v2.1.316
评分
70精选理由
来源可信且信息密度较高,适合进入精选池。
AI 点评
「来自 Claude Code:GitHub Releases(RSS) 的这条信息指向模型能力或模型生态变化,适合用于判断近期 AI 圈的真实动向。」
速览
What's changed Added CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword off Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's…
- What's changed Added CLAUDE_CODE_DISABLE_ULTRATHINK, which turns the ultrathink keyword off Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's…
- After removal, fast mode requests on Opus 4.8 return an error and do not fall back to standard Opus 4.8.
- Migrate to Opus 5.5 to keep the speedup Fixed shell commands being left running on macOS and Linux when Claude Code exits by itself, for example when credentials are refused or a cloud session is archived Fixed bash ali…
正文
以下为原文,中文全文翻译生成中
What's changed
- Added
CLAUDE_CODE_DISABLE_ULTRATHINK, which turns theultrathinkkeyword off - Added pooled group budgets to the Claude apps gateway: one monthly budget that a group's members share, on top of each member's own limit, set with
pooled_budgeton the spend limits admin API - Added
CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROPto keep system cross-certificates that certify each other in a loop, for servers whose private CA needs one - Added
CLAUDE_CODE_SUBAGENT_EFFORTto set the effort level subagents run at when nothing else names one, instead of inheriting the session's - Added
managed.policy_mode: layeredto the Claude apps gateway: every policy that matches a developer applies, each merged over the ones listed below it, not only the first - Added
guardrail.input_taggingon Claude apps gateway Bedrock upstreams, which wraps prompts in the input tags that an Amazon Bedrock guardrail's prompt attacks filter needs;all_messages_and_systemalso tags the system prompt - Deprecated fast mode for Opus 4.8 as of October 30, 2026; it will be removed on November 30, 2026. After removal, fast mode requests on Opus 4.8 return an error and do not fall back to standard Opus 4.8. Migrate to Opus 5.5 to keep the speedup
- Fixed shell commands being left running on macOS and Linux when Claude Code exits by itself, for example when credentials are refused or a cloud session is archived
- Fixed bash aliases with line breaks in their value (except in Git Bash), and functions whose names start with a dash, being garbled or lost in the Bash tool's shell
- Fixed bash scripts started from the Bash tool stopping after their first command when
SHELLOPTSis exported - Fixed PowerShell hooks not blocking on exit code 2 when the command begins with a type cast,
param,usingor an attribute - Fixed some network requests hanging when a compressed response was cut off or corrupted
- Fixed
sonnet,opusandhaikuon Vertex AI and Amazon Bedrock showing an error mid-session instead of switching to an older model when the newest is not yet available to the account or region - Fixed the Claude apps gateway not checking every model a request names against
availableModels,deniedModelsandmodels; a request that names a blocked model now gets a 400 naming the field - Fixed
claude auth loginrefusing to run where managed settings require a Claude apps gateway; in a terminal it now shows the gateway sign-in - Fixed
--restrictedsessions uploading files from outside the working directories when a Read allow rule covered them - Fixed prompts containing invisible characters needing a second Enter to send; plain prompts now send cleaned on the first Enter, and commands still wait for review
- Fixed sub-agents that inherited a parent sub-agent's model moving to the main model when a background job or message woke them
- Fixed a managed
autoMode.allowlist without"$defaults"getting the built-in exceptions back from a host app's--settings, a first rule added in/permissions, or/auto-mode-setup - Fixed cloud sessions and cloud scheduled tasks not being marked as failed when auto mode stopped a turn because the server returned no safety verdict
- Fixed
claude -ptext output sometimes not saying why auto mode stopped a turn when a background agent was still running - Fixed
CLAUDE_CODE_AUTO_MODE_SERVER=1being ignored in sessions started by a host application (such as Claude Desktop) behind a proxy or LLM gateway with experimental betas turned off - Fixed plugin MCP
headersHelperscripts receiving a corruptedCLAUDE_PLUGIN_ROOTand server URL when a credential-named environment variable was set to a switch value such as1 - Fixed the SDK
register_repo_rootcontrol request not loading the CLAUDE.md of a directory outside the working directory (withCLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD=1) - Fixed the Artifact tool showing
?for artifact database access rules at theselflevel, and not quoting those rules back when it refuses a republish that would drop them - Fixed
/model <id>not warning when the model isn't recognized by this version and auto-compact will assume a 200K context window - Fixed the "hold space to speak" hint using up its three showings in one session, and showing an empty key when push-to-talk is unbound
- Fixed Grep and Glob never returning when the search process is killed at the timeout but does not exit, seen on Windows
- Fixed a rare case where resuming a conversation did not restore its plan, when
/clearor/resumehad been run while part of that conversation was still being saved - Fixed first-run setup dropping words from the security notes and the terminal-setup explanation in narrow terminals
- Fixed the Enterprise survey card taking a typed 1 or 0 after a short pause; a typed answer now needs Enter
- Self-hosted runner: Fixed a message sent while Claude was working being answered after a Stop, once the session's process had been replaced
- Self-hosted runner: Fixed an MCP server's on/off switch sometimes being lost when a session moved to a new machine
- Windows: Fixed the Bash tool losing your aliases and functions in Git Bash when the rc file sets errexit and pipefail and only winpty aliases, or none, are defined
- Improved
/code-reviewstarted from the Code tab in Claude Desktop or on the web: cloud andclaude remote-controlsessions now show the findings card, not a plain-text list - Improved
/diffon large repositories: each refresh usually runs one fewer full-repository git command, and refreshes are spaced out when git is slow - Improved the messages shown when
/ultrareview, a cloud session or a cloud agent finds no GitHub remote: they now say to create a repository at https://github.com/new, and/ultrareviewno longer suggests aghcommand thatghrejects - Improved SSL certificate errors to name the likely causes, among them a server that leaves out an intermediate certificate, and the fix for each
- Changed auto mode so that an
autoMode.allowlist without"$defaults"no longer removes the built-in rule on scheduled-task prompts - Changed server-managed settings for Team and Enterprise logins: settings fetched from Anthropic's API now apply without an approval prompt, and a stored copy that doesn't verify is refused
- [VSCode] Added sign-in to a Claude apps gateway from the chat panel, with no terminal needed
- [VSCode] Changed
ultrathinkto run its turn atxhigheffort and show in a rainbow in the chat box, as in the terminal - [VSCode] Fixed the missing Effort slider, Ultracode switch and model name when the model setting has the
[1m]tag, such asopus[1m] - [VSCode] Fixed saved
/btwside-question history being deleted too early while a settings file has errors - [VSCode] Fixed a conversation coming back in Auto mode after a reload or restart when its plan was approved with "Yes, and manually approve edits"
- [Cloud sessions] Added a form card to cloud sessions, so you can fill in or decline a form an MCP server asks for instead of the request being canceled without you seeing it
- [Cloud sessions] Added a "Catching up…" line that shows while a cloud or Remote Control session you switch back to is still bringing its messages up to date
- [Cloud sessions] Changed network secrets so Enterprise members can add and delete them on their own cloud environments, instead of only viewing them
- [Cloud sessions] Improved the Changes pane for cloud sessions: the note about what the list leaves out is now a badge beside the branch name, not a row above the diff
- [Cloud sessions] Fixed file search in a cloud session's Files pane showing folders as ../.. paths after Claude changed directory; results now show their path from the project's root
- [Claude Tag] Fixed Claude refusing to edit or append to a canvas it made in a Slack channel, from that channel, once the canvas was also shared to another channel or a DM
- [Claude Tag] Fixed untagged replies going unanswered in a Slack Connect thread when both organizations have installed Claude and Slack delivered the reply to the other organization's app
- [Claude Tag] Fixed a cloud scheduled task's live status checklist in Slack staying half-done; a run can now edit the top-level messages it posted during that run
- [Claude Tag] Changed a Slack channel's Respond automatically switch to a "How Claude participates" choice on the channel's Configure page and in Claude Tag admin settings
- [Code Review] Added a findings-by-severity card to the Code Review analytics page, showing the period's total findings, a daily chart stacked by severity, and each severity's count
相关条目
精选DeepSeek V4 在 OpenRouter 上的代币份额翻倍,智能体工作负载成主要驱动力
DeepSeek V4 的快速采用表明市场对高性能、低成本推理模型的强烈偏好,尤其是智能体场景将重塑 AI 部署格局。
91
精选启用两项设置使ARC-AGI-3基准测试分数提升三倍
这项发现太关键了!它表明模型的性能不仅取决于训练,还取决于推理时的配置。对于AI工程师和研究者来说,这是一个必须注意的优化方向。特别是那些在资源受限设备上部署模型的团队,可能会因此找到低成本提升能力的方法。
91
精选GPT-5.6:前沿智能与前沿效率的融合
这条消息值得关注,因为它标志着大模型竞争从单纯拼参数转向拼效率。对于AI开发者和企业决策者来说,GPT-5.6意味着可以用更少预算获得更高性能,尤其适合那些被推理成本挡在门外的长上下文或Agent场景。OpenAI这一步,可能重新定义‘前沿’的标准。
91
精选LFM2.5-Encoder:面向CPU快速长上下文推理的新模型
这篇博文让我眼前一亮,因为它直接解决了大模型在CPU上跑长上下文的痛点。对于没有高端GPU的团队或个人开发者,LFM2.5-Encoder系列提供了可立即使用的开源方案。尤其推荐给做RAG、文档搜索或代码分析的朋友——现在用普通服务器就能处理百万级token的文档了。
91
精选GPT-Red:OpenAI通过自我对弈实现AI红队自动化,提升模型鲁棒性
GPT-Red 是红队测试从人工到自动化的里程碑,特别适合安全工程师和对齐研究者关注。它直接降低了测试成本,但也引发了对“自动攻击”本身的伦理讨论——值得所有关注AI治理的人深入思考。
91
精选OpenAI推出GPT-5.5生物漏洞赏金计划
这个计划值得关注,因为它首次将AI漏洞赏金制度拓展到生物安全领域,不仅为安全社区提供了新的研究方向,也为AI风险治理提供了实际演练场。对模型安全研究者、生物安全专家以及关心AI双重用途的从业者尤其重要。
91
精选vLLM推出原生速度Transformers建模后端,大幅提升推理性能
这项更新对于AI工程团队非常关键:无需格式转换意味着能更快地迭代模型,而2-5倍的速度提升直接降低GPU成本。如果你正在做LLM在线服务或者批量推理,这几乎是必读的技术更新。
90
精选Google DeepMind 发布手语转文本模型 SL2T,助力聋人用户
这则消息的意义不仅在于技术突破,更在于AI开始真正关注边缘群体的需求。对开发者而言,SL2T的架构思路和技术路径值得深入研究;对无障碍倡导者来说,这是推动行业标准的重要案例。