## 更新内容
* feat(cli): 中日韩文字分词与 Ctrl+方向键导航优化 by @Apophis3158 在 https://github.com/QwenLM/qwen-code/pull/2942
* fix(vscode): 在新会话操作中强制创建全新的 ACP 会话 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/2874
* feat: 在 /settings 中将快速模型的文本输入替换为模型选择器 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3120
* feat: 在 /settings 对话框中显示当前激活设置的说明 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3116
* fix(cli): 优先处理斜杠命令补全 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/3104
* feat(i18n): 新增法语 (fr-FR) 本地化支持 by @sibylassana95 在 https://github.com/QwenLM/qwen-code/pull/3126
* fix(cli): 改进终端中 Markdown 表格的渲染 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/2914
* fix: 防止状态栏脚本损坏 settings.json by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3091
* fix(cli): 在 TextInput 多行模式中提交前检查换行符 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3094
* fix(input): 保留粘贴内容中的制表符 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3045
* fix: 恢复时使用最新的助手 token 计数而非过期的压缩检查点 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3109
* fix: 升级 normalize-package-data 至 7.0.1（修复 DEP0169 警告） by @evan70 在 https://github.com/QwenLM/qwen-code/pull/2865
* feat(cli): 输入编辑队列 — 通过 ↑/ESC 弹出队列消息进行编辑 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/2871
* fix(core): 将递归文件爬虫上限设为 10 万条以防止内存溢出 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3138
* fix(channels): 将代理设置应用于通道启动命令 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3136
* fix: 延迟加载通道插件以消除 DEP0040 启动警告 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3134
* fix(core): 当 IDE 差异对比打开失败时回退至 CLI 确认 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/3031
* fix(core): 处理 OAuth 刷新响应体为空的情况 by @B-A-M-N 在 https://github.com/QwenLM/qwen-code/pull/3123
* fix(followup): 修复在 OpenAI 兼容提供商上后续建议不生效的问题 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3151
* feat(channels): 在 TelegramAdapter 中新增语音消息支持 by @feyclaw 在 https://github.com/QwenLM/qwen-code/pull/3150
* feat(cli): 在设置中支持 tools.sandboxImage by @doudouOUC 在 https://github.com/QwenLM/qwen-code/pull/3146
* feat(cli): 当工作区覆盖全局 modelProviders 时发出警告 by @doudouOUC 在 https://github.com/QwenLM/qwen-code/pull/3148
* feat(hooks): 新增 StopFailure 和 PostCompact 钩子事件 by @DennisYu07 在 https://github.com/QwenLM/qwen-code/pull/2825
* feat(core): 基于 Kind 的批处理与 Shell 只读检测的智能工具并行执行 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/2864
* docs(readme): 新增关于 Qwen OAuth 免费套餐策略调整的说明 by @pomelo-nwu 在 https://github.com/QwenLM/qwen-code/pull/3207
* fix(cli): 恢复卡住的括号粘贴模式并保持 Ctrl+C 可用 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/3181
* chore: 移除遗留目录 (.gcp, .aoneci, hello, .allstar) by @pomelo-nwu 在 https://github.com/QwenLM/qwen-code/pull/3199
* refactor: 将 test-utils 包合并至 core by @pomelo-nwu 在 https://github.com/QwenLM/qwen-code/pull/3200
* fix(cli): 将 qwen3.5-plus 设为 Coding Plan 的默认模型 by @pomelo-nwu 在 https://github.com/QwenLM/qwen-code/pull/3193
* ci(release): 并行化发布验证流程 by @yiliang114 在 https://github.com/QwenLM/qwen-code/pull/3132
* feat: 新增具备响应后上下文感知能力的上下文提示系统 by @wenshao 在 https://github.com/QwenLM/qwen-code/pull/2904
* feat(subagents): 将审批模式传递给子代理 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3066
* fix(core): 在 @file 注入路径中遵守 respectGitIgnore 设置 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3197
* feat(skills): 通过 skill frontmatter 新增模型覆盖支持 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/2949
* fix(core): 当 MCP 服务器 cwd 不存在时显示明确错误 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3192
* fix(cli): 在非交互式身份验证验证中遵循 --openai-api-key by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3187
* chore: 将版本提升至 0.14.4 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3209
* fix(cli): 取消时停止用之前的提示词重新填充输入 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3208
* feat(cli): 支持 bare exit/quit 命令退出 CLI by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3201
* feat(subagents): 在代理定义中新增 disallowedTools 字段 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3064
* fix(core): 允许代理名称中包含 Unicode 字符 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3194
* feat(core): 新增微压缩功能以清理空闲上下文 by @tanzhenxin 在 https://github.com/QwenLM/qwen-code/pull/3006
## 新增贡献者
* @Apophis3158 在 https://github.com/QwenLM/qwen-code/pull/2942 完成了首次贡献
* @sibylassana95 在 https://github.com/QwenLM/qwen-code/pull/3126 完成了首次贡献
* @evan70 在 https://github.com/QwenLM/qwen-code/pull/2865 完成了首次贡献
* @B-A-M-N 在 https://github.com/QwenLM/qwen-code/pull/3123 完成了首次贡献
* @feyclaw 在 https://github.com/QwenLM/qwen-code/pull/3150 完成了首次贡献
**完整更新日志**: https://github.com/QwenLM/qwen-code/compare/v0.14.3...v0.14.4-preview.0
## What's Changed
* feat(cli): CJK word segmentation and Ctrl+arrow navigation optimization by @Apophis3158 in https://github.com/QwenLM/qwen-code/pull/2942
* fix(vscode): force fresh ACP session on new-session action by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/2874
* feat: replace text input with model picker for Fast Model in /settings by @wenshao in https://github.com/QwenLM/qwen-code/pull/3120
* feat: show description for active setting in /settings dialog by @wenshao in https://github.com/QwenLM/qwen-code/pull/3116
* fix(cli): prioritize slash command completions by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3104
* feat(i18n): add French (fr-FR) locale support by @sibylassana95 in https://github.com/QwenLM/qwen-code/pull/3126
* fix(cli): improve markdown table rendering in terminal by @wenshao in https://github.com/QwenLM/qwen-code/pull/2914
* fix: prevent statusline script from corrupting settings.json by @wenshao in https://github.com/QwenLM/qwen-code/pull/3091
* fix(cli): check NEWLINE before SUBMIT in TextInput multiline mode by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3094
* fix(input): preserve tab characters in pasted content by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3045
* fix: use latest assistant token count on resume instead of stale compression checkpoint by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3109
* fix: upgrade normalize-package-data to 7.0.1 (fixes DEP0169 warning) by @evan70 in https://github.com/QwenLM/qwen-code/pull/2865
* feat(cli): queue input editing — pop queued messages for editing via ↑/ESC by @wenshao in https://github.com/QwenLM/qwen-code/pull/2871
* fix(core): cap recursive file crawler at 100k entries to prevent OOM by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3138
* fix(channels): apply proxy settings to channel start command by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3136
* fix: lazy-load channel plugins to eliminate DEP0040 startup warning by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3134
* fix(core): fall back to CLI confirmation when IDE diff open fails by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3031
* fix(core): handle empty OAuth refresh response body by @B-A-M-N in https://github.com/QwenLM/qwen-code/pull/3123
* fix(followup): fix follow-up suggestions not working on OpenAI-compatible providers by @wenshao in https://github.com/QwenLM/qwen-code/pull/3151
* feat(channels): add voice message support in TelegramAdapter by @feyclaw in https://github.com/QwenLM/qwen-code/pull/3150
* feat(cli): support tools.sandboxImage in settings by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3146
* feat(cli): warn when workspace overrides global modelProviders by @doudouOUC in https://github.com/QwenLM/qwen-code/pull/3148
* feat(hooks): Add StopFailure and PostCompact hook events by @DennisYu07 in https://github.com/QwenLM/qwen-code/pull/2825
* feat(core): intelligent tool parallelism with Kind-based batching and shell read-only detection by @wenshao in https://github.com/QwenLM/qwen-code/pull/2864
* docs(readme): Add announcement for Qwen OAuth free tier policy adjustment by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3207
* fix(cli): recover from stuck bracketed-paste mode and keep Ctrl+C reachable by @wenshao in https://github.com/QwenLM/qwen-code/pull/3181
* chore: remove legacy directories (.gcp, .aoneci, hello, .allstar) by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3199
* refactor: merge test-utils package into core by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3200
* fix(cli): set qwen3.5-plus as default model for Coding Plan by @pomelo-nwu in https://github.com/QwenLM/qwen-code/pull/3193
* ci(release): parallelize release validation by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/3132
* feat: add contextual tips system with post-response context awareness by @wenshao in https://github.com/QwenLM/qwen-code/pull/2904
* feat(subagents): propagate approval mode to sub-agents by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3066
* fix(core): respect respectGitIgnore setting in @file injection path by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3197
* feat(skills): add model override support via skill frontmatter by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/2949
* fix(core): show clear error when MCP server cwd does not exist by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3192
* fix(cli): honor --openai-api-key in non-interactive auth validation by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3187
* chore: bump version to 0.14.4 by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3209
* fix(cli): stop refilling input with prior prompt on cancel by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3208
* feat(cli): support bare exit/quit commands to exit the CLI by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3201
* feat(subagents): add disallowedTools field to agent definitions by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3064
* fix(core): allow Unicode characters in agent names by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3194
* feat(core): add microcompaction for idle context cleanup by @tanzhenxin in https://github.com/QwenLM/qwen-code/pull/3006
## New Contributors
* @Apophis3158 made their first contribution in https://github.com/QwenLM/qwen-code/pull/2942
* @sibylassana95 made their first contribution in https://github.com/QwenLM/qwen-code/pull/3126
* @evan70 made their first contribution in https://github.com/QwenLM/qwen-code/pull/2865
* @B-A-M-N made their first contribution in https://github.com/QwenLM/qwen-code/pull/3123
* @feyclaw made their first contribution in https://github.com/QwenLM/qwen-code/pull/3150
**Full Changelog**: https://github.com/QwenLM/qwen-code/compare/v0.14.3...v0.14.4-preview.0