Claude Code v2.1.229 Released: Remote Control Resume, SSE Keepalive, and Stability Fixes
Score
79版本号迭代但以修复和体验优化为主，对现有用户有明确信息增量但并非颠覆性更新。
官方 changelog 条目清晰，覆盖功能、修复和安全改进，信息结构化且易读。
远程续跑、SSE 保活、崩溃修复以及危险命令自动批准收紧，对开发流程有直接帮助。
这是最新发布版本，信息时效性高，适合开发者及时跟进。
来自 Anthropic 官方 GitHub Releases，信源权威可靠。
Base 83.5 × T1.5 Source weight ×0.95 = 79
Curation line 65Selected
Why selected
This release covers Remote Control resumption, gateway keepalive, security hardening, and many crash fixes, providing strong practical value.
AI commentary
「If your team runs Claude Code on self-hosted runners or Remote Control, this upgrade is worth applying immediately—the keepalive and hook alignment address real production pain points around disconnects and inconsistent behavior. Individual users shouldn't skip it either, since the crash fixes and `/commit-push-pr` auto-approval tightening directly affect daily safety.」
Quick overview
Claude Code v2.1.229 introduces `claude remote-control --continue` for resuming the latest Remote Control session, and adds server-supplied hook support for self-hosted runners to match managed environments. Gateway streams now emit SSE keepalive pings during long thinking pauses to prevent idle disconnects from Vertex and Bedrock. The release also adds plugin marketplace command sources, marks disconnected remote sessions as offline, and fixes issues including truncated/duplicated streaming output, narrow-terminal rendering crashes, Windows extended-length path crashes, MCP OAuth redirects, and auto-mode failures when attribution headers are disabled. Security-conscious changes also stop `/commit-push-pr` from auto-approving dangerous git commands.
- `claude remote-control --continue` resumes the most recent Remote Control session, and self-hosted runner sessions now support server-supplied hooks.
- Gateway streams send SSE keepalive pings during long thinking pauses, preventing idle-timeout disconnects from Vertex/Bedrock.
- Plugin marketplaces can use a local command to print the plugin directory, re-resolved per session and applied without restart; disconnected remote sessions are marked offline.
- Multiple crashes and compatibility issues are fixed, and `/commit-push-pr` no longer auto-approves dangerous git/gh flags such as --force and --amend.
Full text
Showing the source text; the full translation is being generated.
What's changed
- Documented
claude remote-control --continuefor resuming the most recent Remote Control session - Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior
- Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams
- Added plugin marketplace
commandsources: a local command (e.g. an IDE) prints the plugin directory, which is re-resolved each session and applied without a restart;mode: "link"uses it in place ListAgentsnow marks disconnected Remote Control sessions asofflineand labels your cloud sessions ascloud- Fixed long responses partly disappearing while streaming and being printed twice in the terminal
- Fixed a crash to the error screen (including on
--resumeof the affected session) when a tool call had a non-stringglob,file_path, orcommandvalue - Fixed a RangeError crash when a progress bar or markdown table rendered in a very narrow terminal window (could also crash
claude --continue/--resumeat startup) - Fixed a crash on Windows when a tool call or message referenced a file by an extended-length (
\\?\) or UNC path - Fixed auto mode failing on every tool call for users who disable the attribution header via
CLAUDE_CODE_ATTRIBUTION_HEADER(direct Anthropic API connections) - Fixed
/modelrejecting Sonnet/Opus 1M for claude.ai subscribers using a customANTHROPIC_BASE_URLgateway - Fixed MCP OAuth with strict authorization servers by using
127.0.0.1instead oflocalhostin the redirect URI - Fixed Remote Control clients showing a stuck working spinner after a slash command typed in the laptop terminal
- Fixed the Claude Code Review workflow generated by
/install-github-appcompleting without posting its review on the pull request - Fixed multi-second UI stalls after editing a file with thousands of IDE diagnostics while the IDE extension is connected
- Fixed one-shot
claude plugincommands leaving a stray liveness file that could prevent cleanup of outdated plugin versions - Fixed dynamic workflows inside CPU-limited containers using the host machine's core count instead of the container's CPU limit
- Fixed a file-watcher handle leak after atomic file replacements, and an uncaught error on Windows when the scheduled-tasks watcher failed on a network or virtual filesystem
- Fixed SDK and
--input-format stream-jsonsessions getting a 400 API error when a whitespace-only message was submitted - Fixed conversations whose messages alone exceed the API's 32 MB request limit retrying compaction when no images or documents can be stripped; they now fail once with a clear message
- Fixed OpenTelemetry export from Claude Desktop sessions being rejected by the Desktop-managed gateway when that gateway is also the telemetry endpoint
- Fixed self-hosted runner and other remote sessions exiting at startup when
managed-mcp.jsonis deployed and the server delivers MCP servers; those servers are now skipped with a warning - Fixed self-hosted runner repository preparation hanging on a Git Credential Manager prompt; git now fails fast when credentials are missing
- Improved workflow fan-outs to stagger same-prefix sibling agents so subsequent agents read the cached prompt prefix instead of re-paying it (
CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0disables) - Improved "prompt is too long" errors to explain why automatic compaction could not recover instead of only suggesting
/compact - Improved sandbox: IPv6 literals in network domain lists are now bracketed (
[::1]:443), and ambiguous spellings are enforced fail-closed and flagged by/doctor - Updated
/loginto repeat theCLAUDE_CODE_OAUTH_TOKENoverride warning after a successful login - Changed
/commit-push-prso git/gh commands with dangerous flags (--force,--amend,--no-verify, etc.) are no longer auto-approved - Changed self-hosted runner Windows startup to require an explicit
--base-dir; there is no default checkout directory on Windows - [VSCode] "Report a problem" and
/bugnow open the built-in feedback dialog instead of a retired survey link - [VSCode] Made the
/btwside-question panel resizable by dragging its boundary, in both side-docked and stacked layouts - [VSCode] Added session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move several sessions at once
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.