Closed
Conversation
…undling The original bash script failed on Windows environments without bash installed. This change introduces scripts/bundle-a2ui.mjs and updates package.json to use it, ensuring better compatibility across different operating systems.
Correctly identifies and strips Node.js experimental warning flags from process.argv in normalizeWindowsArgv to prevent Commander from misidentifying positional arguments.
…kills, and Windows build fixes
… thinking box components. - Added DeepSeek Web provider with PoW solving and stream handling. - Optimized reasoning tag parsing for various model formats. - Created chat-thinking UI component for collapsible reasoning display. - Updated .gitignore to exclude local logs and test artifacts.
Features: - DeepSeek web authentication (browser login, no API key needed) - Fixed Lit 3.x decorator compatibility (TC39 standard decorators) - Environment isolation from system OpenClaw Modifications: - Added accessor keyword to all @Property(), @State(), @query() decorators - Updated Chrome automation parameters for latest Chrome version - Created independent state directory (.openclaw-state/)
- 新增 doubao-proxy（推荐）与 doubao-web 两种方案 - 接入 doubao-free-api 本地代理，OpenAI 兼容接口 - 新增 run.sh 一体化启动脚本 - 更新 README 中英文档、豆包测试指南 - 添加 doubao.mp4 演示视频 Co-authored-by: Cursor <cursoragent@cursor.com>
- 更新 package.json、run-node.mjs、server.sh - 优化 model-selection、workspace、status.summary - 更新 gateway、cron 相关配置 - 添加 doubao.mp4 更新、工作总结.md Co-authored-by: Cursor <cursoragent@cursor.com>
- 新增首次运行详细指南和快速开始文档 - 支持 macOS/Linux/Windows WSL2 跨平台 - 补充环境检查脚本和配置示例 - 补充 Chrome 调试模式说明文档
核心改动： - 新增 doubao-web-client-browser.ts，参考 Claude 实现 - 使用 page.evaluate() 在浏览器上下文中执行请求 - 简化认证参数：从 13 个减少到 4 个 - 移除 doubao-proxy 相关代码和配置 - 修复 auth-choice-options.ts 中缺失的 choices 字段 文档和工具： - 添加 DOUBAO_REFACTOR_SUMMARY.md 重构文档 - 添加 MODEL_SWITCHING_GUIDE.md 模型切换指南 - 更新 README 添加模型切换说明 - 添加诊断和测试脚本 技术改进： - 浏览器自动处理动态参数（msToken, a_bogus, fp 等） - 保持浏览器连接，避免反爬虫检测 - 代码结构更清晰，易于维护 Breaking Changes: - 移除 doubao-proxy 提供商，用户需重新配置为 doubao-web
- 提供便捷的 Gateway 重启功能 - 自动停止现有进程并重新启动
- 更新中文版 README 的豆包实现原理章节，改为浏览器方案说明 - 更新系统架构图，将 Doubao Proxy 改为 Doubao Web - 更新开发路线，将 'doubao-free-api' 改为 '浏览器方案' - 删除过时的测试指南文件（豆包测试指南.md 和 DOUBAO_TESTING_GUIDE.md） - 所有文档现在只描述浏览器自动化方案，不再提及 doubao-proxy
- 将系统架构图中的 'Doubao Proxy' 改为 'Doubao Web' - 与中文版保持一致
- 将注释中的 'doubao-free-api / samantha' 改为 '豆包 samantha API' - 更新技术说明，使其更准确地描述当前实现 - 保持代码逻辑不变，仅更新注释
- 更新 DOUBAO_REFACTOR_SUMMARY.md 移除所有 doubao-proxy 提及 - 更新 README.md 技术细节部分的描述 - 添加 DEEPSEEK_ANALYSIS.md 分析文档 - 所有文档现在只描述浏览器方案
- Add template file for agent identity configuration - Add template file for user preferences - These are reference templates in docs/reference/templates/
- Add detailed usage instructions - Add comprehensive preference categories - Add bilingual support (Chinese/English) - Add project-specific preferences (AI platforms, testing, etc.) - Add work style configuration - Add filled example based on actual project usage - Include Do's and Don'ts section
Removed: - 15 duplicate/outdated markdown docs - 11 redundant shell scripts Kept only essential files: - Docs: README.md, INSTALLATION.md, START_HERE.md, TEST_STEPS.md - Scripts: start-chrome-debug.sh, onboard.sh, server.sh, check-setup.sh Added: - cleanup-all.sh for future cleanup - 8 new web platforms implementation (32 core files) - Updated configuration files
- Keep ignoring IDENTITY.md and USER.md in general - Add exception for docs/reference/templates/ directory - Allow template files to be committed to repository
- README.md: Added English version with concise format - INSTALLATION.md: Added English installation guide - START_HERE.md: Added English quick start guide - TEST_STEPS.md: Added English testing steps All docs now support both Chinese and English
- server.sh: 添加 OPENCLAW_GATEWAY_PORT 环境变量和 --port 参数 - onboard.sh: 修正环境变量 OPENCLAW_PORT 为 OPENCLAW_GATEWAY_PORT - 确保项目与系统 openclaw 使用不同端口，互不干扰 Made-with: Cursor
- onboard.sh / server.sh / start-chrome-debug.sh 统一加入环境检测 - detect_os(): 识别 mac / linux / win / wsl - detect_node(): 按系统查找 node 路径 - detect_chrome(): 按优先级扫描各系统 Chrome/Chromium 路径（含 Deepin） - open_browser(): 跨平台打开浏览器（open / xdg-open / start / cmd.exe） - port_pid(): 跨平台查端口占用（lsof / ss / netstat） - server.sh: gateway token 改为从配置文件动态读取，回退到环境变量 - 日志路径兼容无 /tmp 的 Windows 环境 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
重写 z-web 全部核心文件，使其从 Untested 变为可用状态： - 逆向 chatglm.cn 请求签名机制 (X-Sign/X-Nonce/X-Timestamp + MD5) - 修正请求体格式 (新增 project_id、chat_type、cogview 等必需字段) - 适配 SSE 累积型响应解析 (parts[].content[] 格式) - 更新模型为 glm-4-plus / glm-4-think，映射对应 assistant_id - 更新认证流程，支持 chatglm_token cookie 直接使用 - 同步更新 README、README_zh-CN、TEST_STEPS 文档状态 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 重写 manus-web-auth.ts：连接已有 Chrome 调试实例，等待 session_id cookie - 更新 manus-web-client-browser.ts：增加 UI 文本过滤，改进回复提取逻辑 - 更新 README 文档：manus-web 状态改为已测试 测试通过： - "say hi in 3 words" → "Hi there, friend!" - "1+1=?" → "2" Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
主要改动: 1. z-web 重命名为 glm-web (智谱清言 chatglm.cn) 2. 移除 manus-web (改用 API Key 方式认证) 3. 修复 Web Provider onboard 后默认模型不切换的问题 - kimi-web 默认改为 moonshot-v1-32k - chatgpt-web, gemini-web, grok-web, glm-web 现在正确设置默认模型 4. 修复 Grok 认证 cookie 检测 (auth_token/ct0 → sso/_ga) 5. 修复 Grok API 无对话时自动创建新对话 6. 修复 Grok 响应解析 (正确提取 NDJSON 内容) 7. WebUI Sessions 表新增 Model 列，支持模型覆盖 文档更新: - ARCHITECTURE.md (新增架构文档) - 更新各平台认证说明 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…y which is ignored by Git)
将示例状态配置改为最小模板，并在文档中明确 openclaw.json 由 onboard 按选择平台增量写入。同步统一 zero-state 路径说明，并清理根目录 GLM 调试脚本入口。 Made-with: Cursor
统一脚本与核心路径解析到 openclaw-zero 命名，完善 claude-web 与 glm-intl-web 的浏览器侧处理逻辑，并清理过时的 Qwen 执行流程文档。 Made-with: Cursor
统一 zero-state 路径与平台清单，补充 onboard 完成后才进入 /models 的关键规则，并修正文档导航中的失效链接与 Windows Bash 使用说明。 Made-with: Cursor
Enable Feishu as an extension channel in the config type system. This allows the Feishu npm plugin to work properly. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
修复wsl环境start-chrome-debug.sh脚本报错问题
|
Important Review skippedToo many files! This PR contains 255 files, which is 105 over the limit of 150. ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (45)
📒 Files selected for processing (255)
You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Comment Tip You can customize the tone of the review comments and chat replies.Configure the |
Author
|
pass |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Describe the problem and fix in 2–5 bullets:
Change Type (select all)
Scope (select all touched areas)
Linked Issue/PR
User-visible / Behavior Changes
List user-visible changes (including defaults/config).
If none, write
None.Security Impact (required)
Yes/No)Yes/No)Yes/No)Yes/No)Yes/No)Yes, explain risk + mitigation:Repro + Verification
Environment
Steps
Expected
Actual
Evidence
Attach at least one:
Human Verification (required)
What you personally verified (not just CI), and how:
Review Conversations
If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.
Compatibility / Migration
Yes/No)Yes/No)Yes/No)Failure Recovery (if this breaks)
Risks and Mitigations
List only real risks for this PR. Add/remove entries as needed. If none, write
None.