Claude Code v2.1.232 Released: Subagent Forking On by Default, Enhanced Security and GitLab Support
Score
77虽然是一次版本迭代,但包含多个新特性与安全修复,对使用体验有明显提升。
更新说明详细完整,覆盖功能、安全、性能等多个方面,信息结构清晰。
默认启用 subagent forking 与安全修复可直接改善日常开发和合规场景。
发布当日即整理,时效性很强。
信源为 Anthropic 官方 GitHub Releases 页面,权威可靠。
Base 81.5 × T1.5 Source weight ×0.95 = 77
Curation line 65Selected
Why selected
This release brings substantial new features and security fixes, offering direct value to Claude Code users.
AI commentary
「What excites me most is not any flashy feature, but the shift in multi-agent collaboration as Subagent Forking becomes default—inheriting full context lets complex tasks be decomposed more naturally. Combined with GitLab ecosystem support, Claude Code is evolving from a local terminal tool into team-grade infrastructure. Team leads should test cross-session messaging and Remote Control first; they may be the hidden lever for synergy.」
Quick overview
Claude Code v2.1.232 is now available. Subagent forking is enabled by default, allowing subagents to inherit the full conversation and prompt cache. Users can mention another Claude session with @ to send direct messages via SendMessage, enabling seamless cross-session collaboration. The update adds GitLab token redaction and GitLab plugin marketplace support, fixes multiple permission bypass vulnerabilities on PowerShell and Git Bash, and hardens enterprise policy validation. Remote Control, session management, and streaming performance also receive notable improvements. Upgrade is recommended to boost collaboration efficiency and strengthen security.
- Subagent forking is enabled by default, with subagents inheriting the full conversation and prompt cache.
- Typing @ in interactive sessions references another Claude session for direct cross-session messaging.
- GitLab token families are now redacted, and GitLab plugin marketplaces are supported.
- Fixed permission bypass vulnerabilities on PowerShell and Git Bash, and hardened enterprise policy validation.
Full text
Showing the source text; the full translation is being generated.
What's changed
- Subagent forking is now on by default: a
subagent_type: "fork"subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default - Type
@in the prompt to mention another Claude session by name; Claude then usesSendMessageto reach that session directly SendMessagenow delivers to a bare name that exactly matches one live session, instead of asking to confirm with a ref first- Interactive sessions on one machine now keep unique names: starting or renaming a session to a name another live session already uses gives it a
name-word-wordvariant and tells you - Added
/configrows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse) - Added secret redaction for GitLab token families (
glrt-,gloas-,glptt-,glagent-,glimt-,glsoat-,glcbt-,glft-,glffct-) and full redaction of routableglpat-/gldt-tokens; theglabCLI config store gets the same sandbox and credential-path protection asgh - Added GitLab support to plugin marketplaces: bare
gitlab.comrepo URLs (including nested subgroups) now clone likegithub.comURLs, and clone auth-failure hints name your actual git host - Settings:
additionalMarketplacesandallowedMarketplacesare now accepted as friendlier aliases forextraKnownMarketplacesandstrictKnownMarketplaces - Enterprise policy: a url-typed
blockedMarketplacesentry for a bare repo URL keeps blocking that URL when the CLI classifies it as a git clone - Gateway: the
desktop:overlay now accepts every released Desktop setting (was 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys fail boot - Gateway: empty
managed.policies[].match.groups/admin.admin_groupsentries and malformedemail_domainvalues (empty, or containing@, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access - Fable 5 is offered as an advisor in
/advisoragain for organizations with Fable access, with usage-credits consent set up through/model fable - Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite
$PSDefaultParameterValuesand redirect later commands' file access - Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval
- Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation
- Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe
- Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials
- Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one
- Fixed Remote Control sessions appearing unreachable to newly attached clients while idle
- Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts
- Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)
- Fixed Cloud gateway
/loginexiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown - Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately
- Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors
- Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region
- Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments
- Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis
- Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji
- Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to
known_marketplaces.json - Fixed
/updateand/tuirefusing to restart while work that survives the relaunch was running - Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions
- Fixed the consent message for interactive
--advisor fablelaunches, which told you to run/model fablein an interactive session that had just exited - Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update
- Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (
sandbox.bwrapPath,sandbox.socatPath,sandbox.ripgrep) /feedbackand/bugnow open immediately when invoked while Claude is responding, instead of waiting for the turn to finish/plugin install plugin@marketplacenow refreshes the marketplace first, so newly published plugins install without a manual marketplace update/code-reviewat high, xhigh, and max effort now runs in a background agent like the other levels- Pasted and clipboard images are read without blocking the event loop
- Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour
- Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run
/remote-controlthere to move it - Updated agent panel: completed subagents hide immediately with a
/tasksfooter hint, and the "↓ N more" overflow indicator moved left for visibility - Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it
- Bash input redirections (
< file) are now permission-checked like their argument spellings on all platforms - Shortened the message shown when resuming a completed background agent
- Cowork sessions no longer inline external @-imports from user-scope memory files
- Hardened the auto-generated cross-session messaging socket directory on shared
/tmp: a pre-planted symlink or another user's directory is now refused instead of used - Hardened the Linux filesystem sandbox against a protected-path bypass
- Changed
sandbox.ripgrepto be honored only from user, managed, and--settingssettings; project settings can no longer override the sandbox's ripgrep binary - Removed the startup tip suggesting you create custom subagents, and the matching nudge in the
/poweruptour
Related items
92
FeaturedOpenRouter Launches Prompt Caching with Sticky Routing to Drastically Reduce Multi-Turn Costs
OpenRouter 推出提示缓存与粘性路由,大幅降低多轮对话成本
For developers making frequent AI API calls, this feature is a direct money-saver. Sticky routing guarantees cache hit rates, and session_id requires zero configuration—every OpenRouter user should try it immediately.
91
FeaturedChatGPT Work: An AI Agent That Takes Action Across Apps and Files
ChatGPT Work:可在跨应用和文件中执行操作的AI Agent
I think this is a key step for AI assistants moving from Q&A to execution. Especially noteworthy for professionals who need to automate complex workflows. ChatGPT Work could become a new paradigm for productivity tools.
90
FeaturedAnatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
前沿实验室代理入侵事件技术时间线:2026年7月事件剖析
This technical timeline is a must-read for all AI security researchers and agent developers—it doesn't just describe one attack but sounds an alarm on the weak defense systems of agent architectures. For teams deploying autonomous agents, this is an essential disaster prevention manual.
90
FeaturedBetter Tools Made Copilot Code Review Worse? Here's How GitHub Improved It
更好的工具反而让Copilot代码审查更糟?GitHub这样改进
This blog post deserves close reading by all AI product engineers and ML practitioners—it breaks the intuition that 'more powerful tools = better AI' and instead emphasizes an engineering philosophy aligned with agent reasoning patterns. Especially important for teams optimizing code review or similar agent-based products.
88
FeaturedOpenRouter Launches Unified Multimodal API: Single Endpoint for Image, Video, Audio, Embeddings, and Transcription
OpenRouter 推出统一多模态 API:单端点支持图像、视频、音频、嵌入与转录
This news is worth attention from all developers building multimodal AI applications: OpenRouter's unified API solves the pain of model switching, especially for startups or rapid prototyping. If you're struggling with multiple API keys and SDKs, this interface could be the unified layer you need.
87
FeaturedAnthropic Launches Claude for Teachers: AI Tools Designed for Educators
Anthropic 推出 Claude for Teachers:面向教师的教育 AI 工具
This announcement is valuable for educators and AI industry watchers alike. Instead of a generic chatbot, Anthropic designed a safety-first tool specifically for teachers, demonstrating the right approach for AI vertical deployment: solving real pain points rather than showing off technology. The built-in guardrails also set a reference for other AI companies, especially when serving scenarios involving children or teenagers.
86
FeaturedOpenRouter Introduces New Auto Router: Model Routing Powered by Market Wisdom
OpenRouter发布全新Auto Router:用市场智慧优化模型路由
This update is worth attention for anyone using APIs to build AI apps. Instead of guessing or testing model selection, market data now does the heavy lifting. Though sparse on details, the direction is right, especially for teams relying on aggregated model services.
86
FeaturedClaude Code v2.1.211 Release: Multiple Fixes and Improvements
Claude Code v2.1.211 发布:多项修复与改进
As a developer who frequently uses Claude Code for automated coding, I'm particularly interested in the security fixes, especially the permission preview character bypass and auto mode overriding hook decisions—these directly affect the security boundaries during team collaboration. The improvement in background agent reporting also makes long-running tasks more reliable. I recommend all users upgrade as soon as possible.