Claude Code v2.1.133: worktree.baseRef revert, sandbox paths, proxy fix for MCP OAuth

Anthropic released Claude Code v2.1.133 with several configuration additions and critical fixes. The notable update is the worktree.baseRef setting, which controls whether --worktree, EnterWorktree, and agent-isolation worktrees branch from origin/<default> or local HEAD. The default is fresh, reverting EnterWorktree to branch from origin/<default> — this changes the behavior from v2.1.128 which used local HEAD. To keep unpushed commits in new worktrees, set worktree.baseRef: "head".
New Settings & Features
- worktree.baseRef (
fresh|head): Choose worktree base branch. Defaultfreshusesorigin/<default>; set toheadto inherit localHEAD. - sandbox.bwrapPath and sandbox.socatPath (Linux/WSL): Specify custom bubblewrap and socat binary paths.
- parentSettingsBehavior (admin-tier key,
first-wins|merge): Allows admins to opt SDKmanagedSettingsinto policy merge. - Hooks now receive effort level: Via
effort.levelJSON input and$CLAUDE_EFFORTenvironment variable. Bash tool commands can read$CLAUDE_EFFORT.
Improvements & Fixes
- Focus mode: Behavior improved.
- Memory usage: Warm-spare background workers released under memory pressure.
- Parallel sessions 401: Fixed dead-end after refresh-token race wiping credentials.
- Edit/Write allow rules: Fixed scope matching on drive root (
C:\) or POSIX/incorrectly always prompting. - ECOMPROMISED lock error: Fixed unhandled rejection from clock skew or slow disk corrupting session-log file locks.
- Spurious compaction error: Pressing Esc during compaction no longer shows "Error compacting conversation".
- HTTP(S)_PROXY / NO_PROXY / mTLS: Now respected for the full MCP OAuth flow (discovery, dynamic client registration, token exchange, token refresh).
- Mapped network drives: Read/Write/Edit allowed when passed via
--add-diror SDKadditionalDirectories. - Remote Control stop: From claude.ai now fully cancels CLI session like local Esc, preventing stuck queued messages.
- Effort cross-session leak:
/effortin one session no longer changes others; IDE effort changes no longer silently dropped. - Subagent skill discovery: Fixed subagents not finding project, user, or plugin skills via the Skill tool.
CLI & VSCode
claude --helpnow lists--remote-controlalongside--remote-control-session-name-prefix.- [VSCode] Fixed
claudeCode.claudeProcessWrapperfailing with "Unsupported platform" when extension build lacks bundled Claude binary.
📖 Read the full source: GitHub Claude-Code
👀 See Also

OpenClaw Codex OAuth returning billing errors despite valid account
OpenClaw Codex OAuth is returning a 429 error stating 'Your account is not active, please check your billing details' even though billing is confirmed valid and the exec command works. The issue persists across multiple OpenClaw versions.

OpenClaw .23 Update Causing Agent Issues and Data Loss
The OpenClaw .23 update is causing agents to become unresponsive, fail to execute tasks, and lose connection with browser extensions. Running the repair command can strip entire JSON configurations, requiring system backups for recovery.

xAI loses legal challenge to California AI data disclosure law
xAI has lost its attempt to block California's AI data disclosure law, which requires companies to disclose training data sources and other details about their AI systems. The court ruling means the law will proceed as scheduled.

Claude Opus 4.7 Released with Hybrid Reasoning and 1M Context Window
Anthropic released Claude Opus 4.7, a hybrid reasoning model with a 1M context window that delivers stronger performance on coding, vision, and complex multi-step tasks. Pricing starts at $5 per million input tokens and $25 per million output tokens.