## 更新内容
* chore(release): 发布 v0.15.10 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4019
* perf(core): 将会话列表元数据读取限制为头/尾 64KB；池化缓冲区；延迟消息计数 by @qqqys in https://github.com/QwenLM/qwen-code/pull/3897
* test: 稳定主测试端到端(e2e)的偶发失败问题 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3992
* feat(cli): 核心内置国际化(i18n)覆盖 by @shenyankm in https://github.com/QwenLM/qwen-code/pull/3871
* feat(core): 为活跃会话写入 runtime.json 旁路(sidecar)文件 by @yeelam-gordon in https://github.com/QwenLM/qwen-code/pull/3714
* feat(telemetry): 将 traceId/spanId 注入调试日志文件以支持 OTel 关联 by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3847
* feat(tools): 延迟加载低频内置工具以减少初始提示词大小 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4022
* ci: 跳过不必要的发布和 SDK 检查 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3984
* feat(installer): 添加独立归档安装 by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3776
* feat(cli): 添加 Ctrl+B 快捷键提升功能 (#3831 PR-3 of 3) by @wenshao in https://github.com/QwenLM/qwen-code/pull/3969
* feat(cli): 在无头(headless)模式下添加 --json-schema 以支持结构化输出 by @wenshao in https://github.com/QwenLM/qwen-code/pull/3598
* refactor(cli): 移除旧的 `qwen auth` CLI 子命令，重定向至 /auth TUI 对话框 by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3959
* chore(deps): 升级 ink 6.2.3 → 7.0.2 + 将 Node 引擎版本提升至 22 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3860
* feat(skills): 新增 codegraph 技能，用于 PR 审查的风险分析与冲突检测 by @BingqingLyu in https://github.com/QwenLM/qwen-code/pull/3910
* refactor(core): 通过 runSideQuery 瓶颈点路由 side-query LLM 调用 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3775
* feat(tools): 保持 ask_user_question 始终可见，以优化澄清交互体验 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4041
* feat(core): 提升 Anthropic 代理兼容性并启用全局提示词缓存作用域 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4020
* fix(cli): 将长模型统计信息标题保持在单行 by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4032
* refactor(telemetry): 移除废弃的 useCollector 设置及无法访问的 TelemetryTarget.QWEN by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4061
* chore(core): 针对 #3714 审查的 runtime.json sidecar 后续修复 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4030
* fix(test): 修复过时的 --json-schema 集成断言 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4075
* feat(cli): 为前缀缓存(prefix-caching)模型添加 tools.toolSearch.enabled 设置 by @wenshao in https://github.com/QwenLM/qwen-code/pull/4069
## 新贡献者
* @BingqingLyu 在 https://github.com/QwenLM/qwen-code/pull/3910 中完成了首次贡献
**完整更新日志**: https://github.com/QwenLM/qwen-code/compare/v0.15.10...v0.15.11-preview.0
## What's Changed
* chore(release): v0.15.10 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4019
* perf(core): bound session-list metadata reads to head/tail 64KB; pool buffer; lazy message count by @qqqys in https://github.com/QwenLM/qwen-code/pull/3897
* test: stabilize main e2e flakes by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3992
* feat(cli): core built-in i18n coverage by @shenyankm in https://github.com/QwenLM/qwen-code/pull/3871
* feat(core): write runtime.json sidecar for active sessions by @yeelam-gordon in https://github.com/QwenLM/qwen-code/pull/3714
* feat(telemetry): inject traceId/spanId into debug log files for OTel correlation by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3847
* feat(tools): defer low-frequency built-in tools to reduce initial prompt size by @wenshao in https://github.com/QwenLM/qwen-code/pull/4022
* ci: skip unnecessary release and SDK checks by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3984
* feat(installer): add standalone archive installation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3776
* feat(cli): Ctrl+B promote keybind (#3831 PR-3 of 3) by @wenshao in https://github.com/QwenLM/qwen-code/pull/3969
* feat(cli): add --json-schema for structured output in headless mode by @wenshao in https://github.com/QwenLM/qwen-code/pull/3598
* refactor(cli): remove legacy `qwen auth` CLI subcommand, redirect to /auth TUI dialog by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3959
* chore(deps): upgrade ink 6.2.3 → 7.0.2 + bump Node engine to 22 by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3860
* feat(skills): Add codegraph skill for PR review risk analysis and conflict detection by @BingqingLyu in https://github.com/QwenLM/qwen-code/pull/3910
* refactor(core): route side-query LLM calls through runSideQuery chokepoint by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3775
* feat(tools): keep ask_user_question always-visible to surface clarification UX by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4041
* feat(core): improve Anthropic proxy compatibility and enable global prompt cache scope by @wenshao in https://github.com/QwenLM/qwen-code/pull/4020
* fix(cli): keep long model stats header on one line by @Jerry2003826 in https://github.com/QwenLM/qwen-code/pull/4032
* refactor(telemetry): remove dead useCollector setting and unreachable TelemetryTarget.QWEN by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4061
* chore(core): runtime.json sidecar follow-ups from #3714 review by @wenshao in https://github.com/QwenLM/qwen-code/pull/4030
* fix(test): repair stale --json-schema integration assertion by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4075
* feat(cli): add tools.toolSearch.enabled setting for prefix-caching models by @wenshao in https://github.com/QwenLM/qwen-code/pull/4069
## New Contributors
* @BingqingLyu made their first contribution in https://github.com/QwenLM/qwen-code/pull/3910
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.15.10...v0.15.11-preview.0