Bug-fix release with 6 new features, 6 improvements, 31 fixes, 1 change, and 7 other updates.
51
3
Patch
Bug Fixes
Category Breakdown
Removed Changes
find -exec, variable assignments, command substitutions, and many other patterns that previously triggered unnecessary prompts. Also fixed tree-sitter not loading in npm-installed versionsCLAUDE_CODE_PROXY_SUPPORTS_TOOL_REFERENCE, now removed)claude plugins as an alias for claude pluginclaude plugin validate to explain that marketplace.json source paths are relative to the repo root when rejecting ../ pathsLast edit detected:
Filter by Platform
w key in /copy to write the focused selection directly to a file, bypassing the clipboard (useful over SSH)/plan (e.g., /plan fix the auth bug) that enters plan mode and immediately startsExitWorktree tool to leave an EnterWorktree sessionCLAUDE_CODE_DISABLE_CRON environment variable to immediately stop scheduled cron jobs mid-sessionlsof, pgrep, tput, ss, fd, and fdfind to the bash auto-approval allowlist, reducing permission prompts for common read-only operations.git suffix (Azure DevOps, AWS CodeCommit)/config — Escape now cancels changes, Enter saves and closes, Space toggles settingsANTHROPIC_BASE_URL as long as ENABLE_TOOL_SEARCH is set.--continue not resuming from the most recent point after --compactEEXIST error in OneDrive folders, marketplace blocking user-scope installs when a project-scope install exists, CLAUDE_CODE_PLUGIN_CACHE_DIR creating literal ~ directories, and plugin.json with marketplace-only fields failing to load--effort CLI flag being reset by unrelated settings writes on startup/clear/clear killing background agent/bash tasks — only foreground tasks are now clearedworktreePath and worktreeBranch/model not displaying results when run while Claude is working/tmp/claude/) prompting unnecessarilyquery() calls, reducing input token costs up to 12xtranscript_path pointing to the wrong directory for resumed/forked sessions, agent prompt being silently deleted from settings.json on every settings write, PostToolUse block reason displaying twice, async hooks not receiving stdin with bash read -r, and validation error message showing an example that fails validationCLAUDE_CODE_DISABLE_TERMINAL_TITLE was setsandbox.excludedCommands failing with env var prefixes; "always allow" suggesting overly broad prefixes for nested CLI tools; and deny rules not applying to all command forms<!-- ... -->) to be hidden from Claude when auto-injected. Comments remain visible when read with the Read toolmodel parameter on the Agent tool for per-invocation model overrides/effort auto to reset to defaultvscode://anthropic.claude-code/open URI handler to open a new Claude Code tab programmatically, with optional prompt and session query parameters