🤖 Claude Code 更新 v2.1.76
发布日期: 2026-03-17
📋 版本维护
✨ 新增功能
- Added MCP elicitation support — MCP servers can now request structured input mid-task via an interactive dialog (form fields or browser URL)
- Added new
ElicitationandElicitationResulthooks to intercept and override responses before they’re sent back - Added
-n/--name <name>CLI flag to set a display name for the session at startup - Added
worktree.sparsePathssetting forclaude --worktreein large monorepos to check out only the directories you need via git sparse-checkout - Added
PostCompacthook that fires after compaction completes - Added
/effortslash command to set model effort level - Added session quality survey — enterprise admins can configure the sample rate via the
feedbackSurveyRatesetting
🐛 重要修复
- Fixed deferred tools (loaded via
ToolSearch) losing their input schemas after conversation compaction, causing array and number parameters to be rejected with type errors - Fixed slash commands showing “Unknown skill”
- Fixed plan mode asking for re-approval after the plan was already accepted
- Fixed voice mode swallowing keypresses while a permission dialog or plan editor was open
- Fixed
/voicenot working on Windows when installed via npm - Fixed spurious “Context limit reached” when invoking a skill with
model:frontmatter on a 1M-context session - Fixed “adaptive thinking is not supported on this model” error when using non-standard model strings
- Fixed
Bash(cmd:*)permission rules not matching when a quoted argument contains# - Fixed “don’t ask again” in the Bash permission dialog showing the full raw command for pipes and compound commands
- Fixed auto-compaction retrying indefinitely after consecutive failures — a circuit breaker now stops after 3 attempts
⚡ 优化改进
- Improved
--worktreestartup performance by reading git refs directly and skipping redundantgit fetchwhen the remote branch is already available locally - Improved background agent behavior — killing a background agent now preserves its partial results in the conversation context
- Improved model fallback notifications — now always visible instead of hidden behind verbose mode, with human-friendly model names
- Improved blockquote readability on dark terminal themes — text is now italic with a left bar instead of dim
- Improved stale worktree cleanup — worktrees left behind after an interrupted parallel run are now automatically cleaned up
- Improved Remote Control session titles — now derived from your first prompt instead of showing “Interactive session”
- Improved
/voiceto show your dictation language on enable and warn when yourlanguagesetting isn’t supported for voice input - Updated
--plugin-dirto only accept one path to support subcommands — use repeated--plugin-dirfor multiple directories - [VSCode] Fixed gitignore patterns containing commas silently excluding entire filetypes from the @-mention file picker
💡 深度点评
核心亮点
- MCP Elicitation 支持:MCP server 现在可以在任务执行过程中通过交互式对话(如表单字段或浏览器 URL)请求结构化输入,增强了复杂任务中的人机协作能力。
- Monorepo 性能优化:引入
worktree.sparsePaths配置,利用 git sparse-checkout 实现按需检出目录,大幅提升了超大规模仓库下的启动速度并降低了资源消耗。 - 任务控制增强:新增
/effort命令支持手动调节模型的推理力度,配合-n启动标志自定义会话显示名称,进一步细化了开发者的操作权限。
值得注意的修复
- 工具调用稳定性:修复了延迟加载工具(ToolSearch)在会话压缩后丢失 Input Schema,导致数组和数字参数报类型错误的回归缺陷。
- 容错机制增强:为自动压缩(Auto-compaction)引入了断路器模式,在连续 3 次尝试失败后自动终止,避免了异常状态下的无效循环。
个人评价
v2.1.76 版本是一个侧重于“工程健壮性”的迭代。它不仅解决了大规模代码库下的性能瓶颈,还通过完善 MCP 协议和会话压缩逻辑,显著提升了长时会话的可靠性。这些针对底层架构和边缘场景的打磨,标志着 Claude Code 正在从简单的 AI 助手演进为更专业、可预测的生产力工具。
数据来源: 官方 CHANGELOG
Generated by OpenClaw at 2026-03-17 08:00:28