Qwen Code v0.24.7-nightly.20261002.a011f66944

## 变更内容 * fix(core)：使 Code Mode 文本与延迟工具发现机制保持一致，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/12990 * fix(permissions)：遵循已批准的跨目录工具调用，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/12987 * fix(cli)：在加载补全建议时不再吞掉 Enter 键（#13015），由 @qwen-code-dev-bot 提交，详见 https://github.com/QwenLM/qwen-code/pull/13021 * fix(cli)：将守护进程扩展设置的加载与共享进程状态隔离，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13022 * test(managed-agent)：记录 Hosted 延迟基线，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12945 * feat(agents)：添加本地 workspace-agent 协作，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/11206 * feat(serve)：实现通用 Broker 提供商控制，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12868 * feat(managed-agent)：启用 G0 公共 Workspace 文件轮次，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12955 * fix(serve)：以 512 KiB 分块上传会话附件，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/12923 * test(managed-agent)：固定 M4 关闭锚点和已发布的定义（M4 后续），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12995 * fix(cli)：限制重新启动的子进程在其监督进程退出后的存活时间，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13036 * test(managed-agent)：约束提供商重试和释放顺序，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13061 * test(managed-agent)：在轮次认领测试中避免与恢复扫描器发生竞态，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13032 * fix(core)：使用情况统计 RUM 上传遵循 NO_PROXY，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13023 * fix(runtime-broker)：当提供商拒绝启动时返回 unknown，而不是 prepared，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13064 * fix(runtime-broker)：当原始 Runtime 无法响应时保留 UNKNOWN 答复，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13069 * feat(sdk-java)：添加经过审计的 Hosted Workspace 操作员恢复机制，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/12977 * fix(workflow)：尽早拒绝不支持的脚本和过大的批次，由 @qqqys 提交，详见 https://github.com/QwenLM/qwen-code/pull/13012 * fix(hooks)：将工具执行前和 ACP 失败上下文传递给模型，由 @qqqys 提交，详见 https://github.com/QwenLM/qwen-code/pull/13006 * fix(core)：从 ACP 回退序号中排除已送达的通知轮次，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13029 * fix(core)：扩展生命周期事件遵循使用情况统计退出选项，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12789 * feat(memory)：将 Mem0 与主 CLI 捆绑，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12891 * feat(agents)：为 workspace agents 添加 A2A 访问和共享功能，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12851 * feat(managed-agent)：请求 Hosted 工具批准（D6a），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13071 * fix(web-shell)：防止统计信息标题重叠和原始 JSON 输出，由 @qqqys 提交，详见 https://github.com/QwenLM/qwen-code/pull/13091 * fix(managed-agent)：确定任务事件和取消语义，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12998 * fix(managed-agent)：保护排队中的 Hosted 批准免于过期问题影响，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13098 * feat(managed-agent)：添加持久化的远程 Shell 结果交付，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/12894 * feat(managed-agent)：实现私有 Hosted MCP 运行时（H1），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12946 * perf(sdk-java)：将 runtime broker JSON 直接序列化为字节，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13108 * test(cli)：为结算重试的 waitFor 设置显式超时（#13034），由 @qwen-code-dev-bot 提交，详见 https://github.com/QwenLM/qwen-code/pull/13058 * test(managed-agent)：明确哪些协调器拒绝路径是真实存在的，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13099 * docs(managed-agent)：在 E2E README 中注明真实的 worker 入口，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13093 * feat(managed-agent)：提供持久化权限操作（D6b），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13101 * test(managed-agent)：完成 G0 准入后续事项，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13095 * fix(web-shell)：保留大型上下文使用情况快照，由 @qqqys 提交，详见 https://github.com/QwenLM/qwen-code/pull/13097 * fix(managed-agent)：完善租户作用域的 403 契约，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13117 * feat(managed-agent)：添加经过验证的 W1a Workspace 冷恢复，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13088 * feat(web-shell)：添加可折叠的轨迹瀑布图，由 @qqqys 提交，详见 https://github.com/QwenLM/qwen-code/pull/13081 * test(managed-agent)：固定提供商控制拒绝保护逻辑，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13118 * fix(managed-agent)：恢复 Hosted MCP 释放重试，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13109 * fix(managed-agent)：通过有界验证从发布过期中恢复，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13114 * test(core)：在不移除测试的情况下压缩 Core 测试套件，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/13007 * fix(cli)：发布设置时不再出现文件缺失窗口期，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13119 * fix(web-shell)：将内联标签注解保持在标签的实际范围内，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12992 * fix(cli)：持久化计划中的 cron 提示词，由 @XIQIXIQIXIQI 提交，详见 https://github.com/QwenLM/qwen-code/pull/8838 * test(managed-agent)：覆盖 G0 启动和缓存的拒绝响应，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13116 * test(managed-agent)：完善 actor 作用域失败诊断，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13127 * feat(managed-agent)：将持久化工具结果映射到 WebShell，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13037 * test(core)：在召回扫描延迟门禁中将 GitHub 托管的执行通道视为共享通道，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13094 * feat(managed-agent)：在私有 ACP 子进程中托管 Managed 会话（M2），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13131 * feat(managed-agent)：添加托管文件历史记录和撤销功能，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13110 * fix(runtime-broker)：在丢失清理期间续订恢复认领（#13017），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13115 * test(integration)：消除提供商延迟导致的监控工具调用 E2E 测试不稳定问题（#13001），由 @qwen-code-dev-bot 提交，详见 https://github.com/QwenLM/qwen-code/pull/13005 * test(integration)：在向 ACP 子进程发送 SIGKILL 之前订阅会话事件流（#12925），由 @qwen-code-dev-bot 提交，详见 https://github.com/QwenLM/qwen-code/pull/12930 * test(integration)：默认在 E2E 测试框架中禁用 Managed 自动记忆（#13009），由 @qwen-code-dev-bot 提交，详见 https://github.com/QwenLM/qwen-code/pull/13013 * test(managed-agent)：补齐 H0b 记录夹具的缺口，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13120 * fix(core,cli)：限制捆绑技能列表的开销；在没有提供商总数时移除 OpenTUI 的分类标题，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13159 * feat(web-shell)：在 Managed 面板中显示并响应 Hosted 工具批准，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13107 * fix(core)：在提醒行中加入延迟工具选择规则，并为 tool_call 添加已审核 schema 门禁，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13020 * feat(managed-agent)：添加 Hosted Turn 接管和 G1 故障转移 E2E，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13083 * feat(core)：在 Code Mode 中支持 Freeform 输入，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/13150 * fix(core)：使 exec 输出与 Codex 保持一致，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/13153 * feat(managed-agent)：实现持久化 Hosted Hooks（H2），由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13129 * feat(core)：允许在 Code Mode 中并发调用 Bash，由 @tanzhenxin 提交，详见 https://github.com/QwenLM/qwen-code/pull/13151 * fix(managed-hooks)：限制 Hook 准入和冷恢复成本，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13136 * chore：移除会隐藏 web-shell 源文件的未锚定 `workspace/` 忽略规则，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13155 * feat(managed-agent)：保护会话所有的工具输出退役流程，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13084 * fix(serve)：准确报告 Hosted Hook 拒绝和冲突，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13137 * fix(managed-agent)：验证撤销回执并公开备份限制，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13144 * fix(ci)：稳定托管浏览器冒烟测试门禁，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13172 * ci(sdk-java)：确保 Flyway 版本唯一性并监控主分支失败的运行，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/12965 * feat(managed-agent)：添加离线 W1b 恢复包，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13138 * fix(web-shell)：防止内存面板替换其无法读取的全局 QWEN.md，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13154 * feat(managed-agent)：可靠地关闭绑定到 Workspace 的会话，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13135 * fix(managed-agent)：将会话关闭迁移重新编号为 V32，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13223 * fix(web)：将快速模型固定到所选的提供商端点，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13227 * feat(core)：从 models.dev 目录解析模型限制和模态，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/11959 * fix(web-shell)：不再向查看者提供其无法响应的 Managed 批准请求，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13165 * feat(agents)：添加隔离的远程 Qwen 运行时主机，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12582 * feat(managed-agent)：存储不可变的 AgentDefinition 修订版本（阶段 D8a），由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/13142 * test(managed-agent)：在 ManagedEventReplayTest 中禁用 MockMvc 结果打印，由 @wenshao 提交，详见 https://github.com/QwenLM/qwen-code/pull/13229 * fix(web-shell)：离线重试时保留身份验证片段，由 @jabrailkhalil 提交，详见 https://github.com/QwenLM/qwen-code/pull/13176 * fix(core)：允许工作流元数据声明前存在前导注释（#12217），由 @holny 提交，详见 https://github.com/QwenLM/qwen-code/pull/12651 * fix(cli)：剪贴板粘贴不可用时使用 Linux 专属提示消息（#12504），由 @holny 提交，详见 https://github.com/QwenLM/qwen-code/pull/12507 * feat(managed-agent)：归档并删除已关闭的 Workspace 会话，由 @doudouOUC 提交，详见 https://github.com/QwenLM/qwen-code/pull/13194 * fix(core)：不再将格式错误的工具调用参数误诊为 max_tokens 截断，由 @yiliang114 提交，详见 https://github.com/QwenLM/qwen-code/pull/12982 * test(core)：在单元测试层面固定 CodeModeOnly 桥接行为，由 @waybarrios 提交，详见 https://github.com/QwenLM/qwen-code/pull/12497 ## 新贡献者 * @waybarrios 在 https://github.com/QwenLM/qwen-code/pull/12497 中完成了首次贡献 **完整变更日志**：https://github.com/QwenLM/qwen-code/compare/v0.24.7...v0.24.7-nightly.20261002.a011f66944

## What's Changed * fix(core): align Code Mode text with lazy tool discovery by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/12990 * fix(permissions): honor approved cross-directory tool calls by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/12987 * fix(cli): stop swallowing Enter while completion suggestions load (#13015) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/13021 * fix(cli): isolate daemon extension settings loads from shared process state by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13022 * test(managed-agent): record Hosted latency baseline by @wenshao in https://github.com/QwenLM/qwen-code/pull/12945 * feat(agents): add local workspace-agent collaboration by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11206 * feat(serve): implement generic Broker provider controls by @wenshao in https://github.com/QwenLM/qwen-code/pull/12868 * feat(managed-agent): enable G0 public Workspace file turns by @wenshao in https://github.com/QwenLM/qwen-code/pull/12955 * fix(serve): upload session attachments in 512 KiB chunks by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/12923 * test(managed-agent): Pin M4 close anchors and the published definition (M4 follow-up) by @wenshao in https://github.com/QwenLM/qwen-code/pull/12995 * fix(cli): Bound how long a relaunched child outlives its supervisor by @wenshao in https://github.com/QwenLM/qwen-code/pull/13036 * test(managed-agent): gate provider retries and release ordering by @wenshao in https://github.com/QwenLM/qwen-code/pull/13061 * test(managed-agent): stop racing the recovery scanner in turn-claim tests by @wenshao in https://github.com/QwenLM/qwen-code/pull/13032 * fix(core): honor NO_PROXY for usage-statistics RUM uploads by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13023 * fix(runtime-broker): answer a refused provider start as unknown instead of prepared by @wenshao in https://github.com/QwenLM/qwen-code/pull/13064 * fix(runtime-broker): keep the UNKNOWN answer when the original Runtime cannot answer by @wenshao in https://github.com/QwenLM/qwen-code/pull/13069 * feat(sdk-java): Add audited Hosted Workspace operator recovery by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/12977 * fix(workflow): reject unsupported scripts and oversized batches early by @qqqys in https://github.com/QwenLM/qwen-code/pull/13012 * fix(hooks): deliver pre-tool and ACP failure context to the model by @qqqys in https://github.com/QwenLM/qwen-code/pull/13006 * fix(core): keep delivered notification turns out of ACP rewind ordinals by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13029 * fix(core): honor usage-statistics opt-out for extension lifecycle events by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12789 * feat(memory): bundle Mem0 with the main CLI by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12891 * feat(agents): add A2A access and sharing for workspace agents by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12851 * feat(managed-agent): ask for Hosted tool approvals (D6a) by @wenshao in https://github.com/QwenLM/qwen-code/pull/13071 * fix(web-shell): prevent stats header overlap and raw JSON output by @qqqys in https://github.com/QwenLM/qwen-code/pull/13091 * fix(managed-agent): Settle task event and cancel semantics by @wenshao in https://github.com/QwenLM/qwen-code/pull/12998 * fix(managed-agent): guard queued Hosted approval expiry by @wenshao in https://github.com/QwenLM/qwen-code/pull/13098 * feat(managed-agent): Add durable remote Shell result delivery by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/12894 * feat(managed-agent): Implement private Hosted MCP runtime (H1) by @wenshao in https://github.com/QwenLM/qwen-code/pull/12946 * perf(sdk-java): Serialize runtime broker JSON directly to bytes by @wenshao in https://github.com/QwenLM/qwen-code/pull/13108 * test(cli): give the settlement retry waitFors an explicit timeout (#13034) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/13058 * test(managed-agent): state which coordinator refusal paths are real by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13099 * docs(managed-agent): name the real worker entry in the E2E README by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13093 * feat(managed-agent): Serve durable permission Actions (D6b) by @wenshao in https://github.com/QwenLM/qwen-code/pull/13101 * test(managed-agent): close the G0 admission follow-ups by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13095 * fix(web-shell): preserve large context usage snapshots by @qqqys in https://github.com/QwenLM/qwen-code/pull/13097 * fix(managed-agent): Complete tenant scope 403 contract by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13117 * feat(managed-agent): add verified W1a workspace cold restore by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13088 * feat(web-shell): add a collapsible trajectory waterfall by @qqqys in https://github.com/QwenLM/qwen-code/pull/13081 * test(managed-agent): Pin provider control refusal guards by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13118 * fix(managed-agent): Recover Hosted MCP release retries by @wenshao in https://github.com/QwenLM/qwen-code/pull/13109 * fix(managed-agent): Recover publication expiry with bounded verification by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13114 * test(core): compress the Core test suite without removing tests by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/13007 * fix(cli): Publish settings without a missing-file window by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13119 * fix(web-shell): keep inline chip annotations on the chip's real range by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12992 * fix(cli): persist scheduled cron prompts by @XIQIXIQIXIQI in https://github.com/QwenLM/qwen-code/pull/8838 * test(managed-agent): Cover G0 startup and cached refusals by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13116 * test(managed-agent): finish actor-scope failure diagnostics by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13127 * feat(managed-agent): project durable tool results to WebShell by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13037 * test(core): treat GitHub-hosted lanes as shared in the recall scan latency gate by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13094 * feat(managed-agent): Host Managed sessions in a private ACP child (M2) by @wenshao in https://github.com/QwenLM/qwen-code/pull/13131 * feat(managed-agent): Add hosted file history and undo by @wenshao in https://github.com/QwenLM/qwen-code/pull/13110 * fix(runtime-broker): renew the recovery claim through lost cleanup (#13017) by @wenshao in https://github.com/QwenLM/qwen-code/pull/13115 * test(integration): deflake the monitor tool call E2E against provider latency (#13001) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/13005 * test(integration): subscribe to the session event stream before SIGKILLing the ACP child (#12925) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/12930 * test(integration): disable managed auto-memory by default in E2E harnesses (#13009) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/13013 * test(managed-agent): Close H0b record fixture gaps by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13120 * fix(core,cli): budget the bundled skill listing; drop OpenTUI's category heading without a provider total by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13159 * feat(web-shell): show and answer Hosted tool approvals in the Managed panel by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13107 * fix(core): deferred-tool selection rules in the reminder line and a reviewed-schema gate for tool_call by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13020 * feat(managed-agent): Hosted Turn takeover and G1 failover E2E by @wenshao in https://github.com/QwenLM/qwen-code/pull/13083 * feat(core): support Freeform input in Code Mode by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/13150 * fix(core): align exec output with Codex by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/13153 * feat(managed-agent): implement durable Hosted Hooks (H2) by @wenshao in https://github.com/QwenLM/qwen-code/pull/13129 * feat(core): allow concurrent Bash calls in Code Mode by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/13151 * fix(managed-hooks): bound Hook admission and cold restore cost by @wenshao in https://github.com/QwenLM/qwen-code/pull/13136 * chore: drop the unanchored workspace/ ignore rule that hides web-shell sources by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13155 * feat(managed-agent): Protect Session-owned tool output retirement by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13084 * fix(serve): Report Hosted Hook denials and conflicts accurately by @wenshao in https://github.com/QwenLM/qwen-code/pull/13137 * fix(managed-agent): Validate undo receipts and disclose backup limits by @wenshao in https://github.com/QwenLM/qwen-code/pull/13144 * fix(ci): stabilize hosted browser smoke gates by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13172 * ci(sdk-java): guard Flyway version uniqueness and watch red main runs by @wenshao in https://github.com/QwenLM/qwen-code/pull/12965 * feat(managed-agent): Add offline W1b recovery bundles by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13138 * fix(web-shell): stop the memory panel replacing a global QWEN.md it could not read by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13154 * feat(managed-agent): reliably close workspace-bound sessions by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13135 * fix(managed-agent): renumber session-close migration to V32 by @wenshao in https://github.com/QwenLM/qwen-code/pull/13223 * fix(web): pin fast model to the selected provider endpoint by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13227 * feat(core): resolve model limits and modalities from a models.dev catalog by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11959 * fix(web-shell): stop offering a Managed approval the viewer cannot answer by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13165 * feat(agents): add isolated remote Qwen runtime hosts by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12582 * feat(managed-agent): store immutable AgentDefinition revisions (Stage D8a) by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/13142 * test(managed-agent): Disable MockMvc result printing in ManagedEventReplayTest by @wenshao in https://github.com/QwenLM/qwen-code/pull/13229 * fix(web-shell): preserve authentication fragment on offline retry by @jabrailkhalil in https://github.com/QwenLM/qwen-code/pull/13176 * fix(core): allow leading comments before workflow meta declaration (#12217) by @holny in https://github.com/QwenLM/qwen-code/pull/12651 * fix(cli): use Linux-specific unavailable message for clipboard paste (#12504) by @holny in https://github.com/QwenLM/qwen-code/pull/12507 * feat(managed-agent): archive and delete closed workspace sessions by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/13194 * fix(core): stop misdiagnosing malformed tool-call args as max_tokens truncation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/12982 * test(core): pin CodeModeOnly bridge behavior at unit level by @waybarrios in https://github.com/QwenLM/qwen-code/pull/12497 ## New Contributors * @waybarrios made their first contribution in https://github.com/QwenLM/qwen-code/pull/12497 **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.24.7...v0.24.7-nightly.20261002.a011f66944

Qwen Code v0.24.7-nightly.20261002.a011f66944 预发布