Merge branch 'agentscope-ai:main' into main

Author: zhangckcup

.gitattributes

@@ -0,0 +1 @@
+*.bat text eol=crlf

.github/PULL_REQUEST_TEMPLATE.md

@@ -28,15 +28,26 @@
 
 ## Checklist
 
-- [ ] Pre-commit hooks pass (`pre-commit run --all-files` or CI)
-- [ ] Tests pass locally (`pytest` or as relevant)
+- [ ] I ran `pre-commit run --all-files` locally and it passes
+- [ ] If pre-commit auto-fixed files, I committed those changes and reran checks
+- [ ] I ran tests locally (`pytest` or as relevant) and they pass
 - [ ] Documentation updated (if needed)
 - [ ] Ready for review
 
 ## Testing
 
 [How to test these changes]
 
+## Local Verification Evidence
+
+```bash
+pre-commit run --all-files
+# paste summary result
+
+pytest
+# paste summary result
+```
+
 ## Additional Notes
 
 [Optional: any other context]

.github/workflows/pr-label.yml

@@ -0,0 +1,36 @@
+name: PR Labeler
+
+on:
+  pull_request_target:
+    types: [opened]
+
+jobs:
+  first-time-contributor:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+    steps:
+      - name: Check if first-time contributor
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const author = context.payload.pull_request.user.login;
+
+            const { data: searchResult } = await github.rest.search.issuesAndPullRequests({
+              q: `repo:${context.repo.owner}/${context.repo.repo} type:pr author:${author} is:closed`,
+            });
+
+            const isFirstTime = searchResult.total_count === 0;
+
+            if (isFirstTime) {
+              await github.rest.issues.addLabels({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                issue_number: context.payload.pull_request.number,
+                labels: ['first-time-contributor'],
+              });
+              core.info(`Labeled PR #${context.payload.pull_request.number} as first-time-contributor`);
+            } else {
+              core.info(`${author} has ${searchResult.total_count} PRs, skipping label`);
+            }

.github/workflows/pre-commit.yml

@@ -35,7 +35,7 @@ jobs:
           pre-commit run --all-files > pre-commit.log 2>&1 || true
           cat pre-commit.log
           if grep -q Failed pre-commit.log; then
-            echo -e "\e[41m  [**FAIL**] Please install pre-commit and format your code first. \e[0m"
+            echo -e "\e[41m  [**FAIL**] pre-commit checks failed. Run 'pre-commit run --all-files' locally, commit any auto-fixes, then push again. \e[0m"
             exit 1
           fi
           echo -e "\e[46m  ********************************Passed******************************** \e[0m"

CONTRIBUTING.md

@@ -67,16 +67,16 @@ docs(skills): document Skills Hub import
 
 ### 4. Code and Quality
 
-- **Pre-commit:** Install and run pre-commit for consistent style and checks:
+- **Required local gate (must pass before push/PR):**
   ```bash
   pip install -e ".[dev]"
   pre-commit install
   pre-commit run --all-files
-  ```
-- **Tests:** Run tests before submitting:
-  ```bash
   pytest
   ```
+- **If pre-commit modifies files:** Commit those changes, then rerun
+  `pre-commit run --all-files` until it passes cleanly.
+- **CI policy:** Pull requests with failing pre-commit checks are not merge-ready.
 - **Frontend formatting:** If your changes involve the `console` or `website` directories, run the formatter before committing:
   ```bash
   cd console && npm run format

CONTRIBUTING_zh.md

@@ -67,16 +67,16 @@ docs(skills): document Skills Hub import
 
 ### 4. 代码和质量
 
-- **Pre-commit：** 安装并运行 pre-commit 以保持一致的风格和检查：
+- **本地必跑门禁（push/提 PR 前必须通过）：**
   ```bash
   pip install -e ".[dev]"
   pre-commit install
   pre-commit run --all-files
-  ```
-- **测试：** 提交前运行测试：
-  ```bash
   pytest
   ```
+- **如果 pre-commit 自动修改了文件：** 先提交这些修改，再重复执行
+  `pre-commit run --all-files`，直到无修改且通过。
+- **CI 策略：** pre-commit 检查失败的 PR 视为未就绪（not merge-ready）。
 - **前端代码格式化：** 如果你的修改涉及到 `console` 或 `website` 目录，请在提交前运行格式化：
   ```bash
   cd console && npm run format

README.md

@@ -15,7 +15,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Join_Us-blueviolet.svg?logo=discord)](https://discord.gg/eYMpfnkG8h)
 [![DingTalk](https://img.shields.io/badge/DingTalk-Join_Us-orange.svg)](https://qr.dingtalk.com/action/joingroup?code=v1,k1,OmDlBXpjW+I2vWjKDsjvI9dhcXjGZi3bQiojOq3dlDw=&_dt_no_comment=1&origin=11)
 
-[[Documentation](https://copaw.agentscope.io/)] [[中文 README](README_zh.md)]
+[[Documentation](https://copaw.agentscope.io/)] [[中文 README](README_zh.md)] [[日本語](README_ja.md)]
 
 <p align="center">
   <img src="https://img.alicdn.com/imgextra/i1/O1CN01tvT5rg1JHQNRP8tXR_!!6000000001003-2-tps-1632-384.png" alt="CoPaw Logo" width="120">
@@ -51,6 +51,18 @@ Your Personal AI Assistant; easy to install, deploy on your own machine or on th
 
 ---
 
+## News
+
+[2026-03-02] We released v0.0.4! See the [v0.0.4 Release Notes](https://github.com/agentscope-ai/CoPaw/releases/tag/v0.0.4) for the full changelog.
+
+- **[v0.0.4]** **FEAT:** Telegram channel; OpenAI & Azure OpenAI providers; Ollama SDK; coding-plan provider; model connection testing; heartbeat monitoring panel; CORS configuration; audio file support for DingTalk & Feishu.
+- **[v0.0.4]** **FEAT:** Token-based memory compaction; file block processing; embedding configuration; normalized tool_choice behavior.
+- **[v0.0.4]** **BUGFIX:** Windows file paths; empty tool calls; console workspace UI; Ollama URL & connectivity; MCP transport; browser resource leak; static asset MIME types; API headers; Playwright Docker; heartbeat parsing; media message queuing.
+- **[v0.0.4]** **RELS:** Installation scripts with PowerShell; Docker guide; channel CLI docs; Feishu SOCKS proxy; MCP & runtime docs; FAQ (EN/ZH); skill-writing guide; CONTRIBUTING; console docs; website improvements.
+- **[v0.0.4]** **COMM:** Special thanks to all new contributors: [@ekzhu](https://github.com/ekzhu), [@fancyboi999](https://github.com/fancyboi999), [@zhaozhuang521](https://github.com/zhaozhuang521), [@hobostay](https://github.com/hobostay), [@dhbxs](https://github.com/dhbxs), [@longway-code](https://github.com/longway-code), [@ydlstartx](https://github.com/ydlstartx), [@LudovicoYIN](https://github.com/LudovicoYIN), [@fenixc9](https://github.com/fenixc9), [@dittotang](https://github.com/dittotang), [@forestxieCode](https://github.com/forestxieCode), [@yongtenglei](https://github.com/yongtenglei), [@kerwin612](https://github.com/kerwin612), [@luixiao0](https://github.com/luixiao0), [@gongpx20069](https://github.com/gongpx20069).
+
+---
+
 ## Table of Contents
 
 > **Recommended reading:**
@@ -59,10 +71,14 @@ Your Personal AI Assistant; easy to install, deploy on your own machine or on th
 > - **I want to chat in DingTalk / Feishu / QQ**: [Quick Start](#quick-start) → [Channels](https://copaw.agentscope.io/docs/channels).
 > - **I don’t want to install Python**: [One-line install](#one-line-install-beta-continuously-improving) handles Python automatically, or use [ModelScope one-click](https://modelscope.cn/studios/fork?target=AgentScope/CoPaw) for cloud.
 
+- [News](#news)
 - [Quick Start](#quick-start)
 - [API Key](#api-key)
 - [Local Models](#local-models)
 - [Documentation](#documentation)
+- [FAQ](#faq)
+- [Roadmap](#roadmap)
+- [Contributing](#get-involved)
 - [Install from source](#install-from-source)
 - [Why CoPaw?](#why-copaw)
 - [Built by](#built-by)
@@ -108,13 +124,44 @@ To install with multiple extras (e.g., Ollama + llama.cpp):
 curl -fsSL https://copaw.agentscope.io/install.sh | bash -s -- --extras ollama,llamacpp
 ```
 
+**Windows (CMD):**
+
+```CMD
+curl -fsSL https://copaw.agentscope.io/install.bat -o install.bat && install.bat
+```
+
 **Windows (PowerShell):**
 
 ```powershell
 irm https://copaw.agentscope.io/install.ps1 | iex
 ```
 
-Then open a new terminal and run:
+> **Note**: The installer will automatically check the status of uv. If it is not installed, it will attempt to download and configure it automatically. If the automatic installation fails, please follow the on-screen prompts or execute `python -m pip install -U uv`, then rerun the installer.
+
+> **⚠️ Special Notice for Windows Enterprise LTSC Users**
+>
+> If you are using Windows LTSC or an enterprise environment governed by strict security policies, PowerShell may run in **Constrained Language Mode**, potentially causing the following issue:
+> 1. **If using CMD (.bat): Script executes successfully but fails to write to `Path`**
+>
+>    The script completes file installation. Due to **Constrained Language Mode**, it cannot automatically update environment variables. Manually configure as follows:
+>    - **Locate the installation directory**:
+>      - Check if `uv` is available: Enter `uv --version` in CMD. If a version number appears, **only configure the CoPaw path**. If you receive the prompt `'uv' is not recognized as an internal or external command, operable program or batch file,` configure both paths.
+>      - uv path (choose one based on installation location; use if `uv` fails): Typically `%USERPROFILE%\.local\bin`, `%USERPROFILE%\AppData\Local\uv`, or the `Scripts` folder within your Python installation directory
+>      - CoPaw path: Typically located at `%USERPROFILE%\.copaw\bin`.
+>    - **Manually add to the system's Path environment variable**:
+>      - Press `Win + R`, type `sysdm.cpl` and press Enter to open System Properties.
+>      - Click “Advanced” -> “Environment Variables”.
+>      - Under “System variables”, locate and select `Path`, then click “Edit”.
+>      - Click “New”, enter both directory paths sequentially, then click OK to save.
+> 2. **If using PowerShell (.ps1): Script execution interrupted**
+>
+>   Due to **Constrained Language Mode**, the script may fail to automatically download `uv`.
+>   - **Manually install uv**: Refer to the [GitHub Release](https://github.com/astral-sh/uv/releases) to download `uv.exe` and place it in `%USERPROFILE%\.local\bin` or `%USERPROFILE%\AppData\Local\uv`; or ensure Python is installed and run `python -m pip install -U uv`.
+>   - **Configure `uv` environment variables**: Add the `uv` directory and `%USERPROFILE%\.copaw\bin` to your system's `Path` variable.
+>   - **Re-run the installation**: Open a new terminal and execute the installation script again to complete the `CoPaw` installation.
+>   - **Configure the `CoPaw` environment variable**: Add `%USERPROFILE%\.copaw\bin` to your system's `Path` variable.
+
+Once installed, open a new terminal and run:
 
 ```bash
 copaw init --defaults   # or: copaw init (interactive)
@@ -251,6 +298,52 @@ Full docs in this repo: [website/public/docs/](website/public/docs/).
 
 ---
 
+## FAQ
+
+For common questions, troubleshooting tips, and known issues, please visit the **[FAQ page](https://copaw.agentscope.io/docs/faq)**.
+
+---
+
+## Roadmap
+
+| Area | Item | Status |
+| --- | --- | --- |
+| Horizontal Expansion | More channels, models, skills, MCPs — **community contributions welcome** | Seeking Contributors |
+| Existing Feature Extension | Display optimization, download hints, Windows path compatibility, etc. — **community contributions welcome** | Seeking Contributors |
+| Compatibility & Ease of Use | App-level packaging (DMG, EXE) | In Progress |
+| | One-click deployment: built-in deps, dev extras, install/upgrade tutorials | In Progress |
+| Release & Contributing | Contributing docs and test framework | In Progress |
+| | Responsive handling of community contributions | In Progress |
+| | Contributing guidance for vibe coding agents | Planned |
+| Bugfixes & Enhancements | Message collapse/hide in UI | Planned |
+| | Skills and MCP runtime install, hot-reload improvements | Planned |
+| | Context management and compression (long tool outputs, lower token usage) | Planned |
+| | Multimodal support | In Progress |
+| Security | Shell execution confirmation | Planned |
+| | Tool/skills security | Planned |
+| | Configurable security levels (user-configurable) | Planned |
+| Multimodal | Voice/video calls and real-time interaction | Long-term Planning |
+| Multi-agent | Built on [AgentScope](https://github.com/agentscope-ai/agentscope), native multi-agent workflows | Long-term Planning |
+| Sandbox | Deeper integration with AgentScope Runtime sandboxes | Long-term Planning |
+| Self-healing | Daemon agent for automated recovery and health monitoring | Long-term Planning |
+| CoPaw-optimized local models | LLMs tuned for CoPaw's native skills and common tasks; better local personal-assistant usability | Long-term Planning |
+| Small + large model collaboration | Local LLMs for sensitive data; cloud LLMs for planning and coding; balance of privacy, performance, and capability | Long-term Planning |
+| Cloud-native | Deeper integration with AgentScope Runtime; leverage cloud compute, storage, and tooling | Long-term Planning |
+| Skills Hub | Enrich the [AgentScope Skills](https://github.com/agentscope-ai/agentscope-skills) repository and improve discoverability of high-quality skills | Long-term Planning |
+
+*Status:* *In Progress* — actively being worked on; *Planned* — queued or under design, also **welcome contributions**; *Seeking Contributors* — we **strongly encourage community contributions**; *Long-term Planning* — longer-horizon roadmap.
+
+### Get involved
+
+We are building CoPaw in the open and welcome contributions of all kinds! Check the [Roadmap](#roadmap) above (especially items marked **Seeking Contributors**) to find areas that interest you, and read [CONTRIBUTING](https://github.com/agentscope-ai/CoPaw/blob/main/CONTRIBUTING.md) to get started. We particularly welcome:
+
+- **Horizontal expansion** — new channels, model providers, skills, MCPs.
+- **Existing feature extension** — display and UX improvements, download hints, Windows path compatibility, and the like.
+
+Join the conversation on [GitHub Discussions](https://github.com/agentscope-ai/CoPaw/discussions) to suggest or pick up work.
+
+---
+
 ## Install from source
 
 ```bash