## 更新内容
* chore(release): v0.15.9 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/3971
* fix(cli): 验证 /model 命令参数 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3963
* fix(core): 记录实际发送的 OpenAI 请求 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3767
* fix(core): 从健康状态注册表中移除已禁用的 MCP 服务器 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/3916
* test(cli): 移除依赖等待的 SessionPicker 搜索测试（关闭 #3977） by @qqqys in https://github.com/QwenLM/qwen-code/pull/3978
* feat(core): 在上下文溢出时添加响应式压缩 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3879
* fix(core): 在请求边界处过滤 Mistral 推理内容 by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/3882
* fix(cli): 在迁移回写期间保留 settings.json 中的注释和格式 by @B-A-M-N in https://github.com/QwenLM/qwen-code/pull/3861
* [codex] 修复子代理的监控通知 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3933
* feat(memory): 添加 autoSkill 后台项目技能提取 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/3673
* feat(cli): 改进斜杠命令发现机制 by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/3736
* fix(cli): 在长对话中解冻 Ctrl+O 紧凑模式切换 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3905
* feat(core): 支持 QWEN_HOME 环境变量以自定义配置目录 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/2953
* feat(vscode): 添加消息编辑/回退和消息元数据 UI by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3762
* fix(cli): 在调整大小时用定向重绘替换 clearTerminal by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3967
* feat(telemetry) 在 UI 中屏蔽 OpenTelemetry 诊断信息 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3986
* fix(core): 增强响应式压缩后续处理 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3985
* fix(core): 限制 shell 工具实时文本更新频率 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3902
* feat: 添加 /diff 命令和 git diff 统计工具 by @BZ-D in https://github.com/QwenLM/qwen-code/pull/3491
* fix(core): 统一 Edit/WriteFile 预读取逻辑以匹配 Claude Code；关闭 #3964 + #3945 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4002
* feat(tools): 添加 ToolSearch 以按需加载延迟的工具模式 by @wenshao in https://github.com/QwenLM/qwen-code/pull/3589
**完整更新日志**: https://github.com/QwenLM/qwen-code/compare/v0.15.9...v0.15.10
## What's Changed
* chore(release): v0.15.9 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/3971
* fix(cli): validate /model command arguments by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3963
* fix(core): log the OpenAI request actually sent on the wire by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3767
* fix(core): drop disabled MCP server from health status registry by @BZ-D in https://github.com/QwenLM/qwen-code/pull/3916
* test(cli): drop wait-dependent SessionPicker search tests (closes #3977) by @qqqys in https://github.com/QwenLM/qwen-code/pull/3978
* feat(core): add reactive compression on context overflow by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3879
* fix(core): filter Mistral reasoning content at request boundary by @cyphercodes in https://github.com/QwenLM/qwen-code/pull/3882
* fix(cli): preserve comments and formatting in settings.json during migration write-back by @B-A-M-N in https://github.com/QwenLM/qwen-code/pull/3861
* [codex] fix monitor notifications for subagents by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3933
* feat(memory): add autoSkill background project skill extraction by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/3673
* feat(cli): improve slash command discovery by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/3736
* fix(cli): unfreeze Ctrl+O compact-mode toggle on long conversations by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3905
* feat(core): support QWEN_HOME env var to customize config directory by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/2953
* feat(vscode): add message edit/rewind and message metadata UI by @DragonnZhang in https://github.com/QwenLM/qwen-code/pull/3762
* fix(cli): replace clearTerminal with targeted repaint on resize by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3967
* feat(telemetry) suppress OpenTelemetry diagnostics from UI by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3986
* fix(core): harden reactive compression follow-ups by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3985
* fix(core): throttle shell tool live text updates by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3902
* feat: add /diff command and git diff statistics utility by @BZ-D in https://github.com/QwenLM/qwen-code/pull/3491
* fix(core): unify Edit/WriteFile prior-read with Claude Code; close #3964 + #3945 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4002
* feat(tools): add ToolSearch for on-demand loading of deferred tool schemas by @wenshao in https://github.com/QwenLM/qwen-code/pull/3589
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.15.9...v0.15.10