Claude Code 2.1.223
This release adds marketplace filtering via owner wildcards, improves permission and security controls including fixes for Bash permission bypasses and sandbox escapes, enhances model discovery and overrides handling, and refines session management and command review workflows.
- Added owner wildcard entries (
"owner/*") to thestrictKnownMarketplacesandblockedMarketplacesmanaged 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
/teleporthint in cloud sessions showing how to continue locally withclaude --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
bypassPermissionsmode ignored the org bypass-permissions disable policy - Fixed resuming a session after a mid-session
/cdcoming back empty - Fixed gateway model discovery hiding Claude models registered under provider-prefixed IDs such as
vertex_ai/claude-*orbedrock/anthropic.claude-* - Fixed
modelOverrideskeys 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.jsonor MDM profile; admin env now merges per key - Fixed sandboxed commands failing to start on Linux when
sandbox.filesystem.denyWritecovers 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 pushoutput - Changed
CLAUDE_CODE_DISABLE_1M_CONTEXTto 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=1to restore the previous behavior - Changed
/reviewto be an alias of/code-review, which reviews the current diff or a PR (/code-review <level> <pr#>); use/code-review ultrafor a deep cloud review - Changed
/code-reviewwith no effort level to reuse the level you typed last; type a level like/code-review highto change it
Source: original entry ↗
More from Claude Code
Follow Claude Code to get its new changes in your feed and email digest.
Claude Code 2.1.299 Release
Major update adding file mention environment variables, idle token compaction for prompt caching, new APIs for mods and plugins (including image attachment handling and session identity), improved agent and skill controls, better tool management for eval runs, and numerous behavioral changes to plugin hooks, MCP requests, and session handling.
Claude Code 2.1.296
This release adds new configuration options for managed policies, subagent behavior, workflow models, and retry handling. It includes improvements to the Claude apps gateway, Desktop Code tab settings, file reading capabilities, and session management across cloud and self-hosted environments. Pricing for Sonnet 5.5 cache reads has been updated to $0.10 per million tokens, and various UI and behavior refinements have been made to Claude Tag, VSCode, Chrome, and Slack integrations.
Claude Code 2.1.295 Release
This release adds onFailure blocking for hooks, Program Status Protocol support for terminal status display, upstream timeout configuration, improved tool descriptions, and numerous UX enhancements including file handling in chat, better error messages, and protocol improvements across VSCode, Claude Tag, and MCP integrations.