<!-- 使用 .github/release.yml 中的配置生成发布说明，分支为 release/v0.22.0-nightly.20260825.22bb5e8b9f -->
## 更新内容
* fix(web-shell)：从概览面板打开时传递会话工作区当前工作目录 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9730
* fix(web-shell)：在过时的中途拒绝后回退 by @ytahdn 在 https://github.com/QwenLM/qwen-code/pull/9732
* fix(review)：阻止在已替代的运行中触发回退评论 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9716
* feat(review)：添加 temporal-reachability 和 incident-replay 透镜 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9708
* fix(web-shell)：固定区域顺序稳定并提供即时固定反馈 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/9560
* feat(review)：要求每个修复提供其测试，并对不收敛做出裁决 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9596
* chore(ci)：将 autofix 说明迁移至设计记录并控制增长 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9677
* feat(cli)：将每个守护进程会话恢复至其上次选择的模型 by @doudouOUC 在 https://github.com/QwenLM/qwen-code/pull/9687
* feat(review)：在发布前根据捕获的差异验证 Aone 行内锚点 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9634
* fix(ci)：在 workflow 尺寸基线中记录 qwen-autofix.yml 的交付尺寸 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9747
* fix(ci)：根据 review 负载提供的字段限制 fork 信号 by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9469
* feat(goal)：核算 Goal 消耗的 token by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9583
* fix(core)：拒绝回显提示词自身示例的会话标题 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/9709
* fix(core)：解析 workflow 元数据字面量而非直接求值 by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9325
* fix(sdk)：支持相对制品下载 URL by @ytahdn 在 https://github.com/QwenLM/qwen-code/pull/9734
* fix(autofix)：为修复轮次提供可完成的预算 by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9691
* feat(cli)：通过设置键启用动态 workflow by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9098
* fix(core)：将 workflow 停滞监控范围扩展至传输重试链之外 by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9397
* test(core)：验证子代理注册表不包含 MCP 指令 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9720
* fix(core)：根据模型声明的内容限制技能公告 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9718
* feat(review)：在 Aone Code 目标上支持 pr-context by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9621
* fix(review)：将修复引发的重新报告计为首次工作 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9744
* docs(review)：当两个轴都称为“rank 3”时明确命名 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9759
* fix(web-shell)：预览按文档分类的制品 by @ytahdn 在 https://github.com/QwenLM/qwen-code/pull/9760
* feat(web-shell)：切换后增量刷新 composer 技能 by @samuelhsin 在 https://github.com/QwenLM/qwen-code/pull/9131
* feat(review)：在 Aone Code 目标上支持 comment-status 和 presubmit by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9627
* perf(cli)：将 VP 滚动渲染提升至 60 FPS by @DragonnZhang 在 https://github.com/QwenLM/qwen-code/pull/9681
* feat(models)：支持双角色图像生成模型 by @callmeYe 在 https://github.com/QwenLM/qwen-code/pull/9650
* fix(daemon)：加载后保持恢复的 ask_user_question 有效 by @doudouOUC 在 https://github.com/QwenLM/qwen-code/pull/9763
* feat(review)：添加持续关键的收敛建议（带残余风险合并） by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9526
* fix(core)：支持旧版 Git 的公共 GitHub 扩展 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/9690
* feat(cua-driver)：添加版本化 Computer Use SDK 及发布流水线 by @LaZzyMan 在 https://github.com/QwenLM/qwen-code/pull/9587
* refactor(node-repl)!: 将持久化 Node REPL 作为独立 MCP 服务器交付 by @LaZzyMan 在 https://github.com/QwenLM/qwen-code/pull/9499
* fix(review)：在放弃 worktree 清理前修复权限 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9748
* fix(core)：规范化会话标题回显比较的两边 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/9809
* refactor(cli)：强制执行 utils 叶层依赖方向 (#9146) by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/9737
* fix(web-shell)：限制 React dev performance.measure 累积以防止渲染器 OOM by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9770
* fix(dingtalk)：解析转发聊天记录 by @qqqys 在 https://github.com/QwenLM/qwen-code/pull/9339
* fix(web-shell)：添加 remark-cjk-friendly 以便粗体紧邻 CJK 标点… by @cactuser-Lu 在 https://github.com/QwenLM/qwen-code/pull/9457
* feat(mcp)：添加 MCP 2026 核心及 WebShell Apps 主机 by @samuelhsin 在 https://github.com/QwenLM/qwen-code/pull/8992
* fix(config)：在设置模式中允许 prompt hooks by @zjunothing 在 https://github.com/QwenLM/qwen-code/pull/8779
* fix(web-shell)：在创建会话前显示推理强度 by @callmeYe 在 https://github.com/QwenLM/qwen-code/pull/9599
* fix(auth)：使 Vertex AI 能够通过 Application Default Credentials 进行认证 by @axiom-of-choice 在 https://github.com/QwenLM/qwen-code/pull/9017
* fix(ci)：在 workflow 尺寸基线中记录 cd-cua-driver.yml 的交付尺寸 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9822
* feat(review)：为验证器提供不可反驳列表及可构建的拒绝阈值 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/9799
* 修复(core)：在等待完成回调前清空工具显示列表 by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/9602
* 重构(cli)：提取 ACP 技能管理 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/8865
* 修复(cli)：规范化 MCP 审批键中的 Win32 驱动器盘符大小写 by @zhou2024NAU in https://github.com/QwenLM/qwen-code/pull/9779
* 新增：支持 MiniMax 图像生成架构 by @octo-patch in https://github.com/QwenLM/qwen-code/pull/8322
* 修复(core)：读取前探测图像内容 by @rbalachandar in https://github.com/QwenLM/qwen-code/pull/9113
* 修复(vscode)：在会话导出中保留 Windows 文件链接 by @yefuyou in https://github.com/QwenLM/qwen-code/pull/8953
* 修复(cli)：防止调整大小时输入框边框溢出 by @tlysanhuo in https://github.com/QwenLM/qwen-code/pull/8991
* 新增(core)：仅在 qwen serve 下声明 create_sub_session by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/9425
* 修复(core)：报告剩余的后台代理 by @tao943 in https://github.com/QwenLM/qwen-code/pull/9018
* 修复(core)：将工作层级限制在各端点接受的范围 by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/9501
* 修复(cli)：在录音开始时探测麦克风权限，而非语音预热 by @Nas01010101 in https://github.com/QwenLM/qwen-code/pull/8912
* 修复(core)：检测内容和推理流中的长段逐字重复循环 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9668
* 新增(scheduled-tasks)：允许使用现有会话创建任务 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9361
* 文档(agent)：澄清参数前置条件 by @tao943 in https://github.com/QwenLM/qwen-code/pull/9580
* 修复(review)：在残留探测中固定已验证的 Git 身份 (#9557) by @wenshao in https://github.com/QwenLM/qwen-code/pull/9742
* 修复(core)：在后台父级下展示嵌套子代理的审批 by @wenshao in https://github.com/QwenLM/qwen-code/pull/9793
* 修复(core)：将代理启动失败标记为失败的 tool calls by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9519
* 重构(goal)：由单一核心渲染器渲染 Goal 续接提示 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9581
* 修复(core)：避免幽灵式关机挂起状态 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9550
* 修复(core)：按会话隔离 fork 缓存读取器 by @tomsen02 in https://github.com/QwenLM/qwen-code/pull/9471
* 重构(review)：将 SKILL.md 拆分为核心正文及判决门控的参考文件 by @wenshao in https://github.com/QwenLM/qwen-code/pull/9804
* 新增(web-shell)：精简代理活动摘要 by @ytahdn in https://github.com/QwenLM/qwen-code/pull/9657
* 新增(auth)：将 Kimi (Moonshot AI) 添加为内置第三方提供商 by @TianYuan1024 in https://github.com/QwenLM/qwen-code/pull/9814
* 修复(goal)：按预算书写单位计算目录预览数量 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9835
* 新增(core)：展示工作流将执行的操作，并限定批准它的授权范围 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9837
* 新增(web-shell)：暴露代理任务变更 by @callmeYe in https://github.com/QwenLM/qwen-code/pull/9637
* 修复(cli)：在 WSL/ConPTY 上跳过终端重绘优化器 by @C0d3N1nja97342 in https://github.com/QwenLM/qwen-code/pull/7897
* 维护(ci)：刷新核心 issue-owner 池 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9808
* 修复(core)：使切换模型路由后记录的 token 计数失效 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9506
* 修复(daemon)：限制条件关闭拒绝持有 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9820
* 修复(core)：允许钩子弹回的 workflow 重新审批 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9547
* 文档(vscode)：更正最低 VS Code 版本 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9852
* 修复(core)：在会话前通过 sessionIdContext 路由调试日志 by @tomsen02 in https://github.com/QwenLM/qwen-code/pull/9538
* 新增(web-shell)：添加异步提交准备 by @dreamWB in https://github.com/QwenLM/qwen-code/pull/9802
* 修复(core)：支持按提供商的流空闲超时 by @yu-xin-c in https://github.com/QwenLM/qwen-code/pull/9795
* 新增(core)：在系统提示词中添加输出样式层 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9565
* 修复(memory)：选择遗忘候选项时无限制扫描 by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/9530
* 新增(serve)：添加 --open-with-auth by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9738
* 修复(core)：将团队关机设为仅领导者可用的工具 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9401
* 新增(vscode-ide-companion)：采用 WebShell 转录作为默认时间线 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9719
* 重构(core)：使 utils/ 成为叶子层 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9778
* 重构：集中审批模式契约 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9796
* 重构(core)：明确派生 Config 的所有权 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/8100
* 测试(acp-cron)：清理时终止整个进程树以停止 ENOTEMPTY 偶发失败 by @dream-creator in https://github.com/QwenLM/qwen-code/pull/9815
* 重构(core)：缩小内容生成器接口 by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/9676
* 修复(ci)：将不可删除的工作区残留移至一旁而非保留 by @wenshao in https://github.com/QwenLM/qwen-code/pull/9868
* 修复(serve)：规范化 Live 任务桥接会话 ID by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9819
* 测试(core)：对齐懒加载生成器顶点测试 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9888
* fix(core): 不区分大小写地映射 OpenAI 兼容的 finish_reason by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9884
* feat(computer-use): 使用捆绑技能替换内置工具 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/9856
* feat(review): 将 language-pitfall 和 wrapper/proxy 检查从 Agent 1a 中提升出来 by @wenshao in https://github.com/QwenLM/qwen-code/pull/9805
* fix(core): 在重试耗尽后接受静默的工具结果后完成 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9196
* feat(review): 说明当方法（而非补丁）是开放性问题时 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9340
* feat(skills): 添加 find-simplifications sweep 技能 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9384
* docs(core): 修复目标裁判超时单位 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9861
* docs(core): 修复读取文件分页默认注释 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9863
* docs(sdk): 修复查询超时示例签名 by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9867
* fix(config): 在配置模式中接受 output.format "stream-json" by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/8966
* fix(core): 拒绝格式错误的 Anthropic 工具参数 by @tlysanhuo in https://github.com/QwenLM/qwen-code/pull/9013
* fix(ci): 将 serve-ab 的自托管清理范围缩小至 A/B 签出目录 by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/9228
* fix(acp-bridge): 默认禁用权限超时 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9933
* test(cli): 在 root 权限下跳过 unreadable-ledger run-ledger 测试 by @wenshao in https://github.com/QwenLM/qwen-code/pull/9913
* fix(core): 放宽函数模式中的 uniqueItems 限制 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9869
* fix(goal): 将三个续写提示词收敛至一个守卫契约 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9834
* feat(core): 模型启动工作流前需用户明确选择加入 by @qqqys in https://github.com/QwenLM/qwen-code/pull/9806
## 新贡献者
* @cactuser-Lu 在 https://github.com/QwenLM/qwen-code/pull/9457 首次贡献
* @axiom-of-choice 在 https://github.com/QwenLM/qwen-code/pull/9017 首次贡献
* @zhou2024NAU 在 https://github.com/QwenLM/qwen-code/pull/9779 首次贡献
* @octo-patch 在 https://github.com/QwenLM/qwen-code/pull/8322 首次贡献
* @yefuyou 在 https://github.com/QwenLM/qwen-code/pull/8953 首次贡献
* @tao943 在 https://github.com/QwenLM/qwen-code/pull/9018 首次贡献
* @AaronZ345 在 https://github.com/QwenLM/qwen-code/pull/9550 首次贡献
* @yu-xin-c 在 https://github.com/QwenLM/qwen-code/pull/9795 首次贡献
* @dream-creator 在 https://github.com/QwenLM/qwen-code/pull/9815 首次贡献
**完整更新日志**: https://github.com/QwenLM/qwen-code/compare/v0.22.0...v0.22.0-nightly.20260825.22bb5e8b9f
<!-- Release notes generated using configuration in .github/release.yml at release/v0.22.0-nightly.20260825.22bb5e8b9f -->
## What's Changed
* fix(web-shell): pass session workspace cwd when opening from overview panel by @wenshao in https://github.com/QwenLM/qwen-code/pull/9730
* fix(web-shell): fall back after stale mid-turn rejection by @ytahdn in https://github.com/QwenLM/qwen-code/pull/9732
* fix(review): stop the fallback comment from firing on superseded runs by @wenshao in https://github.com/QwenLM/qwen-code/pull/9716
* feat(review): add temporal-reachability and incident-replay lenses by @wenshao in https://github.com/QwenLM/qwen-code/pull/9708
* fix(web-shell): stable pinned-section order and instant pin feedback by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9560
* feat(review): ask each fix for its test, and rule on non-convergence by @wenshao in https://github.com/QwenLM/qwen-code/pull/9596
* chore(ci): migrate autofix prose to the design record and ratchet growth by @wenshao in https://github.com/QwenLM/qwen-code/pull/9677
* feat(cli): restore each daemon session onto its last selected model by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9687
* feat(review): validate Aone inline anchors against the captured diff before posting by @wenshao in https://github.com/QwenLM/qwen-code/pull/9634
* fix(ci): record qwen-autofix.yml's shipped size in the workflow size baseline by @wenshao in https://github.com/QwenLM/qwen-code/pull/9747
* fix(ci): gate the fork signal on fields the review payload delivers by @qqqys in https://github.com/QwenLM/qwen-code/pull/9469
* feat(goal): account the tokens a Goal spends by @qqqys in https://github.com/QwenLM/qwen-code/pull/9583
* fix(core): reject session titles that echo the prompt's own examples by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9709
* fix(core): parse the workflow meta literal instead of evaluating it by @qqqys in https://github.com/QwenLM/qwen-code/pull/9325
* fix(sdk): support relative artifact download URLs by @ytahdn in https://github.com/QwenLM/qwen-code/pull/9734
* fix(autofix): give the repair pass a budget it can finish in by @qqqys in https://github.com/QwenLM/qwen-code/pull/9691
* feat(cli): enable dynamic workflows from a settings key by @qqqys in https://github.com/QwenLM/qwen-code/pull/9098
* fix(core): widen the workflow stall watchdog past the transport retry ladder by @qqqys in https://github.com/QwenLM/qwen-code/pull/9397
* test(core): pin that subagent registries carry no MCP instructions by @wenshao in https://github.com/QwenLM/qwen-code/pull/9720
* fix(core): gate skill announcements on what the model was declared by @wenshao in https://github.com/QwenLM/qwen-code/pull/9718
* feat(review): back pr-context on Aone Code targets by @wenshao in https://github.com/QwenLM/qwen-code/pull/9621
* fix(review): count a fix-induced re-report as first-time work by @wenshao in https://github.com/QwenLM/qwen-code/pull/9744
* docs(review): name the axis when two of them both call it "rank 3" by @wenshao in https://github.com/QwenLM/qwen-code/pull/9759
* fix(web-shell): preview document-classified artifacts by @ytahdn in https://github.com/QwenLM/qwen-code/pull/9760
* feat(web-shell): refresh composer skills incrementally after toggles by @samuelhsin in https://github.com/QwenLM/qwen-code/pull/9131
* feat(review): back comment-status and presubmit for Aone Code targets by @wenshao in https://github.com/QwenLM/qwen-code/pull/9627
* perf(cli): raise VP scroll rendering to 60 FPS by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/9681
* feat(models): support dual-role image generation models by @callmeYe in https://github.com/QwenLM/qwen-code/pull/9650
* fix(daemon): keep restored ask_user_question valid after load by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9763
* feat(review): add the persistently-critical convergence advisory (land-with-residual-risk) by @wenshao in https://github.com/QwenLM/qwen-code/pull/9526
* fix(core): support public GitHub extensions with older Git by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9690
* feat(cua-driver): add versioned Computer Use SDK and release pipeline by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/9587
* refactor(node-repl)!: deliver the persistent Node REPL as a standalone MCP server by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/9499
* fix(review): repair permissions before giving up on worktree cleanup by @wenshao in https://github.com/QwenLM/qwen-code/pull/9748
* fix(core): Normalize both sides of the session title echo comparison by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9809
* refactor(cli): enforce utils leaf-layer dependency direction (#9146) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9737
* fix(web-shell): cap React dev performance.measure accumulation to stop renderer OOM by @wenshao in https://github.com/QwenLM/qwen-code/pull/9770
* fix(dingtalk): parse forwarded chat records by @qqqys in https://github.com/QwenLM/qwen-code/pull/9339
* fix(web-shell): add remark-cjk-friendly so bold adjacent to CJK punct… by @cactuser-Lu in https://github.com/QwenLM/qwen-code/pull/9457
* feat(mcp): add MCP 2026 core and WebShell Apps host by @samuelhsin in https://github.com/QwenLM/qwen-code/pull/8992
* fix(config): allow prompt hooks in settings schema by @zjunothing in https://github.com/QwenLM/qwen-code/pull/8779
* fix(web-shell): show reasoning effort before session creation by @callmeYe in https://github.com/QwenLM/qwen-code/pull/9599
* fix(auth): let Vertex AI authenticate with Application Default Credentials by @axiom-of-choice in https://github.com/QwenLM/qwen-code/pull/9017
* fix(ci): record cd-cua-driver.yml's shipped size in the workflow size baseline by @wenshao in https://github.com/QwenLM/qwen-code/pull/9822
* feat(review): give verifiers a do-not-refute list and a constructible rejection bar by @wenshao in https://github.com/QwenLM/qwen-code/pull/9799
* fix(core): clear tool display list before awaiting completion callback by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/9602
* refactor(cli): extract ACP skill management by @callmeYe in https://github.com/QwenLM/qwen-code/pull/8865
* fix(cli): normalize win32 drive-letter casing in MCP approval keys by @zhou2024NAU in https://github.com/QwenLM/qwen-code/pull/9779
* Support MiniMax image generation schema by @octo-patch in https://github.com/QwenLM/qwen-code/pull/8322
* fix(core): sniff image content before read by @rbalachandar in https://github.com/QwenLM/qwen-code/pull/9113
* fix(vscode): preserve Windows file links in session exports by @yefuyou in https://github.com/QwenLM/qwen-code/pull/8953
* fix(cli): prevent input border overflow on resize by @tlysanhuo in https://github.com/QwenLM/qwen-code/pull/8991
* feat(core): declare create_sub_session only under qwen serve by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/9425
* fix(core): report remaining background agents by @tao943 in https://github.com/QwenLM/qwen-code/pull/9018
* fix(core): cap the effort tier at what each endpoint accepts by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/9501
* fix(cli): probe microphone permission on recording start, not voice warmup by @Nas01010101 in https://github.com/QwenLM/qwen-code/pull/8912
* fix(core): detect long verbatim repetition loops in content and reasoning streams by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9668
* feat(scheduled-tasks): allow creating a task with an existing session by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9361
* docs(agent): clarify parameter preconditions by @tao943 in https://github.com/QwenLM/qwen-code/pull/9580
* fix(review): pin the verified git identity across the residue probe (#9557) by @wenshao in https://github.com/QwenLM/qwen-code/pull/9742
* fix(core): surface nested sub-agent approvals under background parents by @wenshao in https://github.com/QwenLM/qwen-code/pull/9793
* fix(core): mark agent launch failures as failed tool calls by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9519
* refactor(goal): render Goal continuation prompts from one core renderer by @qqqys in https://github.com/QwenLM/qwen-code/pull/9581
* fix(core): avoid ghost shutdown pending state by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9550
* fix(core): isolate fork cache readers by session by @tomsen02 in https://github.com/QwenLM/qwen-code/pull/9471
* refactor(review): split SKILL.md into a core body plus verdict-gated reference files by @wenshao in https://github.com/QwenLM/qwen-code/pull/9804
* feat(web-shell): compact agent activity summaries by @ytahdn in https://github.com/QwenLM/qwen-code/pull/9657
* feat(auth): add Kimi (Moonshot AI) as a built-in third-party provider by @TianYuan1024 in https://github.com/QwenLM/qwen-code/pull/9814
* fix(goal): count catalog previews in the unit their budget is written in by @qqqys in https://github.com/QwenLM/qwen-code/pull/9835
* feat(core): show what a workflow will do, and scope the grant that approves it by @qqqys in https://github.com/QwenLM/qwen-code/pull/9837
* feat(web-shell): expose agent task changes by @callmeYe in https://github.com/QwenLM/qwen-code/pull/9637
* fix(cli): skip terminal redraw optimizer on WSL/ConPTY by @C0d3N1nja97342 in https://github.com/QwenLM/qwen-code/pull/7897
* chore(ci): refresh the core issue-owner pool by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9808
* fix(core): invalidate token counts recorded for a switched model route by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9506
* fix(daemon): Bound conditional-close refusal holds by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9820
* fix(core): allow hook-bounced workflow reapproval by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9547
* docs(vscode): correct minimum VS Code version by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9852
* fix(core): route debug logs through sessionIdContext before global session by @tomsen02 in https://github.com/QwenLM/qwen-code/pull/9538
* feat(web-shell): add async submit preparation by @dreamWB in https://github.com/QwenLM/qwen-code/pull/9802
* fix(core): support per-provider stream idle timeout by @yu-xin-c in https://github.com/QwenLM/qwen-code/pull/9795
* feat(core): add the output-style layer to the system prompt by @qqqys in https://github.com/QwenLM/qwen-code/pull/9565
* fix(memory): scan uncapped when selecting forget candidates by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/9530
* feat(serve): add --open-with-auth by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9738
* fix(core): make team shutdown a leader-only tool by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9401
* feat(vscode-ide-companion): adopt WebShell transcript as the default timeline by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9719
* refactor(core): make utils/ a leaf layer by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9778
* refactor: centralize approval mode contracts by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9796
* refactor(core): make derived Config ownership explicit by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/8100
* test(acp-cron): kill whole process tree on cleanup to stop ENOTEMPTY flakes by @dream-creator in https://github.com/QwenLM/qwen-code/pull/9815
* refactor(core): shrink the content generator interface by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/9676
* fix(ci): move undeletable workspace residue aside instead of leaving it by @wenshao in https://github.com/QwenLM/qwen-code/pull/9868
* fix(serve): Canonicalize Live task bridge session IDs by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9819
* test(core): align lazy generator vertex test by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9888
* fix(core): map OpenAI-compatible finish_reason case-insensitively by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9884
* feat(computer-use): replace built-in tools with bundled skill by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/9856
* feat(review): promote language-pitfall and wrapper/proxy checks out of Agent 1a by @wenshao in https://github.com/QwenLM/qwen-code/pull/9805
* fix(core): accept quiet post-tool-result completions after retry exhaustion by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/9196
* feat(review): say when the approach, not the patch, is the open question by @qqqys in https://github.com/QwenLM/qwen-code/pull/9340
* feat(skills): add find-simplifications sweep skill by @qqqys in https://github.com/QwenLM/qwen-code/pull/9384
* docs(core): fix goal judge timeout unit by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9861
* docs(core): fix read file paging default comment by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9863
* docs(sdk): fix query timeout example signature by @AaronZ345 in https://github.com/QwenLM/qwen-code/pull/9867
* fix(config): accept output.format "stream-json" in the settings schema by @harjothkhara in https://github.com/QwenLM/qwen-code/pull/8966
* fix(core): reject malformed Anthropic tool arguments by @tlysanhuo in https://github.com/QwenLM/qwen-code/pull/9013
* fix(ci): narrow serve-ab's self-hosted wipe to the A/B checkout dirs by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/9228
* fix(acp-bridge): Disable permission timeout by default by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/9933
* test(cli): skip unreadable-ledger run-ledger test under root by @wenshao in https://github.com/QwenLM/qwen-code/pull/9913
* fix(core): relax uniqueItems in function schemas by @qqqys in https://github.com/QwenLM/qwen-code/pull/9869
* fix(goal): converge the three continuation prompts on one guarded contract by @qqqys in https://github.com/QwenLM/qwen-code/pull/9834
* feat(core): require an explicit user opt-in before the model launches a workflow by @qqqys in https://github.com/QwenLM/qwen-code/pull/9806
## New Contributors
* @cactuser-Lu made their first contribution in https://github.com/QwenLM/qwen-code/pull/9457
* @axiom-of-choice made their first contribution in https://github.com/QwenLM/qwen-code/pull/9017
* @zhou2024NAU made their first contribution in https://github.com/QwenLM/qwen-code/pull/9779
* @octo-patch made their first contribution in https://github.com/QwenLM/qwen-code/pull/8322
* @yefuyou made their first contribution in https://github.com/QwenLM/qwen-code/pull/8953
* @tao943 made their first contribution in https://github.com/QwenLM/qwen-code/pull/9018
* @AaronZ345 made their first contribution in https://github.com/QwenLM/qwen-code/pull/9550
* @yu-xin-c made their first contribution in https://github.com/QwenLM/qwen-code/pull/9795
* @dream-creator made their first contribution in https://github.com/QwenLM/qwen-code/pull/9815
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.22.0...v0.22.0-nightly.20260825.22bb5e8b9f