cua-driver 预编译二进制文件 — 相对坐标分支 (fork)
(托管于 `packages/cua-driver` 下)。
- **macOS**: 已代码签名 + 公证的通用二进制文件 + `QwenCuaDriver.app`
- **Linux**: 未签名(x86_64 + arm64,glibc 2.31 最低要求)
- **Windows**: 未签名(x86_64 + arm64)
启用相对坐标:设置环境变量 `CUA_DRIVER_RS_COORDINATE_SPACE=1`
(默认 `0` 为关闭;可选设置 `CUA_DRIVER_RS_COORDINATE_SCALE=1000`)。
<!-- 使用 main 分支 .github/release.yml 中的配置生成发布说明 -->
## 更新内容
* fix(cli):持久化 MCP 服务器移除操作 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4535
* fix(models):刷新基于原始模型派生的默认配置 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4517
* fix(vscode-ide-companion):从 NOTICES.txt 生成中排除工作区包 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4455
* fix(telemetry):将交互 span 附加到会话根上下文 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4499
* fix(cli):粘贴或拖放多个文件路径时自动添加 @ 前缀 by @MikeWang0316tw in https://github.com/QwenLM/qwen-code/pull/4544
* feat(prompt):将新应用提示词从系统提示词移至技能模块 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4567
* feat(worktree):阶段 D — 启动 --worktree 标志 + symlinkDirectories + PR 引用 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4381
* fix(permissions):将命令替换改为询问而非拒绝 (#4093) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4386
* feat(cli):默认开启 auto-dream/auto-skill 并添加 /memory 切换开关 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4547
* fix(cli):在 TUI 渲染前将启动警告输出至 stderr (#4448) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4461
* fix(telemetry):改进 LogToSpan 桥接错误信息及 TUI 处理 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4482
* feat(channels):添加飞书 (Lark) 频道适配器 by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/4379
* feat(telemetry):构建基于技能的 RT 优化基础架构 (P0+P1) by @gwinthis in https://github.com/QwenLM/qwen-code/pull/4565
* fix(cli):追踪模型发送的斜杠命令历史记录 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3826
* feat(computer-use):通过 open-computer-use MCP 实现零配置内置功能 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4590
* refactor(core)!: 用摘要 + 恢复附件替换尾部保留压缩 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4599
* 为 AUTO 分类器块触发 PermissionDenied 钩子 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4376
* chore(release):v0.16.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4571
* fix(core):在 IDE 代理请求中使用 undici fetch by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4607
* fix(core,cli):在自动压缩通知中准确标记由截图触发的压缩 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4623
* chore(release):v0.17.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4626
* fix(rewind):修复存在中途消息时的虚假“已压缩轮次”错误 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4580
* fix(core):在推理功能禁用时向 DashScope 发送 enable_thinking by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4505
* fix(core):暴露 Anthropic 空流提供程序错误 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4540
* feat(core):添加内存压力监控 by @ZevGit in https://github.com/QwenLM/qwen-code/pull/4403
* fix(core):防止恢复历史发送时数据过大 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4531
* fix(cli):稳定状态栏预设排序 by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4634
* fix(config):在解析 settings ${VAR} 之前加载 home .env 变量 (#4466) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4474
* fix(acp):弃用已停用的 Qwen OAuth 方法 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4639
* fix(core):强制要求工具结果相邻 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4622
* fix(cli):隐藏已完成的固定待办事项 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4635
* feat(cli):添加设置 JSON 损坏警告对话框 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4560
* fix(core):增强上下文错误文本收集 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4632
* fix(core):将输出语言应用于侧边查询 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4636
* fix(cli):在对话框重新打开时持久化 /memory 切换状态 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4650
* fix(docs):从文档站点隐藏内部文档 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4357
* fix(core):在 atomicWriteFile 中保留 uid 以避免破坏共享写入文件 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4431
* 改进钩子匹配器显示 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4545
* fix(cli):关闭 ACP 会话时使用会话频道 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4522
* fix(core,cli):用浅拷贝/尾部变体替换全历史 structuredClone 以防止恢复时内存溢出 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4644
* feat(cli):为状态栏添加 respectUserColors 和 hideContextIndicator 选项 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4670
* fix(core):兼容不支持的 Streamable HTTP GET SSE by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4521
* fix(insight):增强洞察维度归一化及空定性数据处理 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3557
* feat(cli): 后台 shell 完成时发送通知 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4355
* feat(core): 添加简化的内置技能 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3570
* feat(skills): 添加代理复现工作流 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4118
* feat(cli): 在 ink 7 上为长对话提供虚拟视口 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4146
* feat(cli): 清理过期文件历史目录的后台维护 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4414
* fix(core): 放宽自动模式分类器超时时间,禁用第二阶段思考 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4680
* fix(core): 强制处理非信任提供商的用量 token 计数 (#4350 第一部分) by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4439
* feat(core): 将上下文环境变量(会话/代理/提示词 ID)注入到 shell 子进程中 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4649
* 添加 AUTO 模式拒绝的可观测性与限制 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4476
* feat(core): 检测到内存压力时自动将内存诊断信息转储到磁盘 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4654
* feat(core): 凭据、内存、配置、JSONL 的原子写入部署(关闭 #3681, #4095 第二阶段) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4333
* docs: 添加 /diff 命令和自动主题检测文档 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4699
* feat(cli): 添加可搜索的 MiniMax-M3 模型配置 by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4668
* feat(core,cli): 自动压缩后续操作 — /compress 指令、PreCompact 钩子接入、计划/子代理附件 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4688
* fix(cli): 遵循列出扩展插件的命令行标志 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4673
* feat(input): 将物理光标移至视觉光标以支持 IME 输入 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4652
* feat(core): 添加工具后批处理钩子 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4454
* fix(ui): 区分自动审批模式的指示器 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4600
* fix(core): 在无代理 Node.js 路径下禁用 undici 300s bodyTimeout by @Pepograminger in https://github.com/QwenLM/qwen-code/pull/4605
* feat(prompt): 去重系统提示词与工具描述之间的工具引导 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4569
* chore(deps): 将 @google/genai 从 1.30.0 更新至 2.6.0 by @InfiniteUselessness in https://github.com/QwenLM/qwen-code/pull/4485
* feat(cli): 添加用于 Chrome DevTools 分析的 CPU 性能分析支持 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4620
* feat(prompt): 通过全局推理规范和迭代规划增强系统提示词 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4436
* refactor(cli): 将 "Default" 审批模式重命名为 "Ask permissions" (#4625) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4674
* fix(cli): 在编辑前对历史恢复的文本隐藏补全菜单 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4558
* fix(cli): 修复从预设切换到命令类型时状态栏未重新渲染的问题 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4706
* fix(cli): 避免退出时深度克隆历史记录 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4717
* feat(subagent): 添加 fork 子代理功能开关及“不窥探/不竞争”提示词规范 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4574
* fix(telemetry): 在聊天压缩后清除 span 去重状态 (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4660
* feat(core): 增强编辑前阅读代码、专用工具优先级及逐步沟通的系统提示词 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4375
* fix(core): 移除主动的子代理系统提醒注入 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4587
* fix(cli): 修复 Arena 模型选择对话框中空格键无效的问题 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4701
* feat(skills): 添加用于 Issue/PR 分类的 triage 技能 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4577
* feat(computer-use): 使用 @qwen-code/open-computer-use 分支(已签名+公证) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4726
* chore(release): v0.17.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4742
* fix(cli): 在复制输出时跳过思考部分 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4738
* feat(installer): 验证发布资源 + 将公共文档切换为独立入口 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3855
* feat(ci): 添加用于 Issue 和 PR 自动分类的 @qwen /triage 工作流 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4768
* fix(cli): 改进审批模式显示文本 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4753
* fix(ui): 在状态栏和启动横幅中显示模型名称而非 ID by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4741
* feat(cli): 添加独立自动更新支持 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4629
* fix(ci): 修复分类提示词变量扩展、机器人身份及模型密钥 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4778
* feat(telemetry): 第四阶段 4b — 为 qwen-code.llm_request 添加重试可见性 (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4432
* feat(core): 添加用户提示词扩展钩子 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4377
* fix(computer-use): 在自动审批模式(YOLO/AUTO_EDIT/AUTO)中自动批准安装 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4756
* fix(cli): 实现 --list-extensions 标志处理器 (#4450) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4456
* feat(telemetry): 第三阶段 — 具有并发隔离的 qwen-code.subagent 跨度 (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4410
* feat(skills): /skills 选择器对话框 — 浏览、搜索、切换、选择 (#4532) by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4533
* fix(core): 处理禁用技能命令委托中的错误变体 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4804
* fix(cli): 移除 #4456 中废弃的 --list-extensions 处理器 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4800
* feat(cli): 在 ACP 模式下启用 /remember、/forget、/dream by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4811
* ci(triage): 修复 Qwen 分类工作流提示 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4787
* Revert "feat(cli): 在 ACP 模式下启用 /remember、/forget、/dream" by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4818
* feat(vscode): 显示 ACP 后台通知 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4358
* feat(cli): 支持 /copy N 以复制倒数第 N 条 AI 消息 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4761
* fix(core): 在爬取 git 仓库时递归进入子模块文件 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4596
* 强化自动模式下的自我修改检查 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4572
* fix(clipboard): 在 Linux 上使用平台原生工具进行图片粘贴 by @CNCSMonster in https://github.com/QwenLM/qwen-code/pull/4647
* fix(core): 为 qwen3.7-plus 添加多模态支持 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4803
* feat(cli): 运行时防止系统休眠 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4434
* feat(ci): 添加使用内置 /review 技能的 PR 审查工作流 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4549
* fix(core): 将布尔类型转换限制为布尔类型的模式字段 by @Pluviobyte in https://github.com/QwenLM/qwen-code/pull/4618
* fix(cli): 打包扩展示例 by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4719
* fix(cli): 修复 vim 模式 Esc 键泄漏、Enter 提交、渲染延迟,并实现缺失的 VIM 命令 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4677
* fix(core): 允许为退避机制执行有意的前台休眠 by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4708
* fix(core): 自动内存遵循运行时输出目录 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4715
* feat(cli): 添加 /fork 后台代理命令 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4780
* fix(tui): 在 <Static> 模式下跳过跨组工具合并以消除屏幕闪烁 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4795
* 将启动上下文移至系统提醒 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4053
* feat(core): 通过自动批准声明的工具来遵循技能的 allowedTools 配置 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4704
* 为指令文件加载添加 InstructionsLoaded 钩子 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4665
* fix(cli): 防止选择对话框闪烁 by @ZevGit in https://github.com/QwenLM/qwen-code/pull/4755
* feat(skills): 为自动生成技能强制使用 auto-skill- 目录前缀 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4839
* fix(core): 在每次用户查询时注入当前日期以防止日期过期 by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/4798
* 使自动化 PR 审查与内置技能保持一致 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4843
* fix(ci): 协调 qwen 分类与审查自动化 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4570
* fix(core): 在 formatDateForContext 测试块中添加缺失的闭合大括号 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4863
* fix(core): 通过压缩 API 历史记录、UI 历史记录并在内存压力下触发清理来防止 OOM by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4824
* fix(core): 不终止启动失败的休眠抑制子进程(工具使用时的沙箱中止) by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4865
* fix(skills): 为文档技能添加内置技能 doc-index 验证 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4851
* feat(memory): 在 ~/.qwen/memories/ 添加用户级自动内存 (#4747) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4764
* fix(sdk): 更正 SDK 安装说明中的 npm 包名 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4860
* test(integration): 在 sleep-interception 端到端测试中放宽严格的 30 秒超时 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4878
* fix: 在持久化 model.name 前剥离运行时快照前缀 by @Rakson0209 in https://github.com/QwenLM/qwen-code/pull/4734
* test: 覆盖回退选择器恢复选项 by @han-dreamer in https://github.com/QwenLM/qwen-code/pull/4784
* fix(cli): 处理后台自动更新破坏跨 authType 模型切换的问题 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4760
* fix(core): 在身份验证刷新时保留共享 baseUrl by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4828
* refactor(core): 移除 GitService,将 /restore 迁移至 FileHistoryService by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4871
* feat(acp): 支持桌面端 qwen 集成 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4728
* feat(extension): 为 ExtensionConfig 添加 description 字段 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4857
* fix(ci): 确认队列中的 qwen 审查请求 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4847
* fix(core): 修复 qc-helper 技能的文档索引和配置类别 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4848
* feat(telemetry): 将 TRACEPARENT 环境变量注入到 shell 子进程中 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4906
* fix(ci): 规范化 Windows 上的开发启动器路径断言 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4915
* fix(installer): 修正安装后消息中损坏(404)的“更多信息”链接 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4916
* fix(core): 通过为每个请求创建子控制器来隔离 OpenAI SDK 中止监听器内存泄漏 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4810
* feat(hooks): 支持终端序列通知 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4895
* feat(core): 工作流工具 P1 — 最小化 node:vm 沙箱 + 顺序执行 agent() (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4732
* fix(acp): 防止客户端忽略中途排空请求时导致会话/提示符卡死 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4925
* fix(core): 从智能体工具提示中移除 greeting-responder 示例 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4923
* feat(ci): 添加从发布版本同步的自动生成 CHANGELOG.md (#4872) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4881
* feat(stats): 添加带有跨会话追踪功能的交互式 /stats 仪表盘 by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4779
* fix(core): 从只读 shell 命令白名单中移除 `env` by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4932
* fix(core): 防止 cron 调度器在创建分钟触发 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4946
* fix(core): 确保硬阈值始终高于自动阈值 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4949
* fix(installer): 自动检测 SYSTEM 账户并将 PATH 作用域默认设为机器级 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4903
* fix(skills): 对 frontmatter 使用完整 YAML 解析器以支持块标量 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4870
* fix(core): 在睡眠链首次被拒绝时提供完整的 intentional-sleep 指导 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4948
* fix(core): 将 qwen3.7-plus 加入编程计划模型列表 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4953
* ci: 将 qwen PR 审查超时时间延长至 90 分钟,队列延迟延长至 30 分钟 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4962
* test: 覆盖 rewind 选择器的回退状态 by @han-dreamer in https://github.com/QwenLM/qwen-code/pull/4905
* feat(core): 默认启用 loop/cron 工具 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4950
* test(integration): 增强不稳定的 sleep-interception 端到端测试,以应对被跳过的工具调用 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4936
* fix(openai): 默认启用 splitToolMedia,使工具返回的图片能兼容严格的 OpenAI 兼容后端 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4917
* fix(cli): 修复光标在硬换行边界处向左移动时卡住的问题 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4852
* feat(core): 声明式智能体 frontmatter v1 — permissionMode 桥接 + maxTurns 连线 + 颜色白名单(与 CC 2.1.168 对齐) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4842
* fix(core): 优化 microcompact 钩子延续逻辑 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4840
* feat: 新增 Agent Team 实验性功能,用于并行子智能体协调 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4844
* fix: 修复发布工作区测试失败问题 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4980
* fix(core): 在审批后恢复工具调用时保留队友身份 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4979
* refactor(skills): 移除冗余命令并同步 e2e-testing 技能 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4992
* fix(installer): 当新版本的 qwen 未被加载时,打印 shell 重载提示 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4960
* feat(desktop): 新增集成 Qwen ACP SDK 的桌面应用包 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3778
* feat(daemon): 将 daemon-mode 功能批次合并至 main 分支 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4490
* feat(core): 实现分层工具输出截断、按消息预算及按工具限制 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4880
* fix(auth): 为 Qwen OAuth 刷新添加超时机制 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4829
* fix(cli): 将下箭头键直接路由至实时智能体面板 (#4907) by @wsyjh8 in https://github.com/QwenLM/qwen-code/pull/4911
* fix(core): 增强实验性 agent-team 消息传递机制 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4988
* feat(telemetry): 添加运行时内存/CPU 采样及 OTel 指标上报 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4868
* fix(cli): 在空闲提示符下启用 VP 滚动并修复视口高度 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4959
* fix(core): 解析智能体 frontmatter 中的逗号分隔 tools/disallowedTools by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4935
* perf(filesearch): 将 AsyncFzf 索引构建移至工作线程 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4621
* feat(cli): 新增 /compress-fast 命令,用于无 LLM 的规则上下文压缩 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4893
* fix(cli): 修复在缺少捆绑示例时 extensions new 命令无法工作的问题 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/5009
* feat(web-shell): 新增 Option+Enter 和 Cmd+Enter 换行快捷键 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5005
* chore(daemon): 移除死代码并简化控制流 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4789
* fix(goal):跨恢复操作持久化迭代计数,使 MAX_GOAL_ITERATIONS 限制整个会话 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5000
* 新增 /cd 命令 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4890
* ci(desktop):mac 代码签名 + App Store Connect API 密钥公证 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5013
* feat(core):为跨会话 /rewind 持久化文件历史快照 (T2.1) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4897
* fix(desktop):空闲退出后保持 composer 可发送 by @puneetdixit200 in https://github.com/QwenLM/qwen-code/pull/4788
* fix(cli):避免无头浏览器打开时崩溃 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4716
* fix(cli):防抖调整大小重绘,并在稳定时清除过期的滚动缓冲区 by @wsyjh8 in https://github.com/QwenLM/qwen-code/pull/4919
* feat(core):移植声明式代理 mcpServers + 钩子 (CC 2.1.168 对齐跟进) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4996
* feat(core):工作流 P2 — parallel() + pipeline() 并发扇出 (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4947
* fix(core):在系统提示词中添加 Tool Fallback 规则 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4931
* fix(docs):更正过期的设置键、错误的默认值及缺失的命令 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4969
* fix(core):稳定截断的工具重试键 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4970
* fix(core):针对 MCP/技能变更稳定提示词缓存前缀 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4896
* fix(core):修复因缺少 printf 命令导致的 Windows 启动错误 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/5012
* feat(core):新增 enter_plan_mode 工具和计划审批门控 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4853
* docs(desktop):品牌构建技能使用 main 分支 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5021
* perf(desktop):新增 --cli-only 标志,在 vendor 构建期间跳过非 CLI 包 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5025
* fix(desktop):允许未签名的 Windows 自动更新 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5028
* fix(cli):在列 0 按下 Ctrl+U 时合并上一行 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5011
* fix(tui):收紧消息与工具的间距 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4595
* fix(core):按代理序列化团队任务声明,并添加邮箱锁对齐 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4981
* fix(core):在扩展命令发现中支持 .toml 命令文件 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5017
* test(i18n):提高 Windows CI 上缓慢的必译区域设置套件超时时间 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5024
* fix(stats):按 sessionId 去重使用记录,并跳过进行中的写入 by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4995
* fix(test):在 daemon 批量合并后修复 qwen serve 集成套件 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5041
* feat(acp):向 daemon 客户端广播会话标题更新 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5035
* fix(release):在独立发行版白名单中允许 fzfWorker.js by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5049
* chore(release):v0.18.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5050
* feat(daemon):将直接会话 shell 置于显式可选配置之后 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5031
* fix(telemetry):传播 daemon ACP 跟踪上下文 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5047
* feat(core):将超大的工具结果持久化到磁盘 (#4095 第 4 阶段) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5042
* fix(docs):更新 Coding Plan 模型列表,并修复开发者文档中的过期引用 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5054
* feat(core,cli):将后台子代理权限提示冒泡至父会话 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4955
* feat(core):使 grep 结果满足前置读取检查 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5043
* chore: 同步 package-lock.json 与 packages/cli ws 依赖 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5023
* feat(skills):支持用户可调用的 frontmatter by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/5037
* fix(daemon):清理日志并类型化 MCP 重启 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5006
* fix(memory):避免使用过期的工具模式进行回忆 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5058
* fix(core):消除因 debugResponses 累积导致的内存溢出 (OOM) by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4982
* feat(serve):通过 MCP 传递 A2UI 表面 — 桥接提取与操作端点 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4961
* fix: 默认启用 fork 子代理 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4963
* refactor(web-shell):移除重复的代理面板,封装 SubAgent 视图 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5059
* feat(mcp):项目 .mcp.json + 工作区审批门控及对齐的作用域优先级 (#4615) by @qqqys in https://github.com/QwenLM/qwen-code/pull/4713
* fix(core):保留后台代理启动标志 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5061
* feat(web-shell):daemon web-shell 改进 — 令牌使用、设置、重试、流式指标、隐藏命令 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5066
* feat(web-shell):重构浮动待办面板交互 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5069
* fix(web-shell): 改进斜杠命令面板的层级结构 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5078
* feat(web-shell): 悬停时显示消息时间 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5079
* fix(serve): 重新添加提示词队列背压机制 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5033
* feat(core): 持久化定时任务 — 重启后仍存活的 /loop 任务 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5004
* fix(cli): 门控失败时显示完整计划 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5077
* feat(web-shell): 在并行代理框和子代理工具中显示时间 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5084
* feat(sdk,serve): DaemonTransport 抽象 + ACP 标准合规 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5040
* fix(cli): 流结束后提交快速工具结果 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5071
* feat(core): 工作流 P3 — agent({schema, agentType, model, isolation:'worktree'}) (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5034
* fix(cli): 在焦点导航中忽略过期的实时代理 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5070
* fix(cli): 取消后丢弃工具调用 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5020
* fix(core): 持久化文件历史记录快照更新 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5057
* test(cli): 覆盖回退选择和确认流程 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5044
* fix(cli): 为 SSH 环境添加 OSC 52 剪贴板回退 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4929
* fix(webui): 延迟 DaemonClient 销毁以兼容 React StrictMode by @wenshao in https://github.com/QwenLM/qwen-code/pull/5091
* feat(core): 将 Computer Use 迁移至 cua-driver(跨平台) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5051
* feat(web-shell): 显示完整工具详情并自动折叠已完成的工具 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5088
* fix(cli,core): 强化 OOM 预防 — 幂等压缩测试、显式 GC、调试日志默认值 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4914
* fix(cli): 换行长状态行 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5093
* fix(acp): 添加内部 Kind.Agent,保持 ACP 传输线在 'other' 上(无回归) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5085
* feat(web-shell): 使输入快捷键可发现且可点击 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5096
* fix(ci): 当 PR 审查作业中途中止时使审查作业失败 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5053
* feat(cli,web-shell): 在守护进程转录事件中持久化目标状态 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5098
* fix(core): 默认将 GLM-5.2+ 和 GLM-6.x 及更高版本设为 1M 上下文 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5103
* refactor(core): 统一重试延迟策略 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3827
* feat(acp): 通过 _meta.toolName 提供专用代理权限对话框(#5085 的后续) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5105
* fix(daemon): 避免重播截断的会话差异 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5108
* feat(cli): 导入 Claude MCP 服务器 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5095
* fix(core): 修复重复的工具调用 ID by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5107
* feat(cli): 改进 /copy 命令的 argumentHint 和描述 by @huww98 in https://github.com/QwenLM/qwen-code/pull/5110
* feat(web-shell): 可折叠的 TodoWrite 历史记录及状态差异 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5109
* test: 稳定简单的 MCP 集成检查 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5072
* fix(core): 硬停止重复的相同工具调用 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5036
* fix(core): 在代理轮次间保持 token 升级预热 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5062
* fix(core): 限制硬救援压缩重试次数 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4526
* fix(core): 限制前台 shell 输出捕获 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4524
* fix(core): 在缺少使用元数据时进行压缩 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4528
* docs: 刷新守护进程开发者文档 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4412
* fix(core): 忽略没有活跃团队的代理名称 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5115
* fix(core): 在提示词估算中包含响应 token by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4525
* fix(dual-output): 防止启动时因无读取器连接导致 FIFO 阻塞 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4894
* ci: 为陈旧 bug 问题添加计划自动修复工作流 by @qqqys in https://github.com/QwenLM/qwen-code/pull/4989
* fix(core): 对确定性工具调用循环遵守 skipLoopDetection by @wenshao in https://github.com/QwenLM/qwen-code/pull/5128
* docs: 重写 CLAUDE.md 以指向 AGENTS.md 作为权威来源 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5138
* feat(computer-use): 可配置的截图最大尺寸(设置 + 环境变量) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5122
* fix(core): 限制活跃工具结果历史记录 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5111
* fix(desktop): 将桌面端更新源与 CLI 发行版隔离 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5139
* feat(web-shell): 在已完成的待办事项上显示每项任务的 token 和时间详情 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5118
* fix(web-shell): 移除冗余的 sanitizeSvg,修复 mermaid 渲染失败 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5123
* fix: 修复发布集成环境控制 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5121
* feat(web-shell): 将已完成的对话轮次折叠为提示词 + 最终答案 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5125
* fix(core): 当历史记录中无用户消息时跳过自动生成标题 by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5120
* feat(desktop): 在工作目录徽标中显示 git 分支 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5082
* feat(triage): 将 minimal-change 设为显式的 PR 审查检查项 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5146
* fix(release): 在独立发行版白名单中允许 cli-entry.js by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5153
* fix: 对过大的上下文指令发出警告 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5073
* docs: 修复过时的默认值、CLI 语法及工具命名偏差 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5158
* chore(release): 桌面版 desktop-v0.0.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5127
* chore(release): v0.18.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5164
* feat(web-shell): 支持自定义页脚渲染器 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5166
* fix(core): 将编辑工具描述简化为仅路径 by @huww98 in https://github.com/QwenLM/qwen-code/pull/5140
* fix(monitor): 批量处理通知以减少 token 浪费 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5165
* feat(web-shell): 添加用于外部文本、标签和提交控制的命令式 composer API by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5161
* feat(web-shell): 在折叠处提示词下方显示单轮耗时与 token 数 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5163
* docs(daemon): 刷新英文 daemon 文档 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5144
* fix(core): 在 MCP 工具的 SchemaValidator 中将数字字符串参数强制转换 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4967
* fix(channels): 在 SessionRouter 中将发送者 ID 作为完整段进行匹配 by @Osamaali313 in https://github.com/QwenLM/qwen-code/pull/5116
* docs(design): DaemonTransport 抽象 — SDK 的可插拔传输层 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5026
* ci: 以 qwen-code-ci-bot 身份发布 autofix PR by @qqqys in https://github.com/QwenLM/qwen-code/pull/5137
* fix(agent): 使分叉操作显式化;保持省略的 subagent_type 可等待 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5155
* fix(core): 在首个数据块前自动重试传输流错误 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5171
* docs: 添加 Qwen Code Desktop 发布链接 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5152
* docs: 修复 MCP token 路径、daemon UI 事件计数,添加飞书通道 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5172
* docs(channels): 为飞书设置指南添加截图 by @joeytoday in https://github.com/QwenLM/qwen-code/pull/4983
* feat(cli): 添加 daemon 状态 API by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5174
* docs: 修复 README 中括号前缺失的空格 by @marko1olo in https://github.com/QwenLM/qwen-code/pull/4796
* fix: 绕过 Qwen PR 审查代理、清理过期 worktree 及修复页脚换行 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5168
* feat(core+cli): 工作流 P4 — meta + /workflows + phase-tree (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5094
* feat(daemon): 将 web-shell 的轮次中间消息投递至当前运行轮次 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5175
* feat(tui): 可折叠的思考块及持续时间计时器 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4598
* feat(web-shell): 暴露 transcript 事件变更 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5193
* 优化 web-shell 执行显示 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5190
* 修复已完成提示词生命周期的竞态条件 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5192
* fix(dingtalk): 重新打开代码块时不插入空行 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5204
* fix(cli): 隐藏未配置的已停用 OAuth 模型 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5167
* fix(permissions): 不将 /dev/tcp 和 /dev/udp 重定向建模为文件 I/O by @warmjademe in https://github.com/QwenLM/qwen-code/pull/5196
* fix(core): 强化 exit_plan_mode 描述以防止空 plan 参数 by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5188
* fix(desktop): 保持最新推送源仅包含稳定版 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5149
* fix(core): 在大端序文件中正确读取 SHORT 类型的 TIFF 尺寸 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5209
* fix(cli): 跳过对包含框线/CJK 内容且未标记的代码块进行 highlightAuto by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5198
* fix: 将自托管 LLM 的非字符串工具参数强制转换为字符串 by @launchswitch in https://github.com/QwenLM/qwen-code/pull/4793
* ci(autofix): 优先处理近期未修复的 bug 而非陈旧 bug by @qqqys in https://github.com/QwenLM/qwen-code/pull/5178
* fix(cli): 保留需 sudo 权限的 npm 安装方式,不迁移至独立版本 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5207
* Revert "fix(core): 当历史记录中无用户消息时跳过自动生成标题" by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5200
* fix(e2e): 将 daemon_status 加入服务功能基线;在 PR 上运行 E2E by @wenshao in https://github.com/QwenLM/qwen-code/pull/5211
* fix(web-shell): 本地化剩余的硬编码 UI 字符串 by @carffuca in https://github.com/QwenLM/qwen-code/pull/5189
* fix(acp): 在守护进程会话中加载扩展命令 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5216
* fix(web-shell): 简化折叠元数据显示 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5223
* fix(ci): 基于写入权限限制 PR 审查与分类 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5191
* ci: 在合并队列中运行 CLI 集成测试 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5224
* ci(autofix): 将问题修复与审查响应统一为单一生命周期工作流 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5233
* feat(cli): 新增支持 --json 和 --limit 参数的 sessions list 命令 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5187
* ci(e2e): 停止在每次 PR 推送时运行 E2E 矩阵测试 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5238
* chore(release): v0.18.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5243
* fix(cli): 在取消 ask_user_question 后停止执行 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5218
* fix(cli): 将斜杠建议描述渲染为单行截断显示 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5236
* ci(release): 在发布 PR 上报告必需的 Test 检查并自动批准 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5250
* fix(core): 始终声明 exit_plan_mode 以便计划模式可调用它 (#5210) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5251
* chore(release): v0.18.3 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5255
* fix(core): 在文件历史记录中跟踪受支持的 sed 编辑 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5141
* fix(vscode-ide-companion): 为每个 IDE 会话创建独立的 McpServer by @huww98 in https://github.com/QwenLM/qwen-code/pull/5264
* fix(core): 将 BMP 高度作为有符号 int32 读取以支持自上而下的位图 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5227
* docs: 新增包含 qwen sessions list 的 CLI 子命令章节 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5254
* feat(serve): 使 ACP 权限超时时间可配置 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5260
* fix(cli): 保留对话中途的图片消息 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5183
* docs: 修复 SSE 环形缓冲区大小错误并新增 /workflows 命令 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5205
* fix(core): 通过内容检测 dat 文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5256
* fix(model): 当多个提供商共享同一模型 ID 时记住已选提供商 (#5173) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5179
* docs: 重构 README 以提升清晰度与重点 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5257
* feat(i18n): 本地化 TUI 和 web-shell 徽章中的工具显示名称 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5220
* fix(daemon): 集中化对话中途事件常量 + 恢复超时的 drains by @wenshao in https://github.com/QwenLM/qwen-code/pull/5266
* fix(core): 保持 DeepSeek 预设仅支持文本 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5268
* fix(cli): 移除可能导致 React #185 异常的 AgentView 清理 setState (#5199) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5286
* fix(core): 从正确的字节偏移量读取 WebP VP8X 画布高度 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5194
* fix(cli): 在补全中支持 Ctrl+P/N by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5259
* feat(serve): 在 GET /health?deep=true 中添加守护进程空闲检测 by @jifeng in https://github.com/QwenLM/qwen-code/pull/4934
* fix(core): 确保遥测文件导出器永远不会导致进程崩溃 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5246
* fix(cli): 修正上下文文件名设置 Schema by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5269
* feat(hooks): 将原始 API 调用 ID (toolCallId) 传递给钩子系统 by @shiloong in https://github.com/QwenLM/qwen-code/pull/4918
* fix(core): 逐轮工具调用熔断器 — 始终开启的限额 + 可选循环启发式 (#5234) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5279
* fix(desktop): 处理 git 分支徽章的边界情况 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5247
* feat(core,cli): 工作流工具令牌预算 + 每次运行的 UI 展示 (P5) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5231
* feat(extensions): 为扩展的 displayName 和 description 添加 i18n 支持 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5289
* feat(loop): 将仅提示的 /loop 连接到自定节奏唤醒 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5197
* fix(cli): 修正沙箱设置 Schema by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5272
* test(cli): 启用加载配置模型选择的测试覆盖率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5274
* docs(cli): 记录 tmux 滚动问题的变通方案 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5248
* test(cli): 覆盖选择列表向上滚动测试 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5276
* fix(weixin): 显示允许的图像目录 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5296
* fix(cli): 拒绝格式错误的 OSC rgb 颜色 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5307
* test(cli): 启用表格前景色重置测试覆盖率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5278
* test(core): 启用无头代理终止测试覆盖率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5282
* fix(web-shell): 摘要 grep_search 结果 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5294
* fix(core): 读取短格式 VP8L WebP 尺寸 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5292
* fix(core): 跟踪附加的 stdout 文件描述符重定向 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5317
* fix(dingtalk): 拆分过长的 Markdown 行 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5299
* fix(cli): 保留多行 Shell 历史记录 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5335
* fix(cli): 验证 GitHub 远程主机 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5327
* test(cli): 启用命令搜索长建议覆盖率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5283
* fix(core): 保留已迁移的命令描述字符串 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5321
* fix(cli): 强制执行 stdin 字节限制 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5331
* fix(core): 在转换波浪号路径时尊重主目录路径边界 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5333
* fix(cli): 按显示宽度截断会话选择器文本 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5338
* fix(core): 支持 GIF 图像令牌元数据 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5340
* fix(cli): 处理会话搜索的字符簇(graphemes) by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5342
* fix(cli): 规范化英文输出语言 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5346
* fix(core): 解析 OAuth 资源元数据参数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5344
* fix(core): 处理过期的 worktree 会话标记 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5229
* feat(loop): 添加秒级精度的会话唤醒引擎 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5182
* fix(core): 忽略重复的提供商工具调用 ID by @YingchaoX in https://github.com/QwenLM/qwen-code/pull/5038
* fix(cli): 在完整转录模式下显示思考过程 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5354
* feat(desktop): 在 brand-create 中编译 macOS 26+ Liquid Glass Assets.car by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5284
* fix(cli): 返回全新的空 MCP JSON 结果 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5349
* fix(weixin): 规范化 Markdown 图像语法 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5297
* fix(core): 在无头 SSH 中跳过睡眠抑制器 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5295
* fix(cli): 拒绝格式错误的终端序列 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5305
* fix(cli): 展开 Windows 风格的波浪号路径 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5298
* fix(core): 验证 OAuth expires_in 值 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5356
* fix(core): 拒绝格式错误的 cron 数值字段 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5352
* fix(cli): 解析沙箱镜像注册表端口 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5325
* fix(cli): 保留空的 MCP 提示参数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5323
* fix(core): 拒绝无效的 cron 任务条目 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5309
* fix(cli): 避免代理组合器卸载重置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5302
* fix(cli): 验证通道服务的 PID 文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5300
* fix(core): 保留无效的模式长度字符串 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5312
* fix(weixin): 确认 WEBP 签名,而不仅仅是 RIFF 前缀 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5285
* feat(channel): 添加 QQ 机器人(QQ Bot)通道适配器 by @Eric-GoodBoy-Tech in https://github.com/QwenLM/qwen-code/pull/5202
* fix(cli): 拒绝格式错误的 ACP 超时字符串 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5315
* fix(cli): 通过文件 URL 导入扩展通道 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5301
* fix(cli): 限制流式思考渲染缓冲区 by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/5314
* feat(core): 进入计划模式时自动显示 exit_plan_mode 工具 by @aspnmy in https://github.com/QwenLM/qwen-code/pull/5311
* fix(cli): 窗口标题显示会话名称而非模型活动状态 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5288
* fix(core): 保持 qwen3.6-flash 和 kimi-k2.6 预设仅为文本 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5328
* feat(skills): 添加用于创建像素艺术伙伴的 desktop-pet 技能 by @xxlaura in https://github.com/QwenLM/qwen-code/pull/4808
* fix(cli): 将四舍五入为 60 秒的不足一分钟时长渲染为 "1m" by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5287
* fix: 展开 Windows ~\\ 主目录路径并隐藏桌面会话列表中的幽灵(会话)条目 by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/5253
* feat(stats): 暴露令牌使用情况以实现成本可见性 by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4564
* fix(plan-gate): 将门控代理的 AbortSignal 从父信号链中隔离 by @CubeLander in https://github.com/QwenLM/qwen-code/pull/5185
* fix(core): 在侧边查询中遵循输出语言设置 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4519
* fix(cli): 避免过期的 Git 分支监听器设置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5271
* fix(desktop): 在 RIFF 魔术字节嗅探中检测 WebP 和 AVI by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5336
* fix(input): 恢复在 #4779 中回退的 IME 光标定位 by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4993
* fix(cli): 在按 Enter 接受时关闭 @path 补全下拉菜单 by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/4841
* fix(core): 当钥匙串不可用时,扩展密钥回退到加密文件存储 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5221
* fix(core): 支持会话元数据字段中的空白字符 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5353
* fix(core): 在 /quit 期间防止自动内存提取时发生 OOM(内存溢出) (#5147) by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5181
* refactor(tools): 将 TodoWrite 工具的显示名称重命名为 TodoList by @wenshao in https://github.com/QwenLM/qwen-code/pull/5319
* fix(core): 在缓冲区边界处使令牌过期 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5360
* fix(cli): 在修改前验证恢复检查点 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5358
* fix(core): 在运行时遵循 ripgrep 内置设置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5362
* fix(core): 在首次保存时创建令牌文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5367
* fix(cli): 为扩展程序保留工作区信任状态 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5369
* fix(cli): 在权限被取消后停止 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5258
* fix(core): 在检查搜索权限前解析波浪号路径 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5378
* fix(cli): 遵守沙箱路径边界 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5375
* fix(cli): 更新 acp 取消测试标志 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5384
* fix(core): 在 MCP 工具出错时避免重新连接 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5382
* fix(core): 接受大写 Web 获取协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5391
* fix(cli): 在 mcp 环境变量值中保留等号 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5377
* feat(cli): 在输入占位符中显示后续建议 by @MikeWang0316tw in https://github.com/QwenLM/qwen-code/pull/5145
* fix(core): 避免复用 glob 前缀缓存 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5364
* fix(core): 验证 grep 结果限制 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5389
* fix(core): 解析包含冒号路径的 grep 结果 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5372
* feat(config): 通过 chokidar 监听器添加设置文件更改检测… by @water-in-stone in https://github.com/QwenLM/qwen-code/pull/4933
* fix(acp): 清理子进程的环境变量 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5395
* fix(core): 向 systemd-inhibit 传递 --no-ask-password 以防止 TUI 损坏 by @OrbitZore in https://github.com/QwenLM/qwen-code/pull/5318
* fix(cli): 解析带有 Windows 驱动器的沙箱挂载 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5388
* fix(core): 将 GLM-5.2 添加到 Z.AI 预设 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5397
* fix(openai): 添加字符串工具结果兼容模式 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5399
* fix(cli): 明确累计状态栏令牌标签 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5400
* feat(cli): 显示可选响应令牌速率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5401
* fix(cli): 减少保留的交互式工具输出内存 by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4971
* fix(cli): 根据阶段令牌差值计算响应速率 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5402
* fix(cli): 明确不可用模型配置提示 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5403
* feat(cli): 通过 `qwen serve` 提供 Web Shell UI by @wenshao in https://github.com/QwenLM/qwen-code/pull/5392
* fix(cli): 将 cron 调度器启动绑定至配置初始化 (#5022) by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5230
* fix(core): 保持预估令牌拆分总和等于总量 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5420
* fix(core): 共享内存文件名配置状态 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5419
* fix(channel): 限定 qqbot 会话备份路径范围 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5417
* fix(channel): 跟踪 qqbot 关闭重连计时器 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5416
* fix(auth): 在安装时保留自定义提供商模型 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5404
* fix(core): 处理微压缩缓存解除逻辑 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5407
* fix(channel): 保持 qqbot 令牌刷新重试 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5414
* fix(cli): 保持按键处理程序为最新 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5421
* refactor(serve): 将会话标题/displayName 统一为单个 displayName 字段 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5002
* feat(cli): 在恢复时添加持久化历史折叠功能,并优化命令 by @Gove2004 in https://github.com/QwenLM/qwen-code/pull/4085
* fix(cli): 缩小设置枚举模式范围 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5418
* fix(channel): 限制 qqbot 网关重连重试次数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5415
* fix(core): 阻止全局 Shell 自毁命令 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5409
* fix(cli): 保存时保留 trustedFolders 注释 by @Zoean-z in https://github.com/QwenLM/qwen-code/pull/4746
* fix(hooks): 移除废弃的 updatedMCPToolOutput 字段 (#5422) by @ken-jo in https://github.com/QwenLM/qwen-code/pull/5423
* feat(web-shell): 添加扩展管理功能 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5398
* fix(cli): 在 mcp 添加传输检测中接受大写 URL 协议 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5426
* fix(extensions): 解析安装源时接受大写 URL 协议 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5429
* fix(core): 当计划门不可用时提供逃生路径 by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5430
* feat(extensions): 交互式多标签页 /extensions 管理器(已安装 / 发现 / 来源) by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4850
* fix(cli): 稳定扩展列表间距 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5445
* fix(weixin): 处理大写 CDN 上传协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5439
* fix(core): 计划模式提示需显式启用 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5433
* test(core): 移除重复的 gitdiff 未跟踪文件计数用例 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5468
* fix(core): 正确评估以点号前缀命名的忽略文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5458
* fix(core): 强制 Shell 目录工作区边界 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5454
* fix(core): 验证 LSP 套接字端口 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5493
* fix(core): 严格解析最大输出 Token 环境变量 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5491
* fix(core): 通过主机名检测提供商 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5450
* fix(cli): 验证 ACP 全局匹配最大结果数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5480
* fix(core): 允许以点号前缀的计划目录 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5460
* fix(extensions): 使用 HTTP 客户端获取 HTTP 市场 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5452
* fix(cli): 严格解析 FORCE_HYPERLINK by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5489
* fix(core): 严格解析工具并发环境变量 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5496
* fix(cli): 强制自定义主题主目录边界 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5456
* fix(dingtalk): 跳过大写的 Webhook 反应目标 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5466
* fix(desktop): 接受大写的图标 URL 协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5470
* fix(cli): 拒绝不完整的会话大小值 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5475
* fix(telegram): 断开连接时清除打字状态间隔 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5477
* fix(cli): 尊重安装路径边界限制 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5441
* fix: 接受大写的端点 URL 协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5443
* fix(core): 拒绝计算机使用分数整数字符串 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5500
* fix(core): 匹配提供商基础 URL 的斜杠变体 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5448
* fix(cli): 为 @file 强制临时路径边界 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5446
* fix(desktop): 保留大写 favicon URL by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5463
* fix(desktop): 严格解析 NO_PROXY 端口 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5498
* fix(serve): 验证会话清理器超时设置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5484
* fix(extensions): 处理大写的 npm 注册表协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5437
* fix(core): 补充缺失的 Token Plan 模型 (qwen3.7-plus, glm-5.2, kimi-k2.7-code) by @huww98 in https://github.com/QwenLM/qwen-code/pull/5505
* fix(cli): 接入 ACP 模型可调用命令 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5504
* fix(cli): 拒绝不完整的 CPU 分析持续时间 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5486
* test(desktop): 更新被阻止协议的打开 URL 断言 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5529
* fix(desktop): 恢复区域设置一致性 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5537
* fix(extension): 在 Claude 插件源中接受大写 URL 协议 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5461
* fix(desktop): 严格解析服务器端口 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5509
* fix(desktop): 验证通用 OAuth 令牌响应 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5511
* fix(core): 不将空 parts 消息视为函数调用/响应 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5494
* fix(desktop): 允许包文件名中包含双点号 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5515
* feat(core): 新增 Requesty 提供商 by @Thibaultjaigu in https://github.com/QwenLM/qwen-code/pull/5478
* fix(cli): 处理截断的远程输入文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5473
* test(core): 等待 cron 锁探测接管 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5535
* perf(core): 直接从 .git 读取当前 git 分支,避免派生 git 进程 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5432
* fix(vscode): 保持 UNC 路径为绝对路径 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5542
* chore(release): v0.18.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5464
* feat(ci): 为 PR 提供按需 tmux 真实用户测试 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5203
* test(desktop): 对齐拦截器打包契约 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5531
* fix(desktop): 保持同级路径为绝对路径 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5517
* test(desktop): 在权限测试中启用反馈标志 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5533
* fix(cli): 允许 Web Shell sendFile 使用点文件路径 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5541
* fix(cli): 允许更新归档文件中包含双点号 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5521
* fix(desktop): 分隔转换数据输出行 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5525
* fix(desktop): 处理 Windows 文件引用 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5523
* ci(release): 从 release 分支推送触发 CI by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5543
* 修复(desktop):统一路径边界检查 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5545
* 修复(desktop):拒绝小数传输大小 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5527
* 文档(triage):新增“新代码前复用”审查检查 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5547
* 修复(cli):验证 ACP 文件读取窗口 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5482
* 修复(extensions):接受大写的市场来源协议 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5435
* 使用 VS Code 主题令牌设置伴侣滚动条样式 by @interconnectedMe in https://github.com/QwenLM/qwen-code/pull/5488
* 功能(mcp):支持 MCP 资源并可靠地展示提示词 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5544
* 维护(release):v0.18.5 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5558
* CI(release):稳定版发布后自动发布 VSCode 伴侣版本 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5572
* 修复(cli):渲染完整的恢复预览历史 by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/5565
* 修复(cli):在换行输入时填充内容区域背景 by @lcheng321 in https://github.com/QwenLM/qwen-code/pull/5568
* 修复(cli):检测到循环时终止非交互运行 by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/5564
* 修复(core):尊重零 OpenAI 日志文件限制 by @russeell in https://github.com/QwenLM/qwen-code/pull/5569
* 修复(core):在当前认证下保留裸快速模型 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5553
* 功能(lint):使用 ESLint 强制 kebab-case 文件名 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4797
* [codex] 修复 kebab-case 审查的旧版文件名白名单 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5578
* 重构(cli):将 serve 文件重命名为 kebab-case 格式 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5592
* 功能(extensions):支持归档安装源 by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4909
* 修复(cli):在斜杠补全排名中优先使用命令名而非别名 by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5577
* 测试(integration):为无 AK 守护进程测试添加模拟 OpenAI 服务器 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5560
* 重构(core):在预设中使用 customHeaders 替换 OpenRouter/Requesty 提供商类 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5539
* 功能(voice):支持原生捕获、流式传输和偏置的语音听写 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5502
* 功能:可恢复的后台子代理及子代理转录 TTL by @qqqys in https://github.com/QwenLM/qwen-code/pull/5556
* 功能(core):新增 Artifact 工具以发布交互式 HTML 页面 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5557
* 功能(cli):在每次助手回复前添加可选的 [HH:MM:SS] 时间戳 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5001
* 修复(core):用户手动进入计划模式时要求确认 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5595
* 修复(core):连续相同工具调用始终开启防护 (#5019) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5573
* 修复(ci):强化 tmux 审查报告 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5548
* 修复(voice):暴露原生录音回退机制,避免缺少预编译时静默失败 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5605
* 修复(core):防止 DashScope 上的 GLM 丢弃 web_fetch 内容 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5599
* 修复:停止错误后重试原生语音录音 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5609
* [codex] CI(triage):确认斜杠审查请求 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5594
* [codex] 支持 Artifact 自动打开设置 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5617
* 功能(tui):移除工具组边框并折叠已完成的工具结果 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5003
* 功能(workflows):完成动态工作流移植——恢复、已保存工作流、关键词触发、通知 (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5600
* 功能(web-shell):支持守护进程会话分支 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5613
* 修复(core):后端感知的 Artifact 发布确认及取消处理 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5615
* 测试(integration):在 PR 上运行无 AK 冒烟测试 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5607
* 修复(cli):挂起的重放工具调用失败 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5624
* 修复(voice):将原生音频插件打包到独立归档中 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5628
* CI:将仓库内 PR 的 Linux 测试路由到自托管运行器 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5620
* CI(release):将发布失败排队以进行自动修复 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5551
* 功能(cli):在 /mcp 对话框中浏览 MCP 服务器资源 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5635
* 重构(cli):完成 serve 的 kebab-case 文件名处理 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5604
* 功能(core):DashScope 提供商默认开启 preserve_thinking by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5637
* CI(audio-capture):在 arm64 上交叉编译 darwin-x64 预编译文件,移除 macos-13 运行器 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5643
* CI:强化自托管运行器路由(#5620 审查跟进) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5644
* 修复(cli):强化 ACP 会话列表分页参数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5618
* docs(mcp): 修正 MCP 添加作用域的默认值 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5593
* feat(tui): 新增思考块查看器,支持通过 Alt+T 展开/折叠 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5627
* fix(cli): 严格解析 serve 速率限制环境变量 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5612
* fix(core): 严格解析 API 超时环境变量 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5602
* fix(serve): 校验 readText 行数限制 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5639
* fix(core): 转义 emacs ediff 路径中的反斜杠和引号 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5630
* fix(cli): 当通过 QWEN_MODEL 设置模型时,检测 USE_OPENAI 认证 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5647
* test(integration): 在容器沙箱环境下跳过 qwen serve 流式测试套件 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5655
* refactor(core): 提取 Protocol 枚举并解耦模型标识与认证类型 by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/5089
* fix(webui): 修复用户主动删除会话时自动重新创建的问题 by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5633
* fix(cli): 保持设置 v5 迁移的幂等性 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5676
* fix(test): 在 ACP set_config_option 测试中恢复 openai 模型选择 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5721
* fix(test): 通过 QWEN_HOME 隔离 ACP 集成代理以解决并行设置竞争条件 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5724
* fix(test): 使 ACP set_config_option 测试使用确定的 openai 提供商模型 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5728
* fix(core): 在默认的 getAllConfiguredModels 列表中保留活动运行时模型 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5729
* feat(desktop): 在可调整大小的侧边面板中显示文件预览,而非全屏 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5730
* fix(core): 移除导致统计数据重复计数的冗余 reportSuggestionUsage by @huww98 in https://github.com/QwenLM/qwen-code/pull/5684
* fix(core): 校验 ask_user_question 答案索引 by @russeell in https://github.com/QwenLM/qwen-code/pull/5622
* feat(core): 支持可配置的代理忽略文件 by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4653
* fix(daemon): 刷新工作区提供商默认值 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5638
* feat(core): 新增 fastOnly/voiceOnly 标志以在主模型列表中隐藏特定模型 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5632
* feat(cli): 按名称匹配 MCP 资源补全并发现服务器 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5733
* chore(release): v0.19.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5739
* fix(cli): 跳过不可用的 A2UI 配置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5685
* fix(cli): 避免 ACP 写入重复的 BOM by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5688
* fix(cli): 在 ACP 模式下启用 /lsp by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5689
* fix(core): 要求内联媒体字节限制为整数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5671
* fix(cli): 拒绝无效的会话列表游标 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5709
* fix(cli): 拒绝不支持的扩展作用域 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5714
* fix(core): 拒绝空白的 cron 提示词 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5716
* fix(cli): 校验渠道凭证类型 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5718
* fix(cli): 使用高对比度软件光标 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5720
* fix(core): 要求压缩计数为整数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5646
* fix(core): 严格解析代理与工作流的整数环境变量 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5679
* fix(serve): 校验 list maxEntries 为正整数 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5719
* fix(workflows): 在递归修剪删除前校验 runId(防止路径遍历目录清空) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5740
* fix(triage): 绝不自动批准跨仓库重构 PR by @wenshao in https://github.com/QwenLM/qwen-code/pull/5744
* fix(cli): 仅当主题背景与终端匹配时才绘制背景 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5746
* revert(core): 回退 Protocol 枚举与模型标识解耦 (#5089) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5745
* ci: 重试 merge-ref 检出以修复瞬态“not our ref”失败 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5732
* chore(release): v0.19.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5762
* feat(serve): 新增远程 LSP 状态路由 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5741
* fix(agent): 限制 fork 轮次并透传 fork 权限提示 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5737
* feat(vision-bridge): 为纯文本模型将图像转录为文本 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5126
* feat(core): 在自动模式下为破坏性命令添加确定性防护 by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/5754
* feat(cli): 新增扩展操作轮询 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5753
* fix(vscode): 始终在 Activity Bar 侧边栏中显示聊天视图 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5757
* fix(cli): 从每次会话的聊天中获取 /context 令牌总数 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5764
* fix(core): 消除重复的模型显示名称 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5769
* fix(cli): 移除输入框和用户消息中的主题背景填充 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5772
* feat(cli): 在纯 @ 符号处全局匹配 MCP 资源并显示完整引用 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5774
* ci: 将 PR 检查合并至 Ubuntu 关卡 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5767
* refactor(web-shell): 重构聊天 UI by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5775
* fix(cli): 稳定 VP 鼠标交互 by @ZevGit in https://github.com/QwenLM/qwen-code/pull/5751
* docs: 修复配置/命令/认证漂移问题并展示 model-providers 页面 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5735
* fix(vscode): 限制打开文件的位置 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5711
* fix(config): 回退至用户环境变量文件 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5731
* fix(core): 要求停止钩子容量为整数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5667
* fix(core): 要求微压缩保留计数为整数 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5652
* fix(core): 对齐 MCP OAuth 指导说明与文档 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5589
* feat(cli): 添加工作区权限规则 API by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5743
* fix(cli): 将 emoji 思考/摘要图标替换为 Unicode 文本符号 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5788
* fix(cli): 重新进入认证向导时恢复已保存的自定义模型 ID by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5654
* fix(daemon): 拒绝过期的提示词客户端准入 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5784
* feat(serve): 通过守护进程为 Web Shell 实现语音听写 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5755
* fix(core): 严格将 QWEN_SERVE_MCP_CLIENT_BUDGET 解析为十进制整数 by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5752
* fix(sdk): 在 invalid_client_id 提示时自动修复过期的 clientId by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5797
* feat(voice): 在插入前使用快速模型优化 ASR 转录结果 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5794
* fix(cli): 将粘贴的图片路径提升为附件 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5803
* fix(sdk): 将浏览器守护进程包预算提升至 126 KiB by @wenshao in https://github.com/QwenLM/qwen-code/pull/5801
* ci: 提高 Linux CI 可靠性(浅层 ECS 检出 + CodeQL 超时设置) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5810
* fix(cli): 在导入和 .mcp.json 中正确映射 Claude MCP 服务器传输类型 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/5812
* perf(cli): 优化 serve 守护进程启动 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5785
* 暴露 MCP 资源读取工具 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5781
* ci: 将 macOS/Windows 测试和 CodeQL 移出单 PR 检查路径 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5813
* fix(core): 允许 web_fetch JSON 回退 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5660
* chore(release): v0.19.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5830
* ci: 将平台测试矩阵拆分为命名作业,以便 PR 进入合并队列 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5833
* fix(ide): 读取锁文件前验证 QWEN_CODE_IDE_SERVER_PORT by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/5805
* fix(core): 为 OpenAI 管道添加流式不活动超时 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5827
* fix(cli): 防止多智能体运行时非 VP 模式下滚动回弹和闪烁 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5799
* feat(serve): 添加守护进程工作区语音和控制 API by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5765
* feat(cli): 添加技能使用统计 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5826
* feat(memory): 持久化前确认自动生成的技能 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5616
* fix(cli): 用户中止时取消待处理的自循环唤醒 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5808
* fix(core): 合并助手轮次时保留 reasoning_content by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5815
* feat(cli): 在加载指示器中显示模型思考意图 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5668
* ci: 在合并队列流程中为每个 CI 作业分配唯一归属 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5842
* fix(web-shell): 稳定活动提示词加载状态 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5818
* Revert "feat(cli): 在加载指示器中显示模型思考意图" by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5846
* ci(release): 使发布流程兼容合并队列,并将发布 PR 排除在日志外 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5832
* ci: 添加 `@qwen-code /resolve` by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5779
* fix(cli): 停止重复的提供程序响应 by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5657
* test(cli): 添加守护进程启动基准测试 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5825
* docs: 添加 vertex-ai 认证、缺失命令及 qc-helper 索引条目 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5727
* feat(core): 将 /remember 与自动提取解耦,停止写入 QWEN.md by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5814
* fix(web-shell): 在轮次流式传输期间延迟追加本地命令的转录 by @carffuca in https://github.com/QwenLM/qwen-code/pull/5822
* feat(web-shell): 通过 Excel 风格交互增强助手 Markdown 表格 by @jifeng in https://github.com/QwenLM/qwen-code/pull/5650
* ci(triage): 在自托管 ECS 池上运行 Triage 任务,而非 GitHub 托管 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5851
* feat(cli): 默认对新用户启用内置状态栏预设 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5792
* feat(config): 通过 providerProtocol 将提供商 ID 映射到 SDK 协议 (#5758) by @qqqys in https://github.com/QwenLM/qwen-code/pull/5793
* feat(telemetry): 使敏感 span 属性限制可配置 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5804
* fix(packaging): 为镜像安装捆绑音频捕获功能 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5747
* feat(core): 新增 QWEN_STREAM_IDLE_TIMEOUT_MS 环境变量以控制流空闲超时 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5845
* feat(cli): 支持用户自定义关键词文件用于语音听写 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5817
* fix(core): 在 WebFetch 验证中拒绝 userinfo URL by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/5783
* ci: 将合并队列的 Linux 任务路由至 ECS by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5854
* feat(cli): 简化自动模式启动文本并移除表情符号 (#4584) by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5824
* feat(web-shell): 在思考摘要完成后显示耗时 by @wenshao in https://github.com/QwenLM/qwen-code/pull/5864
* test(cli): 将 i18n ToolMessage 测试超时时间提升至 15 秒,以解决合并队列测试不稳定问题 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5858
* ci: 将 CodeQL 和 E2E 测试从每次合并推送路径中移除 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5859
* ci(qwen-resolve): 在托管运行器上运行 /resolve 任务 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5862
* feat(tui): 按类型分区显示工具 — 折叠读取/搜索类,单独显示修改类工具 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5661
* fix(cli): 在 macOS Option-compose 终端中使 alt+t 展开思考 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5872
* feat(mcp): 设置更改时实时同步 MCP 服务器 by @water-in-stone in https://github.com/QwenLM/qwen-code/pull/5561
* ci(qwen-resolve): 支持 Fork PR 并将 /resolve 精简为仅处理冲突 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5870
* feat(serve): 通过 ID 查询单个会话状态 by @samuelhsin in https://github.com/QwenLM/qwen-code/pull/5857
* chore(cli): 移除冗余的主目录启动警告 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5839
* fix(cli): 在 macOS 上展开思考时显示 ⌥T 而非 alt+T by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5802
* feat(core): 使自定速度的 /loop 依赖 monitor/background-task 通知 by @qqqys in https://github.com/QwenLM/qwen-code/pull/5844
* fix(cli): 改进令牌速度计算 by @seekskyworld in https://github.com/QwenLM/qwen-code/pull/5811
* fix(core): 流式处理聊天压缩旁路查询以应对网关超时 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5865
* perf(cli): 为 `qwen serve` 跳过 spawnSync 包装器 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5874
* fix(web-shell): 重写中文工具组摘要(执行了 → 调用了) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5876
* feat(cli): 加强响应时间戳一致性及测试 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5850
* fix(release): 构建独立归档时跳过 dist/node_modules by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5878
* fix(test): 提升冷导入测试套件的超时时间,以解决 CI 不稳定问题 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5880
* ci: 隔离每次运行的代理状态用于分类和 PR 审查 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5885
* feat(core): 添加内置的扩展创建者技能 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5828
* feat(cli): 在输入自动补全中支持 @extension 提及 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5849
* refactor(cli): 拆分 serve 服务器路由 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5809
* feat(cua-driver): 内置 qwen-cua-driver 并支持可选启用的 0–1000 相对坐标 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5896
## 新增贡献者
* @kagura-agent 在 https://github.com/QwenLM/qwen-code/pull/4461 中首次贡献
* @he-yufeng 在 https://github.com/QwenLM/qwen-code/pull/4607 中首次贡献
* @zzhenyao 在 https://github.com/QwenLM/qwen-code/pull/4560 中首次贡献
* @Pepograminger 在 https://github.com/QwenLM/qwen-code/pull/4605 中首次贡献
* @InfiniteUselessness 在 https://github.com/QwenLM/qwen-code/pull/4485 中首次贡献
* @ZijianZhang989 在 https://github.com/QwenLM/qwen-code/pull/4701 中首次贡献
* @callmeYe 在 https://github.com/QwenLM/qwen-code/pull/4533 中首次贡献
* @CNCSMonster 在 https://github.com/QwenLM/qwen-code/pull/4647 中首次贡献
* @Pluviobyte 在 https://github.com/QwenLM/qwen-code/pull/4618 中首次贡献
* @Alex-ai-future 在 https://github.com/QwenLM/qwen-code/pull/4798 中首次贡献
* @Rakson0209 在 https://github.com/QwenLM/qwen-code/pull/4734 中首次贡献
* @han-dreamer 在 https://github.com/QwenLM/qwen-code/pull/4784 中首次贡献
* @BenGuanRan 在 https://github.com/QwenLM/qwen-code/pull/4779 中首次贡献
* @wsyjh8 在 https://github.com/QwenLM/qwen-code/pull/4911 中首次贡献
* @puneetdixit200 在 https://github.com/QwenLM/qwen-code/pull/4788 中首次贡献
* @Osamaali313 在 https://github.com/QwenLM/qwen-code/pull/5116 中首次贡献
* @marko1olo 在 https://github.com/QwenLM/qwen-code/pull/4796 中首次贡献
* @warmjademe 在 https://github.com/QwenLM/qwen-code/pull/5196 中首次贡献
* @launchswitch 在 https://github.com/QwenLM/qwen-code/pull/4793 中首次贡献
* @carffuca 在 https://github.com/QwenLM/qwen-code/pull/5189 中首次贡献
* @shiloong 在 https://github.com/QwenLM/qwen-code/pull/4918 中首次贡献
* @Eric-GoodBoy-Tech 在 https://github.com/QwenLM/qwen-code/pull/5202 中首次贡献
* @aspnmy 在 https://github.com/QwenLM/qwen-code/pull/5311 中首次贡献
* @xxlaura 在 https://github.com/QwenLM/qwen-code/pull/4808 中首次贡献
* @mvanhorn 在 https://github.com/QwenLM/qwen-code/pull/5253 中首次贡献
* @CubeLander 在 https://github.com/QwenLM/qwen-code/pull/5185 中首次贡献
* @water-in-stone 在 https://github.com/QwenLM/qwen-code/pull/4933 中首次贡献
* @OrbitZore 在 https://github.com/QwenLM/qwen-code/pull/5318 中首次贡献
* @Gove2004 在 https://github.com/QwenLM/qwen-code/pull/4085 中首次贡献
* @Zoean-z 在 https://github.com/QwenLM/qwen-code/pull/4746 中首次贡献
* @ken-jo 在 https://github.com/QwenLM/qwen-code/pull/5423 中首次贡献
* @Thibaultjaigu 在 https://github.com/QwenLM/qwen-code/pull/5478 中首次贡献
* @interconnectedMe 在 https://github.com/QwenLM/qwen-code/pull/5488 中首次贡献
* @lcheng321 在 https://github.com/QwenLM/qwen-code/pull/5568 中首次贡献
* @russeell 在 https://github.com/QwenLM/qwen-code/pull/5569 中首次贡献
* @VectorPeak 在 https://github.com/QwenLM/qwen-code/pull/5783 中首次贡献
* @samuelhsin 在 https://github.com/QwenLM/qwen-code/pull/5857 中首次贡献
* @seekskyworld 在 https://github.com/QwenLM/qwen-code/pull/5811 中首次贡献
**完整更新日志**: https://github.com/QwenLM/qwen-code/compare/sdk-typescript-v0.1.8-preview.1...cua-driver-rs-v0.6.8
cua-driver prebuilt binaries — relative-coordinate fork
(vendored under `packages/cua-driver`).
- **macOS**: codesigned + notarized universal binary + `QwenCuaDriver.app`
- **Linux**: unsigned (x86_64 + arm64, glibc 2.31 floor)
- **Windows**: unsigned (x86_64 + arm64)
Enable relative coordinates: `CUA_DRIVER_RS_COORDINATE_SPACE=1`
(default `0` = off; optional `CUA_DRIVER_RS_COORDINATE_SCALE=1000`).
<!-- Release notes generated using configuration in .github/release.yml at main -->
## What's Changed
* fix(cli): persist MCP server removals by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4535
* fix(models): refresh raw model-derived defaults by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4517
* fix(vscode-ide-companion): exclude workspace packages from NOTICES.txt generation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4455
* fix(telemetry): attach interaction span to session root context by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4499
* fix(cli): auto-prepend @ when pasting or dropping multiple file paths by @MikeWang0316tw in https://github.com/QwenLM/qwen-code/pull/4544
* feat(prompt): move new app prompt from system prompt to skills by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4567
* feat(worktree): Phase D — startup --worktree flag + symlinkDirectories + PR refs by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4381
* fix(permissions): make command substitution ask, not deny (#4093) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4386
* feat(cli): default auto-dream/auto-skill to on and add /memory toggle by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4547
* fix(cli): surface startup warnings on stderr before TUI render (#4448) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4461
* fix(telemetry): improve LogToSpan bridge error info and TUI handling by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4482
* feat(channels): add Feishu (Lark) channel adapter by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/4379
* feat(telemetry): foundation for skill-based RT optimization (P0+P1) by @gwinthis in https://github.com/QwenLM/qwen-code/pull/4565
* fix(cli): track model-sent slash command history by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3826
* feat(computer-use): zero-config built-in via open-computer-use MCP by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4590
* refactor(core)!: replace tail-preservation compaction with summary + restoration attachments by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4599
* Emit PermissionDenied hooks for AUTO classifier blocks by @qqqys in https://github.com/QwenLM/qwen-code/pull/4376
* chore(release): v0.16.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4571
* fix(core): use undici fetch for IDE proxy requests by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4607
* fix(core,cli): label screenshot-triggered compaction accurately in the auto-compact notice by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4623
* chore(release): v0.17.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4626
* fix(rewind): false "compressed turn" error when mid-turn messages exist by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4580
* fix(core): emit enable_thinking on DashScope when reasoning is disabled by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4505
* fix(core): surface Anthropic empty stream provider errors by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4540
* feat(core): add memory pressure monitor by @ZevGit in https://github.com/QwenLM/qwen-code/pull/4403
* fix(core): guard oversized resumed history sends by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4531
* fix(cli): stabilize statusline preset ordering by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4634
* fix(config): load home .env vars before settings ${VAR} resolution (#4466) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4474
* fix(acp): drop discontinued Qwen OAuth method by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4639
* fix(core): enforce adjacent tool results by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4622
* fix(cli): hide completed sticky todos by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4635
* feat(cli): Add settings JSON corrupted warning dialog by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4560
* fix(core): harden context error text collection by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4632
* fix(core): apply output language to side queries by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4636
* fix(cli): persist /memory toggle state across dialog reopen by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4650
* fix(docs): Hide internal docs from docs site by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4357
* fix(core): preserve uid in atomicWriteFile to avoid breaking shared-write files by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4431
* Improve hooks matcher display by @qqqys in https://github.com/QwenLM/qwen-code/pull/4545
* fix(cli): use session channel when closing ACP sessions by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4522
* fix(core,cli): replace full-history structuredClone with shallow/tail variants to prevent OOM on resume by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4644
* feat(cli): add respectUserColors and hideContextIndicator options for statusline by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4670
* fix(core): tolerate unsupported Streamable HTTP GET SSE by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4521
* fix(insight): Harden insight facet normalization and empty qualitative handling by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3557
* feat(cli): notify when background shells finish by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4355
* feat(core): add simplify bundled skill by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3570
* feat(skills): add agent reproduction workflows by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4118
* feat(cli): virtual viewport for long conversations on ink 7 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4146
* feat(cli): background housekeeping for stale file-history dirs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4414
* fix(core): loosen auto-mode classifier timeouts, disable stage-2 thinking by @qqqys in https://github.com/QwenLM/qwen-code/pull/4680
* fix(core): coerce hostile-provider usage token counts (#4350 part 1) by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4439
* feat(core): inject context env vars (session/agent/prompt ID) into shell subprocesses by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4649
* Add AUTO mode denial observability and caps by @qqqys in https://github.com/QwenLM/qwen-code/pull/4476
* feat(core): auto-dump memory diagnostics to disk on pressure detection by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4654
* feat(core): atomic write rollout for credentials, memory, config, JSONL (closes #3681, #4095 Phase 2) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4333
* docs: add /diff command and auto theme detection documentation by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4699
* feat(cli): Add searchable MiniMax-M3 model setup by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4668
* feat(core,cli): auto-compact follow-up — /compress instructions, PreCompact hook plumb, plan/subagent attachments by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4688
* fix(cli): honor list extensions flag by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4673
* feat(input): move physical cursor to visual cursor for IME input by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4652
* feat(core): add post tool batch hooks by @qqqys in https://github.com/QwenLM/qwen-code/pull/4454
* fix(ui): distinguish auto approval mode indicators by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4600
* fix(core): disable undici 300s bodyTimeout for no-proxy Node.js path by @Pepograminger in https://github.com/QwenLM/qwen-code/pull/4605
* feat(prompt): deduplicate tool guidance between system prompt and tool descriptions by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4569
* chore(deps): update @google/genai from 1.30.0 to 2.6.0 by @InfiniteUselessness in https://github.com/QwenLM/qwen-code/pull/4485
* feat(cli): add CPU profiling support for Chrome DevTools analysis by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4620
* feat(prompt): enhance system prompts with global reasoning discipline and iterative planning by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4436
* refactor(cli): rename "Default" approval mode to "Ask permissions" (#4625) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4674
* fix(cli): suppress completion menu for history-restored text until edited by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4558
* fix(cli): statusline not re-rendering when switching from preset to command type by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4706
* fix(cli): avoid exit-time history deep clones by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4717
* feat(subagent): add fork subagent feature gate and "Don't peek / Don't race" prompt discipline by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4574
* fix(telemetry): clear span dedup state after chat compression (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4660
* feat(core):strengthen system prompts for reading code before editing, dedicated tool priority, and step-by-step communication by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4375
* fix(core): remove proactive subagent system-reminder injection by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4587
* fix(cli): fix Space key not working in Arena model selection dialog by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4701
* feat(skills): add triage skill for issue/PR gatekeeping by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4577
* feat(computer-use): use @qwen-code/open-computer-use fork (signed + notarized) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4726
* chore(release): v0.17.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4742
* fix(cli): skip thought parts in copy output by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4738
* feat(installer): verify release assets + switch public docs to standalone entrypoint by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3855
* feat(ci): add @qwen /triage workflow for automated issue and PR triage by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4768
* fix(cli): Improve approval mode display text by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4753
* fix(ui): display model name instead of id in statusline and startup banner by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4741
* feat(cli): add standalone auto-update support by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4629
* fix(ci): fix triage prompt variable expansion, bot identity, and model secret by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4778
* feat(telemetry): Phase 4b — retry visibility for qwen-code.llm_request (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4432
* feat(core): add user prompt expansion hooks by @qqqys in https://github.com/QwenLM/qwen-code/pull/4377
* fix(computer-use): auto-approve install in auto-approve modes (YOLO/AUTO_EDIT/AUTO) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4756
* fix(cli): implement --list-extensions flag handler (#4450) by @kagura-agent in https://github.com/QwenLM/qwen-code/pull/4456
* feat(telemetry): Phase 3 — qwen-code.subagent span with concurrent isolation (#3731) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4410
* feat(skills): /skills picker dialog — browse, search, toggle, pick (#4532) by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4533
* fix(core): handle error variant in disabled skill command delegation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4804
* fix(cli): remove dead --list-extensions handler from #4456 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4800
* feat(cli): enable /remember, /forget, /dream in ACP mode by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4811
* ci(triage): Fix Qwen triage workflow prompt by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4787
* Revert "feat(cli): enable /remember, /forget, /dream in ACP mode" by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4818
* feat(vscode): surface ACP background notifications by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4358
* feat(cli): support /copy N to copy Nth-last AI message by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4761
* fix(core): recurse into submodule files when crawling git repos by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4596
* Harden auto mode self-modification checks by @qqqys in https://github.com/QwenLM/qwen-code/pull/4572
* fix(clipboard): use platform-native tools for image paste on Linux by @CNCSMonster in https://github.com/QwenLM/qwen-code/pull/4647
* fix(core): add multimodal support for qwen3.7-plus by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4803
* feat(cli): prevent system sleep while running by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4434
* feat(ci): add PR review workflow using bundled /review skill by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4549
* fix(core): scope boolean coercion to boolean-typed schema fields by @Pluviobyte in https://github.com/QwenLM/qwen-code/pull/4618
* fix(cli): bundle extension examples by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4719
* fix(cli): fix vim mode Esc leak, Enter submit, render lag and implement missing VIM commands by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4677
* fix(core): allow intentional foreground sleep for backoff by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4708
* fix(core): honor runtime output dir for auto memory by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4715
* feat(cli): add /fork background-agent command by @qqqys in https://github.com/QwenLM/qwen-code/pull/4780
* fix(tui): skip cross-group tool merge in <Static> mode to eliminate screen flash by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4795
* Move startup context into system reminders by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4053
* feat(core): honor skill allowedTools by auto-approving declared tools by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4704
* Add InstructionsLoaded hook for instruction file loading by @qqqys in https://github.com/QwenLM/qwen-code/pull/4665
* fix(cli): prevent selection dialog flicker by @ZevGit in https://github.com/QwenLM/qwen-code/pull/4755
* feat(skills): enforce auto-skill- directory prefix for auto-generated skills by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4839
* fix(core): inject current date on every user query to prevent stale date by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/4798
* Align automated PR review with bundled skill by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4843
* fix(ci): coordinate qwen triage and review automation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4570
* fix(core): add missing closing braces in formatDateForContext test block by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4863
* fix(core): prevent OOM by compacting API history, UI history, and triggering under memory pressure by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4824
* fix(core): don't kill a failed-spawn sleep inhibitor child (sandbox abort on tool use) by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4865
* fix(skills): add bundled skill doc-index validation to docs skills by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4851
* feat(memory): add user-level auto-memory at ~/.qwen/memories/ (#4747) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4764
* fix(sdk): correct npm package name in SDK install instructions by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4860
* test(integration): drop tight 30s timeout in sleep-interception e2e tests by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4878
* fix: strip runtime snapshot prefix before persisting model.name by @Rakson0209 in https://github.com/QwenLM/qwen-code/pull/4734
* test: cover rewind selector restore options by @han-dreamer in https://github.com/QwenLM/qwen-code/pull/4784
* fix(cli): handle background auto-update breaking cross-authType model switching by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4760
* fix(core): preserve shared baseUrl on auth refresh by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4828
* refactor(core): remove GitService, migrate /restore to FileHistoryService by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4871
* feat(acp): support desktop qwen integration by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4728
* feat(extension): add description field to ExtensionConfig by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4857
* fix(ci): acknowledge queued qwen review requests by @qqqys in https://github.com/QwenLM/qwen-code/pull/4847
* fix(core): fix qc-helper skill docs index and config categories by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4848
* feat(telemetry): inject TRACEPARENT env var into shell child processes by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4906
* fix(ci): normalize dev launcher path assertions on Windows by @wenshao in https://github.com/QwenLM/qwen-code/pull/4915
* fix(installer): correct broken (404) 'for more info' URL in post-install message by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4916
* fix(core): isolate OpenAI SDK abort listener leak with per-request child controllers by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4810
* feat(hooks): support terminal sequence notifications by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4895
* feat(core): Workflow tool P1 — minimal node:vm sandbox + sequential agent() (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4732
* fix(acp): prevent session/prompt hang when client ignores mid-turn drain requests by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4925
* fix(core): remove greeting-responder example from agent tool prompt by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4923
* feat(ci): add auto-generated CHANGELOG.md synced from releases (#4872) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4881
* feat(stats): add interactive /stats dashboard with cross-session tracking by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4779
* fix(core): remove `env` from read-only shell command allowlist by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4932
* fix(core): prevent cron scheduler from firing on creation minute by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4946
* fix(core): ensure hard threshold always exceeds auto threshold by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/4949
* fix(installer): auto-detect SYSTEM account and default PATH scope to machine by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4903
* fix(skills): use full YAML parser for frontmatter to support block scalars by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4870
* fix(core): give complete intentional-sleep guidance on first rejection for sleep chains by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4948
* fix(core): add qwen3.7-plus to Coding Plan model list by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4953
* ci: extend qwen PR review timeout to 90min and queue delay to 30min by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4962
* test: cover rewind selector fallback states by @han-dreamer in https://github.com/QwenLM/qwen-code/pull/4905
* feat(core): enable loop/cron tools by default by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4950
* test(integration): harden flaky sleep-interception e2e against skipped tool calls by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4936
* fix(openai): default splitToolMedia so tool-returned images reach strict OpenAI-compatible backends by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4917
* fix(cli): fix cursor left-move stalling at hard-wrapped line boundary by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4852
* feat(core): declarative agent frontmatter v1 — permissionMode bridge + maxTurns wiring + color allowlist (CC 2.1.168 parity) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4842
* fix(core): microcompact hook continuations by @qqqys in https://github.com/QwenLM/qwen-code/pull/4840
* feat: add Agent Team experimental feature for parallel sub-agent coordination by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4844
* Fix release workspace test failures by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4980
* fix(core): preserve teammate identity when resuming a tool call after approval by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4979
* refactor(skills): remove redundant commands and sync e2e-testing skill by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4992
* fix(installer): print shell reload hint when new qwen is not picked up by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4960
* feat(desktop): Add desktop app package with Qwen ACP SDK integration by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3778
* feat(daemon): merge daemon-mode feature batch into main by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4490
* feat(core): layered tool-output truncation, per-message budget, per-tool limits by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4880
* fix(auth): time out Qwen OAuth refresh by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4829
* fix(cli): route down-arrow straight to the live agent panel (#4907) by @wsyjh8 in https://github.com/QwenLM/qwen-code/pull/4911
* fix(core): harden experimental agent-team messaging by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4988
* feat(telemetry): add runtime memory/CPU sampling with OTel metric reporting by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/4868
* fix(cli): enable VP scroll at idle prompt and fix viewport height by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4959
* fix(core): parse comma-separated tools/disallowedTools in agent frontmatter by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4935
* perf(filesearch): move AsyncFzf index construction to a worker thread by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4621
* feat(cli): add /compress-fast command for no-LLM rule-based context compression by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4893
* fix(cli): make extensions new work when bundled examples are missing by @BZ-D in https://github.com/QwenLM/qwen-code/pull/5009
* feat(web-shell): add Option+Enter and Cmd+Enter newline shortcuts by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5005
* chore(daemon): remove dead code and simplify control flow by @qqqys in https://github.com/QwenLM/qwen-code/pull/4789
* fix(goal): persist iteration count across resume so MAX_GOAL_ITERATIONS bounds the whole session by @qqqys in https://github.com/QwenLM/qwen-code/pull/5000
* Add /cd command by @qqqys in https://github.com/QwenLM/qwen-code/pull/4890
* ci(desktop): mac code-signing + App Store Connect API-key notarization by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5013
* feat(core): persist file history snapshots for cross-session /rewind (T2.1) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4897
* fix(desktop): keep composer sendable after idle escape by @puneetdixit200 in https://github.com/QwenLM/qwen-code/pull/4788
* fix(cli): avoid headless browser open crashes by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4716
* fix(cli): debounce resize repaint and clear stale scrollback on settle by @wsyjh8 in https://github.com/QwenLM/qwen-code/pull/4919
* feat(core): port declarative-agent mcpServers + hooks (CC 2.1.168 parity follow-up) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4996
* feat(core): Workflow P2 — parallel() + pipeline() concurrent fan-out (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4947
* fix(core): add Tool Fallback rule to system prompt by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4931
* fix(docs): correct stale settings keys, wrong defaults, and missing commands by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/4969
* fix(core): stabilize truncated tool retry keys by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4970
* fix(core): stabilize prompt-cache prefix against MCP/skills churn by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4896
* fix(core): fix Windows startup error caused by missing printf command by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/5012
* feat(core): add enter_plan_mode tool and Plan Approval Gate by @callmeYe in https://github.com/QwenLM/qwen-code/pull/4853
* docs(desktop): use main for brand builder skill by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5021
* perf(desktop): add --cli-only flag to skip non-CLI packages during vendor build by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5025
* fix(desktop): allow unsigned Windows auto-updates by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5028
* fix(cli): join previous line when Ctrl+U pressed at column 0 by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5011
* fix(tui): Tighten message and tool spacing by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4595
* fix(core): serialize team task claims per agent and add mailbox lock parity by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4981
* fix(core): support .toml command files in extension command discovery by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5017
* test(i18n): raise timeout for slow must-translate locale suites on Windows CI by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5024
* fix(stats): dedup usage records by sessionId and skip in-progress writes by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4995
* fix(test): unbreak qwen serve integration suites after the daemon batch merge by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5041
* feat(acp): broadcast session title updates to daemon clients by @qqqys in https://github.com/QwenLM/qwen-code/pull/5035
* fix(release): allow fzfWorker.js in standalone dist allowlist by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5049
* chore(release): v0.18.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5050
* feat(daemon): gate direct session shell behind explicit opt-in by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5031
* fix(telemetry): Propagate daemon ACP trace context by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5047
* feat(core): persist oversized tool results to disk (#4095 Phase 4) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5042
* fix(docs): update Coding Plan model list and fix stale references in developer docs by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5054
* feat(core,cli): bubble background subagent permission prompts to the parent session by @qqqys in https://github.com/QwenLM/qwen-code/pull/4955
* feat(core): let grep results satisfy prior-read checks by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5043
* chore: sync package-lock.json with packages/cli ws dependencies by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5023
* feat(skills): support user-invocable frontmatter by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/5037
* fix(daemon): Sanitize logs and type MCP restarts by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5006
* fix(memory): avoid stale tool schema recall by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5058
* fix(core): eliminate OOM from debugResponses accumulation by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4982
* feat(serve): deliver A2UI surfaces over MCP — bridge extraction and action endpoint by @qqqys in https://github.com/QwenLM/qwen-code/pull/4961
* fix: enable fork subagents by default by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/4963
* refactor(web-shell): remove duplicate agents panel, contain SubAgent views by @wenshao in https://github.com/QwenLM/qwen-code/pull/5059
* feat(mcp): project .mcp.json + workspace approval gating with aligned scope precedence (#4615) by @qqqys in https://github.com/QwenLM/qwen-code/pull/4713
* fix(core): preserve background agent launch flags by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5061
* feat(web-shell): daemon web-shell improvements — token usage, settings, retry, streaming metrics, hidden commands by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5066
* feat(web-shell): revamp floating todo panel interactions by @wenshao in https://github.com/QwenLM/qwen-code/pull/5069
* fix(web-shell): improve slash command panel layering by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5078
* feat(web-shell): show message time on hover by @wenshao in https://github.com/QwenLM/qwen-code/pull/5079
* fix(serve): Add prompt queue backpressure by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5033
* feat(core): durable cron jobs — /loop tasks that survive restarts by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5004
* fix(cli): show full plan for gate failures by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5077
* feat(web-shell): show time on parallel-agents box and sub-agent tools by @wenshao in https://github.com/QwenLM/qwen-code/pull/5084
* feat(sdk,serve): DaemonTransport abstraction + ACP standard compliance by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5040
* fix(cli): submit fast tool results after stream end by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5071
* feat(core): Workflow P3 — agent({schema, agentType, model, isolation:'worktree'}) (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5034
* fix(cli): ignore expired live agents in focus navigation by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5070
* fix(cli): drop tool calls after cancellation by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5020
* fix(core): Persist file history snapshot updates by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5057
* test(cli): Cover rewind selection and confirm flow by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5044
* fix(cli): add OSC 52 clipboard fallback for SSH environments by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4929
* fix(webui): defer DaemonClient disposal to survive React StrictMode by @wenshao in https://github.com/QwenLM/qwen-code/pull/5091
* feat(core): migrate Computer Use to cua-driver (cross-platform) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5051
* feat(web-shell): reveal full tool detail and auto-collapse finished tools by @wenshao in https://github.com/QwenLM/qwen-code/pull/5088
* fix(cli,core): harden OOM prevention — idempotent compaction tests, explicit GC, debug log defaults by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/4914
* fix(cli): wrap long status lines by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5093
* fix(acp): add internal Kind.Agent, keep ACP wire on 'other' (no-regression) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5085
* feat(web-shell): make input shortcuts discoverable and clickable by @wenshao in https://github.com/QwenLM/qwen-code/pull/5096
* fix(ci): fail PR review job when the run aborts mid-review by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5053
* feat(cli,web-shell): persist goal status in daemon transcript events by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5098
* fix(core): default GLM-5.2+ and GLM-6.x onward to 1M context by @wenshao in https://github.com/QwenLM/qwen-code/pull/5103
* refactor(core): unify retry delay policy by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3827
* feat(acp): dedicated agent permission dialog via _meta.toolName (follow-up to #5085) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5105
* fix(daemon): Avoid replaying truncated session diffs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5108
* feat(cli): import Claude MCP servers by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5095
* fix(core): Repair duplicate tool call IDs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5107
* feat(cli): improve /copy command argumentHint and description by @huww98 in https://github.com/QwenLM/qwen-code/pull/5110
* feat(web-shell): collapsible TodoWrite history with status diff by @wenshao in https://github.com/QwenLM/qwen-code/pull/5109
* test: stabilize simple MCP integration check by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5072
* fix(core): hard-stop repeated identical tool calls by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5036
* fix(core): keep token escalation warm across agent rounds by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5062
* fix(core): bound hard rescue compression retries by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4526
* fix(core): bound foreground shell output capture by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4524
* fix(core): compress when usage metadata is missing by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4528
* docs: Refresh daemon developer docs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4412
* fix(core): ignore agent names without active teams by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5115
* fix(core): include response tokens in prompt estimate by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4525
* fix(dual-output): prevent FIFO blocking on startup when no reader connected by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4894
* ci: add scheduled autofix workflow for stale bug issues by @qqqys in https://github.com/QwenLM/qwen-code/pull/4989
* fix(core): honor skipLoopDetection for the deterministic tool-call loop by @wenshao in https://github.com/QwenLM/qwen-code/pull/5128
* docs: rewrite CLAUDE.md to point to AGENTS.md as authoritative source by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5138
* feat(computer-use): configurable screenshot max dimension (setting + env) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5122
* fix(core): Bound active tool result history by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5111
* fix(desktop): isolate update feed from CLI releases by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5139
* feat(web-shell): per-task token & time detail on completed todos by @wenshao in https://github.com/QwenLM/qwen-code/pull/5118
* fix(web-shell): remove redundant sanitizeSvg, fix mermaid render failure by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5123
* fix release integration env controls by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5121
* feat(web-shell): collapse completed turns to prompt + final answer by @wenshao in https://github.com/QwenLM/qwen-code/pull/5125
* fix(core): skip auto-title generation when history has no user message by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5120
* feat(desktop): show git branch in working directory badge by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5082
* feat(triage): make minimal-change an explicit PR review check by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5146
* fix(release): allow cli-entry.js in standalone dist allowlist by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5153
* fix: warn on oversized context instructions by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5073
* docs: fix stale defaults, CLI syntax, and tool naming drift by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5158
* chore(release): desktop desktop-v0.0.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5127
* chore(release): v0.18.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5164
* feat(web-shell): support custom footer renderer by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5166
* fix(core): simplify edit tool description to path only by @huww98 in https://github.com/QwenLM/qwen-code/pull/5140
* fix(monitor): batch-drain notifications to reduce token waste by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5165
* feat(web-shell): add imperative composer API for external text, tag, and submit control by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5161
* feat(web-shell): per-turn time & tokens on the collapse seam, below the prompt by @wenshao in https://github.com/QwenLM/qwen-code/pull/5163
* docs(daemon): Refresh daemon docs in English by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5144
* fix(core): coerce numeric string params in SchemaValidator for MCP tools by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/4967
* fix(channels): match sender id as a full segment in SessionRouter by @Osamaali313 in https://github.com/QwenLM/qwen-code/pull/5116
* docs(design): DaemonTransport abstraction — pluggable transport for SDK by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5026
* ci: publish autofix PRs as qwen-code-ci-bot by @qqqys in https://github.com/QwenLM/qwen-code/pull/5137
* fix(agent): make forking explicit; keep omitted subagent_type awaitable by @wenshao in https://github.com/QwenLM/qwen-code/pull/5155
* fix(core): auto-retry transport stream errors before the first chunk by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5171
* docs: add Qwen Code Desktop release link by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5152
* docs: fix MCP token path, daemon UI event count, add Feishu channel by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5172
* docs(channels): add screenshots to Feishu setup guide by @joeytoday in https://github.com/QwenLM/qwen-code/pull/4983
* feat(cli): Add daemon status API by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5174
* docs: fix missing spaces before parentheses in README by @marko1olo in https://github.com/QwenLM/qwen-code/pull/4796
* fix: Qwen PR review proxy bypass, stale-worktree cleanup, and footer line break by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5168
* feat(core+cli): Workflow P4 — meta + /workflows + phase-tree (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5094
* feat(daemon): deliver web-shell mid-turn messages into the running turn by @wenshao in https://github.com/QwenLM/qwen-code/pull/5175
* feat(tui): collapsible thinking blocks with duration timer by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4598
* feat(web-shell): expose transcript event changes by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5193
* Polish web-shell execution display by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5190
* Fix completed prompt lifecycle race by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5192
* fix(dingtalk): reopen code fences without inserting a blank line by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5204
* fix(cli): hide unconfigured discontinued OAuth model by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5167
* fix(permissions): do not model /dev/tcp and /dev/udp redirects as file I/O by @warmjademe in https://github.com/QwenLM/qwen-code/pull/5196
* fix(core): strengthen exit_plan_mode descriptions to prevent empty plan parameter by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5188
* fix(desktop): keep latest feed stable-only by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5149
* fix(core): read SHORT-typed TIFF dimensions correctly on big-endian files by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5209
* fix(cli): skip highlightAuto for unlabeled code blocks with box-drawing/CJK content by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5198
* fix: coerce non-string tool params to strings for self-hosted LLMs by @launchswitch in https://github.com/QwenLM/qwen-code/pull/4793
* ci(autofix): prioritize recent unattended bugs over stale ones by @qqqys in https://github.com/QwenLM/qwen-code/pull/5178
* fix(cli): keep sudo-required npm installs on npm instead of migrating to standalone by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5207
* Revert "fix(core): skip auto-title generation when history has no user message" by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5200
* fix(e2e): add daemon_status to serve capabilities baseline; run E2E on PRs by @wenshao in https://github.com/QwenLM/qwen-code/pull/5211
* fix(web-shell): localize remaining hardcoded UI strings by @carffuca in https://github.com/QwenLM/qwen-code/pull/5189
* fix(acp): load extension commands in daemon sessions by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5216
* fix(web-shell): simplify collapse metadata display by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5223
* fix(ci): gate PR review and triage on write permission by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5191
* ci: run CLI integration tests in the merge queue by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5224
* ci(autofix): unify issue-fix and review-response into one lifecycle workflow by @qqqys in https://github.com/QwenLM/qwen-code/pull/5233
* feat(cli): add sessions list command with --json and --limit flags by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5187
* ci(e2e): stop running the E2E matrix on every PR push by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5238
* chore(release): v0.18.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5243
* fix(cli): Stop after cancelled ask_user_question by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5218
* fix(cli): render slash suggestion descriptions on a single truncated line by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5236
* ci(release): report required Test checks on release PRs and auto-approve by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5250
* fix(core): always declare exit_plan_mode so plan mode can call it (#5210) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5251
* chore(release): v0.18.3 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5255
* fix(core): Track supported sed edits in file history by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5141
* fix(vscode-ide-companion): create independent McpServer per IDE session by @huww98 in https://github.com/QwenLM/qwen-code/pull/5264
* fix(core): read BMP height as signed int32 for top-down bitmaps by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5227
* docs: add CLI subcommands section with qwen sessions list by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5254
* feat(serve): make ACP permission timeout configurable by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5260
* fix(cli): Preserve mid-turn image messages by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5183
* docs: fix SSE ring size errors and add /workflows command by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5205
* fix(core): detect dat files by content by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5256
* fix(model): remember selected provider when multiple share a model id (#5173) by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5179
* docs: Revamp README for clarity and focus by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5257
* feat(i18n): localize tool display names in TUI and web-shell badges by @wenshao in https://github.com/QwenLM/qwen-code/pull/5220
* fix(daemon): centralize mid-turn event constant + recover timed-out drains by @wenshao in https://github.com/QwenLM/qwen-code/pull/5266
* fix(core): keep DeepSeek presets text-only by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5268
* fix(cli): drop AgentView cleanup setState that can trip React #185 (#5199) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5286
* fix(core): read WebP VP8X canvas height from the correct byte offset by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5194
* fix(cli): support Ctrl+P/N in completions by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5259
* feat(serve): add daemon idle detection to GET /health?deep=true by @jifeng in https://github.com/QwenLM/qwen-code/pull/4934
* fix(core): never let telemetry file exporters crash the process by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5246
* fix(cli): correct context filename settings schema by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5269
* feat(hooks): pass original API call ID (toolCallId) to hook system by @shiloong in https://github.com/QwenLM/qwen-code/pull/4918
* fix(core): per-turn tool-call circuit breaker — always-on cap + opt-in loop heuristics (#5234) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5279
* fix(desktop): handle git branch badge edge cases by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5247
* feat(core,cli): Workflow tool token budget + per-run UI surfacing (P5) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5231
* feat(extensions): add i18n support for extension displayName and description by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5289
* feat(loop): wire prompt-only /loop to self-paced wakeups by @qqqys in https://github.com/QwenLM/qwen-code/pull/5197
* fix(cli): correct sandbox settings schema by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5272
* test(cli): enable load config model selection coverage by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5274
* docs(cli): document tmux scroll workaround by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5248
* test(cli): cover selection list scroll up by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5276
* fix(weixin): show allowed image directories by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5296
* fix(cli): reject malformed OSC rgb colors by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5307
* test(cli): enable table foreground reset coverage by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5278
* test(core): enable agent headless termination coverage by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5282
* fix(web-shell): summarize grep_search results by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5294
* fix(core): read short VP8L WebP dimensions by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5292
* fix(core): track attached stdout fd redirects by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5317
* fix(dingtalk): split oversized markdown lines by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5299
* fix(cli): preserve multiline shell history by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5335
* fix(cli): validate GitHub remote hosts by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5327
* test(cli): enable command search long suggestion coverage by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5283
* fix(core): preserve migrated command description strings by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5321
* fix(cli): enforce stdin byte limit by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5331
* fix(core): respect home path boundary when tildeifying by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5333
* fix(cli): truncate session picker text by display width by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5338
* fix(core): support GIF image token metadata by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5340
* fix(cli): handle session search graphemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5342
* fix(cli): normalize english output language by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5346
* fix(core): parse OAuth resource metadata params by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5344
* fix(core): handle stale worktree session markers by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5229
* feat(loop): add second-resolution session wakeup engine by @qqqys in https://github.com/QwenLM/qwen-code/pull/5182
* fix(core): ignore duplicate provider tool-call ids by @YingchaoX in https://github.com/QwenLM/qwen-code/pull/5038
* fix(cli): show thinking in full transcript mode by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5354
* feat(desktop): compile macOS 26+ Liquid Glass Assets.car in brand-create by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5284
* fix(cli): return fresh empty mcp json results by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5349
* fix(weixin): normalize markdown image syntax by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5297
* fix(core): skip sleep inhibitor in headless ssh by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5295
* fix(cli): reject malformed terminal sequences by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5305
* fix(cli): expand windows-style tilde paths by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5298
* fix(core): validate oauth expires_in values by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5356
* fix(core): reject malformed cron numeric fields by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5352
* fix(cli): parse sandbox image registry ports by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5325
* fix(cli): preserve empty MCP prompt args by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5323
* fix(core): reject invalid cron task entries by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5309
* fix(cli): avoid agent composer unmount reset by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5302
* fix(cli): validate channel service pidfile by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5300
* fix(core): preserve invalid schema length strings by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5312
* fix(weixin): confirm the WEBP signature, not just the RIFF prefix by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5285
* feat(channel): add QQ Bot (QQ机器人) channel adapter by @Eric-GoodBoy-Tech in https://github.com/QwenLM/qwen-code/pull/5202
* fix(cli): reject malformed ACP timeout strings by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5315
* fix(cli): import extension channels via file urls by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5301
* fix(cli): bound streaming thought render buffers by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/5314
* feat(core): auto-reveal exit_plan_mode tool when entering plan mode by @aspnmy in https://github.com/QwenLM/qwen-code/pull/5311
* fix(cli): window title shows session name instead of model activity status by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5288
* fix(core): keep qwen3.6-flash and kimi-k2.6 presets text-only by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5328
* feat(skills): add desktop-pet skill for creating pixel-art companions by @xxlaura in https://github.com/QwenLM/qwen-code/pull/4808
* fix(cli): render a sub-minute duration that rounds to 60s as "1m" by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5287
* fix: Expand Windows ~\\ home paths and hide phantom (session) entries in the desktop session list by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/5253
* feat(stats): expose token usage for cost visibility by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4564
* fix(plan-gate): isolate gate agent AbortSignal from parent signal chain by @CubeLander in https://github.com/QwenLM/qwen-code/pull/5185
* fix(core): honor output language in side queries by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4519
* fix(cli): avoid stale git branch watcher setup by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5271
* fix(desktop): detect WebP and AVI in RIFF magic-byte sniffing by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5336
* fix(input): restore IME cursor positioning reverted in #4779 by @BenGuanRan in https://github.com/QwenLM/qwen-code/pull/4993
* fix(cli): close @path completion dropdown on Enter accept by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/4841
* fix(core): fall back to encrypted-file storage for extension secrets when keychain is unavailable by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5221
* fix(core): support whitespace in session metadata fields by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5353
* fix(core): prevent OOM in auto-memory extraction during /quit (#5147) by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5181
* refactor(tools): rename TodoWrite tool display name to TodoList by @wenshao in https://github.com/QwenLM/qwen-code/pull/5319
* fix(core): expire tokens at buffer boundary by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5360
* fix(cli): validate restore checkpoints before mutation by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5358
* fix(core): honor ripgrep builtin setting at runtime by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5362
* fix(core): create token file on first save by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5367
* fix(cli): preserve workspace trust state for extensions by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5369
* fix(cli): Stop after cancelled permissions by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5258
* fix(core): resolve tilde paths before search permission checks by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5378
* fix(cli): respect sandbox path boundaries by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5375
* fix(cli): update acp cancel test flag by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5384
* fix(core): avoid reconnecting on MCP tool errors by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5382
* fix(core): accept uppercase web fetch schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5391
* fix(cli): preserve equals in mcp env values by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5377
* feat(cli): show follow-up suggestion in input placeholder by @MikeWang0316tw in https://github.com/QwenLM/qwen-code/pull/5145
* fix(core): avoid glob prefix cache reuse by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5364
* fix(core): validate grep result limits by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5389
* fix(core): parse grep results with colon paths by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5372
* feat(config): add settings file change detection via chokidar watcher… by @water-in-stone in https://github.com/QwenLM/qwen-code/pull/4933
* fix(acp): scrub simple env for spawned children by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5395
* fix(core): pass --no-ask-password to systemd-inhibit to prevent TUI corruption by @OrbitZore in https://github.com/QwenLM/qwen-code/pull/5318
* fix(cli): parse sandbox mounts with windows drives by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5388
* fix(core): add GLM-5.2 to Z.AI preset by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5397
* fix(openai): add string tool result compatibility mode by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5399
* fix(cli): clarify cumulative statusline token labels by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5400
* feat(cli): show optional response token rate by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5401
* fix(cli): reduce retained interactive tool output memory by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4971
* fix(cli): calculate response rate from phase token delta by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5402
* fix(cli): clarify unavailable model configuration hint by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5403
* feat(cli): serve the Web Shell UI from `qwen serve` by @wenshao in https://github.com/QwenLM/qwen-code/pull/5392
* fix(cli): gate cron scheduler startup on config initialization (#5022) by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5230
* fix(core): keep estimated token split summing to total by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5420
* fix(core): share memory filename config state by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5419
* fix(channel): scope qqbot session backup path by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5417
* fix(channel): track qqbot close reconnect timer by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5416
* fix(auth): preserve custom provider models on install by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5404
* fix(core): target microcompaction cache disarms by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5407
* fix(channel): keep qqbot token refresh retrying by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5414
* fix(cli): keep keypress handlers current by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5421
* refactor(serve): unify session title/displayName into single displayName field by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5002
* feat(cli): add persistent history collapse on resume with refined commands by @Gove2004 in https://github.com/QwenLM/qwen-code/pull/4085
* fix(cli): narrow settings enum schemas by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5418
* fix(channel): bound qqbot gateway reconnect retries by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5415
* fix(core): block broad shell self-kill commands by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5409
* fix(cli): preserve trustedFolders comments on save by @Zoean-z in https://github.com/QwenLM/qwen-code/pull/4746
* fix(hooks): remove the dead updatedMCPToolOutput field (#5422) by @ken-jo in https://github.com/QwenLM/qwen-code/pull/5423
* feat(web-shell): add extension management by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5398
* fix(cli): accept uppercase URL schemes in mcp add transport detection by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5426
* fix(extensions): accept uppercase URL schemes when parsing install sources by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5429
* fix(core): provide escape path when plan gate is unavailable by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5430
* feat(extensions): interactive multi-tab /extensions manager (Installed / Discover / Sources) by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4850
* fix(cli): stabilize extension list spacing by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5445
* fix(weixin): handle uppercase CDN upload schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5439
* fix(core): require opt-in for plan mode prompt by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5433
* test(core): drop duplicate gitdiff untracked count case by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5468
* fix(core): evaluate ignore files named with dot prefixes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5458
* fix(core): enforce shell directory workspace boundary by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5454
* fix(core): validate lsp socket ports by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5493
* fix(core): parse max output token env strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5491
* fix(core): detect providers by hostname by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5450
* fix(cli): validate ACP glob max results by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5480
* fix(core): allow dot-prefixed plans directories by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5460
* fix(extensions): fetch http marketplaces with http client by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5452
* fix(cli): parse FORCE_HYPERLINK strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5489
* fix(core): parse tool concurrency env strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5496
* fix(cli): enforce custom theme home boundary by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5456
* fix(dingtalk): skip uppercase webhook reaction targets by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5466
* fix(desktop): accept uppercase icon URL schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5470
* fix(cli): reject partial session size values by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5475
* fix(telegram): clear typing intervals on disconnect by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5477
* fix(cli): respect installation path boundaries by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5441
* fix: accept uppercase endpoint URL schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5443
* fix(core): reject fractional computer-use integer strings by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5500
* fix(core): match provider base URL slash variants by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5448
* fix(cli): enforce temp path boundaries for at-file by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5446
* fix(desktop): preserve uppercase favicon URLs by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5463
* fix(desktop): parse NO_PROXY ports strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5498
* fix(serve): validate session reaper timeouts by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5484
* fix(extensions): handle uppercase npm registry schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5437
* fix(core): add missing Token Plan models (qwen3.7-plus, glm-5.2, kimi-k2.7-code) by @huww98 in https://github.com/QwenLM/qwen-code/pull/5505
* fix(cli): wire ACP model-invocable commands by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5504
* fix(cli): reject partial cpu profile durations by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5486
* test(desktop): update blocked scheme open-url assertion by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5529
* fix(desktop): restore locale parity by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5537
* fix(extension): accept uppercase URL schemes in Claude plugin sources by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5461
* fix(desktop): parse server ports strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5509
* fix(desktop): validate generic oauth token responses by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5511
* fix(core): don't treat an empty-parts message as a function call/response by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5494
* fix(desktop): allow double dots in bundle filenames by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5515
* feat(core): add Requesty provider by @Thibaultjaigu in https://github.com/QwenLM/qwen-code/pull/5478
* fix(cli): handle truncated remote input files by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5473
* test(core): wait for cron lock probe takeover by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5535
* perf(core): read current git branch directly from .git instead of spawning git by @wenshao in https://github.com/QwenLM/qwen-code/pull/5432
* fix(vscode): keep UNC paths absolute by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5542
* chore(release): v0.18.4 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5464
* feat(ci): on-demand tmux real-user testing for PRs by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5203
* test(desktop): align interceptor packaging contract by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5531
* fix(desktop): keep sibling paths absolute by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5517
* test(desktop): enable feedback flag in permission tests by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5533
* fix(cli): allow dotfile paths in Web Shell sendFile by @wenshao in https://github.com/QwenLM/qwen-code/pull/5541
* fix(cli): allow double dots in update archives by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5521
* fix(desktop): separate transform data output lines by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5525
* fix(desktop): handle Windows file mentions by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5523
* ci(release): trigger CI from release branch pushes by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5543
* fix(desktop): consolidate path boundary checks by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5545
* fix(desktop): reject fractional transfer sizes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5527
* docs(triage): Add reuse-before-new-code review check by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5547
* fix(cli): validate ACP file read windows by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5482
* fix(extensions): accept uppercase marketplace source schemes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5435
* Use VS Code theme tokens for companion scrollbar by @interconnectedMe in https://github.com/QwenLM/qwen-code/pull/5488
* feat(mcp): support MCP resources and reliably surface prompts by @wenshao in https://github.com/QwenLM/qwen-code/pull/5544
* chore(release): v0.18.5 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5558
* ci(release): Auto-publish VSCode companion after stable releases by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5572
* fix(cli): render full resume preview history by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/5565
* fix(cli): fill content area background on wrapped input lines by @lcheng321 in https://github.com/QwenLM/qwen-code/pull/5568
* fix(cli): fail non-interactive runs on loop detection by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/5564
* fix(core): respect zero OpenAI log file limit by @russeell in https://github.com/QwenLM/qwen-code/pull/5569
* fix(core): keep bare fast model on current auth by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5553
* feat(lint): enforce kebab-case filenames with ESLint by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/4797
* [codex] Fix legacy filename allowlist for kebab-case lint by @qqqys in https://github.com/QwenLM/qwen-code/pull/5578
* refactor(cli): Rename serve files to kebab-case by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5592
* feat(extensions): support archive install sources by @kkhomej33-netizen in https://github.com/QwenLM/qwen-code/pull/4909
* fix(cli): prefer command name over alias in slash completion ranking by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5577
* test(integration): add fake OpenAI server for no-AK daemon tests by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5560
* refactor(core): replace OpenRouter/Requesty provider classes with customHeaders in preset by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5539
* feat(voice): voice dictation with native capture, streaming, and biasing by @qqqys in https://github.com/QwenLM/qwen-code/pull/5502
* feat: revivable background sub-agents and subagent transcript TTL by @qqqys in https://github.com/QwenLM/qwen-code/pull/5556
* feat(core): add Artifact tool to publish interactive HTML pages by @qqqys in https://github.com/QwenLM/qwen-code/pull/5557
* feat(cli): add optional [HH:MM:SS] timestamp before each assistant turn by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5001
* fix(core): require confirmation when user manually enters plan mode by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5595
* fix(core): always-on guard for consecutive identical tool calls (#5019) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5573
* fix(ci): harden tmux triage reporting by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5548
* fix(voice): surface native recorder fallback so missing prebuilds aren't silent by @qqqys in https://github.com/QwenLM/qwen-code/pull/5605
* fix(core): prevent GLM on DashScope from dropping web_fetch content by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5599
* Fix native voice recorder retry after stop errors by @qqqys in https://github.com/QwenLM/qwen-code/pull/5609
* [codex] ci(triage): acknowledge slash triage requests by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5594
* [codex] Support artifact auto-open setting by @qqqys in https://github.com/QwenLM/qwen-code/pull/5617
* feat(tui): remove tool group borders and collapse completed tool results by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5003
* feat(workflows): finish Dynamic Workflows port — resume, saved workflows, keyword trigger, notifications (#4721) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5600
* feat(web-shell): support daemon session branching by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5613
* fix(core): backend-aware artifact publish confirmation + cancel handling by @qqqys in https://github.com/QwenLM/qwen-code/pull/5615
* test(integration): run no-AK smoke tests on PRs by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5607
* fix(cli): Fail dangling replayed tool calls by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5624
* fix(voice): bundle native audio addon into standalone archives by @qqqys in https://github.com/QwenLM/qwen-code/pull/5628
* ci: route in-repo PRs' Linux test to self-hosted runner by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5620
* ci(release): queue release failures for autofix by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5551
* feat(cli): browse MCP server resources in the /mcp dialog by @wenshao in https://github.com/QwenLM/qwen-code/pull/5635
* refactor(cli): Finish serve kebab-case filenames by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5604
* feat(core): default-on preserve_thinking for DashScope provider by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/5637
* ci(audio-capture): cross-compile darwin-x64 prebuild on arm64, drop macos-13 runner by @qqqys in https://github.com/QwenLM/qwen-code/pull/5643
* ci: harden self-hosted runner routing (follow-up to #5620 review) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5644
* fix(cli): harden ACP session list pagination params by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5618
* docs(mcp): correct mcp add scope default by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5593
* feat(tui): add thinking block viewer with Alt+T expand/collapse by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5627
* fix(cli): parse serve rate limit env strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5612
* fix(core): parse API timeout env strictly by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5602
* fix(serve): validate readText line limits by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5639
* fix(core): escape backslashes and quotes in emacs ediff paths by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5630
* fix(cli): detect USE_OPENAI auth when the model is set via QWEN_MODEL by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5647
* test(integration): skip qwen serve streaming suite under container sandbox by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5655
* refactor(core): extract Protocol enum and decouple model identity from auth type by @zzhenyao in https://github.com/QwenLM/qwen-code/pull/5089
* fix(webui): stop auto-recreating session on user-initiated delete by @yuanyuanAli in https://github.com/QwenLM/qwen-code/pull/5633
* fix(cli): keep settings v5 migration idempotent by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5676
* fix(test): restore openai model selection in ACP set_config_option test by @wenshao in https://github.com/QwenLM/qwen-code/pull/5721
* fix(test): isolate ACP integration agents via QWEN_HOME to end parallel-settings race by @wenshao in https://github.com/QwenLM/qwen-code/pull/5724
* fix(test): make ACP set_config_option test use a deterministic openai provider model by @wenshao in https://github.com/QwenLM/qwen-code/pull/5728
* fix(core): keep active runtime model in default getAllConfiguredModels listing by @wenshao in https://github.com/QwenLM/qwen-code/pull/5729
* feat(desktop): show file preview in a resizable side panel instead of fullscreen by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5730
* fix(core): remove redundant reportSuggestionUsage causing double-counted stats by @huww98 in https://github.com/QwenLM/qwen-code/pull/5684
* fix(core): validate ask_user_question answer indexes by @russeell in https://github.com/QwenLM/qwen-code/pull/5622
* feat(core): respect configurable agent ignore files by @shenyankm in https://github.com/QwenLM/qwen-code/pull/4653
* fix(daemon): Refresh workspace provider defaults by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5638
* feat(core): add fastOnly/voiceOnly flags to hide models from main model list by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5632
* feat(cli): match MCP resource completions by name and discover servers by @wenshao in https://github.com/QwenLM/qwen-code/pull/5733
* chore(release): v0.19.0 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5739
* fix(cli): skip unusable A2UI configs by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5685
* fix(cli): avoid duplicate ACP write BOM by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5688
* fix(cli): enable /lsp in ACP mode by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5689
* fix(core): require integer inline media byte limit by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5671
* fix(cli): reject invalid session list cursors by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5709
* fix(cli): reject unsupported extension scopes by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5714
* fix(core): reject blank cron prompts by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5716
* fix(cli): validate channel credential types by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5718
* fix(cli): use high-contrast software cursor by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5720
* fix(core): require integer compaction counts by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5646
* fix(core): parse agent & workflow integer env vars strictly by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5679
* fix(serve): validate list maxEntries as a positive integer by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5719
* fix(workflows): validate runId before recursive prune delete (path-traversal dir wipe) by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5740
* fix(triage): never auto-approve cross-repo refactor PRs by @wenshao in https://github.com/QwenLM/qwen-code/pull/5744
* fix(cli): only paint theme background when it matches the terminal by @wenshao in https://github.com/QwenLM/qwen-code/pull/5746
* revert(core): revert Protocol enum & model-identity decoupling (#5089) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5745
* ci: retry merge-ref checkout to fix transient "not our ref" failures by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5732
* chore(release): v0.19.1 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5762
* feat(serve): Add remote LSP status route by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5741
* fix(agent): cap fork turns and bubble fork permission prompts by @qqqys in https://github.com/QwenLM/qwen-code/pull/5737
* feat(vision-bridge): transcribe images to text for text-only models by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5126
* feat(core): add deterministic guards for destructive commands in auto mode by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/5754
* feat(cli): add extension operation polling by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5753
* fix(vscode): always show chat view in the Activity Bar sidebar by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5757
* fix(cli): source /context token total from the per-session chat by @qqqys in https://github.com/QwenLM/qwen-code/pull/5764
* fix(core): Disambiguate duplicate model display names by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5769
* fix(cli): remove theme background fills from input box and user messages by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5772
* feat(cli): match MCP resources globally on bare @ and show full references by @wenshao in https://github.com/QwenLM/qwen-code/pull/5774
* ci: collapse PR checks into Ubuntu gate by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5767
* refactor(web-shell): restructure chat UI by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5775
* fix(cli): stabilize VP mouse interactions by @ZevGit in https://github.com/QwenLM/qwen-code/pull/5751
* docs: fix config/command/auth drift and surface the model-providers page by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5735
* fix(vscode): clamp open file positions by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5711
* fix(config): fall back to user env files by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5731
* fix(core): require integer stop hook cap by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5667
* fix(core): require integer microcompaction keep count by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5652
* fix(core): Align MCP OAuth guidance and docs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5589
* feat(cli): Add workspace permissions rules API by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5743
* fix(cli): replace emoji thinking/summary icons with Unicode text symbols by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5788
* fix(cli): restore saved custom model IDs when re-entering the auth wizard by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5654
* fix(daemon): Reject stale prompt client admission by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5784
* feat(serve): voice dictation over the daemon for the Web Shell by @qqqys in https://github.com/QwenLM/qwen-code/pull/5755
* fix(core): parse QWEN_SERVE_MCP_CLIENT_BUDGET strictly as a decimal integer by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5752
* fix(sdk): self-heal stale clientId on invalid_client_id prompts by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5797
* feat(voice): refine ASR transcripts with the fast model before insert by @qqqys in https://github.com/QwenLM/qwen-code/pull/5794
* fix(cli): promote pasted image paths to attachments by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5803
* fix(sdk): raise browser daemon bundle budget to 126 KiB by @wenshao in https://github.com/QwenLM/qwen-code/pull/5801
* ci: harden Linux CI reliability (shallow ECS checkout + CodeQL timeout) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5810
* fix(cli): correctly map Claude MCP server transport types on import and in .mcp.json by @BZ-D in https://github.com/QwenLM/qwen-code/pull/5812
* perf(cli): Optimize serve daemon startup by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5785
* Expose MCP resource read tool by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5781
* ci: move macOS/Windows tests and CodeQL off the per-PR path by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5813
* fix(core): allow web_fetch JSON fallback by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5660
* chore(release): v0.19.2 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/5830
* ci: split platform test matrix into named jobs so PRs can enter the merge queue by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5833
* fix(ide): validate QWEN_CODE_IDE_SERVER_PORT before reading lock file by @mvanhorn in https://github.com/QwenLM/qwen-code/pull/5805
* fix(core): add streaming inactivity timeout to the OpenAI pipeline by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5827
* fix(cli): prevent scroll snap-back and flicker in non-VP mode during multi-agent runs by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5799
* feat(serve): Add daemon workspace voice and control APIs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5765
* feat(cli): Add skill usage stats by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5826
* feat(memory): confirm auto-generated skills before persisting by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5616
* fix(cli): cancel pending self-paced loop wakeups on user abort by @qqqys in https://github.com/QwenLM/qwen-code/pull/5808
* fix(core): preserve reasoning_content when merging assistant turns by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/5815
* feat(cli): Show model thinking intent in loading indicator by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5668
* ci: give each CI job one home in the merge-queue flow by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5842
* fix(web-shell): stabilize active prompt loading state by @ytahdn in https://github.com/QwenLM/qwen-code/pull/5818
* Revert "feat(cli): Show model thinking intent in loading indicator" by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5846
* ci(release): make release flow merge-queue-safe and keep release PRs out of notes by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5832
* ci: add `@qwen-code /resolve` by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5779
* fix(cli): stop repeated duplicate provider responses by @tt-a1i in https://github.com/QwenLM/qwen-code/pull/5657
* test(cli): add daemon startup benchmark by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5825
* docs: add vertex-ai auth, missing commands, and qc-helper index entries by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/5727
* feat(core): decouple /remember from auto-extract, stop writing to QWEN.md by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5814
* fix(web-shell): defer transcript-appending local commands while a turn streams by @carffuca in https://github.com/QwenLM/qwen-code/pull/5822
* feat(web-shell): enhance assistant markdown tables with Excel-style interactions by @jifeng in https://github.com/QwenLM/qwen-code/pull/5650
* ci(triage): run triage on the self-hosted ECS pool instead of GitHub-hosted by @wenshao in https://github.com/QwenLM/qwen-code/pull/5851
* feat(cli): enable built-in status line preset by default for new users by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5792
* feat(config): map provider id to SDK protocol via providerProtocol (#5758) by @qqqys in https://github.com/QwenLM/qwen-code/pull/5793
* feat(telemetry): Make sensitive span attribute limit configurable by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5804
* fix(packaging): bundle audio capture for mirror installs by @qqqys in https://github.com/QwenLM/qwen-code/pull/5747
* feat(core): QWEN_STREAM_IDLE_TIMEOUT_MS env knob for the stream idle timeout by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5845
* feat(cli): support a user-configurable keyterms file for voice dictation by @qqqys in https://github.com/QwenLM/qwen-code/pull/5817
* fix(core): reject userinfo URLs in WebFetch validation by @VectorPeak in https://github.com/QwenLM/qwen-code/pull/5783
* ci: route the merge queue's Linux jobs onto ECS by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5854
* feat(cli): simplify auto mode startup text and remove emoji (#4584) by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5824
* feat(web-shell): show duration on finished thinking summary by @wenshao in https://github.com/QwenLM/qwen-code/pull/5864
* test(cli): raise i18n ToolMessage test timeout to 15s to stop merge-queue flake by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5858
* ci: take CodeQL and E2E off the per-merge push path by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5859
* ci(qwen-resolve): run the /resolve job on a hosted runner by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5862
* feat(tui): partition tool display by type — collapse read/search, show mutation tools individually by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5661
* fix(cli): make alt+t expand thinking on macOS Option-compose terminals by @chiga0 in https://github.com/QwenLM/qwen-code/pull/5872
* feat(mcp): reconcile MCP servers live on settings change by @water-in-stone in https://github.com/QwenLM/qwen-code/pull/5561
* ci(qwen-resolve): support fork PRs and slim /resolve to conflict-only by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5870
* feat(serve): query a single session's status by id by @samuelhsin in https://github.com/QwenLM/qwen-code/pull/5857
* chore(cli): drop redundant home-directory startup warning by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/5839
* fix(cli): show ⌥T instead of alt+T on macOS for thinking expansion by @Alex-ai-future in https://github.com/QwenLM/qwen-code/pull/5802
* feat(core): make self-paced /loop lean on monitor/background-task notifications by @qqqys in https://github.com/QwenLM/qwen-code/pull/5844
* fix(cli): improve token speed accounting by @seekskyworld in https://github.com/QwenLM/qwen-code/pull/5811
* fix(core): stream chat-compression side-query to survive gateway timeout by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5865
* perf(cli): skip spawnSync wrapper for `qwen serve` by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5874
* fix(web-shell): reword the Chinese tool-group summary (执行了 → 调用了) by @wenshao in https://github.com/QwenLM/qwen-code/pull/5876
* feat(cli): tighten response timestamp consistency and tests by @ZijianZhang989 in https://github.com/QwenLM/qwen-code/pull/5850
* fix(release): skip dist/node_modules when building standalone archives by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5878
* fix(test): raise timeout for cold-import suites to stop CI flake by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5880
* ci: isolate per-run agent state for triage and PR review by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/5885
* feat(core): add bundled extension creator skill by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5828
* feat(cli): support @extension mention in input autocomplete by @callmeYe in https://github.com/QwenLM/qwen-code/pull/5849
* refactor(cli): Split serve server routes by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/5809
* feat(cua-driver): vendor qwen-cua-driver with opt-in 0–1000 relative coordinates by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/5896
## New Contributors
* @kagura-agent made their first contribution in https://github.com/QwenLM/qwen-code/pull/4461
* @he-yufeng made their first contribution in https://github.com/QwenLM/qwen-code/pull/4607
* @zzhenyao made their first contribution in https://github.com/QwenLM/qwen-code/pull/4560
* @Pepograminger made their first contribution in https://github.com/QwenLM/qwen-code/pull/4605
* @InfiniteUselessness made their first contribution in https://github.com/QwenLM/qwen-code/pull/4485
* @ZijianZhang989 made their first contribution in https://github.com/QwenLM/qwen-code/pull/4701
* @callmeYe made their first contribution in https://github.com/QwenLM/qwen-code/pull/4533
* @CNCSMonster made their first contribution in https://github.com/QwenLM/qwen-code/pull/4647
* @Pluviobyte made their first contribution in https://github.com/QwenLM/qwen-code/pull/4618
* @Alex-ai-future made their first contribution in https://github.com/QwenLM/qwen-code/pull/4798
* @Rakson0209 made their first contribution in https://github.com/QwenLM/qwen-code/pull/4734
* @han-dreamer made their first contribution in https://github.com/QwenLM/qwen-code/pull/4784
* @BenGuanRan made their first contribution in https://github.com/QwenLM/qwen-code/pull/4779
* @wsyjh8 made their first contribution in https://github.com/QwenLM/qwen-code/pull/4911
* @puneetdixit200 made their first contribution in https://github.com/QwenLM/qwen-code/pull/4788
* @Osamaali313 made their first contribution in https://github.com/QwenLM/qwen-code/pull/5116
* @marko1olo made their first contribution in https://github.com/QwenLM/qwen-code/pull/4796
* @warmjademe made their first contribution in https://github.com/QwenLM/qwen-code/pull/5196
* @launchswitch made their first contribution in https://github.com/QwenLM/qwen-code/pull/4793
* @carffuca made their first contribution in https://github.com/QwenLM/qwen-code/pull/5189
* @shiloong made their first contribution in https://github.com/QwenLM/qwen-code/pull/4918
* @Eric-GoodBoy-Tech made their first contribution in https://github.com/QwenLM/qwen-code/pull/5202
* @aspnmy made their first contribution in https://github.com/QwenLM/qwen-code/pull/5311
* @xxlaura made their first contribution in https://github.com/QwenLM/qwen-code/pull/4808
* @mvanhorn made their first contribution in https://github.com/QwenLM/qwen-code/pull/5253
* @CubeLander made their first contribution in https://github.com/QwenLM/qwen-code/pull/5185
* @water-in-stone made their first contribution in https://github.com/QwenLM/qwen-code/pull/4933
* @OrbitZore made their first contribution in https://github.com/QwenLM/qwen-code/pull/5318
* @Gove2004 made their first contribution in https://github.com/QwenLM/qwen-code/pull/4085
* @Zoean-z made their first contribution in https://github.com/QwenLM/qwen-code/pull/4746
* @ken-jo made their first contribution in https://github.com/QwenLM/qwen-code/pull/5423
* @Thibaultjaigu made their first contribution in https://github.com/QwenLM/qwen-code/pull/5478
* @interconnectedMe made their first contribution in https://github.com/QwenLM/qwen-code/pull/5488
* @lcheng321 made their first contribution in https://github.com/QwenLM/qwen-code/pull/5568
* @russeell made their first contribution in https://github.com/QwenLM/qwen-code/pull/5569
* @VectorPeak made their first contribution in https://github.com/QwenLM/qwen-code/pull/5783
* @samuelhsin made their first contribution in https://github.com/QwenLM/qwen-code/pull/5857
* @seekskyworld made their first contribution in https://github.com/QwenLM/qwen-code/pull/5811
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/sdk-typescript-v0.1.8-preview.1...cua-driver-rs-v0.6.8