream = False
+        if self.config.get('enable-stream-reply', None):
+            is_stream = True
+        return is_stream
+
    async def is_muted(self, group_id: int) -> bool:
        return False

@@ -222,8 +294,12 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
        self.bot_account_id = (await self.bot.get_me()).username
        await self.application.updater.start_polling(allowed_updates=Update.ALL_TYPES)
        await self.application.start()
+        await self.logger.info('Telegram adapter running')

    async def kill(self) -> bool:
        if self.application.running:
            await self.application.stop()
+            if self.application.updater:
+                await self.application.updater.stop()
+            await self.logger.info('Telegram adapter stopped')
        return True
--- a/pkg/platform/sources/telegram.yaml
+++ b/pkg/platform/sources/telegram.yaml
@@ -25,6 +25,16 @@ spec:
      type: boolean
      required: false
      default: true
+    - name: enable-stream-reply
+      label:
+        en_US: Enable Stream Reply Mode
+        zh_Hans: 启用电报流式回复模式
+      description:
+        en_US: If enabled, the bot will use the stream of telegram reply mode
+        zh_Hans: 如果启用，将使用电报流式方式来回复内容
+      type: boolean
+      required: true
+      default: false
 execution:
  python:
    path: ./telegram.py
--- a/pkg/platform/sources/webchat.py
+++ b/pkg/platform/sources/webchat.py
@@ -19,17 +19,20 @@ class WebChatMessage(BaseModel):
    content: str
    message_chain: list[dict]
    timestamp: str
+    is_final: bool = False


 class WebChatSession:
    id: str
    message_lists: dict[str, list[WebChatMessage]] = {}
    resp_waiters: dict[int, asyncio.Future[WebChatMessage]]
+    resp_queues: dict[int, asyncio.Queue[WebChatMessage]]

    def __init__(self, id: str):
        self.id = id
        self.message_lists = {}
        self.resp_waiters = {}
+        self.resp_queues = {}

    def get_message_list(self, pipeline_uuid: str) -> list[WebChatMessage]:
        if pipeline_uuid not in self.message_lists:
@@ -49,6 +52,8 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):
        typing.Callable[[platform_events.Event, msadapter.MessagePlatformAdapter], None],
    ] = {}

+    is_stream: bool
+
    def __init__(self, config: dict, ap: app.Application, logger: EventLogger):
        self.ap = ap
        self.logger = logger
@@ -59,6 +64,8 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):

        self.bot_account_id = 'webchatbot'

+        self.is_stream = False
+
    async def send_message(
        self,
        target_type: str,
@@ -102,12 +109,53 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):

        # notify waiter
        if isinstance(message_source, platform_events.FriendMessage):
-            self.webchat_person_session.resp_waiters[message_source.message_chain.message_id].set_result(message_data)
+            await self.webchat_person_session.resp_queues[message_source.message_chain.message_id].put(message_data)
        elif isinstance(message_source, platform_events.GroupMessage):
-            self.webchat_group_session.resp_waiters[message_source.message_chain.message_id].set_result(message_data)
+            await self.webchat_group_session.resp_queues[message_source.message_chain.message_id].put(message_data)

        return message_data.model_dump()

+    async def reply_message_chunk(
+        self,
+        message_source: platform_events.MessageEvent,
+        bot_message,
+        message: platform_message.MessageChain,
+        quote_origin: bool = False,
+        is_final: bool = False,
+    ) -> dict:
+        """回复消息"""
+        message_data = WebChatMessage(
+            id=-1,
+            role='assistant',
+            content=str(message),
+            message_chain=[component.__dict__ for component in message],
+            timestamp=datetime.now().isoformat(),
+        )
+
+        # notify waiter
+        session = (
+            self.webchat_group_session
+            if isinstance(message_source, platform_events.GroupMessage)
+            else self.webchat_person_session
+        )
+        if message_source.message_chain.message_id not in session.resp_waiters:
+            # session.resp_waiters[message_source.message_chain.message_id] = asyncio.Queue()
+            queue = session.resp_queues[message_source.message_chain.message_id]
+
+        # if isinstance(message_source, platform_events.FriendMessage):
+        #     queue = self.webchat_person_session.resp_queues[message_source.message_chain.message_id]
+        # elif isinstance(message_source, platform_events.GroupMessage):
+        #     queue = self.webchat_group_session.resp_queues[message_source.message_chain.message_id]
+        if is_final and bot_message.tool_calls is None:
+            message_data.is_final = True
+        # print(message_data)
+        await queue.put(message_data)
+
+        return message_data.model_dump()
+
+    async def is_stream_output_supported(self) -> bool:
+        return self.is_stream
+
    def register_listener(
        self,
        event_type: typing.Type[platform_events.Event],
@@ -140,8 +188,13 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):
        await self.logger.info('WebChat调试适配器正在停止')

    async def send_webchat_message(
-        self, pipeline_uuid: str, session_type: str, message_chain_obj: typing.List[dict]
+        self,
+        pipeline_uuid: str,
+        session_type: str,
+        message_chain_obj: typing.List[dict],
+        is_stream: bool = False,
    ) -> dict:
+        self.is_stream = is_stream
        """发送调试消息到流水线"""
        if session_type == 'person':
            use_session = self.webchat_person_session
@@ -152,6 +205,9 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):

        message_id = len(use_session.get_message_list(pipeline_uuid)) + 1

+        use_session.resp_queues[message_id] = asyncio.Queue()
+        logger.debug(f'Initialized queue for message_id: {message_id}')
+
        use_session.get_message_list(pipeline_uuid).append(
            WebChatMessage(
                id=message_id,
@@ -185,21 +241,46 @@ class WebChatAdapter(msadapter.MessagePlatformAdapter):

        self.ap.platform_mgr.webchat_proxy_bot.bot_entity.use_pipeline_uuid = pipeline_uuid

+        # trigger pipeline
        if event.__class__ in self.listeners:
            await self.listeners[event.__class__](event, self)

-        # set waiter
-        waiter = asyncio.Future[WebChatMessage]()
-        use_session.resp_waiters[message_id] = waiter
-        waiter.add_done_callback(lambda future: use_session.resp_waiters.pop(message_id))
+        if is_stream:
+            queue = use_session.resp_queues[message_id]
+            msg_id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            while True:
+                resp_message = await queue.get()
+                resp_message.id = msg_id
+                if resp_message.is_final:
+                    resp_message.id = msg_id
+                    use_session.get_message_list(pipeline_uuid).append(resp_message)
+                    yield resp_message.model_dump()
+                    break
+                yield resp_message.model_dump()
+            use_session.resp_queues.pop(message_id)

-        resp_message = await waiter
+        else:  # non-stream
+            # set waiter
+            # waiter = asyncio.Future[WebChatMessage]()
+            # use_session.resp_waiters[message_id] = waiter
+            # # waiter.add_done_callback(lambda future: use_session.resp_waiters.pop(message_id))
+            #
+            # resp_message = await waiter
+            #
+            # resp_message.id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            #
+            # use_session.get_message_list(pipeline_uuid).append(resp_message)
+            #
+            # yield resp_message.model_dump()
+            msg_id = len(use_session.get_message_list(pipeline_uuid)) + 1

-        resp_message.id = len(use_session.get_message_list(pipeline_uuid)) + 1
+            queue = use_session.resp_queues[message_id]
+            resp_message = await queue.get()
+            use_session.get_message_list(pipeline_uuid).append(resp_message)
+            resp_message.id = msg_id
+            resp_message.is_final = True

-        use_session.get_message_list(pipeline_uuid).append(resp_message)
-
-        return resp_message.model_dump()
+            yield resp_message.model_dump()

    def get_webchat_messages(self, pipeline_uuid: str, session_type: str) -> list[dict]:
        """获取调试消息历史"""
--- a/pkg/platform/sources/webchat.yaml
+++ b/pkg/platform/sources/webchat.yaml
@@ -9,7 +9,8 @@ metadata:
    en_US: "WebChat adapter for pipeline debugging"
    zh_Hans: "用于流水线调试的网页聊天适配器"
  icon: ""
-spec: {}
+spec:
+  config: []
 execution:
  python:
    path: "webchat.py"
--- a/pkg/platform/sources/wechatpad.py
+++ b/pkg/platform/sources/wechatpad.py
@@ -29,10 +29,9 @@ import logging


 class WeChatPadMessageConverter(adapter.MessageConverter):
-
    def __init__(self, config: dict, logger: logging.Logger):
        self.config = config
-        self.bot = WeChatPadClient(self.config["wechatpad_url"],self.config["token"])
+        self.bot = WeChatPadClient(self.config['wechatpad_url'], self.config['token'])
        self.logger = logger

    @staticmethod
@@ -41,9 +40,9 @@ class WeChatPadMessageConverter(adapter.MessageConverter):

        for component in message_chain:
            if isinstance(component, platform_message.AtAll):
-                content_list.append({"type": "at", "target": "all"})
+                content_list.append({'type': 'at', 'target': 'all'})
            elif isinstance(component, platform_message.At):
-                content_list.append({"type": "at", "target": component.target})
+                content_list.append({'type': 'at', 'target': component.target})
            elif isinstance(component, platform_message.Plain):
                content_list.append({'type': 'text', 'content': component.text})
            elif isinstance(component, platform_message.Image):
@@ -77,9 +76,9 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
        return content_list

    async def target2yiri(
-            self,
-            message: dict,
-            bot_account_id: str,
+        self,
+        message: dict,
+        bot_account_id: str,
    ) -> platform_message.MessageChain:
        """外部消息转平台消息"""
        # 数据预处理
@@ -92,18 +91,18 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
        if is_group_message:
            ats_bot = self._ats_bot(message, bot_account_id)

-            self.logger.info(f"ats_bot: {ats_bot}; bot_account_id: {bot_account_id}; bot_wxid: {bot_wxid}")
-            if "@所有人" in content:
+            self.logger.info(f'ats_bot: {ats_bot}; bot_account_id: {bot_account_id}; bot_wxid: {bot_wxid}')
+            if '@所有人' in content:
                message_list.append(platform_message.AtAll())
            if ats_bot:
                message_list.append(platform_message.At(target=bot_account_id))
-            
+
            # 解析@信息并生成At组件
            at_targets = self._extract_at_targets(message)
            for target_id in at_targets:
                if target_id != bot_wxid:  # 避免重复添加机器人的At
                    message_list.append(platform_message.At(target=target_id))
-            
+
            content_no_preifx, _ = self._extract_content_and_sender(content)

        msg_type = message['msg_type']
@@ -241,8 +240,8 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
        #         self.logger.info("_handler_compound_quote", ET.tostring(xml_data, encoding='unicode'))
        appmsg_data = xml_data.find('.//appmsg')
        quote_data = ''  # 引用原文
-        quote_id = None  # 引用消息的原发送者
-        tousername = None  # 接收方: 所属微信的wxid
+        # quote_id = None  # 引用消息的原发送者
+        # tousername = None  # 接收方: 所属微信的wxid
        user_data = ''  # 用户消息
        sender_id = xml_data.findtext('.//fromusername')  # 发送方：单聊用户/群member

@@ -250,13 +249,10 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
        if appmsg_data:
            user_data = appmsg_data.findtext('.//title') or ''
            quote_data = appmsg_data.find('.//refermsg').findtext('.//content')
-            quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
+            # quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
            message_list.append(platform_message.WeChatAppMsg(app_msg=ET.tostring(appmsg_data, encoding='unicode')))
-        if message:
-            tousername = message['to_user_name']['str']
-
-        _ = quote_id
-        _ = tousername
+        # if message:
+        #     tousername = message['to_user_name']['str']

        if quote_data:
            quote_data_message_list = platform_message.MessageChain()
@@ -421,14 +417,14 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
            msg_source = message.get('msg_source', '') or ''
            if len(msg_source) > 0:
                msg_source_data = ET.fromstring(msg_source)
-                at_user_list = msg_source_data.findtext("atuserlist") or ""
+                at_user_list = msg_source_data.findtext('atuserlist') or ''
                if at_user_list:
                    # atuserlist格式通常是逗号分隔的用户ID列表
                    at_targets = [user_id.strip() for user_id in at_user_list.split(',') if user_id.strip()]
        except Exception as e:
-            self.logger.error(f"_extract_at_targets got except: {e}")
+            self.logger.error(f'_extract_at_targets got except: {e}')
        return at_targets
-    
+
    # 提取一下content前面的sender_id, 和去掉前缀的内容
    def _extract_content_and_sender(self, raw_content: str) -> Tuple[str, Optional[str]]:
        try:
@@ -452,22 +448,20 @@ class WeChatPadMessageConverter(adapter.MessageConverter):


 class WeChatPadEventConverter(adapter.EventConverter):
-
    def __init__(self, config: dict, logger: logging.Logger):
        self.config = config
        self.message_converter = WeChatPadMessageConverter(config, logger)
        self.logger = logger
-        
+
    @staticmethod
    async def yiri2target(event: platform_events.MessageEvent) -> dict:
        pass

    async def target2yiri(
-            self,
-            event: dict,
-            bot_account_id: str,
+        self,
+        event: dict,
+        bot_account_id: str,
    ) -> platform_events.MessageEvent:
-
        # 排除公众号以及微信团队消息
        if (
            event['from_user_name']['str'].startswith('gh_')
@@ -579,26 +573,22 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
        for msg in content_list:
            # 文本消息处理@
            if msg['type'] == 'text' and at_targets:
-                if "all" in at_targets:
+                if 'all' in at_targets:
                    msg['content'] = f'@所有人 {msg["content"]}'
                else:
                    at_nick_name_list = []
                    for member in member_info:
-                        if member["user_name"] in at_targets:
+                        if member['user_name'] in at_targets:
                            at_nick_name_list.append(f'@{member["nick_name"]}')
                    msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'

            # 统一消息派发
            handler_map = {
                'text': lambda msg: self.bot.send_text_message(
-                    to_wxid=target_id,
-                    message=msg['content'],
-                    ats= ["notify@all"] if "all" in at_targets else at_targets
+                    to_wxid=target_id, message=msg['content'], ats=['notify@all'] if 'all' in at_targets else at_targets
                ),
                'image': lambda msg: self.bot.send_image_message(
-                    to_wxid=target_id,
-                    img_url=msg["image"],
-                    ats = ["notify@all"] if "all" in at_targets else at_targets
+                    to_wxid=target_id, img_url=msg['image'], ats=['notify@all'] if 'all' in at_targets else at_targets
                ),
                'WeChatEmoji': lambda msg: self.bot.send_emoji_message(
                    to_wxid=target_id, emoji_md5=msg['emoji_md5'], emoji_size=msg['emoji_size']
--- a/pkg/platform/types/message.py
+++ b/pkg/platform/types/message.py
@@ -812,12 +812,14 @@ class File(MessageComponent):
    def __str__(self):
        return f'[文件]{self.name}'

+
 class Face(MessageComponent):
    """系统表情
    此处将超级表情骰子/划拳，一同归类于face
    当face_type为rps(划拳)时 face_id 对应的是手势
    当face_type为dice(骰子)时 face_id 对应的是点数
    """
+
    type: str = 'Face'
    """表情类型"""
    face_type: str = 'face'
@@ -834,15 +836,15 @@ class Face(MessageComponent):
        elif self.face_type == 'rps':
            return f'[表情]{self.face_name}({self.rps_data(self.face_id)})'

-
-    def rps_data(self,face_id):
-        rps_dict ={
-            1 : "布",
-            2 : "剪刀",
-            3 : "石头",
+    def rps_data(self, face_id):
+        rps_dict = {
+            1: '布',
+            2: '剪刀',
+            3: '石头',
        }
        return rps_dict[face_id]

+
 # ================ 个人微信专用组件 ================


@@ -971,5 +973,6 @@ class WeChatFile(MessageComponent):
    """文件地址"""
    file_base64: str = ''
    """base64"""
+
    def __str__(self):
-        return f'[文件]{self.file_name}'
+        return f'[文件]{self.file_name}'
--- a/pkg/provider/entities.py
+++ b/pkg/provider/entities.py
@@ -125,6 +125,95 @@ class Message(pydantic.BaseModel):
            return platform_message.MessageChain(mc)


+class MessageChunk(pydantic.BaseModel):
+    """消息"""
+
+    resp_message_id: typing.Optional[str] = None
+    """消息id"""
+
+    role: str  # user, system, assistant, tool, command, plugin
+    """消息的角色"""
+
+    name: typing.Optional[str] = None
+    """名称，仅函数调用返回时设置"""
+
+    all_content: typing.Optional[str] = None
+    """所有内容"""
+
+    content: typing.Optional[list[ContentElement]] | typing.Optional[str] = None
+    """内容"""
+
+    tool_calls: typing.Optional[list[ToolCall]] = None
+    """工具调用"""
+
+    tool_call_id: typing.Optional[str] = None
+
+    is_final: bool = False
+    """是否是结束"""
+
+    msg_sequence: int = 0
+    """消息迭代次数"""
+
+    def readable_str(self) -> str:
+        if self.content is not None:
+            return str(self.role) + ': ' + str(self.get_content_platform_message_chain())
+        elif self.tool_calls is not None:
+            return f'调用工具: {self.tool_calls[0].id}'
+        else:
+            return '未知消息'
+
+    def get_content_platform_message_chain(self, prefix_text: str = '') -> platform_message.MessageChain | None:
+        """将内容转换为平台消息 MessageChain 对象
+
+        Args:
+            prefix_text (str): 首个文字组件的前缀文本
+        """
+
+        if self.content is None:
+            return None
+        elif isinstance(self.content, str):
+            return platform_message.MessageChain([platform_message.Plain(prefix_text + self.content)])
+        elif isinstance(self.content, list):
+            mc = []
+            for ce in self.content:
+                if ce.type == 'text':
+                    mc.append(platform_message.Plain(ce.text))
+                elif ce.type == 'image_url':
+                    if ce.image_url.url.startswith('http'):
+                        mc.append(platform_message.Image(url=ce.image_url.url))
+                    else:  # base64
+                        b64_str = ce.image_url.url
+
+                        if b64_str.startswith('data:'):
+                            b64_str = b64_str.split(',')[1]
+
+                        mc.append(platform_message.Image(base64=b64_str))
+
+            # 找第一个文字组件
+            if prefix_text:
+                for i, c in enumerate(mc):
+                    if isinstance(c, platform_message.Plain):
+                        mc[i] = platform_message.Plain(prefix_text + c.text)
+                        break
+                else:
+                    mc.insert(0, platform_message.Plain(prefix_text))
+
+            return platform_message.MessageChain(mc)
+
+
+class ToolCallChunk(pydantic.BaseModel):
+    """工具调用"""
+
+    id: str
+    """工具调用ID"""
+
+    type: str
+    """工具调用类型"""
+
+    function: FunctionCall
+    """函数调用"""
+
+
 class Prompt(pydantic.BaseModel):
    """供AI使用的Prompt"""

--- a/pkg/provider/modelmgr/requester.py
+++ b/pkg/provider/modelmgr/requester.py
@@ -84,6 +84,7 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
        messages: typing.List[llm_entities.Message],
        funcs: typing.List[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        """调用API

@@ -92,12 +93,36 @@ class ProviderAPIRequester(metaclass=abc.ABCMeta):
            messages (typing.List[llm_entities.Message]): 消息对象列表
            funcs (typing.List[tools_entities.LLMFunction], optional): 使用的工具函数列表. Defaults to None.
            extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
+            remove_think (bool, optional): 是否移思考中的消息. Defaults to False.

        Returns:
            llm_entities.Message: 返回消息对象
        """
        pass

+    async def invoke_llm_stream(
+        self,
+        query: core_entities.Query,
+        model: RuntimeLLMModel,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.MessageChunk:
+        """调用API
+
+        Args:
+            model (RuntimeLLMModel): 使用的模型信息
+            messages (typing.List[llm_entities.Message]): 消息对象列表
+            funcs (typing.List[tools_entities.LLMFunction], optional): 使用的工具函数列表. Defaults to None.
+            extra_args (dict[str, typing.Any], optional): 额外的参数. Defaults to {}.
+            remove_think (bool, optional): 是否移除思考中的消息. Defaults to False.
+
+        Returns:
+            typing.AsyncGenerator[llm_entities.MessageChunk]: 返回消息对象
+        """
+        pass
+
    async def invoke_embedding(
        self,
        model: RuntimeEmbeddingModel,
--- a/pkg/provider/modelmgr/requesters/anthropicmsgs.py
+++ b/pkg/provider/modelmgr/requesters/anthropicmsgs.py
@@ -21,7 +21,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
    client: anthropic.AsyncAnthropic

    default_config: dict[str, typing.Any] = {
-        'base_url': 'https://api.anthropic.com/v1',
+        'base_url': 'https://api.anthropic.com',
        'timeout': 120,
    }

@@ -44,6 +44,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
        self.client = anthropic.AsyncAnthropic(
            api_key='',
            http_client=httpx_client,
+            base_url=self.requester_cfg['base_url'],
        )

    async def invoke_llm(
@@ -53,6 +54,7 @@ class AnthropicMessages(requester.ProviderAPIRequester):
        messages: typing.List[llm_entities.Message],
        funcs: typing.List[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        self.client.api_key = model.token_mgr.get_token()

@@ -89,7 +91,8 @@ class AnthropicMessages(requester.ProviderAPIRequester):
                            {
                                'type': 'tool_result',
                                'tool_use_id': tool_call_id,
-                                'content': m.content,
+                                'is_error': False,
+                                'content': [{'type': 'text', 'text': m.content}],
                            }
                        ],
                    }
@@ -133,6 +136,9 @@ class AnthropicMessages(requester.ProviderAPIRequester):

        args['messages'] = req_messages

+        if 'thinking' in args:
+            args['thinking'] = {'type': 'enabled', 'budget_tokens': 10000}
+
        if funcs:
            tools = await self.ap.tool_mgr.generate_tools_for_anthropic(funcs)

@@ -140,19 +146,17 @@ class AnthropicMessages(requester.ProviderAPIRequester):
                args['tools'] = tools

        try:
-            # print(json.dumps(args, indent=4, ensure_ascii=False))
            resp = await self.client.messages.create(**args)

            args = {
                'content': '',
                'role': resp.role,
            }
-
            assert type(resp) is anthropic.types.message.Message

            for block in resp.content:
-                if block.type == 'thinking':
-                    args['content'] = '<think>' + block.thinking + '</think>\n' + args['content']
+                if not remove_think and block.type == 'thinking':
+                    args['content'] = '<think>\n' + block.thinking + '\n</think>\n' + args['content']
                elif block.type == 'text':
                    args['content'] += block.text
                elif block.type == 'tool_use':
@@ -176,3 +180,191 @@ class AnthropicMessages(requester.ProviderAPIRequester):
                raise errors.RequesterError(f'模型无效: {e.message}')
            else:
                raise errors.RequesterError(f'请求地址无效: {e.message}')
+
+    async def invoke_llm_stream(
+        self,
+        query: core_entities.Query,
+        model: requester.RuntimeLLMModel,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.Message:
+        self.client.api_key = model.token_mgr.get_token()
+
+        args = extra_args.copy()
+        args['model'] = model.model_entity.name
+        args['stream'] = True
+
+        # 处理消息
+
+        # system
+        system_role_message = None
+
+        for i, m in enumerate(messages):
+            if m.role == 'system':
+                system_role_message = m
+
+                break
+
+        if system_role_message:
+            messages.pop(i)
+
+        if isinstance(system_role_message, llm_entities.Message) and isinstance(system_role_message.content, str):
+            args['system'] = system_role_message.content
+
+        req_messages = []
+
+        for m in messages:
+            if m.role == 'tool':
+                tool_call_id = m.tool_call_id
+
+                req_messages.append(
+                    {
+                        'role': 'user',
+                        'content': [
+                            {
+                                'type': 'tool_result',
+                                'tool_use_id': tool_call_id,
+                                'is_error': False,  # 暂时直接写false
+                                'content': [
+                                    {'type': 'text', 'text': m.content}
+                                ],  # 这里要是list包裹，应该是多个返回的情况？type类型好像也可以填其他的，暂时只写text
+                            }
+                        ],
+                    }
+                )
+
+                continue
+
+            msg_dict = m.dict(exclude_none=True)
+
+            if isinstance(m.content, str) and m.content.strip() != '':
+                msg_dict['content'] = [{'type': 'text', 'text': m.content}]
+            elif isinstance(m.content, list):
+                for i, ce in enumerate(m.content):
+                    if ce.type == 'image_base64':
+                        image_b64, image_format = await image.extract_b64_and_format(ce.image_base64)
+
+                        alter_image_ele = {
+                            'type': 'image',
+                            'source': {
+                                'type': 'base64',
+                                'media_type': f'image/{image_format}',
+                                'data': image_b64,
+                            },
+                        }
+                        msg_dict['content'][i] = alter_image_ele
+            if isinstance(msg_dict['content'], str) and msg_dict['content'] == '':
+                msg_dict['content'] = []  # 这里不知道为什么会莫名有个空导致content为字符
+            if m.tool_calls:
+                for tool_call in m.tool_calls:
+                    msg_dict['content'].append(
+                        {
+                            'type': 'tool_use',
+                            'id': tool_call.id,
+                            'name': tool_call.function.name,
+                            'input': json.loads(tool_call.function.arguments),
+                        }
+                    )
+
+                del msg_dict['tool_calls']
+
+            req_messages.append(msg_dict)
+        if 'thinking' in args:
+            args['thinking'] = {'type': 'enabled', 'budget_tokens': 10000}
+
+        args['messages'] = req_messages
+
+        if funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_anthropic(funcs)
+
+            if tools:
+                args['tools'] = tools
+
+        try:
+            role = 'assistant'  # 默认角色
+            # chunk_idx = 0
+            think_started = False
+            think_ended = False
+            finish_reason = False
+            content = ''
+            tool_name = ''
+            tool_id = ''
+            async for chunk in await self.client.messages.create(**args):
+                tool_call = {'id': None, 'function': {'name': None, 'arguments': None}, 'type': 'function'}
+                if isinstance(
+                    chunk, anthropic.types.raw_content_block_start_event.RawContentBlockStartEvent
+                ):  # 记录开始
+                    if chunk.content_block.type == 'tool_use':
+                        if chunk.content_block.name is not None:
+                            tool_name = chunk.content_block.name
+                        if chunk.content_block.id is not None:
+                            tool_id = chunk.content_block.id
+
+                        tool_call['function']['name'] = tool_name
+                        tool_call['function']['arguments'] = ''
+                        tool_call['id'] = tool_id
+
+                    if not remove_think:
+                        if chunk.content_block.type == 'thinking' and not remove_think:
+                            think_started = True
+                        elif chunk.content_block.type == 'text' and chunk.index != 0 and not remove_think:
+                            think_ended = True
+                        continue
+                elif isinstance(chunk, anthropic.types.raw_content_block_delta_event.RawContentBlockDeltaEvent):
+                    if chunk.delta.type == 'thinking_delta':
+                        if think_started:
+                            think_started = False
+                            content = '<think>\n' + chunk.delta.thinking
+                        elif remove_think:
+                            continue
+                        else:
+                            content = chunk.delta.thinking
+                    elif chunk.delta.type == 'text_delta':
+                        if think_ended:
+                            think_ended = False
+                            content = '\n</think>\n' + chunk.delta.text
+                        else:
+                            content = chunk.delta.text
+                    elif chunk.delta.type == 'input_json_delta':
+                        tool_call['function']['arguments'] = chunk.delta.partial_json
+                        tool_call['function']['name'] = tool_name
+                        tool_call['id'] = tool_id
+                elif isinstance(chunk, anthropic.types.raw_content_block_stop_event.RawContentBlockStopEvent):
+                    continue  # 记录raw_content_block结束的
+
+                elif isinstance(chunk, anthropic.types.raw_message_delta_event.RawMessageDeltaEvent):
+                    if chunk.delta.stop_reason == 'end_turn':
+                        finish_reason = True
+                elif isinstance(chunk, anthropic.types.raw_message_stop_event.RawMessageStopEvent):
+                    continue  # 这个好像是完全结束
+                else:
+                    # print(chunk)
+                    self.ap.logger.debug(f'anthropic chunk: {chunk}')
+                    continue
+
+                args = {
+                    'content': content,
+                    'role': role,
+                    'is_final': finish_reason,
+                    'tool_calls': None if tool_call['id'] is None else [tool_call],
+                }
+                # if chunk_idx == 0:
+                #     chunk_idx += 1
+                #     continue
+
+                # assert type(chunk) is anthropic.types.message.Chunk
+
+                yield llm_entities.MessageChunk(**args)
+
+            # return llm_entities.Message(**args)
+        except anthropic.AuthenticationError as e:
+            raise errors.RequesterError(f'api-key 无效: {e.message}')
+        except anthropic.BadRequestError as e:
+            raise errors.RequesterError(str(e.message))
+        except anthropic.NotFoundError as e:
+            if 'model: ' in str(e):
+                raise errors.RequesterError(f'模型无效: {e.message}')
+            else:
+                raise errors.RequesterError(f'请求地址无效: {e.message}')
--- a/pkg/provider/modelmgr/requesters/anthropicmsgs.yaml
+++ b/pkg/provider/modelmgr/requesters/anthropicmsgs.yaml
@@ -14,7 +14,7 @@ spec:
        zh_Hans: 基础 URL
      type: string
      required: true
-      default: "https://api.anthropic.com/v1"
+      default: "https://api.anthropic.com"
    - name: timeout
      label:
        en_US: Timeout
--- a/pkg/provider/modelmgr/requesters/chatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/chatcmpl.py
@@ -38,9 +38,18 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
    ) -> chat_completion.ChatCompletion:
        return await self.client.chat.completions.create(**args, extra_body=extra_body)

+    async def _req_stream(
+        self,
+        args: dict,
+        extra_body: dict = {},
+    ):
+        async for chunk in await self.client.chat.completions.create(**args, extra_body=extra_body):
+            yield chunk
+
    async def _make_msg(
        self,
        chat_completion: chat_completion.ChatCompletion,
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        chatcmpl_message = chat_completion.choices[0].message.model_dump()

@@ -48,16 +57,192 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
            chatcmpl_message['role'] = 'assistant'

-        reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
+        # 处理思维链
+        content = chatcmpl_message.get('content', '')
+        reasoning_content = chatcmpl_message.get('reasoning_content', None)

-        # deepseek的reasoner模型
-        if reasoning_content is not None:
-            chatcmpl_message['content'] = '<think>\n' + reasoning_content + '\n</think>\n' + chatcmpl_message['content']
+        processed_content, _ = await self._process_thinking_content(
+            content=content, reasoning_content=reasoning_content, remove_think=remove_think
+        )
+
+        chatcmpl_message['content'] = processed_content
+
+        # 移除 reasoning_content 字段，避免传递给 Message
+        if 'reasoning_content' in chatcmpl_message:
+            del chatcmpl_message['reasoning_content']

        message = llm_entities.Message(**chatcmpl_message)
-
        return message

+    async def _process_thinking_content(
+        self,
+        content: str,
+        reasoning_content: str = None,
+        remove_think: bool = False,
+    ) -> tuple[str, str]:
+        """处理思维链内容
+
+        Args:
+            content: 原始内容
+            reasoning_content: reasoning_content 字段内容
+            remove_think: 是否移除思维链
+
+        Returns:
+            (处理后的内容, 提取的思维链内容)
+        """
+        thinking_content = ''
+
+        # 1. 从 reasoning_content 提取思维链
+        if reasoning_content:
+            thinking_content = reasoning_content
+
+        # 2. 从 content 中提取 <think> 标签内容
+        if content and '<think>' in content and '</think>' in content:
+            import re
+
+            think_pattern = r'<think>(.*?)</think>'
+            think_matches = re.findall(think_pattern, content, re.DOTALL)
+            if think_matches:
+                # 如果已有 reasoning_content，则追加
+                if thinking_content:
+                    thinking_content += '\n' + '\n'.join(think_matches)
+                else:
+                    thinking_content = '\n'.join(think_matches)
+                # 移除 content 中的 <think> 标签
+                content = re.sub(think_pattern, '', content, flags=re.DOTALL).strip()
+
+        # 3. 根据 remove_think 参数决定是否保留思维链
+        if remove_think:
+            return content, ''
+        else:
+            # 如果有思维链内容，将其以 <think> 格式添加到 content 开头
+            if thinking_content:
+                content = f'<think>\n{thinking_content}\n</think>\n{content}'.strip()
+            return content, thinking_content
+
+    async def _closure_stream(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.MessageChunk:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        # 流式处理状态
+        tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        tool_id = ""
+        tool_name = ''
+        # accumulated_reasoning = ''  # 仅用于判断何时结束思维链
+
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            reasoning_content = delta.get('reasoning_content', '')
+
+            # 处理 reasoning_content
+            if reasoning_content:
+                # accumulated_reasoning += reasoning_content
+                # 如果设置了 remove_think，跳过 reasoning_content
+                if remove_think:
+                    chunk_idx += 1
+                    continue
+
+                # 第一次出现 reasoning_content，添加 <think> 开始标签
+                if not thinking_started:
+                    thinking_started = True
+                    delta_content = '<think>\n' + reasoning_content
+                else:
+                    # 继续输出 reasoning_content
+                    delta_content = reasoning_content
+            elif thinking_started and not thinking_ended and delta_content:
+                # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                thinking_ended = True
+                delta_content = '\n</think>\n' + delta_content
+
+            # 处理 content 中已有的 <think> 标签（如果需要移除）
+            # if delta_content and remove_think and '<think>' in delta_content:
+            #     import re
+            #
+            #     # 移除 <think> 标签及其内容
+            #     delta_content = re.sub(r'<think>.*?</think>', '', delta_content, flags=re.DOTALL)
+
+            # 处理工具调用增量
+            # delta_tool_calls = None
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] and tool_call['function']['name']:
+                        tool_id = tool_call['id']
+                        tool_name = tool_call['function']['name']
+                    else:
+                        tool_call['id'] = tool_id
+                        tool_call['function']['name'] = tool_name
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+
+
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
+            chunk_idx += 1
+
    async def _closure(
        self,
        query: core_entities.Query,
@@ -65,6 +250,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
        use_model: requester.RuntimeLLMModel,
        use_funcs: list[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        self.client.api_key = use_model.token_mgr.get_token()

@@ -92,10 +278,10 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
        args['messages'] = messages

        # 发送请求
-        resp = await self._req(args, extra_body=extra_args)

+        resp = await self._req(args, extra_body=extra_args)
        # 处理请求结果
-        message = await self._make_msg(resp)
+        message = await self._make_msg(resp, remove_think)

        return message

@@ -106,6 +292,7 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
        messages: typing.List[llm_entities.Message],
        funcs: typing.List[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
        for m in messages:
@@ -119,13 +306,15 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
            req_messages.append(msg_dict)

        try:
-            return await self._closure(
+            msg = await self._closure(
                query=query,
                req_messages=req_messages,
                use_model=model,
                use_funcs=funcs,
                extra_args=extra_args,
+                remove_think=remove_think,
            )
+            return msg
        except asyncio.TimeoutError:
            raise errors.RequesterError('请求超时')
        except openai.BadRequestError as e:
@@ -169,6 +358,45 @@ class OpenAIChatCompletions(requester.ProviderAPIRequester):
            raise errors.RequesterError('请求超时')
        except openai.BadRequestError as e:
            raise errors.RequesterError(f'请求参数错误: {e.message}')
+
+    async def invoke_llm_stream(
+        self,
+        query: core_entities.Query,
+        model: requester.RuntimeLLMModel,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.MessageChunk:
+        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
+        for m in messages:
+            msg_dict = m.dict(exclude_none=True)
+            content = msg_dict.get('content')
+            if isinstance(content, list):
+                # 检查 content 列表中是否每个部分都是文本
+                if all(isinstance(part, dict) and part.get('type') == 'text' for part in content):
+                    # 将所有文本部分合并为一个字符串
+                    msg_dict['content'] = '\n'.join(part['text'] for part in content)
+            req_messages.append(msg_dict)
+
+        try:
+            async for item in self._closure_stream(
+                query=query,
+                req_messages=req_messages,
+                use_model=model,
+                use_funcs=funcs,
+                extra_args=extra_args,
+                remove_think=remove_think,
+            ):
+                yield item
+
+        except asyncio.TimeoutError:
+            raise errors.RequesterError('请求超时')
+        except openai.BadRequestError as e:
+            if 'context_length_exceeded' in e.message:
+                raise errors.RequesterError(f'上文过长，请重置会话: {e.message}')
+            else:
+                raise errors.RequesterError(f'请求参数错误: {e.message}')
        except openai.AuthenticationError as e:
            raise errors.RequesterError(f'无效的 api-key: {e.message}')
        except openai.NotFoundError as e:
--- a/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
@@ -24,6 +24,7 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
        use_model: requester.RuntimeLLMModel,
        use_funcs: list[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        self.client.api_key = use_model.token_mgr.get_token()

@@ -49,10 +50,11 @@ class DeepseekChatCompletions(chatcmpl.OpenAIChatCompletions):
        # 发送请求
        resp = await self._req(args, extra_body=extra_args)

+        # print(resp)
+
        if resp is None:
            raise errors.RequesterError('接口返回为空，请确定模型提供商服务是否正常')
-
        # 处理请求结果
-        message = await self._make_msg(resp)
+        message = await self._make_msg(resp, remove_think)

        return message
--- a/pkg/provider/modelmgr/requesters/deepseekchatcmpl.yaml
+++ b/pkg/provider/modelmgr/requesters/deepseekchatcmpl.yaml
@@ -4,7 +4,7 @@ metadata:
  name: deepseek-chat-completions
  label:
    en_US: DeepSeek
-    zh_Hans: 深度求索
+    zh_Hans: DeepSeek
  icon: deepseek.svg
 spec:
  config:
--- a/pkg/provider/modelmgr/requesters/geminichatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/geminichatcmpl.py
@@ -4,6 +4,13 @@ import typing

 from . import chatcmpl

+import uuid
+
+from .. import errors, requester
+from ....core import entities as core_entities
+from ... import entities as llm_entities
+from ...tools import entities as tools_entities
+

 class GeminiChatCompletions(chatcmpl.OpenAIChatCompletions):
    """Google Gemini API 请求器"""
@@ -12,3 +19,127 @@ class GeminiChatCompletions(chatcmpl.OpenAIChatCompletions):
        'base_url': 'https://generativelanguage.googleapis.com/v1beta/openai',
        'timeout': 120,
    }
+
+
+    async def _closure_stream(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.MessageChunk:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        # 流式处理状态
+        tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        tool_id = ""
+        tool_name = ''
+        # accumulated_reasoning = ''  # 仅用于判断何时结束思维链
+
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            reasoning_content = delta.get('reasoning_content', '')
+
+            # 处理 reasoning_content
+            if reasoning_content:
+                # accumulated_reasoning += reasoning_content
+                # 如果设置了 remove_think，跳过 reasoning_content
+                if remove_think:
+                    chunk_idx += 1
+                    continue
+
+                # 第一次出现 reasoning_content，添加 <think> 开始标签
+                if not thinking_started:
+                    thinking_started = True
+                    delta_content = '<think>\n' + reasoning_content
+                else:
+                    # 继续输出 reasoning_content
+                    delta_content = reasoning_content
+            elif thinking_started and not thinking_ended and delta_content:
+                # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                thinking_ended = True
+                delta_content = '\n</think>\n' + delta_content
+
+            # 处理 content 中已有的 <think> 标签（如果需要移除）
+            # if delta_content and remove_think and '<think>' in delta_content:
+            #     import re
+            #
+            #     # 移除 <think> 标签及其内容
+            #     delta_content = re.sub(r'<think>.*?</think>', '', delta_content, flags=re.DOTALL)
+
+            # 处理工具调用增量
+            # delta_tool_calls = None
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] == '' and tool_id == '':
+                        tool_id = str(uuid.uuid4())
+                    if  tool_call['function']['name']:
+                        tool_name = tool_call['function']['name']
+                    tool_call['id'] = tool_id
+                    tool_call['function']['name'] = tool_name
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+
+
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
+            chunk_idx += 1
--- a/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
@@ -3,14 +3,16 @@ from __future__ import annotations

 import typing

-from . import chatcmpl
+from . import ppiochatcmpl
 from .. import requester
 from ....core import entities as core_entities
 from ... import entities as llm_entities
 from ...tools import entities as tools_entities
+import re
+import openai.types.chat.chat_completion as chat_completion


-class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
+class GiteeAIChatCompletions(ppiochatcmpl.PPIOChatCompletions):
    """Gitee AI ChatCompletions API 请求器"""

    default_config: dict[str, typing.Any] = {
@@ -18,34 +20,3 @@ class GiteeAIChatCompletions(chatcmpl.OpenAIChatCompletions):
        'timeout': 120,
    }

-    async def _closure(
-        self,
-        query: core_entities.Query,
-        req_messages: list[dict],
-        use_model: requester.RuntimeLLMModel,
-        use_funcs: list[tools_entities.LLMFunction] = None,
-        extra_args: dict[str, typing.Any] = {},
-    ) -> llm_entities.Message:
-        self.client.api_key = use_model.token_mgr.get_token()
-
-        args = {}
-        args['model'] = use_model.model_entity.name
-
-        if use_funcs:
-            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
-
-            if tools:
-                args['tools'] = tools
-
-        # gitee 不支持多模态，把content都转换成纯文字
-        for m in req_messages:
-            if 'content' in m and isinstance(m['content'], list):
-                m['content'] = ' '.join([c['text'] for c in m['content']])
-
-        args['messages'] = req_messages
-
-        resp = await self._req(args, extra_body=extra_args)
-
-        message = await self._make_msg(resp)
-
-        return message
--- a/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
@@ -1,6 +1,7 @@
 from __future__ import annotations

 import asyncio
+import json
 import typing

 import openai
@@ -34,9 +35,11 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):

    async def _req(
        self,
+        query: core_entities.Query,
        args: dict,
        extra_body: dict = {},
-    ) -> chat_completion.ChatCompletion:
+        remove_think: bool = False,
+    ) -> list[dict[str, typing.Any]]:
        args['stream'] = True

        chunk = None
@@ -47,78 +50,75 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):

        resp_gen: openai.AsyncStream = await self.client.chat.completions.create(**args, extra_body=extra_body)

+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        tool_id = ''
+        tool_name = ''
+        message_delta = {}
        async for chunk in resp_gen:
-            # print(chunk)
            if not chunk or not chunk.id or not chunk.choices or not chunk.choices[0] or not chunk.choices[0].delta:
                continue

-            if chunk.choices[0].delta.content is not None:
-                pending_content += chunk.choices[0].delta.content
+            delta = chunk.choices[0].delta.model_dump() if hasattr(chunk.choices[0], 'delta') else {}
+            reasoning_content = delta.get('reasoning_content')
+            # 处理 reasoning_content
+            if reasoning_content:
+                # accumulated_reasoning += reasoning_content
+                # 如果设置了 remove_think，跳过 reasoning_content
+                if remove_think:
+                    chunk_idx += 1
+                    continue

-            if chunk.choices[0].delta.tool_calls is not None:
-                for tool_call in chunk.choices[0].delta.tool_calls:
-                    if tool_call.function.arguments is None:
+                # 第一次出现 reasoning_content，添加 <think> 开始标签
+                if not thinking_started:
+                    thinking_started = True
+                    pending_content += '<think>\n' + reasoning_content
+                else:
+                    # 继续输出 reasoning_content
+                    pending_content += reasoning_content
+            elif thinking_started and not thinking_ended and delta.get('content'):
+                # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                thinking_ended = True
+                pending_content += '\n</think>\n' + delta.get('content')
+
+            if delta.get('content') is not None:
+                pending_content += delta.get('content')
+
+            if delta.get('tool_calls') is not None:
+                for tool_call in delta.get('tool_calls'):
+                    if tool_call['id'] != '':
+                        tool_id = tool_call['id']
+                    if tool_call['function']['name'] is not None:
+                        tool_name = tool_call['function']['name']
+                    if tool_call['function']['arguments'] is None:
                        continue
+                    tool_call['id'] = tool_id
+                    tool_call['name'] = tool_name
                    for tc in tool_calls:
-                        if tc.index == tool_call.index:
-                            tc.function.arguments += tool_call.function.arguments
+                        if tc['index'] == tool_call['index']:
+                            tc['function']['arguments'] += tool_call['function']['arguments']
                            break
                    else:
                        tool_calls.append(tool_call)

            if chunk.choices[0].finish_reason is not None:
                break
+        message_delta['content'] = pending_content
+        message_delta['role'] = 'assistant'

-        real_tool_calls = []
-
-        for tc in tool_calls:
-            function = chat_completion_message_tool_call.Function(
-                name=tc.function.name, arguments=tc.function.arguments
-            )
-            real_tool_calls.append(
-                chat_completion_message_tool_call.ChatCompletionMessageToolCall(
-                    id=tc.id, function=function, type='function'
-                )
-            )
-
-        return (
-            chat_completion.ChatCompletion(
-                id=chunk.id,
-                object='chat.completion',
-                created=chunk.created,
-                choices=[
-                    chat_completion.Choice(
-                        index=0,
-                        message=chat_completion.ChatCompletionMessage(
-                            role='assistant',
-                            content=pending_content,
-                            tool_calls=real_tool_calls if len(real_tool_calls) > 0 else None,
-                        ),
-                        finish_reason=chunk.choices[0].finish_reason
-                        if hasattr(chunk.choices[0], 'finish_reason') and chunk.choices[0].finish_reason is not None
-                        else 'stop',
-                        logprobs=chunk.choices[0].logprobs,
-                    )
-                ],
-                model=chunk.model,
-                service_tier=chunk.service_tier if hasattr(chunk, 'service_tier') else None,
-                system_fingerprint=chunk.system_fingerprint if hasattr(chunk, 'system_fingerprint') else None,
-                usage=chunk.usage if hasattr(chunk, 'usage') else None,
-            )
-            if chunk
-            else None
-        )
+        message_delta['tool_calls'] = tool_calls if tool_calls else None
+        return [message_delta]

    async def _make_msg(
        self,
-        chat_completion: chat_completion.ChatCompletion,
+        chat_completion: list[dict[str, typing.Any]],
    ) -> llm_entities.Message:
-        chatcmpl_message = chat_completion.choices[0].message.dict()
+        chatcmpl_message = chat_completion[0]

        # 确保 role 字段存在且不为 None
        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
            chatcmpl_message['role'] = 'assistant'
-
        message = llm_entities.Message(**chatcmpl_message)

        return message
@@ -130,6 +130,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
        use_model: requester.RuntimeLLMModel,
        use_funcs: list[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think:bool = False,
    ) -> llm_entities.Message:
        self.client.api_key = use_model.token_mgr.get_token()

@@ -157,13 +158,146 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
        args['messages'] = messages

        # 发送请求
-        resp = await self._req(args, extra_body=extra_args)
+        resp = await self._req(query, args, extra_body=extra_args, remove_think=remove_think)

        # 处理请求结果
        message = await self._make_msg(resp)

        return message

+    async def _req_stream(
+        self,
+        args: dict,
+        extra_body: dict = {},
+    ) -> chat_completion.ChatCompletion:
+        async for chunk in await self.client.chat.completions.create(**args, extra_body=extra_body):
+            yield chunk
+
+
+    async def _closure_stream(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.Message | typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+
+        # 流式处理状态
+        tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        # accumulated_reasoning = ''  # 仅用于判断何时结束思维链
+
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            reasoning_content = delta.get('reasoning_content', '')
+
+            # 处理 reasoning_content
+            if reasoning_content:
+                # accumulated_reasoning += reasoning_content
+                # 如果设置了 remove_think，跳过 reasoning_content
+                if remove_think:
+                    chunk_idx += 1
+                    continue
+
+                # 第一次出现 reasoning_content，添加 <think> 开始标签
+                if not thinking_started:
+                    thinking_started = True
+                    delta_content = '<think>\n' + reasoning_content
+                else:
+                    # 继续输出 reasoning_content
+                    delta_content = reasoning_content
+            elif thinking_started and not thinking_ended and delta_content:
+                # reasoning_content 结束，normal content 开始，添加 </think> 结束标签
+                thinking_ended = True
+                delta_content = '\n</think>\n' + delta_content
+
+            # 处理 content 中已有的 <think> 标签（如果需要移除）
+            # if delta_content and remove_think and '<think>' in delta_content:
+            #     import re
+            #
+            #     # 移除 <think> 标签及其内容
+            #     delta_content = re.sub(r'<think>.*?</think>', '', delta_content, flags=re.DOTALL)
+
+            # 处理工具调用增量
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] != '':
+                        tool_id = tool_call['id']
+                    if tool_call['function']['name'] is not None:
+                        tool_name = tool_call['function']['name']
+
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+                    tool_call['id'] = tool_id
+                    tool_call['function']['name'] = tool_name
+                    tool_call['function']['arguments'] = "" if tool_call['function']['arguments'] is None else tool_call['function']['arguments']
+
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content and not reasoning_content and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
+            chunk_idx += 1
+            # return
+
    async def invoke_llm(
        self,
        query: core_entities.Query,
@@ -171,6 +305,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
        messages: typing.List[llm_entities.Message],
        funcs: typing.List[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
        for m in messages:
@@ -185,7 +320,7 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):

        try:
            return await self._closure(
-                query=query, req_messages=req_messages, use_model=model, use_funcs=funcs, extra_args=extra_args
+                query=query, req_messages=req_messages, use_model=model, use_funcs=funcs, extra_args=extra_args, remove_think=remove_think
            )
        except asyncio.TimeoutError:
            raise errors.RequesterError('请求超时')
@@ -202,3 +337,50 @@ class ModelScopeChatCompletions(requester.ProviderAPIRequester):
            raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
        except openai.APIError as e:
            raise errors.RequesterError(f'请求错误: {e.message}')
+
+    async def invoke_llm_stream(
+        self,
+        query: core_entities.Query,
+        model: requester.RuntimeLLMModel,
+        messages: typing.List[llm_entities.Message],
+        funcs: typing.List[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.MessageChunk:
+        req_messages = []  # req_messages 仅用于类内，外部同步由 query.messages 进行
+        for m in messages:
+            msg_dict = m.dict(exclude_none=True)
+            content = msg_dict.get('content')
+            if isinstance(content, list):
+                # 检查 content 列表中是否每个部分都是文本
+                if all(isinstance(part, dict) and part.get('type') == 'text' for part in content):
+                    # 将所有文本部分合并为一个字符串
+                    msg_dict['content'] = '\n'.join(part['text'] for part in content)
+            req_messages.append(msg_dict)
+
+        try:
+            async for item in self._closure_stream(
+                query=query,
+                req_messages=req_messages,
+                use_model=model,
+                use_funcs=funcs,
+                extra_args=extra_args,
+                remove_think=remove_think,
+            ):
+                yield item
+
+        except asyncio.TimeoutError:
+            raise errors.RequesterError('请求超时')
+        except openai.BadRequestError as e:
+            if 'context_length_exceeded' in e.message:
+                raise errors.RequesterError(f'上文过长，请重置会话: {e.message}')
+            else:
+                raise errors.RequesterError(f'请求参数错误: {e.message}')
+        except openai.AuthenticationError as e:
+            raise errors.RequesterError(f'无效的 api-key: {e.message}')
+        except openai.NotFoundError as e:
+            raise errors.RequesterError(f'请求路径错误: {e.message}')
+        except openai.RateLimitError as e:
+            raise errors.RequesterError(f'请求过于频繁或余额不足: {e.message}')
+        except openai.APIError as e:
+            raise errors.RequesterError(f'请求错误: {e.message}')
--- a/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/moonshotchatcmpl.py
@@ -25,6 +25,7 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
        use_model: requester.RuntimeLLMModel,
        use_funcs: list[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        self.client.api_key = use_model.token_mgr.get_token()

@@ -54,6 +55,6 @@ class MoonshotChatCompletions(chatcmpl.OpenAIChatCompletions):
        resp = await self._req(args, extra_body=extra_args)

        # 处理请求结果
-        message = await self._make_msg(resp)
+        message = await self._make_msg(resp, remove_think)

        return message
--- a/pkg/provider/modelmgr/requesters/moonshotchatcmpl.yaml
+++ b/pkg/provider/modelmgr/requesters/moonshotchatcmpl.yaml
@@ -14,7 +14,7 @@ spec:
        zh_Hans: 基础 URL
      type: string
      required: true
-      default: "https://api.moonshot.com/v1"
+      default: "https://api.moonshot.ai/v1"
    - name: timeout
      label:
        en_US: Timeout
--- a/pkg/provider/modelmgr/requesters/newapi.png
+++ b/pkg/provider/modelmgr/requesters/newapi.png
--- a/pkg/provider/modelmgr/requesters/newapichatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/newapichatcmpl.py
@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+import typing
+import openai
+
+from . import chatcmpl
+
+
+class NewAPIChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """New API ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'http://localhost:3000/v1',
+        'timeout': 120,
+    }
--- a/pkg/provider/modelmgr/requesters/newapichatcmpl.yaml
+++ b/pkg/provider/modelmgr/requesters/newapichatcmpl.yaml
@@ -0,0 +1,31 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: new-api-chat-completions
+  label:
+    en_US: New API
+    zh_Hans: New API
+  icon: newapi.png
+spec:
+  config:
+    - name: base_url
+      label:
+        en_US: Base URL
+        zh_Hans: 基础 URL
+      type: string
+      required: true
+      default: "http://localhost:3000/v1"
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_Hans: 超时时间
+      type: integer
+      required: true
+      default: 120
+  support_type:
+    - llm
+    - text-embedding
+execution:
+  python:
+    path: ./newapichatcmpl.py
+    attr: NewAPIChatCompletions
--- a/pkg/provider/modelmgr/requesters/ollamachat.py
+++ b/pkg/provider/modelmgr/requesters/ollamachat.py
@@ -44,6 +44,7 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
        use_model: requester.RuntimeLLMModel,
        use_funcs: list[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        args = extra_args.copy()
        args['model'] = use_model.model_entity.name
@@ -110,6 +111,7 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
        messages: typing.List[llm_entities.Message],
        funcs: typing.List[tools_entities.LLMFunction] = None,
        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
    ) -> llm_entities.Message:
        req_messages: list = []
        for m in messages:
@@ -126,6 +128,7 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
                use_model=model,
                use_funcs=funcs,
                extra_args=extra_args,
+                remove_think=remove_think,
            )
        except asyncio.TimeoutError:
            raise errors.RequesterError('请求超时')
@@ -136,8 +139,8 @@ class OllamaChatCompletions(requester.ProviderAPIRequester):
        input_text: list[str],
        extra_args: dict[str, typing.Any] = {},
    ) -> list[list[float]]:
-        return await self.client.embed(
+        return (await self.client.embed(
            model=model.model_entity.name,
            input=input_text,
            **extra_args,
-        )
+        )).embeddings
--- a/pkg/provider/modelmgr/requesters/ppiochatcmpl.py
+++ b/pkg/provider/modelmgr/requesters/ppiochatcmpl.py
@@ -4,6 +4,12 @@ import openai
 import typing

 from . import chatcmpl
+import openai.types.chat.chat_completion as chat_completion
+from .. import requester
+from ....core import entities as core_entities
+from ... import entities as llm_entities
+from ...tools import entities as tools_entities
+import re


 class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
@@ -15,3 +21,193 @@ class PPIOChatCompletions(chatcmpl.OpenAIChatCompletions):
        'base_url': 'https://api.ppinfra.com/v3/openai',
        'timeout': 120,
    }
+
+    is_think: bool = False
+
+    async def _make_msg(
+        self,
+        chat_completion: chat_completion.ChatCompletion,
+        remove_think: bool,
+    ) -> llm_entities.Message:
+        chatcmpl_message = chat_completion.choices[0].message.model_dump()
+        # print(chatcmpl_message.keys(), chatcmpl_message.values())
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in chatcmpl_message or chatcmpl_message['role'] is None:
+            chatcmpl_message['role'] = 'assistant'
+
+        reasoning_content = chatcmpl_message['reasoning_content'] if 'reasoning_content' in chatcmpl_message else None
+
+        # deepseek的reasoner模型
+        chatcmpl_message["content"] = await self._process_thinking_content(
+            chatcmpl_message['content'],reasoning_content,remove_think)
+
+        # 移除 reasoning_content 字段，避免传递给 Message
+        if 'reasoning_content' in chatcmpl_message:
+            del chatcmpl_message['reasoning_content']
+
+
+        message = llm_entities.Message(**chatcmpl_message)
+
+        return message
+
+    async def _process_thinking_content(
+            self,
+            content: str,
+            reasoning_content: str = None,
+            remove_think: bool = False,
+    ) -> tuple[str, str]:
+        """处理思维链内容
+
+        Args:
+            content: 原始内容
+            reasoning_content: reasoning_content 字段内容
+            remove_think: 是否移除思维链
+
+        Returns:
+            处理后的内容
+        """
+        if remove_think:
+            content = re.sub(
+                r'<think>.*?</think>', '', content, flags=re.DOTALL
+            )
+        else:
+            if reasoning_content is not None:
+                content = (
+                    '<think>\n' + reasoning_content + '\n</think>\n' + content
+                )
+        return content
+
+    async def _make_msg_chunk(
+            self,
+            delta: dict[str, typing.Any],
+            idx: int,
+    ) -> llm_entities.MessageChunk:
+        # 处理流式chunk和完整响应的差异
+        # print(chat_completion.choices[0])
+
+        # 确保 role 字段存在且不为 None
+        if 'role' not in delta or delta['role'] is None:
+            delta['role'] = 'assistant'
+
+        reasoning_content = delta['reasoning_content'] if 'reasoning_content' in delta else None
+
+        delta['content'] = '' if delta['content'] is None else delta['content']
+        # print(reasoning_content)
+
+        # deepseek的reasoner模型
+
+        if reasoning_content is not None:
+            delta['content'] += reasoning_content
+
+        message = llm_entities.MessageChunk(**delta)
+
+        return message
+
+    async def _closure_stream(
+        self,
+        query: core_entities.Query,
+        req_messages: list[dict],
+        use_model: requester.RuntimeLLMModel,
+        use_funcs: list[tools_entities.LLMFunction] = None,
+        extra_args: dict[str, typing.Any] = {},
+        remove_think: bool = False,
+    ) -> llm_entities.Message | typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        self.client.api_key = use_model.token_mgr.get_token()
+
+        args = {}
+        args['model'] = use_model.model_entity.name
+
+        if use_funcs:
+            tools = await self.ap.tool_mgr.generate_tools_for_openai(use_funcs)
+
+            if tools:
+                args['tools'] = tools
+
+        # 设置此次请求中的messages
+        messages = req_messages.copy()
+
+        # 检查vision
+        for msg in messages:
+            if 'content' in msg and isinstance(msg['content'], list):
+                for me in msg['content']:
+                    if me['type'] == 'image_base64':
+                        me['image_url'] = {'url': me['image_base64']}
+                        me['type'] = 'image_url'
+                        del me['image_base64']
+
+        args['messages'] = messages
+        args['stream'] = True
+
+        tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+        chunk_idx = 0
+        thinking_started = False
+        thinking_ended = False
+        role = 'assistant'  # 默认角色
+        async for chunk in self._req_stream(args, extra_body=extra_args):
+            # 解析 chunk 数据
+            if hasattr(chunk, 'choices') and chunk.choices:
+                choice = chunk.choices[0]
+                delta = choice.delta.model_dump() if hasattr(choice, 'delta') else {}
+                finish_reason = getattr(choice, 'finish_reason', None)
+            else:
+                delta = {}
+                finish_reason = None
+
+            # 从第一个 chunk 获取 role，后续使用这个 role
+            if 'role' in delta and delta['role']:
+                role = delta['role']
+
+            # 获取增量内容
+            delta_content = delta.get('content', '')
+            # reasoning_content = delta.get('reasoning_content', '')
+
+            if remove_think:
+                if delta['content'] is not None:
+                    if '<think>' in delta['content'] and not thinking_started and not thinking_ended:
+                        thinking_started = True
+                        continue
+                    elif delta['content'] == r'</think>' and not thinking_ended:
+                        thinking_ended = True
+                        continue
+                    elif thinking_ended and delta['content'] == '\n\n' and thinking_started:
+                        thinking_started = False
+                        continue
+                    elif thinking_started and not thinking_ended:
+                        continue
+
+
+            delta_tool_calls = None
+            if delta.get('tool_calls'):
+                for tool_call in delta['tool_calls']:
+                    if tool_call['id'] and tool_call['function']['name']:
+                        tool_id = tool_call['id']
+                        tool_name = tool_call['function']['name']
+
+                    if tool_call['id'] is None:
+                        tool_call['id'] = tool_id
+                    if tool_call['function']['name'] is None:
+                        tool_call['function']['name'] = tool_name
+                    if tool_call['function']['arguments'] is None:
+                        tool_call['function']['arguments'] = ''
+                    if tool_call['type'] is None:
+                        tool_call['type'] = 'function'
+
+            # 跳过空的第一个 chunk（只有 role 没有内容）
+            if chunk_idx == 0 and not delta_content  and not delta.get('tool_calls'):
+                chunk_idx += 1
+                continue
+
+            # 构建 MessageChunk - 只包含增量内容
+            chunk_data = {
+                'role': role,
+                'content': delta_content if delta_content else None,
+                'tool_calls': delta.get('tool_calls'),
+                'is_final': bool(finish_reason),
+            }
+
+            # 移除 None 值
+            chunk_data = {k: v for k, v in chunk_data.items() if v is not None}
+
+            yield llm_entities.MessageChunk(**chunk_data)
+            chunk_idx += 1
--- a/pkg/provider/modelmgr/requesters/shengsuanyun.py
+++ b/pkg/provider/modelmgr/requesters/shengsuanyun.py
@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+import openai
+import typing
+
+from . import chatcmpl
+import openai.types.chat.chat_completion as chat_completion
+
+
+class ShengSuanYunChatCompletions(chatcmpl.OpenAIChatCompletions):
+    """胜算云(ModelSpot.AI) ChatCompletion API 请求器"""
+
+    client: openai.AsyncClient
+
+    default_config: dict[str, typing.Any] = {
+        'base_url': 'https://router.shengsuanyun.com/api/v1',
+        'timeout': 120,
+    }
+
+    async def _req(
+        self,
+        args: dict,
+        extra_body: dict = {},
+    ) -> chat_completion.ChatCompletion:
+        return await self.client.chat.completions.create(
+            **args,
+            extra_body=extra_body,
+            extra_headers={
+                'HTTP-Referer': 'https://langbot.app',
+                'X-Title': 'LangBot',
+            },
+        )
--- a/pkg/provider/modelmgr/requesters/shengsuanyun.svg
+++ b/pkg/provider/modelmgr/requesters/shengsuanyun.svg
--- a/pkg/provider/modelmgr/requesters/shengsuanyun.yaml
+++ b/pkg/provider/modelmgr/requesters/shengsuanyun.yaml
@@ -0,0 +1,38 @@
+apiVersion: v1
+kind: LLMAPIRequester
+metadata:
+  name: shengsuanyun-chat-completions
+  label:
+    en_US: ShengSuanYun
+    zh_Hans: 胜算云
+  icon: shengsuanyun.svg
+spec:
+  config:
+    - name: base_url
+      label:
+        en_US: Base URL
+        zh_Hans: 基础 URL
+      type: string
+      required: true
+      default: "https://router.shengsuanyun.com/api/v1"
+    - name: args
+      label:
+        en_US: Args
+        zh_Hans: 附加参数
+      type: object
+      required: true
+      default: {}
+    - name: timeout
+      label:
+        en_US: Timeout
+        zh_Hans: 超时时间
+      type: int
+      required: true
+      default: 120
+  support_type:
+    - llm
+    - text-embedding
+execution:
+  python:
+    path: ./shengsuanyun.py
+    attr: ShengSuanYunChatCompletions
--- a/pkg/provider/runners/dashscopeapi.py
+++ b/pkg/provider/runners/dashscopeapi.py
@@ -99,8 +99,14 @@ class DashScopeAPIRunner(runner.RequestRunner):
        plain_text = ''  # 用户输入的纯文本信息
        image_ids = []  # 用户输入的图片ID列表 （暂不支持）

-        plain_text, image_ids = await self._preprocess_user_message(query)
+        think_start = False
+        think_end = False

+        plain_text, image_ids = await self._preprocess_user_message(query)
+        has_thoughts = True # 获取思考过程
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
+        if remove_think:
+            has_thoughts = False
        # 发送对话请求
        response = dashscope.Application.call(
            api_key=self.api_key,  # 智能体应用的API Key
@@ -109,43 +115,108 @@ class DashScopeAPIRunner(runner.RequestRunner):
            stream=True,  # 流式输出
            incremental_output=True,  # 增量输出，使用流式输出需要开启增量输出
            session_id=query.session.using_conversation.uuid,  # 会话ID用于，多轮对话
+            has_thoughts=has_thoughts,
            # rag_options={                                     # 主要用于文件交互，暂不支持
            #     "session_file_ids": ["FILE_ID1"],             # FILE_ID1 替换为实际的临时文件ID,逗号隔开多个
            # }
        )
+        idx_chunk = 0
+        try:
+            is_stream = await query.adapter.is_stream_output_supported()

-        for chunk in response:
-            if chunk.get('status_code') != 200:
-                raise DashscopeAPIError(
-                    f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
-                )
-            if not chunk:
-                continue
+        except AttributeError:
+            is_stream = False
+        if is_stream:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+                idx_chunk += 1
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                stream_think = stream_output.get('thoughts', [])
+                if stream_think[0].get('thought'):
+                    if not think_start:
+                        think_start = True
+                        pending_content += f"<think>\n{stream_think[0].get('thought')}"
+                    else:
+                        # 继续输出 reasoning_content
+                        pending_content += stream_think[0].get('thought')
+                elif stream_think[0].get('thought') == "" and not think_end:
+                    think_end = True
+                    pending_content += "\n</think>\n"
+                if stream_output.get('text') is not None:
+                    pending_content += stream_output.get('text')
+                # 是否是流式最后一个chunk
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True

-            # 获取流式传输的output
-            stream_output = chunk.get('output', {})
-            if stream_output.get('text') is not None:
-                pending_content += stream_output.get('text')
+                # 获取模型传出的参考资料列表
+                references_dict_list = stream_output.get('doc_references', [])

-        # 保存当前会话的session_id用于下次对话的语境
-        query.session.using_conversation.uuid = stream_output.get('session_id')
+                # 从模型传出的参考资料信息中提取用于替换的字典
+                if references_dict_list is not None:
+                    for doc in references_dict_list:
+                        if doc.get('index_id') is not None:
+                            references_dict[doc.get('index_id')] = doc.get('doc_name')

-        # 获取模型传出的参考资料列表
-        references_dict_list = stream_output.get('doc_references', [])
+                    # 将参考资料替换到文本中
+                    pending_content = self._replace_references(pending_content, references_dict)

-        # 从模型传出的参考资料信息中提取用于替换的字典
-        if references_dict_list is not None:
-            for doc in references_dict_list:
-                if doc.get('index_id') is not None:
-                    references_dict[doc.get('index_id')] = doc.get('doc_name')
+                if idx_chunk % 8 == 0 or is_final:
+                    yield llm_entities.MessageChunk(
+                        role='assistant',
+                        content=pending_content,
+                        is_final=is_final,
+                    )
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')
+        else:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+                idx_chunk += 1
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                stream_think = stream_output.get('thoughts', [])
+                if stream_think[0].get('thought'):
+                    if not think_start:
+                        think_start = True
+                        pending_content += f"<think>\n{stream_think[0].get('thought')}"
+                    else:
+                        # 继续输出 reasoning_content
+                        pending_content += stream_think[0].get('thought')
+                elif stream_think[0].get('thought') == "" and not think_end:
+                    think_end = True
+                    pending_content += "\n</think>\n"
+                if stream_output.get('text') is not None:
+                    pending_content += stream_output.get('text')

-            # 将参考资料替换到文本中
-            pending_content = self._replace_references(pending_content, references_dict)
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')

-        yield llm_entities.Message(
-            role='assistant',
-            content=pending_content,
-        )
+            # 获取模型传出的参考资料列表
+            references_dict_list = stream_output.get('doc_references', [])
+
+            # 从模型传出的参考资料信息中提取用于替换的字典
+            if references_dict_list is not None:
+                for doc in references_dict_list:
+                    if doc.get('index_id') is not None:
+                        references_dict[doc.get('index_id')] = doc.get('doc_name')
+
+                # 将参考资料替换到文本中
+                pending_content = self._replace_references(pending_content, references_dict)
+
+            yield llm_entities.Message(
+                role='assistant',
+                content=pending_content,
+            )

    async def _workflow_messages(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.Message, None]:
        """Dashscope 工作流对话请求"""
@@ -171,52 +242,108 @@ class DashScopeAPIRunner(runner.RequestRunner):
            incremental_output=True,  # 增量输出，使用流式输出需要开启增量输出
            session_id=query.session.using_conversation.uuid,  # 会话ID用于，多轮对话
            biz_params=biz_params,  # 工作流应用的自定义输入参数传递
+            flow_stream_mode="message_format"  # 消息模式，输出/结束节点的流式结果
            # rag_options={                                     # 主要用于文件交互，暂不支持
            #     "session_file_ids": ["FILE_ID1"],             # FILE_ID1 替换为实际的临时文件ID,逗号隔开多个
            # }
        )

        # 处理API返回的流式输出
-        for chunk in response:
-            if chunk.get('status_code') != 200:
-                raise DashscopeAPIError(
-                    f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
-                )
-            if not chunk:
-                continue
+        try:
+            is_stream = await query.adapter.is_stream_output_supported()

-            # 获取流式传输的output
-            stream_output = chunk.get('output', {})
-            if stream_output.get('text') is not None:
-                pending_content += stream_output.get('text')
+        except AttributeError:
+            is_stream = False
+        idx_chunk = 0
+        if is_stream:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+                idx_chunk += 1
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                if stream_output.get('workflow_message') is not None:
+                    pending_content +=  stream_output.get('workflow_message').get('message').get('content')
+                # if stream_output.get('text') is not None:
+                #     pending_content += stream_output.get('text')

-        # 保存当前会话的session_id用于下次对话的语境
-        query.session.using_conversation.uuid = stream_output.get('session_id')
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True

-        # 获取模型传出的参考资料列表
-        references_dict_list = stream_output.get('doc_references', [])
+                # 获取模型传出的参考资料列表
+                references_dict_list = stream_output.get('doc_references', [])

-        # 从模型传出的参考资料信息中提取用于替换的字典
-        if references_dict_list is not None:
-            for doc in references_dict_list:
-                if doc.get('index_id') is not None:
-                    references_dict[doc.get('index_id')] = doc.get('doc_name')
+                # 从模型传出的参考资料信息中提取用于替换的字典
+                if references_dict_list is not None:
+                    for doc in references_dict_list:
+                        if doc.get('index_id') is not None:
+                            references_dict[doc.get('index_id')] = doc.get('doc_name')

-            # 将参考资料替换到文本中
-            pending_content = self._replace_references(pending_content, references_dict)
+                    # 将参考资料替换到文本中
+                    pending_content = self._replace_references(pending_content, references_dict)
+                if idx_chunk % 8 == 0 or is_final:
+                    yield llm_entities.MessageChunk(
+                        role='assistant',
+                        content=pending_content,
+                        is_final=is_final,
+                    )

-        yield llm_entities.Message(
-            role='assistant',
-            content=pending_content,
-        )
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')
+
+        else:
+            for chunk in response:
+                if chunk.get('status_code') != 200:
+                    raise DashscopeAPIError(
+                        f'Dashscope API 请求失败: status_code={chunk.get("status_code")} message={chunk.get("message")} request_id={chunk.get("request_id")} '
+                    )
+                if not chunk:
+                    continue
+
+                # 获取流式传输的output
+                stream_output = chunk.get('output', {})
+                if stream_output.get('text') is not None:
+                    pending_content += stream_output.get('text')
+
+                is_final = False if stream_output.get('finish_reason', False) == 'null' else True
+
+            # 保存当前会话的session_id用于下次对话的语境
+            query.session.using_conversation.uuid = stream_output.get('session_id')
+
+            # 获取模型传出的参考资料列表
+            references_dict_list = stream_output.get('doc_references', [])
+
+            # 从模型传出的参考资料信息中提取用于替换的字典
+            if references_dict_list is not None:
+                for doc in references_dict_list:
+                    if doc.get('index_id') is not None:
+                        references_dict[doc.get('index_id')] = doc.get('doc_name')
+
+                # 将参考资料替换到文本中
+                pending_content = self._replace_references(pending_content, references_dict)
+
+            yield llm_entities.Message(
+                role='assistant',
+                content=pending_content,
+            )

    async def run(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.Message, None]:
        """运行"""
+        msg_seq = 0
        if self.app_type == 'agent':
            async for msg in self._agent_messages(query):
+                if isinstance(msg, llm_entities.MessageChunk):
+                    msg_seq += 1
+                    msg.msg_sequence = msg_seq
                yield msg
        elif self.app_type == 'workflow':
            async for msg in self._workflow_messages(query):
+                if isinstance(msg, llm_entities.MessageChunk):
+                    msg_seq += 1
+                    msg.msg_sequence = msg_seq
                yield msg
        else:
            raise DashscopeAPIError(f'不支持的 Dashscope 应用类型: {self.app_type}')
--- a/pkg/provider/runners/difysvapi.py
+++ b/pkg/provider/runners/difysvapi.py
@@ -3,7 +3,6 @@ from __future__ import annotations
 import typing
 import json
 import uuid
-import re
 import base64


@@ -38,29 +37,38 @@ class DifyServiceAPIRunner(runner.RequestRunner):
            base_url=self.pipeline_config['ai']['dify-service-api']['base-url'],
        )

-    def _try_convert_thinking(self, resp_text: str) -> str:
-        """尝试转换 Dify 的思考提示"""
-        if not resp_text.startswith(
-            '<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>'
-        ):
-            return resp_text
+    def _process_thinking_content(
+        self,
+        content: str,
+    ) -> tuple[str, str]:
+        """处理思维链内容

-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'original':
-            return resp_text
+        Args:
+            content: 原始内容
+        Returns:
+            (处理后的内容, 提取的思维链内容)
+        """
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
+        thinking_content = ''
+        # 从 content 中提取 <think> 标签内容
+        if content and '<think>' in content and '</think>' in content:
+            import re

-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'remove':
-            return re.sub(
-                r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>.*?</details>',
-                '',
-                resp_text,
-                flags=re.DOTALL,
-            )
+            think_pattern = r'<think>(.*?)</think>'
+            think_matches = re.findall(think_pattern, content, re.DOTALL)
+            if think_matches:
+                thinking_content = '\n'.join(think_matches)
+                # 移除 content 中的 <think> 标签
+                content = re.sub(think_pattern, '', content, flags=re.DOTALL).strip()

-        if self.pipeline_config['ai']['dify-service-api']['thinking-convert'] == 'plain':
-            pattern = r'<details style="color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;" open> <summary> Thinking... </summary>(.*?)</details>'
-            thinking_text = re.search(pattern, resp_text, flags=re.DOTALL)
-            content_text = re.sub(pattern, '', resp_text, flags=re.DOTALL)
-            return f'<think>{thinking_text.group(1)}</think>\n{content_text}'
+        # 3. 根据 remove_think 参数决定是否保留思维链
+        if remove_think:
+            return content, ''
+        else:
+            # 如果有思维链内容，将其以 <think> 格式添加到 content 开头
+            if thinking_content:
+                content = f'<think>\n{thinking_content}\n</think>\n{content}'.strip()
+            return content, thinking_content

    async def _preprocess_user_message(self, query: core_entities.Query) -> tuple[str, list[str]]:
        """预处理用户消息，提取纯文本，并将图片上传到 Dify 服务
@@ -132,17 +140,20 @@ class DifyServiceAPIRunner(runner.RequestRunner):
            if mode == 'workflow':
                if chunk['event'] == 'node_finished':
                    if chunk['data']['node_type'] == 'answer':
+                        content, _ = self._process_thinking_content(chunk['data']['outputs']['answer'])
+
                        yield llm_entities.Message(
                            role='assistant',
-                            content=self._try_convert_thinking(chunk['data']['outputs']['answer']),
+                            content=content,
                        )
            elif mode == 'basic':
                if chunk['event'] == 'message':
                    basic_mode_pending_chunk += chunk['answer']
                elif chunk['event'] == 'message_end':
+                    content, _ = self._process_thinking_content(basic_mode_pending_chunk)
                    yield llm_entities.Message(
                        role='assistant',
-                        content=self._try_convert_thinking(basic_mode_pending_chunk),
+                        content=content,
                    )
                    basic_mode_pending_chunk = ''

@@ -193,14 +204,15 @@ class DifyServiceAPIRunner(runner.RequestRunner):
            if chunk['event'] in ignored_events:
                continue

-            if chunk['event'] == 'agent_message':
+            if chunk['event'] == 'agent_message' or chunk['event'] == 'message':
                pending_agent_message += chunk['answer']
            else:
                if pending_agent_message.strip() != '':
                    pending_agent_message = pending_agent_message.replace('</details>Action:', '</details>')
+                    content, _ = self._process_thinking_content(pending_agent_message)
                    yield llm_entities.Message(
                        role='assistant',
-                        content=self._try_convert_thinking(pending_agent_message),
+                        content=content,
                    )
                pending_agent_message = ''

@@ -308,26 +320,352 @@ class DifyServiceAPIRunner(runner.RequestRunner):
            elif chunk['event'] == 'workflow_finished':
                if chunk['data']['error']:
                    raise errors.DifyAPIError(chunk['data']['error'])
+                content, _ = self._process_thinking_content(chunk['data']['outputs']['summary'])

                msg = llm_entities.Message(
                    role='assistant',
-                    content=chunk['data']['outputs']['summary'],
+                    content=content,
                )

                yield msg

+    async def _chat_messages_chunk(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        """调用聊天助手"""
+        cov_id = query.session.using_conversation.uuid or ''
+        query.variables['conversation_id'] = cov_id
+
+        plain_text, image_ids = await self._preprocess_user_message(query)
+
+        files = [
+            {
+                'type': 'image',
+                'transfer_method': 'local_file',
+                'upload_file_id': image_id,
+            }
+            for image_id in image_ids
+        ]
+
+        basic_mode_pending_chunk = ''
+
+        inputs = {}
+
+        inputs.update(query.variables)
+        message_idx = 0
+
+        chunk = None  # 初始化chunk变量，防止在没有响应时引用错误
+
+        is_final = False
+        think_start = False
+        think_end = False
+
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
+
+        async for chunk in self.dify_client.chat_messages(
+            inputs=inputs,
+            query=plain_text,
+            user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
+            conversation_id=cov_id,
+            files=files,
+            timeout=120,
+        ):
+            self.ap.logger.debug('dify-chat-chunk: ' + str(chunk))
+
+            # if chunk['event'] == 'workflow_started':
+            #     mode = 'workflow'
+            # if mode == 'workflow':
+            # elif mode == 'basic':
+            # 因为都只是返回的 message也没有工具调用什么的，暂时不分类
+            if chunk['event'] == 'message':
+                message_idx += 1
+                if remove_think:
+                    if '<think>' in chunk['answer'] and not think_start:
+                        think_start = True
+                        continue
+                    if '</think>' in chunk['answer'] and not think_end:
+                        import re
+
+                        content = re.sub(r'^\n</think>', '', chunk['answer'])
+                        basic_mode_pending_chunk += content
+                        think_end = True
+                    elif think_end:
+                        basic_mode_pending_chunk += chunk['answer']
+                    if think_start:
+                        continue
+
+                else:
+                    basic_mode_pending_chunk += chunk['answer']
+
+            if chunk['event'] == 'message_end':
+                is_final = True
+
+            if is_final or message_idx % 8 == 0:
+                # content, _ = self._process_thinking_content(basic_mode_pending_chunk)
+                yield llm_entities.MessageChunk(
+                    role='assistant',
+                    content=basic_mode_pending_chunk,
+                    is_final=is_final,
+                )
+
+        if chunk is None:
+            raise errors.DifyAPIError('Dify API 没有返回任何响应，请检查网络连接和API配置')
+
+        query.session.using_conversation.uuid = chunk['conversation_id']
+
+    async def _agent_chat_messages_chunk(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        """调用聊天助手"""
+        cov_id = query.session.using_conversation.uuid or ''
+        query.variables['conversation_id'] = cov_id
+
+        plain_text, image_ids = await self._preprocess_user_message(query)
+
+        files = [
+            {
+                'type': 'image',
+                'transfer_method': 'local_file',
+                'upload_file_id': image_id,
+            }
+            for image_id in image_ids
+        ]
+
+        ignored_events = []
+
+        inputs = {}
+
+        inputs.update(query.variables)
+
+        pending_agent_message = ''
+
+        chunk = None  # 初始化chunk变量，防止在没有响应时引用错误
+        message_idx = 0
+        is_final = False
+        think_start = False
+        think_end = False
+
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
+
+        async for chunk in self.dify_client.chat_messages(
+            inputs=inputs,
+            query=plain_text,
+            user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
+            response_mode='streaming',
+            conversation_id=cov_id,
+            files=files,
+            timeout=120,
+        ):
+            self.ap.logger.debug('dify-agent-chunk: ' + str(chunk))
+
+            if chunk['event'] in ignored_events:
+                continue
+
+            if chunk['event'] == 'agent_message':
+                message_idx += 1
+                if remove_think:
+                    if '<think>' in chunk['answer'] and not think_start:
+                        think_start = True
+                        continue
+                    if '</think>' in chunk['answer'] and not think_end:
+                        import re
+
+                        content = re.sub(r'^\n</think>', '', chunk['answer'])
+                        pending_agent_message += content
+                        think_end = True
+                    elif think_end or not think_start:
+                        pending_agent_message += chunk['answer']
+                    if think_start:
+                        continue
+
+                else:
+                    pending_agent_message += chunk['answer']
+            elif chunk['event'] == 'message_end':
+                is_final = True
+            else:
+                if chunk['event'] == 'agent_thought':
+                    if chunk['tool'] != '' and chunk['observation'] != '':  # 工具调用结果，跳过
+                        continue
+                    message_idx += 1
+                    if chunk['tool']:
+                        msg = llm_entities.MessageChunk(
+                            role='assistant',
+                            tool_calls=[
+                                llm_entities.ToolCall(
+                                    id=chunk['id'],
+                                    type='function',
+                                    function=llm_entities.FunctionCall(
+                                        name=chunk['tool'],
+                                        arguments=json.dumps({}),
+                                    ),
+                                )
+                            ],
+                        )
+                        yield msg
+                if chunk['event'] == 'message_file':
+                    message_idx += 1
+                    if chunk['type'] == 'image' and chunk['belongs_to'] == 'assistant':
+                        base_url = self.dify_client.base_url
+
+                        if base_url.endswith('/v1'):
+                            base_url = base_url[:-3]
+
+                        image_url = base_url + chunk['url']
+
+                        yield llm_entities.MessageChunk(
+                            role='assistant',
+                            content=[llm_entities.ContentElement.from_image_url(image_url)],
+                            is_final=is_final,
+                        )
+
+                if chunk['event'] == 'error':
+                    raise errors.DifyAPIError('dify 服务错误: ' + chunk['message'])
+            if message_idx % 8 == 0 or is_final:
+                yield llm_entities.MessageChunk(
+                    role='assistant',
+                    content=pending_agent_message,
+                    is_final=is_final,
+                )
+
+        if chunk is None:
+            raise errors.DifyAPIError('Dify API 没有返回任何响应，请检查网络连接和API配置')
+
+        query.session.using_conversation.uuid = chunk['conversation_id']
+
+    async def _workflow_messages_chunk(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.MessageChunk, None]:
+        """调用工作流"""
+
+        if not query.session.using_conversation.uuid:
+            query.session.using_conversation.uuid = str(uuid.uuid4())
+
+        query.variables['conversation_id'] = query.session.using_conversation.uuid
+
+        plain_text, image_ids = await self._preprocess_user_message(query)
+
+        files = [
+            {
+                'type': 'image',
+                'transfer_method': 'local_file',
+                'upload_file_id': image_id,
+            }
+            for image_id in image_ids
+        ]
+
+        ignored_events = ['workflow_started']
+
+        inputs = {  # these variables are legacy variables, we need to keep them for compatibility
+            'langbot_user_message_text': plain_text,
+            'langbot_session_id': query.variables['session_id'],
+            'langbot_conversation_id': query.variables['conversation_id'],
+            'langbot_msg_create_time': query.variables['msg_create_time'],
+        }
+
+        inputs.update(query.variables)
+        messsage_idx = 0
+        is_final = False
+        think_start = False
+        think_end = False
+        workflow_contents = ''
+
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')
+        async for chunk in self.dify_client.workflow_run(
+            inputs=inputs,
+            user=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
+            files=files,
+            timeout=120,
+        ):
+            self.ap.logger.debug('dify-workflow-chunk: ' + str(chunk))
+            if chunk['event'] in ignored_events:
+                continue
+            if chunk['event'] == 'workflow_finished':
+                is_final = True
+                if chunk['data']['error']:
+                    raise errors.DifyAPIError(chunk['data']['error'])
+
+            if chunk['event'] == 'text_chunk':
+                messsage_idx += 1
+                if remove_think:
+                    if '<think>' in chunk['data']['text'] and not think_start:
+                        think_start = True
+                        continue
+                    if '</think>' in chunk['data']['text'] and not think_end:
+                        import re
+
+                        content = re.sub(r'^\n</think>', '', chunk['data']['text'])
+                        workflow_contents += content
+                        think_end = True
+                    elif think_end:
+                        workflow_contents += chunk['data']['text']
+                    if think_start:
+                        continue
+
+                else:
+                    workflow_contents += chunk['data']['text']
+
+            if chunk['event'] == 'node_started':
+                if chunk['data']['node_type'] == 'start' or chunk['data']['node_type'] == 'end':
+                    continue
+                messsage_idx += 1
+                msg = llm_entities.MessageChunk(
+                    role='assistant',
+                    content=None,
+                    tool_calls=[
+                        llm_entities.ToolCall(
+                            id=chunk['data']['node_id'],
+                            type='function',
+                            function=llm_entities.FunctionCall(
+                                name=chunk['data']['title'],
+                                arguments=json.dumps({}),
+                            ),
+                        )
+                    ],
+                )
+
+                yield msg
+
+            if messsage_idx % 8 == 0 or is_final:
+                yield llm_entities.MessageChunk(
+                    role='assistant',
+                    content=workflow_contents,
+                    is_final=is_final,
+                )
+
    async def run(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.Message, None]:
        """运行请求"""
-        if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
-            async for msg in self._chat_messages(query):
-                yield msg
-        elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
-            async for msg in self._agent_chat_messages(query):
-                yield msg
-        elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
-            async for msg in self._workflow_messages(query):
-                yield msg
+        if await query.adapter.is_stream_output_supported():
+            msg_idx = 0
+            if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
+                async for msg in self._chat_messages_chunk(query):
+                    msg_idx += 1
+                    msg.msg_sequence = msg_idx
+                    yield msg
+            elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
+                async for msg in self._agent_chat_messages_chunk(query):
+                    msg_idx += 1
+                    msg.msg_sequence = msg_idx
+                    yield msg
+            elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
+                async for msg in self._workflow_messages_chunk(query):
+                    msg_idx += 1
+                    msg.msg_sequence = msg_idx
+                    yield msg
+            else:
+                raise errors.DifyAPIError(
+                    f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
+                )
        else:
-            raise errors.DifyAPIError(
-                f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
-            )
+            if self.pipeline_config['ai']['dify-service-api']['app-type'] == 'chat':
+                async for msg in self._chat_messages(query):
+                    yield msg
+            elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'agent':
+                async for msg in self._agent_chat_messages(query):
+                    yield msg
+            elif self.pipeline_config['ai']['dify-service-api']['app-type'] == 'workflow':
+                async for msg in self._workflow_messages(query):
+                    yield msg
+            else:
+                raise errors.DifyAPIError(
+                    f'不支持的 Dify 应用类型: {self.pipeline_config["ai"]["dify-service-api"]["app-type"]}'
+                )
--- a/pkg/provider/runners/localagent.py
+++ b/pkg/provider/runners/localagent.py
@@ -27,7 +27,16 @@ Respond in the same language as the user's input.
 class LocalAgentRunner(runner.RequestRunner):
    """本地Agent请求运行器"""

-    async def run(self, query: core_entities.Query) -> typing.AsyncGenerator[llm_entities.Message, None]:
+    class ToolCallTracker:
+        """工具调用追踪器"""
+
+        def __init__(self):
+            self.active_calls: dict[str, dict] = {}
+            self.completed_calls: list[llm_entities.ToolCall] = []
+
+    async def run(
+        self, query: core_entities.Query
+    ) -> typing.AsyncGenerator[llm_entities.Message | llm_entities.MessageChunk, None]:
        """运行请求"""
        pending_tool_calls = []

@@ -56,7 +65,7 @@ class LocalAgentRunner(runner.RequestRunner):
                self.ap.logger.warning(f'Knowledge base {kb_uuid} not found')
                raise ValueError(f'Knowledge base {kb_uuid} not found')

-            result = await kb.retrieve(user_message_text)
+            result = await kb.retrieve(user_message_text, kb.knowledge_base_entity.top_k)

            final_user_message_text = ''

@@ -80,20 +89,92 @@ class LocalAgentRunner(runner.RequestRunner):

        req_messages = query.prompt.messages.copy() + query.messages.copy() + [user_message]

-        # 首次请求
-        msg = await query.use_llm_model.requester.invoke_llm(
-            query,
-            query.use_llm_model,
-            req_messages,
-            query.use_funcs,
-            extra_args=query.use_llm_model.model_entity.extra_args,
-        )
+        try:
+            is_stream = await query.adapter.is_stream_output_supported()
+        except AttributeError:
+            is_stream = False

-        yield msg
+        remove_think = self.pipeline_config['output'].get('misc', '').get('remove-think')

-        pending_tool_calls = msg.tool_calls
+        if not is_stream:
+            # 非流式输出，直接请求

-        req_messages.append(msg)
+            msg = await query.use_llm_model.requester.invoke_llm(
+                query,
+                query.use_llm_model,
+                req_messages,
+                query.use_funcs,
+                extra_args=query.use_llm_model.model_entity.extra_args,
+                remove_think=remove_think,
+            )
+            yield msg
+            final_msg = msg
+        else:
+            # 流式输出，需要处理工具调用
+            tool_calls_map: dict[str, llm_entities.ToolCall] = {}
+            msg_idx = 0
+            accumulated_content = ''  # 从开始累积的所有内容
+            last_role = 'assistant'
+            msg_sequence = 1
+            async for msg in query.use_llm_model.requester.invoke_llm_stream(
+                query,
+                query.use_llm_model,
+                req_messages,
+                query.use_funcs,
+                extra_args=query.use_llm_model.model_entity.extra_args,
+                remove_think=remove_think,
+            ):
+                msg_idx = msg_idx + 1
+
+                # 记录角色
+                if msg.role:
+                    last_role = msg.role
+
+                # 累积内容
+                if msg.content:
+                    accumulated_content += msg.content
+
+                # 处理工具调用
+                if msg.tool_calls:
+                    for tool_call in msg.tool_calls:
+                        if tool_call.id not in tool_calls_map:
+                            tool_calls_map[tool_call.id] = llm_entities.ToolCall(
+                                id=tool_call.id,
+                                type=tool_call.type,
+                                function=llm_entities.FunctionCall(
+                                    name=tool_call.function.name if tool_call.function else '', arguments=''
+                                ),
+                            )
+                        if tool_call.function and tool_call.function.arguments:
+                            # 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
+                            tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
+                # continue
+                # 每8个chunk或最后一个chunk时，输出所有累积的内容
+                if msg_idx % 8 == 0 or msg.is_final:
+                    msg_sequence += 1
+                    yield llm_entities.MessageChunk(
+                        role=last_role,
+                        content=accumulated_content,  # 输出所有累积内容
+                        tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
+                        is_final=msg.is_final,
+                        msg_sequence=msg_sequence,
+                    )
+
+            # 创建最终消息用于后续处理
+            final_msg = llm_entities.MessageChunk(
+                role=last_role,
+                content=accumulated_content,
+                tool_calls=list(tool_calls_map.values()) if tool_calls_map else None,
+                msg_sequence=msg_sequence,
+            )
+
+        pending_tool_calls = final_msg.tool_calls
+        first_content = final_msg.content
+        if isinstance(final_msg, llm_entities.MessageChunk):
+
+            first_end_sequence = final_msg.msg_sequence
+
+        req_messages.append(final_msg)

        # 持续请求，只要还有待处理的工具调用就继续处理调用
        while pending_tool_calls:
@@ -104,12 +185,18 @@ class LocalAgentRunner(runner.RequestRunner):
                    parameters = json.loads(func.arguments)

                    func_ret = await self.ap.tool_mgr.execute_func_call(query, func.name, parameters)
-
-                    msg = llm_entities.Message(
-                        role='tool',
-                        content=json.dumps(func_ret, ensure_ascii=False),
-                        tool_call_id=tool_call.id,
-                    )
+                    if is_stream:
+                        msg = llm_entities.MessageChunk(
+                            role='tool',
+                            content=json.dumps(func_ret, ensure_ascii=False),
+                            tool_call_id=tool_call.id,
+                        )
+                    else:
+                        msg = llm_entities.Message(
+                            role='tool',
+                            content=json.dumps(func_ret, ensure_ascii=False),
+                            tool_call_id=tool_call.id,
+                        )

                    yield msg

@@ -122,17 +209,82 @@ class LocalAgentRunner(runner.RequestRunner):

                    req_messages.append(err_msg)

-            # 处理完所有调用，再次请求
-            msg = await query.use_llm_model.requester.invoke_llm(
-                query,
-                query.use_llm_model,
-                req_messages,
-                query.use_funcs,
-                extra_args=query.use_llm_model.model_entity.extra_args,
-            )
+            if is_stream:
+                tool_calls_map = {}
+                msg_idx = 0
+                accumulated_content = ''  # 从开始累积的所有内容
+                last_role = 'assistant'
+                msg_sequence = first_end_sequence

-            yield msg
+                async for msg in query.use_llm_model.requester.invoke_llm_stream(
+                    query,
+                    query.use_llm_model,
+                    req_messages,
+                    query.use_funcs,
+                    extra_args=query.use_llm_model.model_entity.extra_args,
+                    remove_think=remove_think,
+                ):
+                    msg_idx += 1

-            pending_tool_calls = msg.tool_calls
+                    # 记录角色
+                    if msg.role:
+                        last_role = msg.role

-            req_messages.append(msg)
+                    # 第一次请求工具调用时的内容
+                    if msg_idx == 1:
+                        accumulated_content = first_content if first_content is not None else accumulated_content
+
+                    # 累积内容
+                    if msg.content:
+                        accumulated_content += msg.content
+
+                    # 处理工具调用
+                    if msg.tool_calls:
+                        for tool_call in msg.tool_calls:
+                            if tool_call.id not in tool_calls_map:
+                                tool_calls_map[tool_call.id] = llm_entities.ToolCall(
+                                    id=tool_call.id,
+                                    type=tool_call.type,
+                                    function=llm_entities.FunctionCall(
+                                        name=tool_call.function.name if tool_call.function else '', arguments=''
+                                    ),
+                                )
+                            if tool_call.function and tool_call.function.arguments:
+                                # 流式处理中，工具调用参数可能分多个chunk返回，需要追加而不是覆盖
+                                tool_calls_map[tool_call.id].function.arguments += tool_call.function.arguments
+
+                    # 每8个chunk或最后一个chunk时，输出所有累积的内容
+                    if msg_idx % 8 == 0 or msg.is_final:
+                        msg_sequence += 1
+                        yield llm_entities.MessageChunk(
+                            role=last_role,
+                            content=accumulated_content,  # 输出所有累积内容
+                            tool_calls=list(tool_calls_map.values()) if (tool_calls_map and msg.is_final) else None,
+                            is_final=msg.is_final,
+                            msg_sequence=msg_sequence,
+                        )
+
+                final_msg = llm_entities.MessageChunk(
+                    role=last_role,
+                    content=accumulated_content,
+                    tool_calls=list(tool_calls_map.values()) if tool_calls_map else None,
+                    msg_sequence=msg_sequence,
+
+                )
+            else:
+                # 处理完所有调用，再次请求
+                msg = await query.use_llm_model.requester.invoke_llm(
+                    query,
+                    query.use_llm_model,
+                    req_messages,
+                    query.use_funcs,
+                    extra_args=query.use_llm_model.model_entity.extra_args,
+                    remove_think=remove_think,
+                )
+
+                yield msg
+                final_msg = msg
+
+            pending_tool_calls = final_msg.tool_calls
+
+            req_messages.append(final_msg)
--- a/pkg/rag/knowledge/kbmgr.py
+++ b/pkg/rag/knowledge/kbmgr.py
@@ -123,11 +123,11 @@ class RuntimeKnowledgeBase:
        )
        return wrapper.id

-    async def retrieve(self, query: str) -> list[retriever_entities.RetrieveResultEntry]:
+    async def retrieve(self, query: str, top_k: int) -> list[retriever_entities.RetrieveResultEntry]:
        embedding_model = await self.ap.model_mgr.get_embedding_model_by_uuid(
            self.knowledge_base_entity.embedding_model_uuid
        )
-        return await self.retriever.retrieve(self.knowledge_base_entity.uuid, query, embedding_model)
+        return await self.retriever.retrieve(self.knowledge_base_entity.uuid, query, embedding_model, top_k)

    async def delete_file(self, file_id: str):
        # delete vector
--- a/pkg/utils/constants.py
+++ b/pkg/utils/constants.py
@@ -1,6 +1,6 @@
-semantic_version = 'v4.1.1'
+semantic_version = 'v4.2.1'

-required_database_version = 4
+required_database_version = 5
 """Tag the version of the database schema, used to check if the database needs to be migrated"""

 debug_mode = False
--- a/pkg/utils/image.py
+++ b/pkg/utils/image.py
@@ -204,9 +204,9 @@ async def get_slack_image_to_base64(pic_url: str, bot_token: str):
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(pic_url, headers=headers) as resp:
-                mime_type = resp.headers.get("Content-Type", "application/octet-stream")
+                mime_type = resp.headers.get('Content-Type', 'application/octet-stream')
                file_bytes = await resp.read()
-                base64_str = base64.b64encode(file_bytes).decode("utf-8")
-            return f"data:{mime_type};base64,{base64_str}"
+                base64_str = base64.b64encode(file_bytes).decode('utf-8')
+            return f'data:{mime_type};base64,{base64_str}'
    except Exception as e:
-        raise (e)
+        raise (e)
--- a/pkg/utils/importutil.py
+++ b/pkg/utils/importutil.py
@@ -32,7 +32,7 @@ def import_dir(path: str):
            rel_path = full_path.replace(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), '')
            rel_path = rel_path[1:]
            rel_path = rel_path.replace('/', '.')[:-3]
-            rel_path = rel_path.replace("\\",".")
+            rel_path = rel_path.replace('\\', '.')
            importlib.import_module(rel_path)


--- a/templates/default-pipeline-config.json
+++ b/templates/default-pipeline-config.json
@@ -51,7 +51,6 @@
            "base-url": "https://api.dify.ai/v1",
            "app-type": "chat",
            "api-key": "your-api-key",
-            "thinking-convert": "plain",
            "timeout": 30
        },
        "dashscope-app-api": {
@@ -87,7 +86,8 @@
            "hide-exception": true,
            "at-sender": true,
            "quote-origin": true,
-            "track-function-calls": false
+            "track-function-calls": false,
+            "remove-think": false
        }
    }
 }
--- a/templates/metadata/pipeline/ai.yaml
+++ b/templates/metadata/pipeline/ai.yaml
@@ -118,26 +118,6 @@ stages:
          zh_Hans: API 密钥
        type: string
        required: true
-      - name: thinking-convert
-        label:
-          en_US: CoT Convert
-          zh_Hans: 思维链转换策略
-        type: select
-        required: true
-        default: plain
-        options:
-          - name: plain
-            label:
-              en_US: Convert to <think>...</think>
-              zh_Hans: 转换成 <think>...</think>
-          - name: original
-            label:
-              en_US: Original
-              zh_Hans: 原始
-          - name: remove
-            label:
-              en_US: Remove
-              zh_Hans: 移除
  - name: dashscope-app-api
    label:
      en_US: Aliyun Dashscope App API
--- a/templates/metadata/pipeline/output.yaml
+++ b/templates/metadata/pipeline/output.yaml
@@ -105,3 +105,13 @@ stages:
        type: boolean
        required: true
        default: false
+      - name: remove-think
+        label:
+          en_US: Remove CoT
+          zh_Hans: 删除思维链
+        description:
+          en_US: 'If enabled, LangBot will remove the LLM thought content in response. Note: When using streaming response, removing CoT may cause the first token to wait for a long time.'
+          zh_Hans: '如果启用，将自动删除大模型回复中的模型思考内容。注意：当您使用流式响应时，删除思维链可能会导致首个 Token 的等待时间过长'
+        type: boolean
+        required: true
+        default: false
--- a/web/.env.example
+++ b/web/.env.example
@@ -0,0 +1 @@
+NEXT_PUBLIC_API_BASE_URL=http://localhost:5300
--- a/web/.gitignore
+++ b/web/.gitignore
@@ -32,6 +32,7 @@ yarn-error.log*

 # env files (can opt-in for committing if needed)
 .env*
+!.env.example

 # vercel
 .vercel
--- a/web/README.md
+++ b/web/README.md
@@ -1,36 +1,3 @@
-This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app).
+# Debug LangBot Frontend

-## Getting Started
-
-First, run the development server:
-
-```bash
-npm run dev
-# or
-yarn dev
-# or
-pnpm dev
-# or
-bun dev
-```
-
-Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
-
-You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
-
-This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
-
-## Learn More
-
-To learn more about Next.js, take a look at the following resources:
-
- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
-
-You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js) - your feedback and contributions are welcome!
-
-## Deploy on Vercel
-
-The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
-
-Check out our [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.
+Please refer to the [Development Guide](https://docs.langbot.app/en/develop/dev-config.html) for more information.
--- a/web/package-lock.json
+++ b/web/package-lock.json
@@ -10,8 +10,10 @@
      "dependencies": {
        "@dnd-kit/core": "^6.3.1",
        "@dnd-kit/sortable": "^10.0.0",
+        "@dnd-kit/utilities": "^3.2.2",
        "@hookform/resolvers": "^5.0.1",
        "@radix-ui/react-checkbox": "^1.3.1",
+        "@radix-ui/react-context-menu": "^2.2.15",
        "@radix-ui/react-dialog": "^1.1.14",
        "@radix-ui/react-dropdown-menu": "^2.1.15",
        "@radix-ui/react-hover-card": "^1.1.13",
@@ -145,6 +147,7 @@
      "version": "1.3.1",
      "resolved": "https://registry.npmjs.org/@emnapi/core/-/core-1.3.1.tgz",
      "integrity": "sha512-pVGjBIt1Y6gg3EJN8jTcfpP/+uuRksIo055oE/OBkDNcjZqVbfkWCksG1Jp4yZnj3iKWyWX8fdG/j6UDYPbFog==",
+      "dev": true,
      "optional": true,
      "dependencies": {
        "@emnapi/wasi-threads": "1.0.1",
@@ -164,6 +167,7 @@
      "version": "1.0.1",
      "resolved": "https://registry.npmjs.org/@emnapi/wasi-threads/-/wasi-threads-1.0.1.tgz",
      "integrity": "sha512-iIBu7mwkq4UQGeMEM8bLwNK962nXdhodeScX4slfQnRhEMMzvYivHhutCIk8uojvmASXXPC2WNEjwxFWk72Oqw==",
+      "dev": true,
      "optional": true,
      "dependencies": {
        "tslib": "^2.4.0"
@@ -754,6 +758,7 @@
      "version": "0.2.7",
      "resolved": "https://registry.npmjs.org/@napi-rs/wasm-runtime/-/wasm-runtime-0.2.7.tgz",
      "integrity": "sha512-5yximcFK5FNompXfJFoWanu5l8v1hNGqNHh9du1xETp9HWk/B/PzvchX55WYOPaIeNglG8++68AAiauBAtbnzw==",
+      "dev": true,
      "optional": true,
      "dependencies": {
        "@emnapi/core": "^1.3.1",
@@ -1090,6 +1095,57 @@
        }
      }
    },
+    "node_modules/@radix-ui/react-context-menu": {
+      "version": "2.2.15",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-context-menu/-/react-context-menu-2.2.15.tgz",
+      "integrity": "sha512-UsQUMjcYTsBjTSXw0P3GO0werEQvUY2plgRQuKoCTtkNr45q1DiL51j4m7gxhABzZ0BadoXNsIbg7F3KwiUBbw==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-menu": "2.1.15",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-use-callback-ref": "1.1.1",
+        "@radix-ui/react-use-controllable-state": "1.2.2"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@radix-ui/react-context-menu/node_modules/@radix-ui/react-primitive": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-2.1.3.tgz",
+      "integrity": "sha512-m9gTwRkhy2lvCPe6QJp4d3G1TYEUHn/FzJUtq9MjH46an1wJU+GdoGC5VLof8RX8Ft/DlpshApkhswDLZzHIcQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/react-slot": "1.2.3"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/@radix-ui/react-dialog": {
      "version": "1.1.14",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-dialog/-/react-dialog-1.1.14.tgz",
@@ -2855,6 +2911,60 @@
        "node": ">=14.0.0"
      }
    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/core": {
+      "version": "1.4.3",
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@emnapi/wasi-threads": "1.0.2",
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/runtime": {
+      "version": "1.4.3",
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/wasi-threads": {
+      "version": "1.0.2",
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
+      "version": "0.2.9",
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@emnapi/core": "^1.4.0",
+        "@emnapi/runtime": "^1.4.0",
+        "@tybys/wasm-util": "^0.9.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@tybys/wasm-util": {
+      "version": "0.9.0",
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/tslib": {
+      "version": "2.8.0",
+      "inBundle": true,
+      "license": "0BSD",
+      "optional": true
+    },
    "node_modules/@tailwindcss/oxide-win32-arm64-msvc": {
      "version": "4.1.5",
      "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.5.tgz",
@@ -2937,6 +3047,7 @@
      "version": "0.9.0",
      "resolved": "https://registry.npmjs.org/@tybys/wasm-util/-/wasm-util-0.9.0.tgz",
      "integrity": "sha512-6+7nlbMVX/PVDCwaIQ8nTOPveOcFLSt8GcXdx8hD0bt39uWxYT88uXzqTd4fTvqta7oeUJqudepapKNt2DYJFw==",
+      "dev": true,
      "optional": true,
      "dependencies": {
        "tslib": "^2.4.0"
@@ -5014,14 +5125,15 @@
      }
    },
    "node_modules/form-data": {
-      "version": "4.0.2",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.2.tgz",
-      "integrity": "sha512-hGfm/slu0ZabnNt4oaRZ6uREyfCj6P4fT/n6A1rGV+Z0VdGXjfOhVUpkn6qVQONHGIFwmveGXyDs75+nr6FM8w==",
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
+      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
      "license": "MIT",
      "dependencies": {
        "asynckit": "^0.4.0",
        "combined-stream": "^1.0.8",
        "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
        "mime-types": "^2.1.12"
      },
      "engines": {
--- a/web/package.json
+++ b/web/package.json
@@ -4,8 +4,6 @@
  "private": true,
  "scripts": {
    "dev": "next dev --turbopack",
-    "dev:local": "NEXT_PUBLIC_API_BASE_URL=http://localhost:5300 next dev --turbopack",
-    "dev:local:win": "set NEXT_PUBLIC_API_BASE_URL=http://localhost:5300&&next dev --turbopack",
    "build": "next build",
    "start": "next start",
    "lint": "next lint",
@@ -23,8 +21,10 @@
  "dependencies": {
    "@dnd-kit/core": "^6.3.1",
    "@dnd-kit/sortable": "^10.0.0",
+    "@dnd-kit/utilities": "^3.2.2",
    "@hookform/resolvers": "^5.0.1",
    "@radix-ui/react-checkbox": "^1.3.1",
+    "@radix-ui/react-context-menu": "^2.2.15",
    "@radix-ui/react-dialog": "^1.1.14",
    "@radix-ui/react-dropdown-menu": "^2.1.15",
    "@radix-ui/react-hover-card": "^1.1.13",
--- a/web/src/app/global.css
+++ b/web/src/app/global.css
@@ -56,6 +56,15 @@
  background: rgba(0, 0, 0, 0.35); /* 悬停加深 */
 }

+/* 暗黑模式下的滚动条 */
+.dark ::-webkit-scrollbar-thumb {
+  background: rgba(255, 255, 255, 0.2); /* 半透明白色 */
+}
+
+.dark ::-webkit-scrollbar-thumb:hover {
+  background: rgba(255, 255, 255, 0.35); /* 悬停加深 */
+}
+
 /* 兼容 Edge */
@supports (-ms-ime-align: auto) {
  body {
@@ -108,36 +117,36 @@
 }

 .dark {
-  --background: oklch(0.141 0.005 285.823);
+  --background: oklch(0.08 0.002 285.823);
  --foreground: oklch(0.985 0 0);
-  --card: oklch(0.21 0.006 285.885);
+  --card: oklch(0.12 0.004 285.885);
  --card-foreground: oklch(0.985 0 0);
-  --popover: oklch(0.21 0.006 285.885);
+  --popover: oklch(0.12 0.004 285.885);
  --popover-foreground: oklch(0.985 0 0);
-  --primary: oklch(0.92 0.004 286.32);
-  --primary-foreground: oklch(0.21 0.006 285.885);
-  --secondary: oklch(0.274 0.006 286.033);
+  --primary: oklch(0.62 0.2 255);
+  --primary-foreground: oklch(1 0 0);
+  --secondary: oklch(0.18 0.004 286.033);
  --secondary-foreground: oklch(0.985 0 0);
-  --muted: oklch(0.274 0.006 286.033);
+  --muted: oklch(0.18 0.004 286.033);
  --muted-foreground: oklch(0.705 0.015 286.067);
-  --accent: oklch(0.274 0.006 286.033);
+  --accent: oklch(0.18 0.004 286.033);
  --accent-foreground: oklch(0.985 0 0);
  --destructive: oklch(0.704 0.191 22.216);
-  --border: oklch(1 0 0 / 10%);
-  --input: oklch(1 0 0 / 15%);
+  --border: oklch(1 0 0 / 8%);
+  --input: oklch(1 0 0 / 10%);
  --ring: oklch(0.552 0.016 285.938);
  --chart-1: oklch(0.488 0.243 264.376);
  --chart-2: oklch(0.696 0.17 162.48);
  --chart-3: oklch(0.769 0.188 70.08);
  --chart-4: oklch(0.627 0.265 303.9);
  --chart-5: oklch(0.645 0.246 16.439);
-  --sidebar: oklch(0.21 0.006 285.885);
+  --sidebar: oklch(0.1 0.003 285.885);
  --sidebar-foreground: oklch(0.985 0 0);
-  --sidebar-primary: oklch(0.488 0.243 264.376);
-  --sidebar-primary-foreground: oklch(0.985 0 0);
-  --sidebar-accent: oklch(0.274 0.006 286.033);
+  --sidebar-primary: oklch(0.62 0.2 255);
+  --sidebar-primary-foreground: oklch(1 0 0);
+  --sidebar-accent: oklch(0.18 0.004 286.033);
  --sidebar-accent-foreground: oklch(0.985 0 0);
-  --sidebar-border: oklch(1 0 0 / 10%);
+  --sidebar-border: oklch(1 0 0 / 8%);
  --sidebar-ring: oklch(0.552 0.016 285.938);
 }

--- a/web/src/app/home/bots/BotDetailDialog.tsx
+++ b/web/src/app/home/bots/BotDetailDialog.tsx
@@ -159,7 +159,7 @@ export default function BotDetailDialog({
          <SidebarProvider className="items-start w-full flex">
            <Sidebar
              collapsible="none"
-              className="hidden md:flex h-[80vh] w-40 min-w-[120px] border-r bg-white"
+              className="hidden md:flex h-[80vh] w-40 min-w-[120px] border-r bg-white dark:bg-black"
            >
              <SidebarContent>
                <SidebarGroup>
--- a/web/src/app/home/bots/components/bot-card/botCard.module.css
+++ b/web/src/app/home/bots/components/bot-card/botCard.module.css
@@ -6,12 +6,22 @@
  box-shadow: 0px 2px 2px 0 rgba(0, 0, 0, 0.2);
  padding: 1.2rem;
  cursor: pointer;
+  transition: all 0.2s ease;
+}
+
+:global(.dark) .cardContainer {
+  background-color: #1f1f22;
+  box-shadow: 0;
 }

 .cardContainer:hover {
  box-shadow: 0px 2px 8px 0 rgba(0, 0, 0, 0.1);
 }

+:global(.dark) .cardContainer:hover {
+  box-shadow: 0;
+}
+
 .iconBasicInfoContainer {
  width: 100%;
  height: 100%;
@@ -47,6 +57,11 @@
  white-space: nowrap;
  overflow: hidden;
  text-overflow: ellipsis;
+  color: #1a1a1a;
+}
+
+:global(.dark) .basicInfoName {
+  color: #f0f0f0;
 }

 .basicInfoDescription {
@@ -58,6 +73,10 @@
  text-overflow: ellipsis;
 }

+:global(.dark) .basicInfoDescription {
+  color: #888888;
+}
+
 .basicInfoAdapterContainer {
  display: flex;
  flex-direction: row;
@@ -71,12 +90,20 @@
  color: #626262;
 }

+:global(.dark) .basicInfoAdapterIcon {
+  color: #a0a0a0;
+}
+
 .basicInfoAdapterLabel {
  font-size: 1.2rem;
  font-weight: 500;
  color: #626262;
 }

+:global(.dark) .basicInfoAdapterLabel {
+  color: #a0a0a0;
+}
+
 .basicInfoPipelineContainer {
  display: flex;
  flex-direction: row;
@@ -90,12 +117,20 @@
  margin-top: 0.2rem;
 }

+:global(.dark) .basicInfoPipelineIcon {
+  color: #a0a0a0;
+}
+
 .basicInfoPipelineLabel {
  font-size: 1.2rem;
  font-weight: 500;
  color: #626262;
 }

+:global(.dark) .basicInfoPipelineLabel {
+  color: #a0a0a0;
+}
+
 .bigText {
  white-space: nowrap;
  overflow: hidden;
--- a/web/src/app/home/bots/components/bot-form/BotForm.tsx
+++ b/web/src/app/home/bots/components/bot-form/BotForm.tsx
@@ -394,7 +394,7 @@ export default function BotForm({
                      <FormLabel>{t('bots.bindPipeline')}</FormLabel>
                      <FormControl>
                        <Select onValueChange={field.onChange} {...field}>
-                          <SelectTrigger>
+                          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
                            <SelectValue
                              placeholder={t('bots.selectPipeline')}
                            />
@@ -467,7 +467,7 @@ export default function BotForm({
                        }}
                        value={field.value}
                      >
-                        <SelectTrigger className="w-[180px]">
+                        <SelectTrigger className="w-[180px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                          <SelectValue placeholder={t('bots.selectAdapter')} />
                        </SelectTrigger>
                        <SelectContent className="fixed z-[1000]">
--- a/web/src/app/home/bots/components/bot-log/view/botLog.module.css
+++ b/web/src/app/home/bots/components/bot-log/view/botLog.module.css
@@ -18,6 +18,11 @@
  cursor: pointer;
 }

+:global(.dark) .botLogCardContainer {
+  background-color: #1f1f22;
+  border: 1px solid #2a2a2e;
+}
+
 .listHeader {
  width: 100%;
  height: 2.5rem;
--- a/web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx
+++ b/web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx
@@ -26,6 +26,7 @@ import {
 } from '@/components/ui/hover-card';
 import { useTranslation } from 'react-i18next';
 import { i18nObj } from '@/i18n/I18nProvider';
+import { Textarea } from '@/components/ui/textarea';

 export default function DynamicFormItemComponent({
  config,
@@ -132,7 +133,7 @@ export default function DynamicFormItemComponent({
    case DynamicFormItemType.SELECT:
      return (
        <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger>
+          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
            <SelectValue placeholder={t('common.select')} />
          </SelectTrigger>
          <SelectContent>
@@ -150,7 +151,7 @@ export default function DynamicFormItemComponent({
    case DynamicFormItemType.LLM_MODEL_SELECTOR:
      return (
        <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger>
+          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
            <SelectValue placeholder={t('models.selectModel')} />
          </SelectTrigger>
          <SelectContent>
@@ -267,7 +268,7 @@ export default function DynamicFormItemComponent({
    case DynamicFormItemType.KNOWLEDGE_BASE_SELECTOR:
      return (
        <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger>
+          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
            <SelectValue placeholder={t('knowledge.selectKnowledgeBase')} />
          </SelectTrigger>
          <SelectContent>
@@ -291,7 +292,7 @@ export default function DynamicFormItemComponent({
              <div key={index} className="flex gap-2 items-center">
                {/* 角色选择 */}
                {index === 0 ? (
-                  <div className="w-[120px] px-3 py-2 border rounded bg-gray-50 text-gray-500">
+                  <div className="w-[120px] px-3 py-2 border rounded bg-gray-50 dark:bg-[#2a292e] text-gray-500 dark:text-white dark:border-gray-600">
                    system
                  </div>
                ) : (
@@ -303,7 +304,7 @@ export default function DynamicFormItemComponent({
                      field.onChange(newValue);
                    }}
                  >
-                    <SelectTrigger className="w-[120px]">
+                    <SelectTrigger className="w-[120px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                      <SelectValue />
                    </SelectTrigger>
                    <SelectContent>
@@ -315,7 +316,7 @@ export default function DynamicFormItemComponent({
                  </Select>
                )}
                {/* 内容输入 */}
-                <Input
+                <Textarea
                  className="w-[300px]"
                  value={item.content}
                  onChange={(e) => {
--- a/web/src/app/home/components/empty-and-create-component/EmptyAndCreateComponent.tsx
+++ b/web/src/app/home/components/empty-and-create-component/EmptyAndCreateComponent.tsx
@@ -1,27 +0,0 @@
-import styles from './emptyAndCreate.module.css';
-
-export default function EmptyAndCreateComponent({
-  title,
-  subTitle,
-  buttonText,
-  onButtonClick,
-}: {
-  title: string;
-  subTitle: string;
-  buttonText: string;
-  onButtonClick: () => void;
-}) {
-  return (
-    <div className={`${styles.emptyPageContainer}`}>
-      <div className={`${styles.emptyContainer}`}>
-        <div className={`${styles.emptyInfoContainer}`}>
-          <div className={`${styles.emptyInfoText}`}>{title}</div>
-          <div className={`${styles.emptyInfoSubText}`}>{subTitle}</div>
-        </div>
-        <div className={`${styles.emptyCreateButton}`} onClick={onButtonClick}>
-          {buttonText}
-        </div>
-      </div>
-    </div>
-  );
-}
--- a/web/src/app/home/components/empty-and-create-component/emptyAndCreate.module.css
+++ b/web/src/app/home/components/empty-and-create-component/emptyAndCreate.module.css
@@ -1,54 +0,0 @@
-.emptyPageContainer {
-  width: 100%;
-  height: 100%;
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-  justify-content: center;
-  background: #fff;
-  border: 1px solid #c5c5c5;
-  border-radius: 10px;
-}
-
-.emptyContainer {
-  width: 100%;
-  height: 50%;
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-  justify-content: space-evenly;
-}
-
-.emptyCreateButton {
-  width: 200px;
-  height: 50px;
-  border-radius: 20px;
-  background-color: #2288ee;
-  color: #fff;
-  font-size: 20px;
-  font-weight: bold;
-  text-align: center;
-  line-height: 50px;
-  user-select: none;
-}
-
-.emptyCreateButton:hover {
-  background-color: #1b77d2;
-}
-
-.emptyInfoContainer {
-  width: 100%;
-  height: 60px;
-  display: flex;
-  flex-direction: column;
-  align-items: center;
-  color: #353535;
-}
-
-.emptyInfoText {
-  font-size: 30px;
-}
-
-.emptyInfoSubText {
-  font-size: 28px;
-}
--- a/web/src/app/home/components/home-sidebar/HomeSidebar.module.css
+++ b/web/src/app/home/components/home-sidebar/HomeSidebar.module.css
@@ -13,6 +13,10 @@
  /* box-shadow: 0 0 5px 0 rgba(0, 0, 0, 0.1); */
 }

+:global(.dark) .sidebarContainer {
+  background-color: #0a0a0b !important;
+}
+
 .langbotIconContainer {
  width: 200px;
  height: 70px;
@@ -21,32 +25,49 @@
  align-items: center;
  justify-content: center;
  gap: 0.8rem;
+}

-  .langbotIcon {
-    width: 2.8rem;
-    height: 2.8rem;
-    box-shadow: 0 0 10px 0 rgba(0, 0, 0, 0.1);
-    border-radius: 8px;
-  }
+.langbotIcon {
+  width: 2.8rem;
+  height: 2.8rem;
+  box-shadow: 0 0 10px 0 rgba(0, 0, 0, 0.1);
+  border-radius: 8px;
+}

-  .langbotTextContainer {
-    display: flex;
-    flex-direction: column;
-    align-items: flex-start;
-    justify-content: flex-start;
-    gap: 0.1rem;
-  }
+:global(.dark) .langbotIcon {
+  box-shadow: 0 0 10px 0 rgba(255, 255, 255, 0.1);
+}

-  .langbotText {
-    font-size: 1.4rem;
-    font-weight: 500;
-  }
+.langbotTextContainer {
+  display: flex;
+  flex-direction: column;
+  align-items: flex-start;
+  justify-content: flex-start;
+  gap: 0.1rem;
+}

-  .langbotVersion {
-    font-size: 0.8rem;
-    font-weight: 700;
-    color: #6c6c6c;
-  }
+.langbotText {
+  font-size: 1.4rem;
+  font-weight: 500;
+  color: #1a1a1a;
+}
+
+:global(.dark) .langbotText {
+  font-size: 1.4rem;
+  font-weight: 500;
+  color: #f0f0f0 !important;
+}
+
+.langbotVersion {
+  font-size: 0.8rem;
+  font-weight: 700;
+  color: #6c6c6c;
+}
+
+:global(.dark) .langbotVersion {
+  font-size: 0.8rem;
+  font-weight: 700;
+  color: #a0a0a0 !important;
 }

 .sidebarTopContainer {
@@ -76,6 +97,7 @@
  justify-content: flex-start;
  cursor: pointer;
  gap: 0.5rem;
+  transition: all 0.2s ease;
  /* background-color: aqua; */
 }

@@ -85,16 +107,40 @@
  box-shadow: 0 0 10px 0 rgba(0, 0, 0, 0.1);
 }

+:global(.dark) .sidebarSelected {
+  background-color: #2288ee;
+  color: white;
+  box-shadow: 0 0 10px 0 rgba(34, 136, 238, 0.3);
+}
+
 .sidebarUnselected {
  color: #6c6c6c;
 }

+:global(.dark) .sidebarUnselected {
+  color: #a0a0a0 !important;
+}
+
+.sidebarUnselected:hover {
+  background-color: rgba(34, 136, 238, 0.1);
+  color: #2288ee;
+}
+
+:global(.dark) .sidebarUnselected:hover {
+  background-color: rgba(34, 136, 238, 0.2);
+  color: #66baff;
+}
+
 .sidebarChildIcon {
  width: 20px;
  height: 20px;
  background-color: rgba(96, 149, 209, 0);
 }

+.sidebarChildName {
+  color: inherit;
+}
+
 .sidebarBottomContainer {
  width: 100%;
  display: flex;
--- a/web/src/app/home/components/home-sidebar/HomeSidebar.tsx
+++ b/web/src/app/home/components/home-sidebar/HomeSidebar.tsx
@@ -11,6 +11,18 @@ import { sidebarConfigList } from '@/app/home/components/home-sidebar/sidbarConf
 import langbotIcon from '@/app/assets/langbot-logo.webp';
 import { systemInfo } from '@/app/infra/http/HttpClient';
 import { useTranslation } from 'react-i18next';
+import { Moon, Sun, Monitor } from 'lucide-react';
+import { useTheme } from 'next-themes';
+
+import {
+  Popover,
+  PopoverContent,
+  PopoverTrigger,
+} from '@/components/ui/popover';
+import { Button } from '@/components/ui/button';
+import { ToggleGroup, ToggleGroupItem } from '@/components/ui/toggle-group';
+import { LanguageSelector } from '@/components/ui/language-selector';
+import PasswordChangeDialog from '@/app/home/components/password-change-dialog/PasswordChangeDialog';

 // TODO 侧边导航栏要加动画
 export default function HomeSidebar({
@@ -27,8 +39,11 @@ export default function HomeSidebar({
  }, [pathname]);

  const [selectedChild, setSelectedChild] = useState<SidebarChildVO>();
-
+  const { theme, setTheme } = useTheme();
  const { t } = useTranslation();
+  const [popoverOpen, setPopoverOpen] = useState(false);
+  const [passwordChangeOpen, setPasswordChangeOpen] = useState(false);
+  const [languageSelectorOpen, setLanguageSelectorOpen] = useState(false);

  useEffect(() => {
    initSelect();
@@ -144,6 +159,11 @@ export default function HomeSidebar({
                'https://docs.langbot.app/zh/insight/guide.html',
                '_blank',
              );
+            } else if (language === 'zh-Hant') {
+              window.open(
+                'https://docs.langbot.app/zh/insight/guide.html',
+                '_blank',
+              );
            } else {
              window.open(
                'https://docs.langbot.app/en/insight/guide.html',
@@ -163,23 +183,113 @@ export default function HomeSidebar({
          }
          name={t('common.helpDocs')}
        />
-        <SidebarChild
-          onClick={() => {
-            handleLogout();
+
+        <Popover
+          open={popoverOpen}
+          onOpenChange={(open) => {
+            // 防止语言选择器打开时关闭popover
+            if (!open && languageSelectorOpen) return;
+            setPopoverOpen(open);
          }}
-          isSelected={false}
-          icon={
-            <svg
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M4 18H6V20H18V4H6V6H4V3C4 2.44772 4.44772 2 5 2H19C19.5523 2 20 2.44772 20 3V21C20 21.5523 19.5523 22 19 22H5C4.44772 22 4 21.5523 4 21V18ZM6 11H13V13H6V16L1 12L6 8V11Z"></path>
-            </svg>
-          }
-          name={t('common.logout')}
-        />
+        >
+          <PopoverTrigger>
+            <SidebarChild
+              onClick={() => {}}
+              isSelected={false}
+              icon={
+                <svg
+                  xmlns="http://www.w3.org/2000/svg"
+                  viewBox="0 0 24 24"
+                  fill="currentColor"
+                >
+                  <path d="M12 3C10.9 3 10 3.9 10 5C10 6.1 10.9 7 12 7C13.1 7 14 6.1 14 5C14 3.9 13.1 3 12 3ZM12 17C10.9 17 10 17.9 10 19C10 20.1 10.9 21 12 21C13.1 21 14 20.1 14 19C14 17.9 13.1 17 12 17ZM12 10C10.9 10 10 10.9 10 12C10 13.1 10.9 14 12 14C13.1 14 14 13.1 14 12C14 10.9 13.1 10 12 10Z"></path>
+                </svg>
+              }
+              name={t('common.accountOptions')}
+            />
+          </PopoverTrigger>
+          <PopoverContent
+            side="right"
+            align="end"
+            className="w-auto p-4 flex flex-col gap-4"
+          >
+            <div className="flex flex-col gap-2 w-full">
+              <span className="text-sm font-medium">{t('common.theme')}</span>
+              <ToggleGroup
+                type="single"
+                value={theme}
+                onValueChange={(value) => {
+                  if (value) setTheme(value);
+                }}
+                className="justify-start"
+              >
+                <ToggleGroupItem value="light" size="sm">
+                  <Sun className="h-4 w-4" />
+                </ToggleGroupItem>
+                <ToggleGroupItem value="dark" size="sm">
+                  <Moon className="h-4 w-4" />
+                </ToggleGroupItem>
+                <ToggleGroupItem value="system" size="sm">
+                  <Monitor className="h-4 w-4" />
+                </ToggleGroupItem>
+              </ToggleGroup>
+            </div>
+
+            <div className="flex flex-col gap-2 w-full">
+              <span className="text-sm font-medium">
+                {t('common.language')}
+              </span>
+              <LanguageSelector
+                triggerClassName="w-full"
+                onOpenChange={setLanguageSelectorOpen}
+              />
+            </div>
+
+            <div className="flex flex-col gap-2 w-full">
+              <span className="text-sm font-medium">{t('common.account')}</span>
+              <Button
+                variant="ghost"
+                className="w-full justify-start font-normal"
+                onClick={() => {
+                  setPasswordChangeOpen(true);
+                  setPopoverOpen(false);
+                }}
+              >
+                <svg
+                  xmlns="http://www.w3.org/2000/svg"
+                  viewBox="0 0 24 24"
+                  fill="currentColor"
+                  className="w-4 h-4 mr-2"
+                >
+                  <path d="M6 8V7C6 3.68629 8.68629 1 12 1C15.3137 1 18 3.68629 18 7V8H20C20.5523 8 21 8.44772 21 9V21C21 21.5523 20.5523 22 20 22H4C3.44772 22 3 21.5523 3 21V9C3 8.44772 3.44772 8 4 8H6ZM19 10H5V20H19V10ZM11 15.7324C10.4022 15.3866 10 14.7403 10 14C10 12.8954 10.8954 12 12 12C13.1046 12 14 12.8954 14 14C14 14.7403 13.5978 15.3866 13 15.7324V18H11V15.7324ZM8 8H16V7C16 4.79086 14.2091 3 12 3C9.79086 3 8 4.79086 8 7V8Z"></path>
+                </svg>
+                {t('common.changePassword')}
+              </Button>
+              <Button
+                variant="ghost"
+                className="w-full justify-start font-normal"
+                onClick={() => {
+                  handleLogout();
+                }}
+              >
+                <svg
+                  xmlns="http://www.w3.org/2000/svg"
+                  viewBox="0 0 24 24"
+                  fill="currentColor"
+                  className="w-4 h-4 mr-2"
+                >
+                  <path d="M4 18H6V20H18V4H6V6H4V3C4 2.44772 4.44772 2 5 2H19C19.5523 2 20 2.44772 20 3V21C20 21.5523 19.5523 22 19 22H5C4.44772 22 4 21.5523 4 21V18ZM6 11H13V13H6V16L1 12L6 8V11Z"></path>
+                </svg>
+                {t('common.logout')}
+              </Button>
+            </div>
+          </PopoverContent>
+        </Popover>
      </div>
+      <PasswordChangeDialog
+        open={passwordChangeOpen}
+        onOpenChange={setPasswordChangeOpen}
+      />
    </div>
  );
 }
--- a/web/src/app/home/components/home-titlebar/HomeTittleBar.module.css
+++ b/web/src/app/home/components/home-titlebar/HomeTittleBar.module.css
@@ -17,6 +17,10 @@
  color: #585858;
 }

+:global(.dark) .titleText {
+  color: #e0e0e0;
+}
+
 .subtitleText {
  margin-left: 3.2rem;
  font-size: 0.8rem;
@@ -25,8 +29,16 @@
  align-items: center;
 }

+:global(.dark) .subtitleText {
+  color: #b0b0b0;
+}
+
 .helpLink {
  margin-left: 0.2rem;
  font-size: 0.8rem;
  color: #8b8b8b;
 }
+
+:global(.dark) .helpLink {
+  color: #a0a0a0;
+}
--- a/web/src/app/home/components/password-change-dialog/PasswordChangeDialog.tsx
+++ b/web/src/app/home/components/password-change-dialog/PasswordChangeDialog.tsx
@@ -0,0 +1,163 @@
+'use client';
+
+import * as React from 'react';
+import { useState } from 'react';
+import { useForm } from 'react-hook-form';
+import { zodResolver } from '@hookform/resolvers/zod';
+import { z } from 'zod';
+import { toast } from 'sonner';
+import { useTranslation } from 'react-i18next';
+import {
+  Dialog,
+  DialogContent,
+  DialogHeader,
+  DialogTitle,
+  DialogFooter,
+} from '@/components/ui/dialog';
+import { Button } from '@/components/ui/button';
+import {
+  Form,
+  FormControl,
+  FormField,
+  FormItem,
+  FormLabel,
+  FormMessage,
+} from '@/components/ui/form';
+import { Input } from '@/components/ui/input';
+import { httpClient } from '@/app/infra/http/HttpClient';
+
+const getFormSchema = (t: (key: string) => string) =>
+  z
+    .object({
+      currentPassword: z
+        .string()
+        .min(1, { message: t('common.currentPasswordRequired') }),
+      newPassword: z
+        .string()
+        .min(1, { message: t('common.newPasswordRequired') }),
+      confirmNewPassword: z
+        .string()
+        .min(1, { message: t('common.confirmPasswordRequired') }),
+    })
+    .refine((data) => data.newPassword === data.confirmNewPassword, {
+      message: t('common.passwordsDoNotMatch'),
+      path: ['confirmNewPassword'],
+    });
+
+interface PasswordChangeDialogProps {
+  open: boolean;
+  onOpenChange: (open: boolean) => void;
+}
+
+export default function PasswordChangeDialog({
+  open,
+  onOpenChange,
+}: PasswordChangeDialogProps) {
+  const { t } = useTranslation();
+  const [isSubmitting, setIsSubmitting] = useState(false);
+  const formSchema = getFormSchema(t);
+
+  const form = useForm<z.infer<typeof formSchema>>({
+    resolver: zodResolver(formSchema),
+    defaultValues: {
+      currentPassword: '',
+      newPassword: '',
+      confirmNewPassword: '',
+    },
+  });
+
+  const onSubmit = async (values: z.infer<typeof formSchema>) => {
+    setIsSubmitting(true);
+    try {
+      await httpClient.changePassword(
+        values.currentPassword,
+        values.newPassword,
+      );
+      toast.success(t('common.changePasswordSuccess'));
+      form.reset();
+      onOpenChange(false);
+    } catch {
+      toast.error(t('common.changePasswordFailed'));
+    } finally {
+      setIsSubmitting(false);
+    }
+  };
+
+  return (
+    <Dialog open={open} onOpenChange={onOpenChange}>
+      <DialogContent className="sm:max-w-md">
+        <DialogHeader>
+          <DialogTitle>{t('common.changePassword')}</DialogTitle>
+        </DialogHeader>
+        <Form {...form}>
+          <form onSubmit={form.handleSubmit(onSubmit)} className="space-y-4">
+            <FormField
+              control={form.control}
+              name="currentPassword"
+              render={({ field }) => (
+                <FormItem>
+                  <FormLabel>{t('common.currentPassword')}</FormLabel>
+                  <FormControl>
+                    <Input
+                      type="password"
+                      placeholder={t('common.enterCurrentPassword')}
+                      {...field}
+                    />
+                  </FormControl>
+                  <FormMessage />
+                </FormItem>
+              )}
+            />
+            <FormField
+              control={form.control}
+              name="newPassword"
+              render={({ field }) => (
+                <FormItem>
+                  <FormLabel>{t('common.newPassword')}</FormLabel>
+                  <FormControl>
+                    <Input
+                      type="password"
+                      placeholder={t('common.enterNewPassword')}
+                      {...field}
+                    />
+                  </FormControl>
+                  <FormMessage />
+                </FormItem>
+              )}
+            />
+            <FormField
+              control={form.control}
+              name="confirmNewPassword"
+              render={({ field }) => (
+                <FormItem>
+                  <FormLabel>{t('common.confirmNewPassword')}</FormLabel>
+                  <FormControl>
+                    <Input
+                      type="password"
+                      placeholder={t('common.enterConfirmPassword')}
+                      {...field}
+                    />
+                  </FormControl>
+                  <FormMessage />
+                </FormItem>
+              )}
+            />
+            <DialogFooter>
+              <Button
+                type="button"
+                variant="outline"
+                onClick={() => onOpenChange(false)}
+                disabled={isSubmitting}
+              >
+                {t('common.cancel')}
+              </Button>
+              <Button type="submit" disabled={isSubmitting}>
+                {isSubmitting ? t('common.saving') : t('common.save')}
+              </Button>
+            </DialogFooter>
+          </form>
+        </Form>
+      </DialogContent>
+    </Dialog>
+  );
+}
--- a/web/src/app/home/knowledge/KBDetailDialog.tsx
+++ b/web/src/app/home/knowledge/KBDetailDialog.tsx
@@ -152,7 +152,7 @@ export default function KBDetailDialog({
          <SidebarProvider className="items-start w-full flex">
            <Sidebar
              collapsible="none"
-              className="hidden md:flex h-[80vh] w-40 min-w-[120px] border-r bg-white"
+              className="hidden md:flex h-[80vh] w-40 min-w-[120px] border-r bg-white dark:bg-black"
            >
              <SidebarContent>
                <SidebarGroup>
--- a/web/src/app/home/knowledge/components/kb-card/KBCard.module.css
+++ b/web/src/app/home/knowledge/components/kb-card/KBCard.module.css
@@ -10,12 +10,22 @@
  flex-direction: row;
  justify-content: space-between;
  gap: 0.5rem;
+  transition: all 0.2s ease;
+}
+
+:global(.dark) .cardContainer {
+  background-color: #1f1f22;
+  box-shadow: 0;
 }

 .cardContainer:hover {
  box-shadow: 0px 2px 8px 0 rgba(0, 0, 0, 0.1);
 }

+:global(.dark) .cardContainer:hover {
+  box-shadow: 0;
+}
+
 .basicInfoContainer {
  width: 100%;
  height: 100%;
@@ -35,6 +45,11 @@
 .basicInfoNameText {
  font-size: 1.4rem;
  font-weight: 500;
+  color: #1a1a1a;
+}
+
+:global(.dark) .basicInfoNameText {
+  color: #f0f0f0;
 }

 .basicInfoDescriptionText {
@@ -48,6 +63,10 @@
  color: #b1b1b1;
 }

+:global(.dark) .basicInfoDescriptionText {
+  color: #888888;
+}
+
 .basicInfoLastUpdatedTimeContainer {
  display: flex;
  flex-direction: row;
@@ -58,11 +77,21 @@
 .basicInfoUpdateTimeIcon {
  width: 1.2rem;
  height: 1.2rem;
+  color: #626262;
+}
+
+:global(.dark) .basicInfoUpdateTimeIcon {
+  color: #a0a0a0;
 }

 .basicInfoUpdateTimeText {
  font-size: 1rem;
  font-weight: 400;
+  color: #626262;
+}
+
+:global(.dark) .basicInfoUpdateTimeText {
+  color: #a0a0a0;
 }

 .operationContainer {
@@ -86,12 +115,20 @@
  color: #ffcd27;
 }

+:global(.dark) .operationDefaultBadgeIcon {
+  color: #fbbf24;
+}
+
 .operationDefaultBadgeText {
  font-size: 1rem;
  font-weight: 400;
  color: #ffcd27;
 }

+:global(.dark) .operationDefaultBadgeText {
+  color: #fbbf24;
+}
+
 .bigText {
  white-space: nowrap;
  overflow: hidden;
--- a/web/src/app/home/knowledge/components/kb-card/KBCardVO.ts
+++ b/web/src/app/home/knowledge/components/kb-card/KBCardVO.ts
@@ -3,6 +3,7 @@ export interface IKnowledgeBaseVO {
  name: string;
  description: string;
  embeddingModelUUID: string;
+  top_k: number;
  lastUpdatedTimeAgo: string;
 }

@@ -11,6 +12,7 @@ export class KnowledgeBaseVO implements IKnowledgeBaseVO {
  name: string;
  description: string;
  embeddingModelUUID: string;
+  top_k: number;
  lastUpdatedTimeAgo: string;

  constructor(props: IKnowledgeBaseVO) {
@@ -18,6 +20,7 @@ export class KnowledgeBaseVO implements IKnowledgeBaseVO {
    this.name = props.name;
    this.description = props.description;
    this.embeddingModelUUID = props.embeddingModelUUID;
+    this.top_k = props.top_k;
    this.lastUpdatedTimeAgo = props.lastUpdatedTimeAgo;
  }
 }
--- a/web/src/app/home/knowledge/components/kb-docs/FileUploadZone.tsx
+++ b/web/src/app/home/knowledge/components/kb-docs/FileUploadZone.tsx
@@ -127,12 +127,12 @@ export default function FileUploadZone({
              </div>

              <div>
-                <p className="text-base font-medium text-gray-900">
+                <p className="text-base font-medium text-gray-900 dark:text-gray-100">
                  {isUploading
                    ? t('knowledge.documentsTab.uploading')
                    : t('knowledge.documentsTab.dragAndDrop')}
                </p>
-                <p className="text-xs text-gray-500 mt-1">
+                <p className="text-xs text-gray-500 mt-1 dark:text-gray-400">
                  {t('knowledge.documentsTab.supportedFormats')}
                </p>
              </div>
--- a/web/src/app/home/knowledge/components/kb-docs/documents/columns.tsx
+++ b/web/src/app/home/knowledge/components/kb-docs/documents/columns.tsx
@@ -77,7 +77,10 @@ export const columns = (
                <MoreHorizontal className="h-4 w-4" />
              </Button>
            </DropdownMenuTrigger>
-            <DropdownMenuContent align="end">
+            <DropdownMenuContent
+              align="end"
+              className="bg-white dark:bg-[#2a2a2e]"
+            >
              <DropdownMenuLabel>
                {t('knowledge.documentsTab.actions')}
              </DropdownMenuLabel>
--- a/web/src/app/home/knowledge/components/kb-form/KBForm.tsx
+++ b/web/src/app/home/knowledge/components/kb-form/KBForm.tsx
@@ -35,6 +35,10 @@ const getFormSchema = (t: (key: string) => string) =>
    embeddingModelUUID: z
      .string()
      .min(1, { message: t('knowledge.embeddingModelUUIDRequired') }),
+    top_k: z
+      .number()
+      .min(1, { message: t('knowledge.topKRequired') })
+      .max(30, { message: t('knowledge.topKMax') }),
  });

 export default function KBForm({
@@ -55,6 +59,7 @@ export default function KBForm({
      name: '',
      description: t('knowledge.defaultDescription'),
      embeddingModelUUID: '',
+      top_k: 5,
    },
  });

@@ -69,6 +74,7 @@ export default function KBForm({
          form.setValue('name', val.name);
          form.setValue('description', val.description);
          form.setValue('embeddingModelUUID', val.embeddingModelUUID);
+          form.setValue('top_k', val.top_k || 5);
        });
      }
    });
@@ -83,6 +89,7 @@ export default function KBForm({
          name: res.base.name,
          description: res.base.description,
          embeddingModelUUID: res.base.embedding_model_uuid,
+          top_k: res.base.top_k || 5,
        });
      });
    });
@@ -109,6 +116,7 @@ export default function KBForm({
        name: data.name,
        description: data.description,
        embedding_model_uuid: data.embeddingModelUUID,
+        top_k: data.top_k,
      };
      httpClient
        .updateKnowledgeBase(initKbId, updateKb)
@@ -127,6 +135,7 @@ export default function KBForm({
        name: data.name,
        description: data.description,
        embedding_model_uuid: data.embeddingModelUUID,
+        top_k: data.top_k,
      };
      httpClient
        .createKnowledgeBase(newKb)
@@ -200,7 +209,7 @@ export default function KBForm({
                        }}
                        value={field.value}
                      >
-                        <SelectTrigger className="w-[180px]">
+                        <SelectTrigger className="w-[180px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                          <SelectValue
                            placeholder={t('knowledge.selectEmbeddingModel')}
                          />
@@ -226,6 +235,30 @@ export default function KBForm({
                </FormItem>
              )}
            />
+            <FormField
+              control={form.control}
+              name="top_k"
+              render={({ field }) => (
+                <FormItem>
+                  <FormLabel>
+                    {t('knowledge.topK')}
+                    <span className="text-red-500">*</span>
+                  </FormLabel>
+                  <FormControl>
+                    <Input
+                      type="number"
+                      {...field}
+                      onChange={(e) => field.onChange(Number(e.target.value))}
+                      className="w-[180px] h-10 text-base appearance-none"
+                    />
+                  </FormControl>
+                  <FormDescription>
+                    {t('knowledge.topKdescription')}
+                  </FormDescription>
+                  <FormMessage />
+                </FormItem>
+              )}
+            />
          </div>
        </form>
      </Form>
--- a/web/src/app/home/knowledge/page.tsx
+++ b/web/src/app/home/knowledge/page.tsx
@@ -46,6 +46,7 @@ export default function KnowledgePage() {
          name: kb.name,
          description: kb.description,
          embeddingModelUUID: kb.embedding_model_uuid,
+          top_k: kb.top_k ?? 5,
          lastUpdatedTimeAgo: lastUpdatedTimeAgoText,
        });
      }),
--- a/web/src/app/home/layout.module.css
+++ b/web/src/app/home/layout.module.css
@@ -7,6 +7,19 @@
  background-color: #eee;
 }

+:global(.dark) .homeLayoutContainer {
+  background-color: #0a0a0b;
+}
+
+/* 侧边栏区域 */
+.sidebar {
+  background-color: #eee;
+}
+
+:global(.dark) .sidebar {
+  background-color: #0a0a0b;
+}
+
 /* 主内容区域 */
 .main {
  background-color: #fafafa;
@@ -23,6 +36,11 @@
  box-shadow: 0 0 6px 0 rgba(0, 0, 0, 0.05);
 }

+:global(.dark) .main {
+  background-color: #151518;
+  box-shadow: 0 0 6px 0 rgba(255, 255, 255, 0.05);
+}
+
 .mainContent {
  padding: 1.5rem;
  padding-left: 2rem;
@@ -30,3 +48,7 @@
  overflow-y: auto;
  background-color: #fafafa;
 }
+
+:global(.dark) .mainContent {
+  background-color: #151518;
+}
--- a/web/src/app/home/models/component/embedding-card/EmbeddingCard.module.css
+++ b/web/src/app/home/models/component/embedding-card/EmbeddingCard.module.css
@@ -6,12 +6,22 @@
  box-shadow: 0px 2px 2px 0 rgba(0, 0, 0, 0.2);
  padding: 1.2rem;
  cursor: pointer;
+  transition: all 0.2s ease;
+}
+
+:global(.dark) .cardContainer {
+  background-color: #1f1f22;
+  box-shadow: 0;
 }

 .cardContainer:hover {
  box-shadow: 0px 2px 8px 0 rgba(0, 0, 0, 0.1);
 }

+:global(.dark) .cardContainer:hover {
+  box-shadow: 0;
+}
+
 .iconBasicInfoContainer {
  width: 100%;
  height: 100%;
@@ -39,6 +49,11 @@
 .basicInfoText {
  font-size: 1.4rem;
  font-weight: bold;
+  color: #1a1a1a;
+}
+
+:global(.dark) .basicInfoText {
+  color: #f0f0f0;
 }

 .providerContainer {
@@ -56,12 +71,20 @@
  color: #626262;
 }

+:global(.dark) .providerIcon {
+  color: #a0a0a0;
+}
+
 .providerLabel {
  font-size: 1.2rem;
  font-weight: 600;
  color: #626262;
 }

+:global(.dark) .providerLabel {
+  color: #a0a0a0;
+}
+
 .baseURLContainer {
  display: flex;
  flex-direction: row;
@@ -77,6 +100,10 @@
  color: #626262;
 }

+:global(.dark) .baseURLIcon {
+  color: #a0a0a0;
+}
+
 .baseURLText {
  font-size: 1rem;
  width: 100%;
@@ -87,6 +114,10 @@
  max-width: 100%;
 }

+:global(.dark) .baseURLText {
+  color: #a0a0a0;
+}
+
 .bigText {
  white-space: nowrap;
  overflow: hidden;
--- a/web/src/app/home/models/component/embedding-form/EmbeddingForm.tsx
+++ b/web/src/app/home/models/component/embedding-form/EmbeddingForm.tsx
@@ -298,6 +298,18 @@ export default function EmbeddingForm({

  function testEmbeddingModelInForm() {
    setModelTesting(true);
+    const extraArgsObj: Record<string, string | number | boolean> = {};
+    form
+      .getValues('extra_args')
+      ?.forEach((arg: { key: string; type: string; value: string }) => {
+        if (arg.type === 'number') {
+          extraArgsObj[arg.key] = Number(arg.value);
+        } else if (arg.type === 'boolean') {
+          extraArgsObj[arg.key] = arg.value === 'true';
+        } else {
+          extraArgsObj[arg.key] = arg.value;
+        }
+      });
    httpClient
      .testEmbeddingModel('_', {
        uuid: '',
@@ -309,6 +321,7 @@ export default function EmbeddingForm({
          timeout: 120,
        },
        api_keys: [form.getValues('api_key')],
+        extra_args: extraArgsObj,
      })
      .then((res) => {
        console.log(res);
@@ -404,7 +417,7 @@ export default function EmbeddingForm({
                      }}
                      value={field.value}
                    >
-                      <SelectTrigger className="w-[180px]">
+                      <SelectTrigger className="w-[180px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                        <SelectValue
                          placeholder={t('models.selectModelProvider')}
                        />
@@ -479,7 +492,7 @@ export default function EmbeddingForm({
                        updateExtraArg(index, 'type', value)
                      }
                    >
-                      <SelectTrigger className="w-[120px]">
+                      <SelectTrigger className="w-[120px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                        <SelectValue placeholder={t('models.type')} />
                      </SelectTrigger>
                      <SelectContent>
--- a/web/src/app/home/models/component/llm-card/LLMCard.module.css
+++ b/web/src/app/home/models/component/llm-card/LLMCard.module.css
@@ -6,12 +6,22 @@
  box-shadow: 0px 2px 2px 0 rgba(0, 0, 0, 0.2);
  padding: 1.2rem;
  cursor: pointer;
+  transition: all 0.2s ease;
+}
+
+:global(.dark) .cardContainer {
+  background-color: #1f1f22;
+  box-shadow: 0;
 }

 .cardContainer:hover {
  box-shadow: 0px 2px 8px 0 rgba(0, 0, 0, 0.1);
 }

+:global(.dark) .cardContainer:hover {
+  box-shadow: 0;
+}
+
 .iconBasicInfoContainer {
  width: 100%;
  height: 100%;
@@ -40,6 +50,11 @@
 .basicInfoText {
  font-size: 1.4rem;
  font-weight: bold;
+  color: #1a1a1a;
+}
+
+:global(.dark) .basicInfoText {
+  color: #f0f0f0;
 }

 .providerContainer {
@@ -57,12 +72,20 @@
  color: #626262;
 }

+:global(.dark) .providerIcon {
+  color: #a0a0a0;
+}
+
 .providerLabel {
  font-size: 1.2rem;
  font-weight: 600;
  color: #626262;
 }

+:global(.dark) .providerLabel {
+  color: #a0a0a0;
+}
+
 .baseURLContainer {
  display: flex;
  flex-direction: row;
@@ -78,6 +101,10 @@
  color: #626262;
 }

+:global(.dark) .baseURLIcon {
+  color: #a0a0a0;
+}
+
 .baseURLText {
  font-size: 1rem;
  width: 100%;
@@ -88,6 +115,10 @@
  max-width: 100%;
 }

+:global(.dark) .baseURLText {
+  color: #a0a0a0;
+}
+
 .abilitiesContainer {
  display: flex;
  flex-direction: row;
@@ -108,18 +139,30 @@
  background-color: #66baff80;
 }

+:global(.dark) .abilityBadge {
+  background-color: rgba(34, 136, 238, 0.3);
+}
+
 .abilityIcon {
  width: 1rem;
  height: 1rem;
  color: #2288ee;
 }

+:global(.dark) .abilityIcon {
+  color: #66baff;
+}
+
 .abilityLabel {
  font-size: 0.8rem;
  font-weight: 400;
  color: #2288ee;
 }

+:global(.dark) .abilityLabel {
+  color: #66baff;
+}
+
 .bigText {
  white-space: nowrap;
  overflow: hidden;
--- a/web/src/app/home/models/component/llm-form/LLMForm.tsx
+++ b/web/src/app/home/models/component/llm-form/LLMForm.tsx
@@ -312,6 +312,18 @@ export default function LLMForm({

  function testLLMModelInForm() {
    setModelTesting(true);
+    const extraArgsObj: Record<string, string | number | boolean> = {};
+    form
+      .getValues('extra_args')
+      ?.forEach((arg: { key: string; type: string; value: string }) => {
+        if (arg.type === 'number') {
+          extraArgsObj[arg.key] = Number(arg.value);
+        } else if (arg.type === 'boolean') {
+          extraArgsObj[arg.key] = arg.value === 'true';
+        } else {
+          extraArgsObj[arg.key] = arg.value;
+        }
+      });
    httpClient
      .testLLMModel('_', {
        uuid: '',
@@ -324,7 +336,7 @@ export default function LLMForm({
        },
        api_keys: [form.getValues('api_key')],
        abilities: form.getValues('abilities'),
-        extra_args: form.getValues('extra_args'),
+        extra_args: extraArgsObj,
      })
      .then((res) => {
        console.log(res);
@@ -420,7 +432,7 @@ export default function LLMForm({
                      }}
                      value={field.value}
                    >
-                      <SelectTrigger className="w-[180px]">
+                      <SelectTrigger className="w-[180px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                        <SelectValue
                          placeholder={t('models.selectModelProvider')}
                        />
@@ -553,7 +565,7 @@ export default function LLMForm({
                        updateExtraArg(index, 'type', value)
                      }
                    >
-                      <SelectTrigger className="w-[120px]">
+                      <SelectTrigger className="w-[120px] bg-[#ffffff] dark:bg-[#2a2a2e]">
                        <SelectValue placeholder={t('models.type')} />
                      </SelectTrigger>
                      <SelectContent>
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Junyan Qin	87ecb4e519	feat: add note for remove_think & remove dify remove cot code	2025-08-21 21:38:58 +08:00
Ljzd_PRO	df524b8a7a	Fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages (#1624 ) * fix: update invoke_embedding to return only embeddings from client.embed * fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages	2025-08-21 20:46:26 +08:00
Junyan Qin	8a7df423ab	chore: update shengsuanyun url	2025-08-21 14:14:25 +08:00
Junyan Qin	cafd623c92	chore: update shengsuanyun	2025-08-21 12:03:04 +08:00
Junyan Qin	4df11ef064	chore: update for shengsuanyun	2025-08-21 11:47:40 +08:00
Junyan Qin	aa7c08ee00	chore: release v4.2.1	2025-08-21 10:15:05 +08:00
Junyan Qin	b98de29b07	feat: add shengsuanyun requester	2025-08-20 23:33:35 +08:00
fdc310	c7c2eb4518	fix:in the gmini tool_calls no id The resulting call failure (#1622 ) * fix:in the dify agent llm return message can not joint * fix:in the gmini tool_calls no id The resulting call failure	2025-08-20 22:39:16 +08:00
Ljzd_PRO	37fa318258	fix: update invoke_embedding to return only embeddings from client.embed (#1619 )	2025-08-20 10:25:33 +08:00
fdc310	ff7bebb782	fix:in the dify agent llm return message can not joint (#1617 )	2025-08-19 23:23:00 +08:00
Junyan Qin	30bb26f898	doc(README): streaming output	2025-08-18 21:21:50 +08:00
Junyan Qin	9c1f4e1690	chore: release v4.2.0	2025-08-18 18:43:20 +08:00
dependabot[bot]	865ee2ca01	Merge pull request #1612 from langbot-app/dependabot/npm_and_yarn/web/form-data-4.0.4 chore(deps): bump form-data from 4.0.2 to 4.0.4 in /web	2025-08-18 16:10:56 +08:00
Junyan Qin (Chin)	c2264080bd	Merge pull request #1442 from langbot-app/feat/streaming feat: streaming output	2025-08-17 23:36:30 +08:00
Dong_master	67b622d5a6	fix:Some adjustments to the return types	2025-08-17 23:34:19 +08:00
Dong_master	a534c02d75	fix:remove print	2025-08-17 23:34:01 +08:00
Junyan Qin	da890d3074	chore: remove `fix.MD`	2025-08-17 21:20:32 +08:00
Junyan Qin	3049aa7a96	feat: add migration for pipeline `remove-think`	2025-08-17 21:18:41 +08:00
Junyan Qin (Chin)	e66f674968	Merge branch 'master' into feat/streaming	2025-08-17 14:30:22 +08:00
Junyan Qin (Chin)	dd0e0abdc4	Merge pull request #1571 from fdc310/streaming_feature feat:add streaming output and pipeline stream	2025-08-17 14:27:39 +08:00
Junyan Qin (Chin)	13f6396eb4	Merge pull request #1610 from langbot-app/devin/1755399221-add-password-change-feature feat: add password change functionality	2025-08-17 14:25:24 +08:00
Junyan Qin	7bbaa4fcad	feat: perf ui & complete i18n	2025-08-17 14:09:28 +08:00
Junyan Qin	e931d5eb88	chore: remove print	2025-08-17 13:52:40 +08:00
Junyan Qin	4bbfa2f1d7	fix: telegram adapter gracefully stop	2025-08-17 13:52:02 +08:00
Devin AI	dd30d08c68	feat: add password change functionality - Add password change button to sidebar account menu - Create PasswordChangeDialog component with shadcn UI components - Implement backend API endpoint /api/v1/user/change-password - Add form validation with current password verification - Include internationalization support for Chinese and English - Add proper error handling and success notifications Co-Authored-By: Rock <rockchinq@gmail.com>	2025-08-17 03:03:36 +00:00
Dong_master	8ccda10045	fix: in the dashscopeapi.py workflow stream bug	2025-08-16 12:11:00 +08:00
Dong_master	46fbfbefea	fix: in the dashscopeapi.py stream and non-stream remove_think logic	2025-08-16 02:13:45 +08:00
Dong_master	8f863cf530	fix: remove_think bug	2025-08-15 00:55:39 +08:00
Dong_master	2351193c51	fix: in the difysvapi.py add stream , and remove_think on chunk	2025-08-15 00:50:32 +08:00
Dong_master	8c87a47f5a	fix: in the ollamachat.py func _closure add remove_think agr	2025-08-14 22:35:30 +08:00
Dong_master	b8b9a37825	fix: in the dify non-stream remove_think lgic	2025-08-14 22:32:22 +08:00
Dong_master	13dd6fcee3	fix: in the webchat non-stream not save resp_message in message_lists	2025-08-14 22:29:42 +08:00
Junyan Qin	29f0075bd8	perf: zh-Hant specs	2025-08-13 17:49:54 +08:00
Junyan Qin	8a96ffbcc0	chore: complete zh-Hant specs for top_k	2025-08-13 17:33:47 +08:00
Junyan Qin (Chin)	67f68d8101	Merge pull request #1606 from langbot-app/feat/topk_splitter Feat/topk splitter	2025-08-13 17:31:11 +08:00
Junyan Qin	ad59d92cef	perf: i18n	2025-08-13 17:28:00 +08:00
Dong_master	85f97860c5	fix: Fixed the errors in modelscopechatcmpl.py when in pseudo-non-streaming mode, regarding the display of main content and tool calls.	2025-08-13 01:55:06 +08:00
Dong_master	8fd21e76f2	fix: Only when messagechunk is present, will msg_sequence be assigned to the subsequent tool calls.	2025-08-13 00:00:10 +08:00
Dong_master	cc83ddbe21	fix: del print	2025-08-12 23:29:32 +08:00
Dong_master	99fcde1586	fix: in the MessageChunk add msg_sequence ,And obtain the usage in the adapter.	2025-08-12 23:20:41 +08:00
WangCham	eab08dfbf3	fix: format the code	2025-08-12 23:13:00 +08:00
Dong_master	dbf0200cca	feat:add More attractive card templates	2025-08-12 22:36:42 +08:00
Junyan Qin	ac44f35299	chore: remove comments	2025-08-12 21:07:23 +08:00
Junyan Qin	d6a5fdd911	perf: complete sidebar menu	2025-08-12 21:02:40 +08:00
Dong_master	4668db716a	fix: fix command reply_message error bug,del some print	2025-08-12 20:54:47 +08:00
Junyan Qin	f7cd6b76f2	feat: refactor account menu	2025-08-12 20:13:18 +08:00
Junyan Qin	b6d47187f5	perf: prettier	2025-08-12 19:39:41 +08:00
Junyan Qin	051fffd41e	fix: stash	2025-08-12 19:18:49 +08:00
Junyan Qin	c5480078b3	perf: make prompt editor textarea	2025-08-12 11:30:42 +08:00
Dong_master	e744e9c4ef	fix: in the localagent.py yield MessageChunk add agr tool_calls,and After calling the "tool_calls", the first returned body data will be concatenated.	2025-08-12 11:25:37 +08:00
Dong_master	9f22b8b585	fix: be adapter.py func reply_message_chunk agr message_id alter bot_message,and in pipelinemgr.py respback.py agr alter	2025-08-12 11:21:08 +08:00
Dong_master	27cee0a4e1	fix: in the adapter.py func reply_message_chunk agr message_id alter bot_message,and in dingtalk.py lark.py telegram.py webchat.py agr alter	2025-08-12 11:19:27 +08:00
Dong_master	6d35fc408c	fix: some time in the anthropicmsgs.py mesg_dcit["content"] is str can not append	2025-08-12 11:15:17 +08:00
Dong_master	0607a0fa5c	fix: in the modelscopechatcmpl.py stream tool_calls arguments bug,	2025-08-12 00:04:21 +08:00
Dong_master	ed57d2fafa	del localagent.py print	2025-08-11 23:49:19 +08:00
Junyan Qin	39ef92676b	doc: add back wechat	2025-08-11 23:38:41 +08:00
Dong_master	7301476228	fix:Because the message_id was popped out, it caused the issue where the tool couldn't find the message_id after being invoked.	2025-08-11 23:36:01 +08:00
WangCham	457cc3eecd	fix: wrong definition of topk	2025-08-11 23:22:36 +08:00
Dong_master	a381069bcc	fix:fix tool_result argument bug	2025-08-11 23:05:47 +08:00
WangCham	146c38e64c	fix: wrong positions	2025-08-11 22:58:48 +08:00
Junyan Qin (Chin)	763c41729e	Merge pull request #1605 from TwperBody/master feat: dark mode supports for webui	2025-08-11 20:51:58 +08:00
Junyan Qin	0021efebd7	perf: minor fix	2025-08-11 20:50:39 +08:00
Junyan Qin	5f18a1b13a	chore: prettier	2025-08-11 20:46:08 +08:00
Junyan Qin	0124448479	perf: card shadowbox	2025-08-11 20:41:57 +08:00
WangCham	e76bc80e51	Merge branch 'feat/topk_splitter' of github.com:RockChinQ/LangBot into feat/topk_splitter	2025-08-11 00:20:13 +08:00
WangCham	a27560e804	fix: page bug	2025-08-11 00:12:06 +08:00
Dong_master	46452de7b5	fix:The handling of the streaming tool calls has been fixed, but there are still bugs in the model's reply messages with thoughtfulness.	2025-08-10 23:14:57 +08:00
TwperBody	2aef139577	dark mode	2025-08-10 22:17:06 +08:00
Dong_master	03b11481ed	fix:fix remove_think logic, and end<think> fix </think>	2025-08-10 00:28:55 +08:00
Dong_master	8c5cb71812	fix:del the chatcmpl.py useless logic,and in the modelscopechatcmpl.py Non-streaming add and del <think> logic,and fix the ppiochatcmpl.py stream logic and the giteeaichatcmpl.py inherit ppiochatcmpl.py	2025-08-10 00:16:13 +08:00
Dong_master	7c59bc1ce5	feat:add anthropic stream ouput	2025-08-10 00:09:19 +08:00
Dong_master	eede354d3b	fix:chatcmpl.py del content <think>,in the ppiochatcmpl.py and modelsopechatcmpl.py fun _closure_stream stream logic	2025-08-09 02:46:13 +08:00
Junyan Qin	eb7b5dcc25	chore: rename zh_Hans label of deepseek requester	2025-08-08 17:31:24 +08:00
WangCham	47e9ce96fc	feat: add topk	2025-08-07 18:10:33 +08:00
WangCham	4e95bc542c	fix: kb form	2025-08-07 18:10:33 +08:00
WangCham	e4f321ea7a	feat: add description for topk	2025-08-07 18:10:33 +08:00
WangCham	246eb71b75	feat: add topk	2025-08-07 18:10:33 +08:00
Junyan Qin	261f50b8ec	feat: refactor with cursor max mode claude 4.1 opus	2025-08-07 15:47:57 +08:00
Junyan Qin	9736d0708a	fix: missing deps	2025-08-07 10:15:09 +08:00
Junyan Qin	02dbe80d2f	perf: model testing	2025-08-07 10:01:04 +08:00
Dong_master	0f239ace17	Merge remote-tracking branch 'origin/streaming_feature' into streaming_feature	2025-08-06 23:02:35 +08:00
Dong_master	3a82ae8da5	fix: the bug in the "remove_think" function.	2025-08-06 23:00:57 +08:00
Junyan Qin	c33c9eaab0	chore: remove `remove_think` param in trigger.yaml	2025-08-06 15:45:35 +08:00
Junyan Qin	87f626f3cc	doc(README): add HelloGitHub badge	2025-08-05 17:40:27 +08:00
Dong_master	e88302f1b4	fix:The handling logic of remove_think in the connector and Temporarily blocked the processing of streaming tool calls in the runner.	2025-08-05 04:24:03 +08:00
Dong_master	5597dffaeb	Merge remote-tracking branch 'origin/streaming_feature' into streaming_feature # Conflicts: # pkg/api/http/controller/groups/pipelines/webchat.py # pkg/pipeline/process/handlers/chat.py # pkg/platform/sources/aiocqhttp.py # pkg/platform/sources/dingtalk.py # pkg/platform/sources/discord.py # pkg/platform/sources/lark.py # pkg/platform/sources/telegram.py # pkg/platform/sources/wechatpad.py # pkg/provider/modelmgr/requester.py # pkg/provider/modelmgr/requesters/chatcmpl.py # pkg/provider/modelmgr/requesters/deepseekchatcmpl.py # pkg/provider/modelmgr/requesters/giteeaichatcmpl.py # pkg/provider/modelmgr/requesters/modelscopechatcmpl.py # pkg/provider/modelmgr/requesters/ppiochatcmpl.py # pkg/provider/runners/dashscopeapi.py # pkg/provider/runners/difysvapi.py # pkg/provider/runners/localagent.py	2025-08-04 23:17:36 +08:00
Junyan Qin	7f25d61531	fix: minor fix	2025-08-04 23:00:54 +08:00
Junyan Qin	15e524c6e6	perf: move `remove-think` to output tab	2025-08-04 19:26:19 +08:00
fdc	4a1d033ee9	fix: Reduce chunk returns in dify and Hundred Refining Runner to every 8 chunks	2025-08-04 19:26:19 +08:00
fdc	8adc88a8c0	fix:Modify the remove_think that directly retrieves the configuration file from the requester, retrieves it from the runner, and passes it to the required function	2025-08-04 19:26:18 +08:00
fdc	a62b38eda7	fix: In the reply_message_chunk of the adapter, the message is only streamed into the card or edited at the end of the 8th chunk return or streaming	2025-08-04 19:26:18 +08:00
Dong_master	fcef784180	fix: In the runner, every 8 tokens yield	2025-08-04 19:26:18 +08:00
Junyan Qin	c3ed4ef6a1	feat: no longer use typewriter in debug dialog	2025-08-04 19:26:18 +08:00
Junyan Qin	b9f768af25	perf: minor fixes	2025-08-04 19:26:18 +08:00
Junyan Qin	47ff883fc7	perf: ruff format & remove `stream` params in requester	2025-08-04 19:26:18 +08:00
Dong_master	68906c43ff	feat: add webchat Word-by-word output fix:webchat on message stream bug	2025-08-04 19:26:18 +08:00
Dong_master	c6deed4e6e	feat: webchat stream is ok	2025-08-04 19:26:18 +08:00
Dong_master	b45cc59322	fix:webchat stream judge bug and frontend bug	2025-08-04 19:26:17 +08:00
fdc	c33a96823b	fix: frontend bug	2025-08-04 19:26:17 +08:00
fdc	d3ab16761d	fix:lsome bug	2025-08-04 19:26:17 +08:00
fdc	70f23f24b0	fix: is_stream_output_supperted in webchat return	2025-08-04 19:26:17 +08:00
fdc	00a8410c94	feat:webchat frontend stream	2025-08-04 19:26:17 +08:00
fdc	2a17e89a99	feat: add webchat stream but only some	2025-08-04 19:26:17 +08:00
fdc	8fe0992c15	fix:in chat judge create_message_card telegram reply_message_chunk no message	2025-08-04 19:26:17 +08:00
Dong_master	a9776b7b53	fix:del some print ,and amend respback on stream judge ,and del in dingtalk this is_stream_output_supported() use	2025-08-04 19:26:16 +08:00
Dong_master	074d359c8e	feat:add dashscopeapi stream fix:dify 64chunk yield	2025-08-04 19:26:16 +08:00
Dong_master	7728b4262b	fix:lark message_id and dingtalk incoming_message	2025-08-04 19:26:16 +08:00
Dong_master	4905b5a738	feat:add dingtalk stream fix:adapter is_stream_output_supported bug fix:stream message reply chunk in message_id	2025-08-04 19:26:16 +08:00
Dong_master	43a259a1ae	feat:add dingtalk stream	2025-08-04 19:26:16 +08:00
Dong_master	cffe493db0	feat:add telegram stream	2025-08-04 19:26:16 +08:00
Dong_master	0042629bf0	feat:add ppio and openrouter llm stream,and ppio think in content remove_think. fix: giteeai stream no remove_think content add char"<think>"	2025-08-04 19:26:16 +08:00
Dong_master	a7d638cc9a	feat:add deepseek and modelscope llm stream,and giteeai think in content remove_think	2025-08-04 19:26:16 +08:00
Dong_master	f84a79bf74	perf:del dify stream in ai.yaml config.and enbale stream in lark.yaml. fix:localagent remove_think bug	2025-08-04 19:26:15 +08:00
Dong_master	f5a0cb9175	feat:add dify _agent_chat_message streaming	2025-08-04 19:26:15 +08:00
Dong_master	f9a5507029	fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及有思考的think处理 feat:增加带有深度思考模型的think的去think操作 feat:dify中聊天机器人，chatflow对流式的支持	2025-08-04 19:26:15 +08:00
Dong_master	5ce32d2f04	fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及带有深度思考模型的think增加	2025-08-04 19:26:15 +08:00
Dong_master	4908996cac	流式基本流程已通过修改了yield和return的冲突导致的问题	2025-08-04 19:26:15 +08:00
fdc	ee545a163f	增加了飞书中的流式但是好像还有问题	2025-08-04 19:26:15 +08:00
fdc	6e0e5802cc	fix:修改手误message_id写进reply_message中	2025-08-04 19:26:15 +08:00
fdc	0d53843230	chat中的流式修改	2025-08-04 19:26:14 +08:00
fdc	b65670cd1a	feat: 实现流式消息处理支持	2025-08-04 19:26:14 +08:00
zejiewang	ba4b5255a2	feat:support dify message streaming output (#1437 ) * fix:lark adapter listeners init problem * feat:support dify streaming mode * feat:remove some log * fix(bot form): field desc missing * fix: not compatible with chatflow --------- Co-authored-by: wangzejie <wangzejie@meicai.cn> Co-authored-by: Junyan Qin <rockchinq@gmail.com>	2025-08-04 18:45:52 +08:00
Junyan Qin (Chin)	d60af2b451	fix(pipeline dialog): config reset between tabs switching (#1597 )	2025-08-04 00:05:55 +08:00
Dong_master	44ac8b2b63	fix: In the runner, every 8 tokens yield	2025-08-03 23:23:51 +08:00
Junyan Qin	b70001c579	chore: release v4.1.2	2025-08-03 22:52:47 +08:00
Junyan Qin (Chin)	4a8f5516f6	feat: add new api requester (#1596 )	2025-08-03 22:30:52 +08:00
Junyan Qin	48d11540ae	feat: no longer use typewriter in debug dialog	2025-08-03 17:18:44 +08:00
Junyan Qin	84129e3339	perf: minor fixes	2025-08-03 15:30:11 +08:00
Junyan Qin	377d455ec1	perf: ruff format & remove `stream` params in requester	2025-08-03 13:08:51 +08:00
Dong_master	52280d7a05	feat: add webchat Word-by-word output fix:webchat on message stream bug	2025-08-02 01:42:22 +08:00
Dong_master	0ce81a2df2	feat: webchat stream is ok	2025-08-01 11:33:16 +08:00
Dong_master	d9a2bb9a06	fix:webchat stream judge bug and frontend bug	2025-07-31 14:49:12 +08:00
fdc	cb88da7f02	fix: frontend bug	2025-07-31 10:34:36 +08:00
fdc	5560a4f52d	fix:lsome bug	2025-07-31 10:28:43 +08:00
fdc	e4d951b174	fix: is_stream_output_supperted in webchat return	2025-07-31 10:01:47 +08:00
fdc	6e08bf71c9	feat:webchat frontend stream	2025-07-31 09:51:25 +08:00
fdc	daaf4b54ef	feat: add webchat stream but only some	2025-07-30 17:06:14 +08:00
fdc	3291266f5d	fix:in chat judge create_message_card telegram reply_message_chunk no message	2025-07-30 15:21:59 +08:00
Dong_master	307f6acd8c	fix:del some print ,and amend respback on stream judge ,and del in dingtalk this is_stream_output_supported() use	2025-07-29 23:09:02 +08:00
Junyan Qin	f1ac9c77e6	doc: update README_TW	2025-07-28 15:50:00 +08:00
Junyan Qin	b434a4e3d7	doc: add README_TW	2025-07-28 15:47:50 +08:00
Junyan Qin	2f209cd59f	chore(i18n): add `zh-Hant`	2025-07-28 15:11:41 +08:00
Junyan Qin	0f585fd5ef	fix(moonshot): make `api.moonshot.ai` the default api base url	2025-07-26 22:23:33 +08:00
Junyan Qin	a152dece9a	chore: switch to pnpm	2025-07-26 19:45:38 +08:00
WangCham	3fa38f71f1	feat: add topk	2025-07-23 17:29:36 +08:00
WangCham	d651d956d6	Merge branch 'master' into feat/topk_splitter	2025-07-23 16:37:27 +08:00
Dong_master	8f8c8ff367	feat:add dashscopeapi stream fix:dify 64chunk yield	2025-07-21 18:45:45 +08:00
Dong_master	63ec2a8c34	fix:lark message_id and dingtalk incoming_message	2025-07-21 17:28:11 +08:00
Dong_master	f58c8497c3	feat:add dingtalk stream fix:adapter is_stream_output_supported bug fix:stream message reply chunk in message_id	2025-07-20 23:53:20 +08:00
Dong_master	adb0bf2473	feat:add dingtalk stream	2025-07-19 01:05:44 +08:00
Dong_master	11e52a3ade	feat:add telegram stream	2025-07-17 14:29:30 +08:00
WangCham	e986a0acaf	fix: kb form	2025-07-16 22:50:17 +08:00
WangCham	e31883547d	feat: add description for topk	2025-07-16 18:15:27 +08:00
WangCham	88c0066b06	feat: add topk	2025-07-16 17:20:13 +08:00
Dong_master	d15df3338f	feat:add ppio and openrouter llm stream,and ppio think in content remove_think. fix: giteeai stream no remove_think content add char"<think>"	2025-07-15 00:50:42 +08:00
Dong_master	c74cf38e9f	feat:add deepseek and modelscope llm stream,and giteeai think in content remove_think	2025-07-14 23:53:55 +08:00
Dong_master	0e68a922bd	perf:del dify stream in ai.yaml config.and enbale stream in lark.yaml. fix:localagent remove_think bug	2025-07-14 01:42:42 +08:00
Dong_master	4e1d81c9f8	feat:add dify _agent_chat_message streaming	2025-07-14 00:40:02 +08:00
Dong_master	0be08d8882	fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及有思考的think处理 feat:增加带有深度思考模型的think的去think操作 feat:dify中聊天机器人，chatflow对流式的支持	2025-07-13 22:41:39 +08:00
Dong_master	301509b1db	fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大，以及带有深度思考模型的think增加	2025-07-12 18:09:24 +08:00
Dong_master	68cdd163d3	流式基本流程已通过修改了yield和return的冲突导致的问题	2025-07-04 03:26:44 +08:00
fdc	4005a8a3e2	增加了飞书中的流式但是好像还有问题	2025-07-03 22:58:17 +08:00
fdc	542409d48d	Merge branch 'feat/streaming' of github.com:fdc310/LangBot into streaming_feature	2025-07-02 14:09:01 +08:00
zejiewang	3c6e858c35	feat:support dify message streaming output (#1437 ) * fix:lark adapter listeners init problem * feat:support dify streaming mode * feat:remove some log * fix(bot form): field desc missing * fix: not compatible with chatflow --------- Co-authored-by: wangzejie <wangzejie@meicai.cn> Co-authored-by: Junyan Qin <rockchinq@gmail.com>	2025-07-02 11:07:31 +08:00
fdc	8670ae82a3	fix:修改手误message_id写进reply_message中	2025-07-02 10:49:50 +08:00
fdc	48c9d66ab8	chat中的流式修改	2025-07-01 18:03:05 +08:00
fdc	0eac9135c0	feat: 实现流式消息处理支持	2025-06-30 17:58:18 +08:00
				`@@ -0,0 +1 @@`
				`NEXT_PUBLIC_API_BASE_URL=http://localhost:5300`