Qwen Code v0.15.12-preview.0

## 更新内容 * feat(cli): 将 Markdown 链接包裹在 OSC 8 中，使换行后的 URL 保持可点击，由 @BZ-D 在 https://github.com/QwenLM/qwen-code/pull/4037 贡献 * fix(core): 将累积的 OpenAI 流式增量标准化为后缀，由 @chiga0 在 https://github.com/QwenLM/qwen-code/pull/3896 贡献 * fix(cli): 取消时自动恢复提示词并保留队列，由 @wenshao 在 https://github.com/QwenLM/qwen-code/pull/4023 贡献 * docs(auth): 添加自定义 API 密钥向导的产品需求文档 (PRD)，由 @pomelo-nwu 在 https://github.com/QwenLM/qwen-code/pull/3583 贡献 * feat(cli): 在 /delete 命令中支持会话批量删除，由 @qqqys 在 https://github.com/QwenLM/qwen-code/pull/3733 贡献 * feat(cli,sdk): qwen serve 守护进程（第一阶段），由 @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3889 贡献 * fix(core): 为子代理的 OpenAI JSON 日志添加标签，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4099 贡献 * feat(subagents): 为 Explore 子代理使用 fastModel，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4086 贡献 * fix(dashscope): 使用 URL 主机名检查替代正则表达式以避免 ReDoS（CodeQL），由 @qqqys 在 https://github.com/QwenLM/qwen-code/pull/4112 贡献 * fix(core): 改进运行时 fetch 选项的错误处理与文档，由 @ZevGit 在 https://github.com/QwenLM/qwen-code/pull/3997 贡献 * fix(telemetry): 处理 PR #3847 审查后续意见以完善链路追踪关联，由 @doudouOUC 在 https://github.com/QwenLM/qwen-code/pull/4058 贡献 * feat(perf): 渐进式 MCP 可用性 — MCP 不再阻塞首次输入，由 @chiga0 在 https://github.com/QwenLM/qwen-code/pull/3994 贡献 * fix(search): 使空查询退出变为同步操作，并统一 Windows 退格键行为，由 @B-A-M-N 在 https://github.com/QwenLM/qwen-code/pull/3981 贡献 * chore(release): v0.15.11 版本发布，由 @qwen-code-ci-bot 在 https://github.com/QwenLM/qwen-code/pull/4100 贡献 * fix(anthropic): 允许在 tool_result 块上使用 cache_control，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4121 贡献 * feat(core): 在对话压缩摘要前剥离内联媒体，由 @LaZzyMan 在 https://github.com/QwenLM/qwen-code/pull/4101 贡献 * ci(deps): 将 docker/* actions 升级至 Node 24 主版本（消除 GitHub Node 20 弃用警告），由 @chiga0 在 https://github.com/QwenLM/qwen-code/pull/4131 贡献 * fix(core): 将 IDE 上下文合并至用户提示词，由 @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/3980 贡献 * fix(cli): 无需重启即可将 /language 输出应用到运行中的会话，由 @chiga0 在 https://github.com/QwenLM/qwen-code/pull/4143 贡献 * feat(tools): 添加通用 worktree 支持 — EnterWorktree/ExitWorktree + 代理隔离，由 @LaZzyMan 在 https://github.com/QwenLM/qwen-code/pull/4073 贡献 * feat(cli): 将 ModelScope 添加为内置第三方 API 提供商，由 @Col0ring 在 https://github.com/QwenLM/qwen-code/pull/4150 贡献 * fix(core): 修正提示词大小与 Anthropic 缓存的上下文使用页脚，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4109 贡献 * fix(core): 支持跨认证快速侧边查询，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4117 贡献 * test(integration): 在 #4163 修复前，将 simple-mcp-server 锁定至旧版 MCP 路径，由 @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/4164 贡献 ## 新贡献者 * @ZevGit 在 https://github.com/QwenLM/qwen-code/pull/3997 完成首次贡献 * @Col0ring 在 https://github.com/QwenLM/qwen-code/pull/4150 完成首次贡献 **完整更新日志**: https://github.com/QwenLM/qwen-code/compare/v0.15.11...v0.15.12-preview.0

## What's Changed * feat(cli): wrap markdown links in OSC 8 so wrapped URLs stay clickable by @BZ-D in https://github.com/QwenLM/qwen-code/pull/4037 * fix(core): normalize cumulative OpenAI stream deltas to suffixes by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3896 * fix(cli): auto-restore prompt and preserve queue on cancel by @wenshao in https://github.com/QwenLM/qwen-code/pull/4023 * docs(auth): add custom API key wizard PRD by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3583 * feat(cli): support batch deletion of sessions in /delete by @qqqys in https://github.com/QwenLM/qwen-code/pull/3733 * feat(cli,sdk): qwen serve daemon (Stage 1) by @wenshao in https://github.com/QwenLM/qwen-code/pull/3889 * fix(core): tag subagent OpenAI JSON logs by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4099 * feat(subagents): use fastModel for Explore subagent by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4086 * fix(dashscope): use URL hostname check instead of regex to avoid ReDoS (CodeQL) by @qqqys in https://github.com/QwenLM/qwen-code/pull/4112 * fix(core): improve runtime fetch options error handling and documentation by @ZevGit in https://github.com/QwenLM/qwen-code/pull/3997 * fix(telemetry): address PR #3847 review follow-ups for trace correlation by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/4058 * feat(perf): progressive MCP availability — MCP no longer blocks first input by @chiga0 in https://github.com/QwenLM/qwen-code/pull/3994 * fix(search): make empty-query exit synchronous and normalize Windows Backspace by @B-A-M-N in https://github.com/QwenLM/qwen-code/pull/3981 * chore(release): v0.15.11 by @qwen-code-ci-bot in https://github.com/QwenLM/qwen-code/pull/4100 * fix(anthropic): allow cache_control on tool_result blocks by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4121 * feat(core): strip inline media before chat compaction summary by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4101 * ci(deps): bump docker/* actions to Node 24 majors (silences GitHub Node 20 deprecation warning) by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4131 * fix(core): merge IDE context into user prompt by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3980 * fix(cli): apply /language output to running session without restart by @chiga0 in https://github.com/QwenLM/qwen-code/pull/4143 * feat(tools): add generic worktree support — EnterWorktree/ExitWorktree + Agent isolation by @LaZzyMan in https://github.com/QwenLM/qwen-code/pull/4073 * feat(cli): add ModelScope as a built-in third-party API provider by @Col0ring in https://github.com/QwenLM/qwen-code/pull/4150 * fix(core): correct context-usage Footer for prompt size and Anthropic caches by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4109 * fix(core): support cross-auth fast side queries by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4117 * test(integration): pin simple-mcp-server to legacy MCP path until #4163 is fixed by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/4164 ## New Contributors * @ZevGit made their first contribution in https://github.com/QwenLM/qwen-code/pull/3997 * @Col0ring made their first contribution in https://github.com/QwenLM/qwen-code/pull/4150 **Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.15.11...v0.15.12-preview.0

Qwen Code v0.15.12-preview.0 预发布