feat(pipes): v0.7.0 final release with native tool UI and CLI integration

- Core: Adapt to OpenWebUI native tool call UI and thinking process visualization
- Infra: Bundle Copilot CLI via pip package (no more background curl installation)
- Fix: Resolve "Error getting file content" on OpenWebUI v0.8.0+ via absolute paths
- i18n: Add native localization for status messages in 11 languages
- UX: Optimize reasoning status display logic and cleanup legacy code

.github/copilot-instructions.md

@@ -478,7 +478,117 @@ async def get_user_language(self):
 
 **注意**: 即使插件有 `Valves` 配置，也应优先尝试自动探测，提升用户体验。
 
-### 8. 智能代理文件交付规范 (Agent File Delivery Standards)
+### 8. 国际化 (i18n) 适配规范 (Internationalization Standards)
+
+开发供全球用户使用的插件时，必须预置多语言支持（如中文、英文等）。
+
+#### i18n 字典定义
+
+在文件顶部定义 `TRANSLATIONS` 字典存储多语言字符串：
+
+```python
+TRANSLATIONS = {
+    "en-US": {
+        "status_starting": "Smart Mind Map is starting...",
+    },
+    "zh-CN": {
+        "status_starting": "智能思维导图正在启动...",
+    },
+    # ... 其他语言
+}
+
+# 语言回退映射 (Fallback Map)
+FALLBACK_MAP = {
+    "zh": "zh-CN",
+    "zh-TW": "zh-CN",
+    "zh-HK": "zh-CN",
+    "en": "en-US",
+    "en-GB": "en-US"
+}
+```
+
+#### 获取当前用户真实语言 (Robust Language Detection)
+
+Open WebUI 的前端（localStorage）并未自动同步语言设置到后端数据库或通过标准 API 参数传递。为了获取精准的用户偏好语言，**必须**使用多层级回退机制（Multi-level Fallback）：
+`JS 动态探测 (localStorage)` > `HTTP 浏览器头 (Accept-Language)` > `用户 Profile 默认设置` > `en-US`
+
+> **注意！防卡死指南 (Anti-Deadlock Guide)**
+> 在通过 `__event_call__` 执行前端 JS 脚本时，如果前端脚本不慎抛出异常 (`Exception`) 会导致回调函数 `cb()` 永不执行，这会让后端的 `asyncio` 永远阻塞并卡死整个请求队列！
+> **必须**做两重防护：
+> 1. JS 内部包裹 `try...catch` 保证必须有 `return`。
+> 2. 后端使用 `asyncio.wait_for` 设置强制超时（建议 2 秒）。
+
+```python
+import asyncio
+from fastapi import Request
+
+async def _get_user_context(
+    self,
+    __user__: Optional[dict],
+    __event_call__: Optional[callable] = None,
+    __request__: Optional[Request] = None,
+) -> dict:
+    user_language = __user__.get("language", "en-US") if __user__ else "en-US"
+    
+    # 1st Fallback: HTTP Accept-Language header
+    if __request__ and hasattr(__request__, "headers") and "accept-language" in __request__.headers:
+        raw_lang = __request__.headers.get("accept-language", "")
+        if raw_lang:
+            user_language = raw_lang.split(",")[0].split(";")[0]
+
+    # 2nd Fallback (Best): Execute JS in frontend to read localStorage
+    if __event_call__:
+        try:
+            js_code = """
+                try {
+                    return (
+                        document.documentElement.lang ||
+                        localStorage.getItem('locale') || 
+                        navigator.language || 
+                        'en-US'
+                    );
+                } catch (e) {
+                    return 'en-US';
+                }
+            """
+            # 【致命！】必须设置 wait_for 防止前端无响应卡死后端
+            frontend_lang = await asyncio.wait_for(
+                __event_call__({"type": "execute", "data": {"code": js_code}}),
+                timeout=2.0
+            )
+            if frontend_lang and isinstance(frontend_lang, str):
+                user_language = frontend_lang
+        except Exception as e:
+            pass # fallback to accept-language or en-US
+
+    return {
+        "user_language": user_language,
+        # ... user_name, user_id etc.
+    }
+```
+
+#### 实际使用 (Usage in Action/Filter)
+
+在 Action 或者 Filter 执行时引用这套上下文获取机制，然后传入映射器获取最终翻译：
+
+```python
+async def action(
+    self, 
+    body: dict, 
+    __user__: Optional[dict] = None,
+    __event_call__: Optional[callable] = None, 
+    __request__: Optional[Request] = None,
+    **kwargs
+) -> Optional[dict]:
+    
+    user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+    user_lang = user_ctx["user_language"]
+    
+    # 获取多语言文本 (通过你的 translation.get() 扩展)
+    # start_msg = self._get_translation(user_lang, "status_starting")
+```
+
+### 9. 智能代理文件交付规范 (Agent File Delivery Standards)
 
 在开发具备文件生成能力的智能代理插件（如 GitHub Copilot SDK 集成）时，必须遵循以下标准流程，以确保文件在不同存储后端（本地/S3）下的可用性并绕过不必要的 RAG 处理。
 
@@ -498,7 +608,7 @@ async def get_user_language(self):
 - 代理应始终将“当前目录”视为其受保护所在的私有工作空间。
 - `publish_file_from_workspace` 的参数 `filename` 仅需传入相对于当前目录的文件名。
 
-### 9. Copilot SDK 插件工具定义规范 (Copilot SDK Tool Definition Standards)
+### 10. Copilot SDK 插件工具定义规范 (Copilot SDK Tool Definition Standards)
 
 在为 GitHub Copilot SDK 开发自定义工具时，为了确保大模型能正确识别参数（避免生成空的 `properties` Schema），必须遵循以下定义模式：
 
@@ -532,6 +642,63 @@ my_tool = define_tool(
 2.  **Field 描述**: 在 `BaseModel` 中使用 `Field(..., description="...")` 为每个参数提供详细的描述信息。
 3.  **Required vs Optional**: 明确标注必填项（无默认值）和可选项（带 `default`）。
 
+### 11. Copilot SDK 流式渲染与工具卡片规范 (Streaming & Tool Card Standards)
+
+在处理大模型的思维链（Reasoning）输出和工具调用（Tool Calls）时，为了确保能完美兼容 OpenWebUI 0.8.x 前端的 Markdown 解析器及原生折叠 UI 组件，必须遵循以下极度严格的输出格式规范。
+
+#### 思维链流式渲染 (Reasoning Streaming)
+
+为了让前端能够正确显示“Thinking...”的折叠框和 Spinner 动画，**必须**使用原生的 `<think>` 标签。
+
+- **正确的标签包裹**:
+  ```html
+  <think>
+  这里是思考过程...
+  </think>
+  ```
+- **关键细节**:
+  - **标签闭合检测**: 必须在代码内部维护状态（如 `state["thinking_started"]`）。当（1）正文内容即将开始输出，或（2）工具调用触发 (`tool.execution_start`) 时，**必须优先输出 `\n</think>\n` 强制闭合标签**。如果不闭合，后续的正文或工具面板会被全部吞进思考框内，导致页面完全崩坏！
+  - **不要手动拼装**: 严禁通过手动输出 `<details type="reasoning">` 等大段 HTML 来模拟思考过程，这种方式极易在流式片段发送中破坏前端 DOM 树并导致错位。
+
+#### 工具调用原生卡片 (Native Tool Calls Block)
+
+为了在对话界面中生成标准、原生的下拉折叠“工具调用”卡片，当 `event_type == "tool.execution_complete"` 时，必须向队列输出如下严格格式的 HTML：
+
+```python
+# 必须转义属性中的双引号为 &quot;
+args_for_attr = args_json_str.replace('"', "&quot;")
+result_for_attr = result_content.replace('"', "&quot;")
+
+tool_block = (
+    f'\\n<details type="tool_calls"'
+    f' id="{tool_call_id}"'
+    f' name="{tool_name}"'
+    f' arguments="{args_for_attr}"'
+    f' result="{result_for_attr}"'
+    f' done="true">\\n'
+    f"<summary>Tool Executed</summary>\\n"
+    f"</details>\\n\\n"
+)
+queue.put_nowait(tool_block)
+```
+
+- **致命避坑点 (Critical Pitfalls)**:
+  1. **属性转义 (Extremely Important)**: `<details>` 内的 `arguments` 和 `result` 属性**必须**将内部的所有双引号 `"` 替换为 `&quot;`。因为 OpenWebUI 前端提取这些数据的 Regex 是严格的 `="([^"]*)"`，一旦内容中出现原生双引号，就会被瞬间截断，导致参数被渲染为空并引发解析错误！
+  2. **换行符要求**: `<details ...>` 尖括号闭合后紧接着的内容**必须换行**（即 `>\\n`），否则 Markdown 扩展引擎无法将其识别为独立的 UI Block。
+  3. **去除冗余通知**: 不要在 `tool.execution_start` 事件中提前向对话流输出普通的 `🔧 Executing...` 纯文本块，这会导致最终页面上同时出现两块工具提示（一个文本，一个折叠卡片）。
+
+#### Debug 信息的解耦 (Decoupling Debug Logs)
+
+对于连接建立、运行环境、缓存加载等属于 *脚本自身运行状态* 的 Debug 信息：
+- **禁止**: 不要将这些内容 yield 到最终的回答数据流（或塞进 `<think>` 标签内），这会污染回答的纯粹性。
+- **推荐**: 统一使用 OpenWebUI 顶部的原生状态反馈气泡（Status Events）：
+  ```python
+  await __event_emitter__({
+      "type": "status",
+      "data": {"description": "连接建立，正在等待响应...", "done": True}
+  })
+  ```
+
 ---
 
 ## ⚡ Action 插件规范 (Action Plugin Standards)

docs/plugins/pipes/github-copilot-sdk.md

@@ -1,6 +1,6 @@
 # GitHub Copilot SDK Pipe for OpenWebUI
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.6.2 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.7.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
 
 This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/open-webui) that integrates the official [GitHub Copilot SDK](https://github.com/github/copilot-sdk). It enables you to use **GitHub Copilot models** (e.g., `gpt-5.2-codex`, `claude-sonnet-4.5`,`gemini-3-pro`, `gpt-5-mini`) **AND** your own models via **BYOK** (OpenAI, Anthropic) directly within OpenWebUI, providing a unified agentic experience with **strict User & Chat-level Workspace Isolation**.
 
@@ -14,12 +14,13 @@ This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/
 
 ---
 
-## ✨ v0.6.2 Updates (What's New)
+## ✨ v0.7.0 Updates (What's New)
 
-- **🛠️ New Workspace Artifacts Tool**: Introduced `publish_file_from_workspace`. Agents can now generate files (e.g., Python-generated Excel/CSV) and provide direct download links for the user to click and save.
-- **⚙️ Workflow Optimization**: Improved reliability of the internal agentic workspace management.
-- **🛡️ Enhanced Security**: Refined access control for system resources within the isolated environment.
-- **🔧 Performance Tuning**: Optimized stream processing for larger context windows.
+- **🚀 Integrated CLI Management**: The Copilot CLI is now automatically managed and bundled via the `github-copilot-sdk` pip package. (v0.7.0)
+- **🧠 Native Tool Call UI**: Full adaptation to **OpenWebUI's native tool call UI** and thinking process visualization. (v0.7.0)
+- **🏠 OpenWebUI v0.8.0+ Fix**: Resolved "Error getting file content" download failure by switching to absolute path registration for published files. (v0.7.0)
+- **🌐 Comprehensive Multi-language Support**: Native localization for status messages in 11 languages (EN, ZH, JA, KO, FR, DE, ES, IT, RU, VI, ID). (v0.7.0)
+- **🧹 Architecture Cleanup**: Refactored core setup and optimized reasoning status display for a leaner experience. (v0.7.0)
 
 ---
 
@@ -31,8 +32,8 @@ This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/
 - **♾️ Infinite Session Management**: Smart context window management with automatic compaction for indefinite conversation capability.
 - **🧠 Deep Database Integration**: Real-time persistence of TOD·O lists for long-running workflows.
 - **🌊 Advanced Streaming**: Full support for thinking process/Chain of Thought visualization.
-- **🖼️ Intelligent Multimodal**: Vision capabilities and raw file analysis support.
-- **⚡ Full-Lifecycle File Agent**: Supports receiving uploaded files for raw bypass analysis and publishing results (Excel/reports) as downloadable links.
+- **🖼️ Intelligent Multimodal**: Vision capabilities and raw file analysis support (bypasses RAG for direct binary access).
+- **📤 Workspace Artifacts (`publish_file_from_workspace`)**: Agents can generate files (Excel, CSV, HTML reports, etc.) and provide **persistent download links** directly in the chat.
 - **🖼️ Interactive Artifacts**: Automatically renders HTML/JS apps generated by the agent directly in the chat interface.
 
 ---
@@ -110,7 +111,7 @@ If this plugin has been useful, a **Star** on [OpenWebUI Extensions](https://git
 
 - **Agent ignores files?**: Ensure the Files Filter is enabled, otherwise RAG will interfere with raw binaries.
 - **No progress bar?**: The bar only appears when the Agent uses the `update_todo` tool.
-- **Dependencies**: This Pipe automatically installs `github-copilot-sdk` (Python) and `github-copilot-cli` (Binary).
+- **Dependencies**: This Pipe automatically manages `github-copilot-sdk` (Python) and utilizes the bundled binary CLI. No manual install required.
 
 ---
 

docs/plugins/pipes/github-copilot-sdk.zh.md

@@ -1,6 +1,6 @@
 # GitHub Copilot SDK 官方管道
 
-**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 0.6.2 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie) | **版本:** 0.7.0 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
 
 这是一个用于 [OpenWebUI](https://github.com/open-webui/open-webui) 的高级 Pipe 函数，深度集成了 **GitHub Copilot SDK**。它不仅支持 **GitHub Copilot 官方模型**（如 `gpt-5.2-codex`, `claude-sonnet-4.5`, `gemini-3-pro`, `gpt-5-mini`），还支持 **BYOK (自带 Key)** 模式对接自定义服务商（OpenAI, Anthropic），并具备**严格的用户与会话级工作区隔离**能力，提供统一且安全的 Agent 交互体验。
 
@@ -14,12 +14,13 @@
 
 ---
 
-## ✨ 0.6.2 更新内容 (What's New)
+## ✨ 0.7.0 更新内容 (What's New)
 
-- **🛠️ 新增工作区产物工具**: 引入 `publish_file_from_workspace`。Agent 现在可以生成物理文件（如使用 Python 生成的 Excel/CSV 报表），并直接在聊天界面提供点击下载链接。
-- **⚙️ 工作流优化**: 提升了内部 Agent 物理工作区管理的可靠性与原子性。
-- **🛡️ 安全增强**: 精细化了隔离环境下系统资源的访问控制策略。
-- **🔧 性能微调**: 针对大上下文窗口优化了流式数据处理性能。
+- **🚀 CLI 免维护集成**: Copilot CLI 现在通过 `github-copilot-sdk` pip 包自动同步管理，彻底告别手动 `curl | bash` 安装问题。(v0.7.0)
+- **🧠 原生工具调用 UI**: 全面适配 **OpenWebUI 原生工具调用 UI** 与模型思考过程（思维链）展示。(v0.7.0)
+- **🏠 OpenWebUI v0.8.0+ 兼容性修复**: 通过切换为绝对路径注册发布文件，彻底解决了“Error getting file content”无法下载到本地的问题。(v0.7.0)
+- **🌐 全面的多语言支持**: 针对状态消息进行了 11 国语言的原生本地化 (中/英/日/韩/法/德/西/意/俄/越/印尼)。(v0.7.0)
+- **🧹 架构精简**: 重构了初始化逻辑并优化了推理状态显示，提供更轻量稳健的体验。(v0.7.0)
 
 ---
 
@@ -31,8 +32,8 @@
 - **♾️ 无限会话管理**: 智能上下文窗口管理与自动压缩算法，支持无限时长的对话交互。
 - **🧠 深度数据库集成**: 实时持久化 TOD·O 列表到 UI 进度条。
 - **🌊 深度推理展示**: 完整支持模型思考过程 (Thinking Process) 的流式渲染。
-- **🖼️ 智能多模态**: 完整支持图像识别与附件上传分析。
-- **⚡ 全生命周期文件 Agent**: 支持接收上传文件进行绕过 RAG 的深度分析，并将处理结果（如 Excel/报告）发布为下载链接实现闭环。
+- **🖼️ 智能多模态**: 完整支持图像识别与附件上传分析（绕过 RAG 直接访问原始二进制内容）。
+- **📤 工作区产物工具 (`publish_file_from_workspace`)**: Agent 可生成文件（Excel、CSV、HTML 报告等）并直接提供**持久化下载链接**。管理员还可额外获得通过 `/content/html` 接口的**聊天内 HTML 预览**链接。
 - **🖼️ 交互式伪影 (Artifacts)**: 自动渲染 Agent 生成的 HTML/JS 应用程序，直接在聊天界面交互。
 
 ---
@@ -95,7 +96,7 @@
 ### 1) 导入函数
 
 1. 打开 OpenWebUI，前往 **工作区** -> **函数**。
-2. 点击 **+** (创建函数)，完整粘贴 `github_copilot_sdk_cn.py` 的内容。
+2. 点击 **+** (创建函数)，完整粘贴 `github_copilot_sdk.py` 的内容。
 3. 点击保存并确保已启用。
 
 ### 2) 获取 Token (Get Token)
@@ -110,7 +111,7 @@
 
 - **Agent 无法识别文件？**: 请确保已安装并启用了 Files Filter 插件，否则原始文件会被 RAG 干扰。
 - **看不到 TODO 进度条？**: 进度条仅在 Agent 使用 `update_todo` 工具（通常是处理复杂任务）时出现。
-- **依赖安装**: 本管道会自动尝试安装 `github-copilot-sdk` (Python 包) 和 `github-copilot-cli` (官方二进制)。
+- **依赖安装**: 本管道会自动管理 `github-copilot-sdk` (Python 包) 并优先直接使用内置的二进制 CLI，无需手动干预。
 
 ---
 

docs/plugins/pipes/index.md

@@ -15,7 +15,7 @@ Pipes allow you to:
 
 ## Available Pipe Plugins
 
-- [GitHub Copilot SDK](github-copilot-sdk.md) (v0.6.2) - Official GitHub Copilot SDK integration. Features **Workspace Isolation**, **Database Persistence**, **Zero-config OpenWebUI Tool Bridge**, **BYOK** support, and **dynamic MCP discovery**. Supports streaming, multimodal, and infinite sessions. [View Deep Dive](github-copilot-sdk-deep-dive.md) | [**View Advanced Tutorial**](github-copilot-sdk-tutorial.md).
+- [GitHub Copilot SDK](github-copilot-sdk.md) (v0.7.0) - Official GitHub Copilot SDK integration. Features **Workspace Isolation**, **Database Persistence**, **Zero-config OpenWebUI Tool Bridge**, **BYOK** support, and **dynamic MCP discovery**. Supports streaming, multimodal, and infinite sessions. [View Deep Dive](github-copilot-sdk-deep-dive.md) | [**View Advanced Tutorial**](github-copilot-sdk-tutorial.md).
 - **[Case Study: GitHub 100 Star Growth Analysis](star-prediction-example.md)** - Learn how to use the GitHub Copilot SDK Pipe with Minimax 2.1 to automatically analyze CSV data and generate project growth reports.
 - **[Case Study: High-Quality Video to GIF Conversion](video-processing-example.md)** - See how the model uses system-level FFmpeg to accelerate, scale, and optimize colors for screen recordings.
 

docs/plugins/pipes/index.zh.md

@@ -15,7 +15,7 @@ Pipes 可以用于：
 
 ## 可用的 Pipe 插件
 
-- [GitHub Copilot SDK](github-copilot-sdk.zh.md) (v0.6.2) - GitHub Copilot SDK 官方集成。具备**工作区安全隔离**、**数据库持久化**、**零配置工具桥接**与**BYOK (自带 Key) 支持**。支持流式输出、打字机思考过程及无限会话。[查看深度架构解析](github-copilot-sdk-deep-dive.zh.md) | [**查看进阶实战教程**](github-copilot-sdk-tutorial.zh.md)。
+- [GitHub Copilot SDK](github-copilot-sdk.zh.md) (v0.7.0) - GitHub Copilot SDK 官方集成。具备**工作区安全隔离**、**数据库持久化**、**零配置工具桥接**与**BYOK (自带 Key) 支持**。支持流式输出、打字机思考过程及无限会话。[查看深度架构解析](github-copilot-sdk-deep-dive.zh.md) | [**查看进阶实战教程**](github-copilot-sdk-tutorial.zh.md)。
 - **[实战案例：GitHub 100 Star 增长预测](star-prediction-example.zh.md)** - 展示如何使用 GitHub Copilot SDK Pipe 结合 Minimax 2.1 模型，自动编写脚本分析 CSV 数据并生成详细的项目增长报告。
 - **[实战案例：视频高质量 GIF 转换与加速](video-processing-example.zh.md)** - 演示模型如何通过底层 FFmpeg 工具对录屏进行加速、缩放及双阶段色彩优化处理。
 

plugins/actions/smart-mind-map/smart_mind_map.py

@@ -9,6 +9,7 @@ icon_url: data:image/svg+xml;base64,PHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAw
 description: Intelligently analyzes text content and generates interactive mind maps to help users structure and visualize knowledge.
 """
 
+import asyncio
 import logging
 import os
 import re
@@ -1514,6 +1515,7 @@ class Action:
         self,
         __user__: Optional[Dict[str, Any]],
         __event_call__: Optional[Callable[[Any], Awaitable[None]]] = None,
+        __request__: Optional[Request] = None,
     ) -> Dict[str, str]:
         """Extract basic user context with safe fallbacks."""
         if isinstance(__user__, (list, tuple)):
@@ -1528,20 +1530,36 @@ class Action:
         # Default from profile
         user_language = user_data.get("language", "en-US")
 
-        # Priority: Document Lang > LocalStorage (Frontend) > Browser > Profile (Default)
+        # Level 1 Fallback: Accept-Language from __request__ headers
+        if (
+            __request__
+            and hasattr(__request__, "headers")
+            and "accept-language" in __request__.headers
+        ):
+            raw_lang = __request__.headers.get("accept-language", "")
+            if raw_lang:
+                user_language = raw_lang.split(",")[0].split(";")[0]
+
+        # Priority: Document Lang > LocalStorage (Frontend) > Browser > Request Header > Profile
         if __event_call__:
             try:
                 js_code = """
-                    return (
-                        document.documentElement.lang ||
-                        localStorage.getItem('locale') || 
-                        localStorage.getItem('language') || 
-                        navigator.language || 
-                        'en-US'
-                    );
+                    try {
+                        return (
+                            document.documentElement.lang ||
+                            localStorage.getItem('locale') || 
+                            localStorage.getItem('language') || 
+                            navigator.language || 
+                            'en-US'
+                        );
+                    } catch (e) {
+                        return 'en-US';
+                    }
                 """
-                frontend_lang = await __event_call__(
-                    {"type": "execute", "data": {"code": js_code}}
+                # Use asyncio.wait_for to prevent hanging if frontend fails to callback
+                frontend_lang = await asyncio.wait_for(
+                    __event_call__({"type": "execute", "data": {"code": js_code}}),
+                    timeout=2.0,
                 )
                 if frontend_lang and isinstance(frontend_lang, str):
                     user_language = frontend_lang
@@ -2387,7 +2405,7 @@ class Action:
         __request__: Optional[Request] = None,
     ) -> Optional[dict]:
         logger.info("Action: Smart Mind Map (v1.0.0) started")
-        user_ctx = await self._get_user_context(__user__, __event_call__)
+        user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
         user_language = user_ctx["user_language"]
         user_name = user_ctx["user_name"]
         user_id = user_ctx["user_id"]

plugins/pipes/github-copilot-sdk/README.md

@@ -1,6 +1,6 @@
 # GitHub Copilot SDK Pipe for OpenWebUI
 
-**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.6.2 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
+**Author:** [Fu-Jie](https://github.com/Fu-Jie) | **Version:** 0.7.0 | **Project:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **License:** MIT
 
 This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/open-webui) that integrates the official [GitHub Copilot SDK](https://github.com/github/copilot-sdk). It enables you to use **GitHub Copilot models** (e.g., `gpt-5.2-codex`, `claude-sonnet-4.5`,`gemini-3-pro`, `gpt-5-mini`) **AND** your own models via **BYOK** (OpenAI, Anthropic) directly within OpenWebUI, providing a unified agentic experience with **strict User & Chat-level Workspace Isolation**.
 
@@ -14,12 +14,13 @@ This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/
 
 ---
 
-## ✨ v0.6.2 Updates (What's New)
+## ✨ v0.7.0 Updates (What's New)
 
-- **🛠️ New Workspace Artifacts Tool**: Introduced `publish_file_from_workspace`. Agents can now generate files (e.g., Python-generated Excel/CSV) and provide direct download links for the user to click and save.
-- **⚙️ Workflow Optimization**: Improved reliability of the internal agentic workspace management.
-- **🛡️ Enhanced Security**: Refined access control for system resources within the isolated environment.
-- **🔧 Performance Tuning**: Optimized stream processing for larger context windows.
+- **🚀 Integrated CLI Management**: The Copilot CLI is now automatically managed and bundled via the `github-copilot-sdk` pip package. No more manual `curl | bash` installation or version mismatches. (v0.7.0)
+- **🧠 Native Tool Call UI**: Full adaptation to **OpenWebUI's native tool call UI** and thinking process visualization. (v0.7.0)
+- **🏠 OpenWebUI v0.8.0+ Fix**: Resolved "Error getting file content" download failure by switching to absolute path registration for published files. (v0.7.0)
+- **🌐 Comprehensive Multi-language Support**: Native localization for status messages in 11 languages (EN, ZH, JA, KO, FR, DE, ES, IT, RU, VI, ID). (v0.7.0)
+- **🧹 Architecture Cleanup**: Refactored core setup and optimized reasoning status display for a leaner experience. (v0.7.0)
 
 ---
 
@@ -31,8 +32,8 @@ This is an advanced Pipe function for [OpenWebUI](https://github.com/open-webui/
 - **♾️ Infinite Session Management**: Smart context window management with automatic compaction for indefinite conversation capability.
 - **🧠 Deep Database Integration**: Real-time persistence of TOD·O lists for long-running workflows.
 - **🌊 Advanced Streaming**: Full support for thinking process/Chain of Thought visualization.
-- **🖼️ Intelligent Multimodal**: Vision capabilities and raw file analysis support.
-- **⚡ Full-Lifecycle File Agent**: Supports receiving uploaded files for raw bypass analysis and publishing results (Excel/reports) as downloadable links.
+- **🖼️ Intelligent Multimodal**: Vision capabilities and raw file analysis support (bypasses RAG for direct binary access).
+- **📤 Workspace Artifacts (`publish_file_from_workspace`)**: Agents can generate files (Excel, CSV, HTML reports, etc.) and provide **persistent download links** directly in the chat.
 - **🖼️ Interactive Artifacts**: Automatically renders HTML/JS apps generated by the agent directly in the chat interface.
 
 ---
@@ -110,7 +111,7 @@ If this plugin has been useful, a **Star** on [OpenWebUI Extensions](https://git
 
 - **Agent ignores files?**: Ensure the Files Filter is enabled, otherwise RAG will interfere with raw binaries.
 - **No progress bar?**: The bar only appears when the Agent uses the `update_todo` tool.
-- **Dependencies**: This Pipe automatically installs `github-copilot-sdk` (Python) and `github-copilot-cli` (Binary).
+- **Dependencies**: This Pipe automatically manages `github-copilot-sdk` (Python) and utilizes the bundled binary CLI. No manual install required.
 
 ---
 

plugins/pipes/github-copilot-sdk/README_CN.md

@@ -1,6 +1,6 @@
 # GitHub Copilot SDK 官方管道
 
-**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 0.6.2 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
+**作者:** [Fu-Jie](https://github.com/Fu-Jie/openwebui-extensions) | **版本:** 0.7.0 | **项目:** [OpenWebUI Extensions](https://github.com/Fu-Jie/openwebui-extensions) | **许可证:** MIT
 
 这是一个用于 [OpenWebUI](https://github.com/open-webui/open-webui) 的高级 Pipe 函数，深度集成了 **GitHub Copilot SDK**。它不仅支持 **GitHub Copilot 官方模型**（如 `gpt-5.2-codex`, `claude-sonnet-4.5`, `gemini-3-pro`, `gpt-5-mini`），还支持 **BYOK (自带 Key)** 模式对接自定义服务商（OpenAI, Anthropic），并具备**严格的用户与会话级工作区隔离**能力，提供统一且安全的 Agent 交互体验。
 
@@ -14,12 +14,13 @@
 
 ---
 
-## ✨ 0.6.2 更新内容 (What's New)
+## ✨ 0.7.0 更新内容 (What's New)
 
-- **🛠️ 新增工作区产物工具**: 引入 `publish_file_from_workspace`。Agent 现在可以生成物理文件（如使用 Python 生成的 Excel/CSV 报表），并直接在聊天界面提供点击下载链接。
-- **⚙️ 工作流优化**: 提升了内部 Agent 物理工作区管理的可靠性与原子性。
-- **🛡️ 安全增强**: 精细化了隔离环境下系统资源的访问控制策略。
-- **🔧 性能微调**: 针对大上下文窗口优化了流式数据处理性能。
+- **🚀 CLI 免维护集成**: Copilot CLI 现在通过 `github-copilot-sdk` pip 包自动同步管理，彻底告别手动 `curl | bash` 安装及版本不匹配问题。(v0.7.0)
+- **🧠 原生工具调用 UI**: 全面适配 **OpenWebUI 原生工具调用 UI** 与模型思考过程（思维链）展示。(v0.7.0)
+- **🏠 OpenWebUI v0.8.0+ 兼容性修复**: 通过切换为绝对路径注册发布文件，彻底解决了“Error getting file content”无法下载到本地的问题。(v0.7.0)
+- **🌐 全面的多语言支持**: 针对状态消息进行了 11 国语言的原生本地化 (中/英/日/韩/法/德/西/意/俄/越/印尼)。(v0.7.0)
+- **🧹 架构精简**: 重构了初始化逻辑并优化了推理状态显示，提供更轻量稳健的体验。(v0.7.0)
 
 ---
 
@@ -31,8 +32,8 @@
 - **♾️ 无限会话管理**: 智能上下文窗口管理与自动压缩算法，支持无限时长的对话交互。
 - **🧠 深度数据库集成**: 实时持久化 TOD·O 列表到 UI 进度条。
 - **🌊 深度推理展示**: 完整支持模型思考过程 (Thinking Process) 的流式渲染。
-- **🖼️ 智能多模态**: 完整支持图像识别与附件上传分析。
-- **⚡ 全生命周期文件 Agent**: 支持接收上传文件进行绕过 RAG 的深度分析，并将处理结果（如 Excel/报告）发布为下载链接。
+- **🖼️ 智能多模态**: 完整支持图像识别与附件上传分析（绕过 RAG 直接访问原始二进制内容）。
+- **📤 工作区产物工具 (`publish_file_from_workspace`)**: Agent 可生成文件（Excel、CSV、HTML 报告等）并直接在聊天中提供**持久化下载链接**。
 - **🖼️ 交互式伪影 (Artifacts)**: 自动渲染 Agent 生成的 HTML/JS 应用程序，直接在聊天界面交互。
 
 ---
@@ -95,7 +96,7 @@
 ### 1) 导入函数
 
 1. 打开 OpenWebUI，前往 **工作区** -> **函数**。
-2. 点击 **+** (创建函数)，完整粘贴 `github_copilot_sdk_cn.py` 的内容。
+2. 点击 **+** (创建函数)，完整粘贴 `github_copilot_sdk.py` 的内容。
 3. 点击保存并确保已启用。
 
 ### 2) 获取 Token (Get Token)
@@ -114,7 +115,7 @@
 
 - **Agent 无法识别文件？**: 请确保已安装并启用了 Files Filter 插件，否则原始文件会被 RAG 干扰。
 - **看不到 TODO 进度条？**: 进度条仅在 Agent 使用 `update_todo` 工具（通常是处理复杂任务）时出现。
-- **依赖安装**: 本管道会自动尝试安装 `github-copilot-sdk` (Python 包) 和 `github-copilot-cli` (官方二进制)。
+- **依赖安装**: 本管道会自动管理 `github-copilot-sdk` (Python 包) 并优先直接使用内置的二进制 CLI，无需手动干预。
 
 ---
 

plugins/pipes/github-copilot-sdk/github_copilot_sdk.py

@@ -1,12 +1,12 @@
 """
 title: GitHub Copilot Official SDK Pipe
 author: Fu-Jie
-author_url: https://github.com/Fu-Jie/awesome-openwebui
+author_url: https://github.com/Fu-Jie/openwebui-extensions
 funding_url: https://github.com/open-webui
 openwebui_id: ce96f7b4-12fc-4ac3-9a01-875713e69359
 description: Integrate GitHub Copilot SDK. Supports dynamic models, multi-turn conversation, streaming, multimodal input, infinite sessions, and frontend debug logging.
-version: 0.6.2
-requirements: github-copilot-sdk==0.1.23
+version: 0.7.0
+requirements: github-copilot-sdk==0.1.25
 """
 
 import os
@@ -226,10 +226,7 @@ class Pipe:
             default=300,
             description="Timeout for each stream chunk (seconds)",
         )
-        COPILOT_CLI_VERSION: str = Field(
-            default="0.0.406",
-            description="Specific Copilot CLI version to install/enforce (e.g. '0.0.406'). Leave empty for latest.",
-        )
+
         EXCLUDE_KEYWORDS: str = Field(
             default="",
             description="Exclude models containing these keywords (comma separated, e.g.: codex, haiku)",
@@ -360,6 +357,116 @@ class Pipe:
     _env_setup_done = False  # Track if env setup has been completed
     _last_update_check = 0  # Timestamp of last CLI update check
 
+    TRANSLATIONS = {
+        "en-US": {
+            "status_conn_est": "Connection established, waiting for response...",
+            "status_reasoning_inj": "Reasoning Effort injected: {effort}",
+            "debug_agent_working_in": "Agent working in: {path}",
+            "debug_mcp_servers": "🔌 Connected MCP Servers: {servers}",
+            "publish_success": "File published successfully.",
+            "publish_hint_html": "Link: [View {filename}]({view_url}) | [Download]({download_url})",
+            "publish_hint_default": "Link: [Download {filename}]({download_url})",
+        },
+        "zh-CN": {
+            "status_conn_est": "已建立连接，等待响应...",
+            "status_reasoning_inj": "已注入推理级别：{effort}",
+            "debug_agent_working_in": "Agent 工作目录: {path}",
+            "debug_mcp_servers": "🔌 已连接 MCP 服务器: {servers}",
+            "publish_success": "文件发布成功。",
+            "publish_hint_html": "链接: [查看 {filename}]({view_url}) | [下载]({download_url})",
+            "publish_hint_default": "链接: [下载 {filename}]({download_url})",
+        },
+        "zh-HK": {
+            "status_conn_est": "已建立連接，等待響應...",
+            "status_reasoning_inj": "已注入推理級別：{effort}",
+            "debug_agent_working_in": "Agent 工作目錄: {path}",
+            "debug_mcp_servers": "🔌 已連接 MCP 伺服器: {servers}",
+            "publish_success": "文件發布成功。",
+            "publish_hint_html": "連結: [查看 {filename}]({view_url}) | [下載]({download_url})",
+            "publish_hint_default": "連結: [下載 {filename}]({download_url})",
+        },
+        "zh-TW": {
+            "status_conn_est": "已建立連接，等待響應...",
+            "status_reasoning_inj": "已注入推理級別：{effort}",
+            "debug_agent_working_in": "Agent 工作目錄: {path}",
+            "debug_mcp_servers": "🔌 已連接 MCP 伺服器: {servers}",
+            "publish_success": "文件發布成功。",
+            "publish_hint_html": "連結: [查看 {filename}]({view_url}) | [下載]({download_url})",
+            "publish_hint_default": "連結: [下載 {filename}]({download_url})",
+        },
+        "ja-JP": {
+            "status_conn_est": "接続が確立されました。応答を待っています...",
+            "status_reasoning_inj": "推論レベルが注入されました：{effort}",
+            "debug_agent_working_in": "Agent 作業ディレクトリ: {path}",
+            "debug_mcp_servers": "🔌 接続済み MCP サーバー: {servers}",
+        },
+        "ko-KR": {
+            "status_conn_est": "연결이 설정되었습니다. 응답을 기다리는 중...",
+            "status_reasoning_inj": "추론 수준 설정됨: {effort}",
+            "debug_agent_working_in": "Agent 작업 디렉토리: {path}",
+            "debug_mcp_servers": "🔌 연결된 MCP 서버: {servers}",
+        },
+        "fr-FR": {
+            "status_conn_est": "Connexion établie, en attente de réponse...",
+            "status_reasoning_inj": "Effort de raisonnement injecté : {effort}",
+            "debug_agent_working_in": "Répertoire de travail de l'Agent : {path}",
+            "debug_mcp_servers": "🔌 Serveurs MCP connectés : {servers}",
+        },
+        "de-DE": {
+            "status_conn_est": "Verbindung hergestellt, warte auf Antwort...",
+            "status_reasoning_inj": "Argumentationsaufwand injiziert: {effort}",
+            "debug_agent_working_in": "Agent-Arbeitsverzeichnis: {path}",
+            "debug_mcp_servers": "🔌 Verbundene MCP-Server: {servers}",
+        },
+        "es-ES": {
+            "status_conn_est": "Conexión establecida, esperando respuesta...",
+            "status_reasoning_inj": "Nivel de razonamiento inyectado: {effort}",
+            "debug_agent_working_in": "Directorio de trabajo del Agente: {path}",
+            "debug_mcp_servers": "🔌 Servidores MCP conectados: {servers}",
+        },
+        "it-IT": {
+            "status_conn_est": "Connessione stabilita, in attesa di risposta...",
+            "status_reasoning_inj": "Livello di ragionamento iniettato: {effort}",
+            "debug_agent_working_in": "Directory di lavoro dell'Agente: {path}",
+            "debug_mcp_servers": "🔌 Server MCP connessi: {servers}",
+        },
+        "ru-RU": {
+            "status_conn_est": "Соединение установлено, ожидание ответа...",
+            "status_reasoning_inj": "Уровень рассуждения внедрен: {effort}",
+            "debug_agent_working_in": "Рабочий каталог Агента: {path}",
+            "debug_mcp_servers": "🔌 Подключенные серверы MCP: {servers}",
+        },
+        "vi-VN": {
+            "status_conn_est": "Đã thiết lập kết nối, đang chờ phản hồi...",
+            "status_reasoning_inj": "Cấp độ suy luận đã được áp dụng: {effort}",
+            "debug_agent_working_in": "Thư mục làm việc của Agent: {path}",
+            "debug_mcp_servers": "🔌 Các máy chủ MCP đã kết nối: {servers}",
+        },
+        "id-ID": {
+            "status_conn_est": "Koneksi terjalin, menunggu respons...",
+            "status_reasoning_inj": "Tingkat penalaran diterapkan: {effort}",
+            "debug_agent_working_in": "Direktori kerja Agent: {path}",
+            "debug_mcp_servers": "🔌 Server MCP yang terhubung: {servers}",
+        },
+    }
+
+    FALLBACK_MAP = {
+        "zh": "zh-CN",
+        "zh-TW": "zh-TW",
+        "zh-HK": "zh-HK",
+        "en": "en-US",
+        "en-GB": "en-US",
+        "ja": "ja-JP",
+        "ko": "ko-KR",
+        "fr": "fr-FR",
+        "de": "de-DE",
+        "es": "es-ES",
+        "it": "it-IT",
+        "ru": "ru-RU",
+        "vi": "vi-VN",
+        "id": "id-ID",
+    }
+
     def __init__(self):
         self.type = "pipe"
         self.id = "github_copilot_sdk"
@@ -390,6 +497,83 @@ class Pipe:
         except Exception as e:
             logger.error(f"[Database] ❌ Initialization failed: {str(e)}")
 
+    def _resolve_language(self, user_language: str) -> str:
+        """Normalize user language code to a supported translation key."""
+        if not user_language:
+            return "en-US"
+        if user_language in self.TRANSLATIONS:
+            return user_language
+        lang_base = user_language.split("-")[0]
+        if user_language in self.FALLBACK_MAP:
+            return self.FALLBACK_MAP[user_language]
+        if lang_base in self.FALLBACK_MAP:
+            return self.FALLBACK_MAP[lang_base]
+        return "en-US"
+
+    def _get_translation(self, lang: str, key: str, **kwargs) -> str:
+        """Helper function to get translated string for a key."""
+        lang_key = self._resolve_language(lang)
+        trans_map = self.TRANSLATIONS.get(lang_key, self.TRANSLATIONS["en-US"])
+        text = trans_map.get(key, self.TRANSLATIONS["en-US"].get(key, key))
+        if kwargs:
+            try:
+                text = text.format(**kwargs)
+            except Exception as e:
+                logger.warning(f"Translation formatting failed for {key}: {e}")
+        return text
+
+    async def _get_user_context(self, __user__, __event_call__=None, __request__=None):
+        """Extract basic user context with safe fallbacks including JS localStorage."""
+        if isinstance(__user__, (list, tuple)):
+            user_data = __user__[0] if __user__ else {}
+        elif isinstance(__user__, dict):
+            user_data = __user__
+        else:
+            user_data = {}
+
+        user_id = user_data.get("id", "unknown_user")
+        user_name = user_data.get("name", "User")
+        user_language = user_data.get("language", "en-US")
+
+        if (
+            __request__
+            and hasattr(__request__, "headers")
+            and "accept-language" in __request__.headers
+        ):
+            raw_lang = __request__.headers.get("accept-language", "")
+            if raw_lang:
+                user_language = raw_lang.split(",")[0].split(";")[0]
+
+        if __event_call__:
+            try:
+                js_code = """
+                    try {
+                        return (
+                            document.documentElement.lang ||
+                            localStorage.getItem('locale') || 
+                            localStorage.getItem('language') || 
+                            navigator.language || 
+                            'en-US'
+                        );
+                    } catch (e) {
+                        return 'en-US';
+                    }
+                """
+                frontend_lang = await asyncio.wait_for(
+                    __event_call__({"type": "execute", "data": {"code": js_code}}),
+                    timeout=2.0,
+                )
+                if frontend_lang and isinstance(frontend_lang, str):
+                    user_language = frontend_lang
+            except Exception as e:
+                pass
+
+        return {
+            "user_id": user_id,
+            "user_name": user_name,
+            "user_language": user_language,
+        }
+
     @contextlib.contextmanager
     def _db_session(self):
         """Yield a database session using Open WebUI helpers with graceful fallbacks."""
@@ -611,6 +795,8 @@ class Pipe:
             user_data = {}
 
         user_id = user_data.get("id") or user_data.get("user_id")
+        user_lang = user_data.get("language") or "en-US"
+        is_admin = user_data.get("role") == "admin"
         if not user_id:
             return None
 
@@ -746,10 +932,7 @@ class Pipe:
                     dest_path = Path(UPLOAD_DIR) / f"{file_id}_{safe_filename}"
                     await asyncio.to_thread(shutil.copy2, target_path, dest_path)
 
-                    try:
-                        db_path = str(os.path.relpath(dest_path, DATA_DIR))
-                    except:
-                        db_path = str(dest_path)
+                    db_path = str(dest_path)
 
                     file_form = FileForm(
                         id=file_id,
@@ -769,12 +952,37 @@ class Pipe:
 
                 # 5. Result
                 download_url = f"/api/v1/files/{file_id}/content"
+                view_url = download_url
+                is_html = safe_filename.lower().endswith(".html")
+
+                # For HTML files, if user is admin, provide a direct view link (/content/html)
+                if is_html and is_admin:
+                    view_url = f"{download_url}/html"
+
+                # Localized output
+                msg = self._get_translation(user_lang, "publish_success")
+                if is_html and is_admin:
+                    hint = self._get_translation(
+                        user_lang,
+                        "publish_hint_html",
+                        filename=safe_filename,
+                        view_url=view_url,
+                        download_url=download_url,
+                    )
+                else:
+                    hint = self._get_translation(
+                        user_lang,
+                        "publish_hint_default",
+                        filename=safe_filename,
+                        download_url=download_url,
+                    )
+
                 return {
                     "file_id": file_id,
                     "filename": safe_filename,
                     "download_url": download_url,
-                    "message": "File published successfully.",
-                    "hint": f"Link: [Download {safe_filename}]({download_url})",
+                    "message": msg,
+                    "hint": hint,
                 }
             except Exception as e:
                 return {"error": str(e)}
@@ -1921,10 +2129,6 @@ class Pipe:
             "on_post_tool_use": on_post_tool_use,
         }
 
-    def _get_user_context(self):
-        """Helper to get user context (placeholder for future use)."""
-        return {}
-
     def _get_chat_context(
         self,
         body: dict,
@@ -2327,25 +2531,11 @@ class Pipe:
         token: str = None,
         enable_mcp: bool = True,
         enable_cache: bool = True,
-        skip_cli_install: bool = False,
+        skip_cli_install: bool = False,  # Kept for call-site compatibility, no longer used
         __event_emitter__=None,
+        user_lang: str = "en-US",
     ):
-        """Setup environment variables and verify Copilot CLI. Dynamic Token Injection."""
-        def emit_status_sync(description: str, done: bool = False):
-            if not __event_emitter__:
-                return
-            try:
-                loop = asyncio.get_running_loop()
-                loop.create_task(
-                    __event_emitter__(
-                        {
-                            "type": "status",
-                            "data": {"description": description, "done": done},
-                        }
-                    )
-                )
-            except Exception:
-                pass
+        """Setup environment variables and resolve Copilot CLI path from SDK bundle."""
 
         # 1. Real-time Token Injection (Always updates on each call)
         effective_token = token or self.valves.GH_TOKEN
@@ -2353,8 +2543,6 @@ class Pipe:
             os.environ["GH_TOKEN"] = os.environ["GITHUB_TOKEN"] = effective_token
 
         if self._env_setup_done:
-            # If done, we only sync MCP if called explicitly or in debug mode
-            # To improve speed, we avoid redundant file I/O here for regular requests
             if debug_enabled:
                 self._sync_mcp_config(
                     __event_call__,
@@ -2365,186 +2553,46 @@ class Pipe:
             return
 
         os.environ["COPILOT_AUTO_UPDATE"] = "false"
-        self._emit_debug_log_sync(
-            "Disabled CLI auto-update (COPILOT_AUTO_UPDATE=false)",
-            __event_call__,
-            debug_enabled=debug_enabled,
-        )
 
-        # 2. CLI Path Discovery
-        cli_path = "/usr/local/bin/copilot"
-        if os.environ.get("COPILOT_CLI_PATH"):
-            cli_path = os.environ["COPILOT_CLI_PATH"]
-
-        target_version = self.valves.COPILOT_CLI_VERSION.strip()
-        found = False
-        current_version = None
-
-        def get_cli_version(path):
-            try:
-                output = (
-                    subprocess.check_output(
-                        [path, "--version"], stderr=subprocess.STDOUT
-                    )
-                    .decode()
-                    .strip()
-                )
-                import re
-
-                match = re.search(r"(\d+\.\d+\.\d+)", output)
-                return match.group(1) if match else output
-            except Exception:
-                return None
-
-        # Check existing version
-        if os.path.exists(cli_path):
-            found = True
-            current_version = get_cli_version(cli_path)
+        # 2. CLI Path Discovery (priority: env var > PATH > SDK bundle)
+        cli_path = os.environ.get("COPILOT_CLI_PATH", "")
+        found = bool(cli_path and os.path.exists(cli_path))
 
         if not found:
             sys_path = shutil.which("copilot")
             if sys_path:
                 cli_path = sys_path
                 found = True
-                current_version = get_cli_version(cli_path)
 
         if not found:
-            pkg_path = os.path.join(os.path.dirname(__file__), "bin", "copilot")
-            if os.path.exists(pkg_path):
-                cli_path = pkg_path
-                found = True
-                current_version = get_cli_version(cli_path)
-
-        # 3. Installation/Update Logic
-        should_install = not found
-        install_reason = "CLI not found"
-        if found and target_version:
-            norm_target = target_version.lstrip("v")
-            norm_current = current_version.lstrip("v") if current_version else ""
-
-            # Only install if target version is GREATER than current version
             try:
-                from packaging.version import parse as parse_version
+                from copilot.client import _get_bundled_cli_path
 
-                if parse_version(norm_target) > parse_version(norm_current):
-                    should_install = True
-                    install_reason = (
-                        f"Upgrade needed ({current_version} -> {target_version})"
-                    )
-                elif parse_version(norm_target) < parse_version(norm_current):
-                    self._emit_debug_log_sync(
-                        f"Current version ({current_version}) is newer than specified ({target_version}). Skipping downgrade.",
-                        __event_call__,
-                        debug_enabled=debug_enabled,
-                    )
-            except Exception as e:
-                # Fallback to string comparison if packaging is not available
-                if norm_target != norm_current:
-                    should_install = True
-                    install_reason = (
-                        f"Version mismatch ({current_version} != {target_version})"
-                    )
+                bundled_path = _get_bundled_cli_path()
+                if bundled_path and os.path.exists(bundled_path):
+                    cli_path = bundled_path
+                    found = True
+            except ImportError:
+                pass
 
-        if should_install and not skip_cli_install:
-            self._emit_debug_log_sync(
-                f"Installing/Updating Copilot CLI: {install_reason}...",
-                __event_call__,
-                debug_enabled=debug_enabled,
-            )
-            emit_status_sync(
-                "🔧 正在安装/更新 Copilot CLI（首次可能需要 1-3 分钟）...",
-                done=False,
-            )
-            try:
-                env = os.environ.copy()
-                if target_version:
-                    env["VERSION"] = target_version
-                proc = subprocess.Popen(
-                    "curl -fsSL https://gh.io/copilot-install | bash",
-                    shell=True,
-                    stdout=subprocess.PIPE,
-                    stderr=subprocess.STDOUT,
-                    text=True,
-                    bufsize=1,
-                    env=env,
-                )
-
-                progress_percent = -1
-                line_count = 0
-                while True:
-                    raw_line = proc.stdout.readline() if proc.stdout else ""
-                    if raw_line == "" and proc.poll() is not None:
-                        break
-
-                    line = (raw_line or "").strip()
-                    if not line:
-                        continue
-
-                    line_count += 1
-                    percent_match = re.search(r"(\d{1,3})%", line)
-                    if percent_match:
-                        try:
-                            pct = int(percent_match.group(1))
-                            if pct >= progress_percent + 5:
-                                progress_percent = pct
-                                emit_status_sync(
-                                    f"📦 Copilot CLI 安装中：{pct}%", done=False
-                                )
-                        except Exception:
-                            pass
-                    elif line_count % 20 == 0:
-                        emit_status_sync(
-                            f"📦 Copilot CLI 安装中：{line[:120]}", done=False
-                        )
-
-                return_code = proc.wait()
-                if return_code != 0:
-                    raise subprocess.CalledProcessError(
-                        return_code,
-                        "curl -fsSL https://gh.io/copilot-install | bash",
-                    )
-
-                # Re-verify
-                current_version = get_cli_version(cli_path)
-                emit_status_sync(
-                    f"✅ Copilot CLI 安装完成（v{current_version or target_version or 'latest'}）",
-                    done=False,
-                )
-            except Exception as e:
-                self._emit_debug_log_sync(
-                    f"CLI installation failed: {e}",
-                    __event_call__,
-                    debug_enabled=debug_enabled,
-                )
-                emit_status_sync(
-                    f"❌ Copilot CLI 安装失败：{str(e)[:120]}",
-                    done=True,
-                )
-        elif should_install and skip_cli_install:
-            self._emit_debug_log_sync(
-                f"Skipping CLI install during model listing: {install_reason}",
-                __event_call__,
-                debug_enabled=debug_enabled,
-            )
-
-        # 4. Finalize
-        cli_ready = bool(cli_path and os.path.exists(cli_path))
+        # 3. Finalize
+        cli_ready = found
         if cli_ready:
             os.environ["COPILOT_CLI_PATH"] = cli_path
+            # Add the CLI's parent directory to PATH so subprocesses can invoke `copilot` directly
+            cli_bin_dir = os.path.dirname(cli_path)
+            current_path = os.environ.get("PATH", "")
+            if cli_bin_dir and cli_bin_dir not in current_path.split(os.pathsep):
+                os.environ["PATH"] = cli_bin_dir + os.pathsep + current_path
 
         self.__class__._env_setup_done = cli_ready
         self.__class__._last_update_check = datetime.now().timestamp()
 
         self._emit_debug_log_sync(
-            f"Environment setup complete. CLI ready={cli_ready}. Path: {cli_path} (v{current_version})",
+            f"Environment setup complete. CLI ready={cli_ready}. Path: {cli_path}",
             __event_call__,
             debug_enabled=debug_enabled,
         )
-        if not skip_cli_install:
-            if cli_ready:
-                emit_status_sync("✅ Copilot CLI 已就绪", done=True)
-            else:
-                emit_status_sync("⚠️ Copilot CLI 尚未就绪，请稍后重试。", done=True)
 
     def _process_attachments(
         self,
@@ -2822,6 +2870,9 @@ class Pipe:
         effective_mcp = user_valves.ENABLE_MCP_SERVER
         effective_cache = user_valves.ENABLE_TOOL_CACHE
 
+        user_ctx = await self._get_user_context(__user__, __event_call__, __request__)
+        user_lang = user_ctx["user_language"]
+
         # 2. Setup environment with effective settings
         self._setup_env(
             __event_call__,
@@ -2830,11 +2881,12 @@ class Pipe:
             enable_mcp=effective_mcp,
             enable_cache=effective_cache,
             __event_emitter__=__event_emitter__,
+            user_lang=user_lang,
         )
 
         cwd = self._get_workspace_dir(user_id=user_id, chat_id=chat_id)
         await self._emit_debug_log(
-            f"Agent working in: {cwd} (Admin: {is_admin}, MCP: {effective_mcp})",
+            f"{self._get_translation(user_lang, 'debug_agent_working_in', path=cwd)} (Admin: {is_admin}, MCP: {effective_mcp})",
             __event_call__,
             debug_enabled=effective_debug,
         )
@@ -3269,9 +3321,9 @@ class Pipe:
             if body.get("stream", False):
                 init_msg = ""
                 if effective_debug:
-                    init_msg = f"> [Debug] Agent working in: {self._get_workspace_dir(user_id=user_id, chat_id=chat_id)}\n"
+                    init_msg = f"> [Debug] {self._get_translation(user_lang, 'debug_agent_working_in', path=self._get_workspace_dir(user_id=user_id, chat_id=chat_id))}\n"
                     if mcp_server_names:
-                        init_msg += f"> [Debug] 🔌 Connected MCP Servers: {', '.join(mcp_server_names)}\n"
+                        init_msg += f"> [Debug] {self._get_translation(user_lang, 'debug_mcp_servers', servers=', '.join(mcp_server_names))}\n"
 
                 # Transfer client ownership to stream_response
                 should_stop_client = False
@@ -3284,9 +3336,14 @@ class Pipe:
                     init_message=init_msg,
                     __event_call__=__event_call__,
                     __event_emitter__=__event_emitter__,
-                    reasoning_effort=effective_reasoning_effort,
+                    reasoning_effort=(
+                        effective_reasoning_effort
+                        if (is_reasoning and not is_byok_model)
+                        else "off"
+                    ),
                     show_thinking=show_thinking,
                     debug_enabled=effective_debug,
+                    user_lang=user_lang,
                 )
             else:
                 try:
@@ -3332,6 +3389,7 @@ class Pipe:
         reasoning_effort: str = "",
         show_thinking: bool = True,
         debug_enabled: bool = False,
+        user_lang: str = "en-US",
     ) -> AsyncGenerator:
         """
         Stream response from Copilot SDK, handling various event types.
@@ -3476,14 +3534,8 @@ class Pipe:
                     queue.put_nowait("\n</think>\n")
                     state["thinking_started"] = False
 
-                # Display tool call with improved formatting
-                if tool_args:
-                    tool_args_json = json.dumps(tool_args, indent=2, ensure_ascii=False)
-                    tool_display = f"\n\n<details>\n<summary>🔧 Executing Tool: {tool_name}</summary>\n\n**Parameters:**\n\n```json\n{tool_args_json}\n```\n\n</details>\n\n"
-                else:
-                    tool_display = f"\n\n<details>\n<summary>🔧 Executing Tool: {tool_name}</summary>\n\n*No parameters*\n\n</details>\n\n"
-
-                queue.put_nowait(tool_display)
+                # Note: We do NOT emit a done="false" card here to avoid card duplication
+                # (unless we have a way to update text which SSE content stream doesn't)
 
                 self._emit_debug_log_sync(
                     f"Tool Start: {tool_name}",
@@ -3600,31 +3652,55 @@ class Pipe:
                             )
                     # ------------------------
 
-                    # Try to detect content type for better formatting
-                    is_json = False
-                    try:
-                        json_obj = (
-                            json.loads(result_content)
-                            if isinstance(result_content, str)
-                            else result_content
+                    # --- Build native OpenWebUI 0.8.3 tool_calls block ---
+                    # Serialize input args (from execution_start)
+                    tool_args_for_block = {}
+                    if tool_call_id and tool_call_id in active_tools:
+                        tool_args_for_block = active_tools[tool_call_id].get(
+                            "arguments", {}
                         )
-                        if isinstance(json_obj, (dict, list)):
-                            result_content = json.dumps(
-                                json_obj, indent=2, ensure_ascii=False
-                            )
-                            is_json = True
-                    except:
-                        pass
 
-                    # Format based on content type
-                    if is_json:
-                        # JSON content: use code block with syntax highlighting
-                        result_display = f"\n<details>\n<summary>{status_icon} Tool Result: {tool_name}</summary>\n\n```json\n{result_content}\n```\n\n</details>\n\n"
-                    else:
-                        # Plain text: use text code block to preserve formatting and add line breaks
-                        result_display = f"\n<details>\n<summary>{status_icon} Tool Result: {tool_name}</summary>\n\n```text\n{result_content}\n```\n\n</details>\n\n"
+                    try:
+                        args_json_str = json.dumps(
+                            tool_args_for_block, ensure_ascii=False
+                        )
+                    except Exception:
+                        args_json_str = "{}"
 
-                    queue.put_nowait(result_display)
+                    def escape_html_attr(s: str) -> str:
+                        if not isinstance(s, str):
+                            return ""
+                        return (
+                            str(s)
+                            .replace("&", "&amp;")
+                            .replace("<", "&lt;")
+                            .replace(">", "&gt;")
+                            .replace('"', "&quot;")
+                            .replace("\n", "&#10;")
+                            .replace("\r", "&#13;")
+                        )
+
+                    # MUST escape both arguments and result with &quot; and &#10; to satisfy OpenWebUI's strict regex /="([^"]*)"/
+                    # OpenWebUI `marked` extension does not match multiline attributes properly without &#10;
+                    args_for_attr = (
+                        escape_html_attr(args_json_str) if args_json_str else "{}"
+                    )
+                    result_for_attr = escape_html_attr(result_content)
+
+                    # Emit the unified native tool_calls block:
+                    # OpenWebUI 0.8.3 frontend regex explicitly expects: name="xxx" arguments="..." result="..." done="true"
+                    # CRITICAL: <details> tag MUST be followed immediately by \n for the frontend Markdown extension to parse it!
+                    tool_block = (
+                        f'\n<details type="tool_calls"'
+                        f' id="{tool_call_id}"'
+                        f' name="{tool_name}"'
+                        f' arguments="{args_for_attr}"'
+                        f' result="{result_for_attr}"'
+                        f' done="true">\n'
+                        f"<summary>Tool Executed</summary>\n"
+                        f"</details>\n\n"
+                    )
+                    queue.put_nowait(tool_block)
 
             elif event_type == "tool.execution_progress":
                 # Tool execution progress update (for long-running tools)
@@ -3725,20 +3801,42 @@ class Pipe:
 
         # Safe initial yield with error handling
         try:
-            if debug_enabled and show_thinking:
-                yield "<think>\n"
+            if debug_enabled and __event_emitter__:
+                # Emit debug info as UI status rather than reasoning block
+                async def _emit_status(key: str, desc: str = None, **kwargs):
+                    try:
+                        final_desc = (
+                            desc
+                            if desc
+                            else self._get_translation(user_lang, key, **kwargs)
+                        )
+                        await __event_emitter__(
+                            {
+                                "type": "status",
+                                "data": {"description": final_desc, "done": True},
+                            }
+                        )
+                    except:
+                        pass
+
                 if init_message:
-                    yield init_message
+                    for line in init_message.split("\n"):
+                        if line.strip():
+                            clean_msg = line.replace("> [Debug] ", "").strip()
+                            asyncio.create_task(_emit_status("custom", desc=clean_msg))
 
                 if reasoning_effort and reasoning_effort != "off":
-                    yield f"> [Debug] Reasoning Effort injected: {reasoning_effort.upper()}\n"
+                    asyncio.create_task(
+                        _emit_status(
+                            "status_reasoning_inj", effort=reasoning_effort.upper()
+                        )
+                    )
 
-                yield "> [Debug] Connection established, waiting for response...\n"
-                state["thinking_started"] = True
+                asyncio.create_task(_emit_status("status_conn_est"))
         except Exception as e:
             # If initial yield fails, log but continue processing
             self._emit_debug_log_sync(
-                f"Initial yield warning: {e}",
+                f"Initial status warning: {e}",
                 __event_call__,
                 debug_enabled=debug_enabled,
             )
@@ -3766,12 +3864,21 @@ class Pipe:
                 except asyncio.TimeoutError:
                     if done.is_set():
                         break
-                    if state["thinking_started"]:
+                    if __event_emitter__ and debug_enabled:
                         try:
-                            yield f"> [Debug] Waiting for response ({self.valves.TIMEOUT}s exceeded)...\n"
+                            asyncio.create_task(
+                                __event_emitter__(
+                                    {
+                                        "type": "status",
+                                        "data": {
+                                            "description": f"Waiting for response ({self.valves.TIMEOUT}s exceeded)...",
+                                            "done": True,
+                                        },
+                                    }
+                                )
+                            )
                         except:
-                            # If yield fails during timeout, connection is gone
-                            break
+                            pass
                     continue
 
             while not queue.empty():

plugins/pipes/github-copilot-sdk/v0.7.0.md

@@ -0,0 +1,82 @@
+# GitHub Copilot SDK Pipe v0.7.0
+
+**GitHub Copilot SDK Pipe v0.7.0** — A major infrastructure and UX upgrade. This release eliminates manual CLI management, fully embraces OpenWebUI's native tool calling interface, and ensures seamless compatibility with the latest OpenWebUI versions.
+
+---
+
+## 📦 Quick Installation
+
+- **GitHub Copilot SDK (Pipe)**: [Install v0.7.0](https://openwebui.com/posts/ce96f7b4-12fc-4ac3-9a01-875713e69359)
+- **GitHub Copilot SDK (Filter)**: [Install v0.1.2](https://openwebui.com/posts/403a62ee-a596-45e7-be65-fab9cc249dd6)
+
+---
+
+## 🚀 What's New in v0.7.0
+
+### 1. Zero-Maintenance CLI Integration
+
+The most significant infrastructure change: you no longer need to worry about CLI versions or background downloads.
+
+| Before (v0.6.x) | After (v0.7.0) |
+| :--- | :--- |
+| CLI installed via background `curl \| bash` | CLI bundled inside the `github-copilot-sdk` pip package |
+| Version mismatches between SDK and CLI | Versions are always in sync automatically |
+| Fails in restricted networks | Works everywhere `pip install` works |
+
+**How it works**: When you install `github-copilot-sdk==0.1.25`, the matching `copilot-cli v0.0.411` is included. The plugin auto-discovers the path and injects it into the environment—zero configuration required.
+
+### 2. Native OpenWebUI Tool Call UI
+
+Tool calls from Copilot agents now render using **OpenWebUI's built-in tool call UI**.
+
+- Tool execution status is displayed natively in the chat interface.
+- Thinking processes (Chain of Thought) are visualized with the standard collapsible UI.
+- Improved visual consistency and integration with the main OpenWebUI interface.
+
+### 3. OpenWebUI v0.8.0+ Compatibility Fix (Bug Fix)
+
+Resolved the **"Error getting file content"** failure that affected users on OpenWebUI v0.8.0 and later.
+
+- **The Issue**: Relative path registration for published files was rejected by the latest OpenWebUI versions.
+- **The Fix**: Switched to **absolute path registration**, restoring the ability to download generated artifacts to your local machine.
+
+### 4. Comprehensive Multi-language Support (i18n)
+
+Native localization for status messages and UI hints in **11 languages**:
+*English, Chinese (Simp/Trad/HK/TW), Japanese, Korean, French, German, Spanish, Italian, Russian, Vietnamese, and Indonesian.*
+
+### 5. Reasoning Status & UX Optimizations
+
+- **Intelligent Status Display**: `Reasoning Effort injected` status is now only shown for native Copilot reasoning models.
+- **Clean UI**: Removed redundant debug/status noise for BYOK and standard models.
+- **Architecture Cleanup**: Refactored core setup and removed legacy installation code for a robust "one-click" experience.
+
+---
+
+## 🛠️ Key Capabilities
+
+| Feature | Description |
+| :--- | :--- |
+| **Universal Tool Protocol** | Native support for **MCP**, **OpenAPI**, and **OpenWebUI built-in tools**. |
+| **Native Tool Call UI** | Adapted to OpenWebUI's built-in tool call rendering. |
+| **Workspace Isolation** | Strict sandboxing for per-session data privacy and security. |
+| **Workspace Artifacts** | Agents generate files (Excel/CSV/HTML) with persistent download links via `publish_file_from_workspace`. |
+| **Tool Execution** | Direct access to system binaries (Python, FFmpeg, Git, etc.). |
+| **11-Language Localization** | Auto-detected, native status messages for global users. |
+| **OpenWebUI v0.8.0+ Support** | Robust file handling for the latest OpenWebUI platform versions. |
+
+---
+
+## 📥 Import Chat Templates
+
+- [📥 Star Prediction Chat log](https://fu-jie.github.io/awesome-openwebui/plugins/pipes/star-prediction-chat.json)
+- [📥 Video Processing Chat log](https://fu-jie.github.io/awesome-openwebui/plugins/pipes/video-processing-chat.json)
+
+*Settings -> Data -> Import Chats.*
+
+---
+
+## 🔗 Resources
+
+- **GitHub Repository**: [openwebui-extensions](https://github.com/Fu-Jie/openwebui-extensions)
+- **Full Changelog**: [README.md](https://github.com/Fu-Jie/openwebui-extensions/blob/main/plugins/pipes/github-copilot-sdk/README.md)