Claude Code v2.1.223 发布：强化权限安全、市场规则与上下文管理

更新内容

• 在 strictKnownMarketplaces 和 blockedMarketplaces 托管设置中新增所有者通配符条目（"owner/*"），可用于允许或阻止某个 GitHub 组织下的全部 Marketplace 仓库。
• 当工作流 Agent、派生 Skill、斜杠命令或恢复的后台 Agent 所请求的子 Agent 模型受到限制、因而改由父模型运行时，新增警告提示。
• 在云端会话中新增 /teleport 提示，说明如何通过 claude --teleport <session id> 在本地继续会话。
• 修复 Bash 权限绕过问题：特制命令此前可在权限检查中隐藏自身的一部分内容。
• 修复权限提示问题：以制表符或不可见 Unicode 字符填充的命令，现已无法在批准对话框中隐藏部分命令内容。
• 修复工作流脚本可通过动态 import() 在工作流沙箱之外执行代码的问题。
• 修复权限缺口：Agent 定义的 bypassPermissions 模式此前会忽略组织层面的“禁用绕过权限”策略。
• 修复会话在中途执行 /cd 后恢复时返回空结果的问题。
• 修复网关模型发现问题：此前会隐藏注册为带提供商前缀 ID 的 Claude 模型，例如 vertex_ai/claude-* 或 bedrock/anthropic.claude-*。
• 修复 modelOverrides 中非 Anthropic 模型 ID 的键被视为会话规范模型 ID 的问题；现在会按文档说明忽略未知键。
• 修复托管设置问题：服务器下发的设置不再禁用机器本地 managed-settings.json 或 MDM 配置文件中的环境变量区块；管理员环境变量现在按键合并。
• 修复 Linux 上的沙箱命令启动失败问题：当 sandbox.filesystem.denyWrite 覆盖工作目录时，此前命令无法启动。
• 修复派生后台 Agent 恢复时的问题：如果重建派生分支的父提示词失败，Agent 此前会在该会话剩余时间内一直卡在“already resuming”状态。
• 修复恢复的会话在历史记录包含格式错误的诊断附件时，每一轮均失败或导致交互式应用停留在无响应错误界面的问题。
• 修复解析异常 git push 输出时罕见的挂起问题。
• 调整 CLAUDE_CODE_DISABLE_1M_CONTEXT：该设置现在会通过自动压缩，将所有原生支持 100 万上下文窗口的 Claude 模型限制至 20 万上下文，而不再仅针对固定模型列表；当自动压缩未能将会话限制在 20 万上下文时，启动时将显示警告。
• 调整自动压缩行为：对于未识别模型 ID，自动压缩现在会将会话保持在假定的上下文窗口内，而不再允许其超出该窗口增长。设置 CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1 可恢复此前行为。
• 将 /review 改为 /code-review 的别名，后者可审查当前 diff 或 PR（/code-review <level> <pr#>）；使用 /code-review ultra 可进行深度云端审查。
• 调整未指定工作强度级别时的 /code-review：现在会复用上一次输入的级别；输入如 /code-review high 的级别参数即可更改。

1. Releases
2. v2.1.223

Compare

Sorry, something went wrong.

No results found

What's changed

• Added owner wildcard entries ("owner/*") to the strictKnownMarketplaces and blockedMarketplaces managed settings for allowing or blocking all marketplace repos under a GitHub org
• Added a warning when workflow agents, forked skills, slash commands, or resumed background agents' requested subagent model is restricted and the parent model runs instead
• Added a /teleport hint in cloud sessions showing how to continue locally with claude --teleport <session id>
• Fixed a Bash permission bypass where a crafted command could hide parts of itself from permission checks
• Fixed permission prompts so commands padded with tabs or invisible Unicode can no longer hide part of the command from the approval dialog
• Fixed workflow scripts being able to use dynamic import() to run code outside the workflow sandbox
• Fixed a permission gap where an agent definition's bypassPermissions mode ignored the org bypass-permissions disable policy
• Fixed resuming a session after a mid-session /cd coming back empty
• Fixed gateway model discovery hiding Claude models registered under provider-prefixed IDs such as vertex_ai/claude-* or bedrock/anthropic.claude-*
• Fixed modelOverrides keys that aren't Anthropic model IDs being treated as the session's canonical model ID; unknown keys are now ignored as documented
• Fixed managed settings: server-delivered settings no longer disable the env block of a machine-local managed-settings.json or MDM profile; admin env now merges per key
• Fixed sandboxed commands failing to start on Linux when sandbox.filesystem.denyWrite covers the working directory
• Fixed forked background agents getting stuck "already resuming" for the rest of the session when rebuilding the fork's parent prompt failed during resume
• Fixed a resumed session failing every turn, or leaving the interactive app on an unresponsive error screen, when its history held a malformed diagnostics attachment
• Fixed a rare hang when parsing unusual git push output
• Changed CLAUDE_CODE_DISABLE_1M_CONTEXT to hold every Claude model with a native 1M window to 200K via auto-compaction, not just a fixed list; a startup warning now appears when auto-compaction isn't holding the session to 200K
• Changed auto-compact to keep sessions on unrecognized model IDs within the assumed context window instead of letting them grow past it; set CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1 to restore the previous behavior
• Changed /review to be an alias of /code-review, which reviews the current diff or a PR (/code-review <level> <pr#>); use /code-review ultra for a deep cloud review
• Changed /code-review with no effort level to reuse the level you typed last; type a level like /code-review high to change it

You can’t perform that action at this time.