Update Jun 4, 2026 tracked by Updatify
2.1.159
- Internal infrastructure improvements (no user-facing changes)
Anthropic's agentic coding tool for developers.
Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_ENABLE_AUTO_MODE=1 Update Jun 4, 2026 tracked by Updatify
.claude/skills directories are now automatically loaded, no marketplace required claude plugin init <name> to scaffold a new plugin in .claude/skills /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces claude agents: the agent field in settings.json is now honored for dispatched sessions, with --agent <name> to override it EnterWorktree can now switch between Claude-managed worktrees mid-session tool_decision telemetry events now include tool_parameters (bash commands, MCP/skill names) when OTEL_LOG_TOOL_DETAILS=1 git worktree remove/prune can clean them up claude agents completed sessions not retiring when an idle subagent was still parked or had leaked a backgrounded shell claude agents pressing Esc not cancelling a slow “opening…”, leaving the list unresponsive .claude/worktrees/ being orphaned after the 30-day job retention sweep claude agents not reaching the system clipboard inside tmux with set-clipboard on (regression in 2.1.153) --resume not reporting background subagents that were running when the previous Claude Code process exited --resume session picker leaving its contents on the terminal after exiting in fullscreen mode --worktree and --worktree --tmux returning to the canonical repo root instead of the current linked worktree /model picker showing an incorrect “Newer version available” hint when the selected model is already the newest in its family; the pinned-model row now shows the model’s description instead of its raw ID alt+v keybinding), screenshot paste on Windows 11, and added support for dragging images from Windows Explorer /terminal-setup now disables GPU acceleration in VS Code/Cursor/Windsurf integrated terminals to prevent garbled-text rendering claude agents: slash-command autocomplete in the dispatch input now matches substrings /status and when a command is blocked Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
/workflows to view your runs /simplify now runs a cleanup-only review (reuse, simplification, efficiency, altitude) and applies the fixes, instead of running the full /code-review --fix bug-hunting review /effort slider labels from “Speed”/“Intelligence” to “Faster”/“Smarter” for clarity claude agents: type ! <command> to run a shell command as a background session you can attach to and detach from. Also available as claude --bg --exec '<command>' claude agents: /logout now signs you out instead of being sent to a background session ←← to open the agents view now works on Bedrock, Vertex, Foundry, and with telemetry disabled /chrome → “Select browser…”, or in-chat when a browser action runs with multiple connected defaultEnabled: false in plugin.json or a marketplace entry; enable them with /plugin or claude plugin enable. Dependencies of enabled plugins are still enabled automatically /plugin Discover tab now pins plugins whose relevance signals match the current directory with a “suggested for this directory” annotation CLAUDE_CODE_SESSION_ID and CLAUDECODE=1 in their environment claude mcp list/get now show unapproved .mcp.json servers as ⏸ Pending approval instead of auto-approving and connecting when output is piped /remote-control autocomplete now shows “Disconnect Remote Control” when Remote Control is already active /claude-api skill CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE (will be removed on 06/01). To use fast mode on Opus 4.6, switch with /model claude-opus-4-6[1m] and then /fast on rm -rf $HOME not being blocked as a dangerous path when HOME has a trailing slash $TMPDIR resolving to different directories in sandboxed vs unsandboxed Bash commands within the same session claude agents when the Claude Code theme doesn’t match the terminal background /command fires claude --bg-pty-host processes spinning at 100% CPU after the daemon exits on macOS worktree.baseRef: "head" resolving to the main checkout’s HEAD instead of the current worktree’s HEAD when spawning subagents or calling EnterWorktree from inside a linked worktree [Image #N] / [Pasted text #N] placeholders when a plan-mode prompt starts with pasted images or text allowedMcpServers/deniedMcpServers entry in managed settings discarding all managed-settings policy; the bad entry is now dropped with a claude doctor warning CLAUDE_CODE_ALWAYS_ENABLE_EFFORT is set claude.exe being in use showing a generic error instead of telling you to close other sessions and retry Update Jun 4, 2026 tracked by Updatify
skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update /doctor lists the fixes COLUMNS and LINES environment variables so scripts can size output to the terminal width claude agents: autocomplete in the dispatch input now suggests native slash commands and bundled skills, not just project skills claude agents: PR column now shows PR #N for a single PR or N PRs for multiple claude doctor now shows the result of your last update attempt tools/list (regression in v2.1.147) --strict-mcp-config, --bare, remote mode, enterprise managed MCP config, and managed-settings MCP server allow/deny policies --strict-mcp-config no longer strips inline mcpServers from explicitly-passed agent definitions (--agents / SDK agents), and blocked subagent MCP servers now surface a visible warning claude update installing the latest version instead of the configured release channel’s version for npm installations claude agents and claude --bg running on a stale daemon started before binary-takeover support, even after upgrading file:// links in Claude’s responses not being clickable in the terminal claude --help rendering unwrapped output on terminals narrower than 92 columns Agent tool with subagent_type: 'claude' running in an undocumented temporary worktree, which could silently discard outputs written to gitignored paths /bg while Claude is responding now continues the response in the background session instead of dropping it /btw keyboard shortcuts becoming unresponsive in background sessions while a task is running $CLAUDE_JOB_DIR triggering a “sensitive file” permission prompt EnterWorktree not being available immediately in background sessions (previously required ToolSearch first) cmd+k in iTerm2/Terminal.app not repainting attached background sessions /copy and copy-on-select silently failing to update the system clipboard when attached to a background session inside tmux claude agents with Remote Control enabled leaving zombie session entries on the Code tab after exiting /rename in background sessions not updating the session banner immediately /model now saves your selection as the default for new sessions (matching the IDE). Press s in the picker to switch models for the current session only. modelPicker:setAsDefault keybinding, rename it to modelPicker:thisSessionOnly in keybindings.json (the d action was replaced by s) Update Jun 4, 2026 tracked by Updatify
/code-review --fix now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; /simplify now invokes /code-review --fix disallowed-tools in frontmatter to remove tools from the model while the skill is active /reload-skills command to re-scan skill directories without restarting the session SessionStart hooks can now return reloadSkills: true to re-scan skill directories, making skills installed by the hook available in the same session SessionStart hooks can now set the session title via hookSpecificOutput.sessionTitle on startup and resume MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed pluginSuggestionMarketplaces managed setting: admins can allowlist org marketplaces whose plugins may be suggested via context-aware tips claude plugin marketplace remove now accepts --scope user|project|local for symmetry with marketplace add, install, and uninstall --fallback-model for the rest of the session when the primary model is not found, instead of failing every request / in NORMAL mode now opens reverse history search (like Ctrl+R), matching bash/zsh vi-mode /usage breakdown now includes large session files; files are scanned with a streaming read so memory usage stays flat Ctrl+O shows the full thinking) app.entrypoint, opt-in via OTEL_METRICS_INCLUDE_ENTRYPOINT=true) /doctor reporting “marketplace not found” or “plugin not found” for stale enabledPlugins entries referencing removed marketplaces or dropped plugins --bare or with attachments disabled claude agents when accepting a stale permission prompt after a subagent was cancelled cache_creation_input_tokens reporting as 0 in transcript and result usage when the API reports cache writes only via the nested cache_creation breakdown Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
/usage now shows a per-category breakdown of what’s driving your limits usage — skills, subagents, plugins, and per-MCP-server cost /diff detail view can now be scrolled with the keyboard (arrows, j/k, PgUp/PgDn, Space, Home/End) - [ ] todo / - [x] done) instead of plain bullets allowAllClaudeAiMcps managed setting to load claude.ai cloud MCP connectors alongside managed-mcp.json cd functions (cd.., cd\, cd~, X:) changed the working directory undetected, letting a later command read outside the workspace .git directory (with hooks/ and config denied) PowerShell(dotnet.exe build *)) not pre-approving native executables and scripts PWD/OLDPWD/DIRSTACK across cd/pushd/popd find in the Bash tool exhausting the macOS system file/vnode table and crashing the host on large directory trees /ultraplan and remote session creation failing with “Could not capture uncommitted changes” when the working tree has no real changes otelHeadersHelper failing silently when the script path contains spaces; helper failures are now reported in /doctor and the debug log name: differs from its directory basename /effort setting instead of the effort level applied by skill/agent effort: frontmatter /config exit summary reporting phantom changes to auto-compact and theme when toggling unrelated settings /insights crashing when cached session-meta files are missing optional fields claude --resume /feedback reports to include the conversation that happened before context compaction, making issues from earlier in long sessions easier to triage Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
Ctrl+T in claude agents) now stay alive when idle, are restarted in place to apply Claude Code updates, and are shed under memory pressure only after non-pinned sessions /simplify to /code-review. It now reports correctness bugs at a chosen effort level (e.g., /code-review high); pass --comment to post findings as inline GitHub PR comments. The old cleanup-and-fix behavior has been removed forceLoginOrgUUID and forceLoginMethod managed-settings) not being enforced against third-party-provider and API-key sessions & in ! command output displaying as &, which broke copy-pasting URLs from commands like gcloud auth login on headless machines /help rendering a broken tab header and showing only one command per page on small terminals when not in fullscreen mode Agent(...) types in tools: frontmatter dropping all but the last entry if conditions like PowerShell(git push*) never matching — only PowerShell(*) worked pwsh is installed via winget or the Microsoft Store /effort opening with the slider on the wrong level — it now starts at your current effort /background refusing sessions whose only typed input was a skill or custom slash command AskUserQuestion when the user or a skill explicitly relies on it; the auto-mode classifier now sees the user’s answers as intent signal /theme “New custom theme” and color editor dialogs not responding to Esc [Pasted text #N] placeholder instead of the actual content claude plugin details and /plugin being doubled when a plugin’s manifest listed paths overlapping its default directories CLAUDE_CODE_SUBAGENT_MODEL not applying to teammate processes spawned by agent teams /plugin, /status, /mobile, /sandbox, and /permissions menus Update Jun 4, 2026 tracked by Updatify
claude agents --json to list live Claude sessions as JSON for scripting (tmux-resurrect, status bars, session pickers) agent_id and parent_agent_id attributes to claude_code.tool OTEL spans, and fixed trace parenting so background subagent spans nest under the dispatching Agent tool span /plugin Discover and Browse screens now show a plugin’s commands, agents, skills, hooks, and MCP/LSP servers before installation claude agents terminal tab title now shows the awaiting-input count so an alt-tabbed window tells you when an agent needs attention background_tasks and session_crons fields ; as the command separator gh pr create and other PR-state-changing commands run in-session /review using a deprecated projectCards GraphQL query that errored on repos with Classic Projects claude plugin validate not flagging skills: entries that point at a file instead of a directory — the error now suggests the parent directory context: fork could repeatedly re-invoke itself instead of running Update Jun 4, 2026 tracked by Updatify
/resume support for background sessions — sessions started via claude --bg or agent view now appear alongside interactive ones, marked with bg /plugin browse and discover panes now show when a plugin was last updated /model now changes the model for the current session only; press d in the model picker to set a default for new sessions /extra-usage is now /usage-credits (old name still works) api.anthropic.com is unreachable (captive portal, firewall, VPN issues) — side-channel API calls now time out after 15s head/tail file views now satisfy the read-before-edit check, and a “no matches” result (exit code 1) from egrep, fgrep, git grep, or git diff is no longer reported as a command failure /branch failing with “No conversation to branch” after entering a worktree or in some background sessions applyFlagSettings after startup /model choice /model picker (regression in v2.1.129) forceLoginMethod and forceLoginOrgUUID set tools/list responses only returning the first page, silently dropping tools .md files no longer trigger skill reloads .claude/settings.json now show an actionable claude plugin install hint claude mcp list silently reporting no servers when .mcp.json can’t be parsed (e.g. using VS Code’s "servers" key instead of "mcpServers") — now shows configuration errors ANTHROPIC_BASE_URL setups and Bedrock Mantle not using Haiku — now falls back correctly when a first-party API key is configured or no Haiku model is set claude agents leaving the list unresponsive to keyboard input /bg and ←-detach now preserve directories added via /add-dir claude respawn <id> on a stopped background session showing “stopped” instead of running /resume picker not showing sessions forked from a background session claude agents or running claude logs <id> hanging when the background service is unresponsive — now times out after 10s with a recovery hint claude agents attached sessions rendering as plain text instead of clickable hyperlinks spinnerVerbs applying to the post-turn duration message — past-tense built-ins like “Worked for 5s” are restored there claude agents / --bg rejection messages now name the specific gate (non-TTY, env var, or setting) instead of a generic message claude --bg --name <label> now echoes the name in the post-spawn confirmation claude agents: renaming a background session with Ctrl+R now updates the attached session’s banner immediately WorktreeCreate hooks configured CLAUDE_CODE_PLUGIN_PREFER_HTTPS /plugin now returns to the Installed list after enabling, disabling, or uninstalling a plugin /doctor now shows an exec-form example when a command hook is missing the command field /doctor for the full breakdown Update Jun 4, 2026 tracked by Updatify
claude plugin disable now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and claude plugin enable force-enables transitive dependencies /plugin marketplace browse pane worktree.bgIsolation: "none" setting to let background sessions edit the working copy directly without EnterWorktree, for repos where worktrees are impractical -ExecutionPolicy Bypass. Opt out with CLAUDE_CODE_POWERSHELL_RESPECT_EXECUTION_POLICY=1 .credentials.json with a non-array scopes value hanging the CLI on startup or silently aborting OAuth token refresh claude agents on Windows Terminal and WSL CLAUDE_CODE_STOP_HOOK_BLOCK_CAP) /loop wakeup while Claude is idle between iterations /goal evaluator firing while background shells or delegated subagents are still running NO_COLOR/FORCE_COLOR in settings.json env stripping Claude Code’s own UI colors — they now apply to subprocesses only /bg without a prompt sending “continue” to the forked session — the fork now waits for input --agent <name> not finding plugin-contributed agents without the plugin: prefix CLAUDE_CODE_USE_POWERSHELL_TOOL=0. claude agents now accepts --add-dir, --settings, --mcp-config, and --plugin-dir and applies them to the dashboard and to background sessions dispatched from it claude agents accepts --permission-mode, --model, --effort, and --dangerously-skip-permissions to set defaults for sessions dispatched from the view claude --bg --dangerously-skip-permissions now persists across retire→wake claude agents rm -rf when git worktree remove fails, preventing loss of gitignored or in-progress files ~/Documents, ~/Desktop, or ~/Downloads, even with Full Disk Access granted. /bg now preserves --mcp-config, --settings, --add-dir, --plugin-dir, and --strict-mcp-config, so backgrounded sessions keep their MCP servers and settings across respawn. claude agents now honor permissions.defaultMode from settings.json (was previously overridden to auto mode) claude agents while a response was streaming could leave the agents list unresponsive to all input /bg and ←-detach now preserve --fallback-model, so backgrounded workers degrade to the fallback model on overload instead of hard-failing. /bg and ←-detach now preserve --allow-dangerously-skip-permissions, so the forked worker keeps bypass-permissions available in its Shift+Tab cycle. ~/.local/bin/claude launcher is missing or non-executable claude agents --allow-dangerously-skip-permissions defaulting dispatched sessions to bypass mode instead of making it available in the permission cycle Update Jun 4, 2026 tracked by Updatify
claude agents flags: --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions to configure dispatched background sessions CLAUDE_CODE_OPUS_4_6_FAST_MODE_OVERRIDE=1 to pin fast mode to Opus 4.6 SKILL.md and no skills/ subdirectory are now surfaced as a skill /plugin details pane and claude plugin details now show LSP servers a plugin provides /web-setup warns before replacing an existing GitHub App connection MCP_TOOL_TIMEOUT not raising the per-request fetch timeout for remote HTTP and SSE MCP servers, which capped tool calls at 60 seconds regardless of the configured value brew upgrade), causing dispatched agents to crash-loop on the deleted path claude agents session — the background worker’s headless browser shim no longer applies while attached claude agents “v to open in editor” using the daemon’s default editor instead of your shell’s $EDITOR/$VISUAL claude agents deadlocking on Windows with network-drive working directories; Ctrl+C now works during startup claude agents session from Apple Terminal or other 256-color-only terminals claude --bg --dangerously-skip-permissions not persisting across retire/wake set_model requests from remote clients injecting duplicate /model breadcrumbs into the transcript skills: ["./"] showing a false “path escapes plugin directory” error /plugin browse pane showing “0 installs” for newly published plugins plugin.json key that shadows a default folder SessionStart/Setup/SubagentStart now shows a clear “use a command-type hook instead” error /model claude-sonnet-4-20250514 suggestion from Usage Policy refusal messages Update Jun 4, 2026 tracked by Updatify
terminalSequence field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal CLAUDE_CODE_PLUGIN_PREFER_HTTPS to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH key ANTHROPIC_WORKSPACE_ID environment variable for workload identity federation — scopes the minted token to a specific workspace when the federation rule covers more than one claude agents --cwd <path> to scope the session list to a directory /feedback can now include recent sessions (last 24 hours or 7 days) for issues spanning more than the current session permissions.ask rule caused the prompt /bg or ←← now preserve the current permission mode instead of reverting to default claude agents: agents that finish work but leave a background shell running now move to Completed instead of staying under Working →/Tab switch tabs, ↑ moves to the tab strip, and tab headers and search box are clickable in fullscreen mode ANTHROPIC_SMALL_FAST_MODEL override is set — now falls back to the main-loop model claude daemon status and /doctor on Windows throwing when the daemon pipe key file is locked or unreadable — now shows the underlying error instead of an opaque failure claude agents showing the agent-type list instead of the dashboard when launched through a wrapper that adds flags claude agents opening a crashed session firing redundant dispatches when the working directory was deleted ANTHROPIC_BASE_URL gateway not getting auto-named — the namer now uses the main model when no Haiku model is configured /model in one session silently changing the autocompact threshold in other concurrent sessions transcript_path after EnterWorktree switches the working directory chat:submit keybindings (e.g. meta+enter, ctrl+enter) not working when enter is rebound to chat:newline spinnerVerbs setting not being honored in turn-completion messages x on a selected subagent in the agent panel typing into the prompt instead of stopping the agent /tui silently dropping running background shells and subagents — now refuses and asks to wait for them to finish /mcp server list not keeping the focused server visible in short terminals in fullscreen mode /feedback bundles producing invalid JSON for quoted values like session IDs apiKeyHelper/ANTHROPIC_AUTH_TOKEN from host managed-settings claude plugin install failing for plugins whose marketplace ref no longer exists upstream when a sha is also pinned .mcp.json .mcp.json entries no longer drop other MCP servers ${var%pattern}) being incorrectly flagged as missing environment variables /login voice:pushToTalk keybindings and "space": null unbinds being silently ignored awsCredentialExport now always runs when configured instead of being skipped when ambient AWS credentials resolve, fixing auth for cross-account access sox libsox-fmt-pulse for WSLg users claude agents: launching a session no longer fails when the pre-warmed background worker is unhealthy — now falls back to a fresh launch claude agents no longer shows empty placeholder sessions left over from backgrounding a fresh REPL, and shows onboarding text when entered via ← with no other agents ← are now automatically retired by the daemon after 5 minutes Update Jun 4, 2026 tracked by Updatify
subagent_type matching to accept case- and separator-insensitive values (e.g. "Code Reviewer" resolves to code-reviewer) /goal silently hanging when disableAllHooks or allowManagedHooksOnly is set — now shows a clear message instead of an indicator that never resolves ConfigChange hooks claude --bg failing with “connection dropped mid-request” when the background service was about to idle-exit extraKnownMarketplaces auto-update policy not being persisted to known_marketplaces.json /loop scheduling redundant wakeups to poll for background tasks that already notify on completion gh) triggered synchronous where.exe re-spawns on every check Read tool calls failing validation when offset is passed as a whitespace-padded or +-prefixed string commands/) is silently ignored because plugin.json sets the matching key. Shown in /doctor, claude plugin list, and /plugin. Update Jun 4, 2026 tracked by Updatify
claude agents to get started. See https://code.claude.com/docs/en/agent-view /goal command: set a completion condition and Claude keeps working across turns until it’s met. Works in interactive, -p, and Remote Control. Shows live elapsed/turns/tokens as an overlay panel /scroll-speed command to tune mouse wheel scroll speed with a live preview claude plugin details <name> to show a plugin’s component inventory and projected per-session token cost ? for keyboard shortcuts, {/} to jump between user prompts, v to toggle shortcut panel args: string[] field (exec form) that spawns the command directly without a shell, so path placeholders never need quoting continueOnBlock config option for PostToolUse — set to true to feed the hook’s rejection reason back to Claude and continue the turn CLAUDE_PROJECT_DIR in their environment, matching hooks. Plugin configs can reference ${CLAUDE_PROJECT_DIR} in commands /mcp Reconnect now picks up .mcp.json edits without a restart, and shows the HTTP status and URL when reconnecting fails /context all per-skill token estimates now account for the model’s tokenizer and show rounded values claude plugin install <name>@<marketplace> now auto-refreshes the marketplace and retries before reporting a plugin as not found /plugin installed-plugin details now show hook event names and MCP server names cleanly /context now shows the providing plugin’s name for plugin-sourced skills x-claude-code-agent-id / x-claude-code-parent-agent-id headers, and claude_code.llm_request OTEL spans include agent_id / parent_agent_id attributes /schedule, claude.ai MCP connectors, and notification preferences are now disabled when ANTHROPIC_API_KEY / apiKeyHelper / ANTHROPIC_AUTH_TOKEN is set, even if a Claude.ai login also exists. Unset the API key to use these features forceRemoteSettingsRefresh policy setting blocked claude auth login/logout/status with no way to recover autoAllowBashIfSandboxed not auto-approving commands with shell expansions like $VAR and $(cmd) Skill(name *) permission rules — the wildcard form now works as a prefix match, matching Bash(ls *) behavior ~/.claude/settings.json /model picker “Default” row not reflecting ANTHROPIC_DEFAULT_OPUS_MODEL/ANTHROPIC_DEFAULT_SONNET_MODEL overrides exit 1 when 10+ MCP servers are configured and the cache directory is unwritable — the error message now includes the underlying cause opus alias @server: autocomplete fs.watch being resurrected when the last subscriber leaves while a fetch is in flight claude_code.active_time.total OpenTelemetry metric not being emitted in --print mode claude plugin update not preserving cross-plugin symlinks inside a marketplace claudeCode.enableReopenClosedSessionShortcut Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL to re-enable the session quality survey for enterprises capturing responses through OpenTelemetry settings.autoMode.hard_deny for auto mode classifier rules that block unconditionally regardless of user intent or allow exceptions .mcp.json, plugins, and claude.ai connectors silently disappearing after /clear in the VS Code extension, JetBrains plugin, and Agent SDK --resume / --continue not finding sessions when the project path contains underscores Edit(...) allow rule exists Stop/UserPromptSubmit hooks failing when cache cleanup deletes a version still in use by a running session @ file picker not matching files created mid-session in small non-git directories @-mention file picker not finding files in directories with more than 100 entries /usage weekly reset showing time of day instead of the calendar date /insights crash when session history contains tool calls with malformed input fields skills entry in plugin.json hiding the plugin’s default skills/ directory, and listing a file path now shows an error instead of failing silently CLAUDE_CONFIG_DIR CLAUDE_ENV_FILE SessionStart hooks going stale after /resume or /clear /branch saving a multi-line session title when given a pasted multi-line name /install-github-app, /desktop, /resume, and /web-setup /doctor MCP schema errors not naming the missing field or showing the source file path /myplugin review) not resolving to their namespaced form AskUserQuestion discarding multi-select answers when supplied as an array /clear <name> not labeling the cleared session for /resume CronList output missing qualifiers and the scheduled prompt /release-notes getting stuck on an old version after a failed changelog refresh /mcp server list not scrolling when there are more servers than fit in the terminal autoScrollEnabled: false keybindings.json /settings language change being reverted on Escape after confirming /terminal-setup only appearing in autocomplete on exact name match instead of partial prefixes AskUserQuestion dialog erasing the question text --worktree collides with an existing or stale worktree d (matching delete elsewhere) instead of r which collided with retry Update Jun 4, 2026 tracked by Updatify
Added worktree.baseRef setting (fresh | head) to choose whether --worktree, EnterWorktree, and agent-isolation worktrees branch from origin/<default> or local HEAD. Note: the default fresh changes EnterWorktree‘s base back to origin/<default> (it has been local HEAD since 2.1.128) — set worktree.baseRef: "head" to keep unpushed commits in new worktrees
sandbox.bwrapPath and sandbox.socatPath managed settings (Linux/WSL) to specify custom bubblewrap and socat binary locations
Added parentSettingsBehavior admin-tier key ('first-wins' | 'merge') to let admins opt SDK managedSettings (parent tier) into the policy merge
effort.level JSON input field and the $CLAUDE_EFFORT environment variable, and Bash tool commands can read $CLAUDE_EFFORT Edit/Write allow rules scoped to a drive root (C:\) or POSIX / matching incorrectly and always prompting ECOMPROMISED) when a history or session-log file lock is compromised by clock skew or slow disk HTTP(S)_PROXY / NO_PROXY / mTLS not being respected for the full MCP OAuth flow including discovery, dynamic client registration, token exchange, and token refresh --add-dir / SDK additionalDirectories /effort in one session unexpectedly changing the effort level of other concurrent sessions, and a related issue where an IDE effort change could be silently dropped claude --help now lists --remote-control alongside --remote-control-session-name-prefix claudeCode.claudeProcessWrapper failing with “Unsupported platform” when the extension build doesn’t bundle a Claude binary Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_SESSION_ID environment variable to the Bash tool subprocess environment, matching the session_id passed to hooks CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 env var to opt out of the fullscreen alternate-screen renderer and keep the conversation in the terminal’s native scrollback kill -INT) not running graceful shutdown — terminal modes are now restored and the --resume hint is printed instead of an abrupt exit --resume failing with no low surrogate in string when a tool error truncation split an emoji; pre-corrupted sessions are sanitized on load --permission-mode flag being ignored when resuming a plan-mode session with -p --continue/--resume, and plan mode not being re-applied after ExitPlanMode within the same session fg until the next keystroke or stream output / silently swallowing the input or triggering an unknown-command reply /usage Ctrl+S hanging when copying the stats screenshot to the clipboard on Linux/X11 /terminal-setup showing a contradictory error in Windows Terminal — Shift+Enter is natively supported there /effort picker not reflecting the CLAUDE_CODE_EFFORT_LEVEL env var override /status showing the wrong default model for some users context_window token counts reflecting cumulative session totals instead of current context usage claude agents tools/list silently showing 0 tools — they now retry once and show “connected · tools fetch failed” in /mcp -p mode retrying non-transient 4xx connection failures /login, /upgrade, /extra-usage dialog spacing /tui fullscreen startup banner to describe additional renderer benefits (lower memory usage, mouse support, auto-copy on select) ENABLE_PROMPT_CACHING_1H is set Update Jun 4, 2026 tracked by Updatify
--plugin-url <url> flag to fetch a plugin .zip archive from a URL for the current session CLAUDE_CODE_FORCE_SYNC_OUTPUT=1 env var to force-enable synchronized output on terminals that auto-detection misses (e.g. Emacs eat) CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE: when set on Homebrew or WinGet installations, Claude Code runs the upgrade command in the background and prompts to restart themes and monitors should now be declared under "experimental": { ... }. Top-level declarations still work but claude plugin validate will warn /v1/models discovery for the /model picker is now opt-in via CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1 (was automatic in 2.1.126–2.1.128) ANTHROPIC_BASE_URL gateway) no longer see spinner tips pointing at first-party Anthropic surfaces skillOverrides setting now works: off hides from model and /, user-invocable-only hides from model only, name-only collapses description claude_code.pull_request.count OTel metric now counts PRs/MRs created via MCP tools, not just shell commands /clear not resetting the terminal tab title after a conversation /rename disappearing while a permission or other dialog is active /context dumping its rendered ASCII visualization grid into the conversation, wasting ~1.6k tokens per call /agents Library list arrow-key navigation: the highlighted agent now stays visible when the list exceeds the viewport /branch success message not including the new branch’s session id for /resume user:inference scope /clear or compaction when changing /effort or /model Bash(mkdir *), Bash(touch *) and similar allow rules not being honored for in-project paths deniedMcpServers patterns with a *:// scheme wildcard not matching mixed-case hostnames --debug during voice mode /clear not clearing the conversation context and displayed transcript Update Jun 4, 2026 tracked by Updatify
/color (no args) now picks a random session color /mcp now shows the tool count for connected servers and flags servers that connected with 0 tools --plugin-dir now accepts .zip plugin archives in addition to directories --channels now works with console (API key) authentication — console orgs with managed settings must set channelsEnabled: true to enable /model picker: collapsed duplicate Opus 4.7 entries, and current Opus now shows as “Opus” instead of “Opus 4.7” OTEL_* environment variables, so OTEL-instrumented apps run via the Bash tool no longer pick up the CLI’s own OTLP endpoint workspace is now a reserved server name — existing servers with that name will be skipped with a warning localSettings suggestion for Bash permission prompts, so “Always allow” writes to .claude/settings.local.json EnterWorktree now creates the new branch from local HEAD as documented, instead of origin/<default-branch> — unpushed commits are no longer dropped /compact, or run with --debug) /exit in Kitty and other terminals that interpret OSC 9 as a notification claude -p via stdin /plugin Components panel showing “Marketplace ‘inline’ not found” for plugins loaded via --plugin-dir /config stranding focus — the tab header now stays focused so arrows and Esc keep working label (url) instead of just the URL /fast on 3P providers fuzzy-matching to an unrelated skill instead of showing “not available” global.* instead of the region-appropriate prefix Space in NORMAL mode now moves the cursor right, matching standard vi/vim behavior /rename without args failing on resumed sessions whose last entry is a compact boundary --resume/--continue installed_plugins.json entries pointing at deleted cache directories polluting PATH CLAUDE_CODE_SHELL_PREFIX is set and an argument contains spaces or shell metacharacters cache_creation reduction) /plugin update never detecting new versions of npm-sourced plugins --output-format stream-json: init.plugin_errors now includes --plugin-dir load failures in addition to dependency demotions Update Jun 4, 2026 tracked by Updatify
/model picker now lists models from your gateway’s /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway claude project purge [path] to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — supports --dry-run, -y/--yes, -i/--interactive, and --all --dangerously-skip-permissions now bypasses prompts for writes to .claude/, .git/, .vscode/, shell config files, and other previously-protected paths (catastrophic removal commands still prompt as a safety net) claude auth login now accepts the OAuth code pasted into the terminal when the browser callback can’t reach localhost (WSL2, SSH, containers) claude_code.skill_activated OpenTelemetry event now fires for user-typed slash commands and carries a new invocation_trigger attribute ("user-slash", "claude-proactive", or "nested-skill") CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST) no longer auto-disable analytics on Bedrock/Vertex/Foundry .NET global tool is now detected allowManagedDomainsOnly / allowManagedReadPathsOnly being ignored when a higher-priority managed-settings source lacked a sandbox block Ctrl+L clearing the prompt input — it now only forces a screen redraw, matching readline behavior context: fork and other subagents on their first turn --channels /plugin Uninstall reporting “Enabled” instead of “Uninstalled” /remote-control retries appearing stuck on “connecting…” — each retry now shows its result -- (e.g. git diff -- file) is no longer mis-flagged as the --% stop-parsing token Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 is set Update Jun 4, 2026 tracked by Updatify
ANTHROPIC_BEDROCK_SERVICE_TIER environment variable to select a Bedrock service tier (default, flex, or priority), sent as the X-Amzn-Bedrock-Service-Tier header /resume search box now finds the session that created that PR (GitHub, GitHub Enterprise, GitLab, and Bitbucket) /mcp now shows claude.ai connectors hidden by a manually-added server with the same URL, with a hint to remove the duplicate /mcp message shown when an MCP server is still unauthorized after the browser sign-in flow api_request/api_error log events are now emitted as numbers, not strings claude_code.at_mention log event for @-mention resolution /branch producing forks that fail with “tool_use ids were found without tool_result blocks” when the source session contained entries from rewound timelines /model not showing the Effort option for Bedrock application inference profile ARNs, and those ARNs not receiving output_config.effort invalid_request_error: output_config: Extra inputs are not permitted on session-title generation and other structured-output queries count_tokens endpoint returning 400 errors for users behind proxy gateways spinnerTipsOverride.excludeDefault not suppressing the time-based spinner tips !exit / !quit in bash mode terminating the CLI instead of running as a shell command tmux -CC control pipes and pause the terminal settings.json no longer invalidating the entire file Update Jun 4, 2026 tracked by Updatify
alwaysLoad option to MCP server config — when true, all tools from that server skip tool-search deferral and are always available claude plugin prune to remove orphaned auto-installed plugin dependencies; plugin uninstall --prune cascades /skills so you can find a skill in long lists without scrolling hookSpecificOutput.updatedToolOutput (previously MCP-only) claude -p: CLAUDE_CODE_FORK_SUBAGENT=1 now works in non-interactive sessions --dangerously-skip-permissions no longer prompts for writes to .claude/skills/, .claude/agents/, and .claude/commands/ /terminal-setup now enables iTerm2’s “Applications in terminal may access clipboard” setting so /copy works, including from tmux language setting mcp_authenticate now supports redirectUri for custom scheme completion and claude.ai connectors stop_reason, gen_ai.response.finish_reasons, and user_system_prompt (gated behind OTEL_LOG_USER_PROMPTS) to LLM request spans accessibility.voice.speechLanguage setting when no Claude Code language is configured /context now opens a native token usage dialog /usage leaking up to ~2GB of memory on machines with large transcript histories --resume crashing on startup in external builds --resume failing on large sessions when a transcript line was corrupted by an unclean shutdown — the corrupt line is now skipped thinking.type.enabled is not supported error when using Bedrock application inference profile ARNs prompt parameter NO_PROXY not being respected for all HTTP clients when set via managed-settings.json under the native build /usage returning “rate limited” after a stale OAuth token — now refreshes automatically settings.json invalidating the entire settings file /usage dialog content being clipped when no-flicker mode is off /focus showing “Unknown command” when the fullscreen renderer is off — now explains how to enable it find in the Bash tool on large directory trees Update Jun 4, 2026 tracked by Updatify
claude ultrareview [target] subcommand to run /ultrareview non-interactively from CI or scripts — prints findings to stdout (--json for raw output) and exits 0 on completion or 1 on failure ${CLAUDE_EFFORT} in their content AI_AGENT environment variable for subprocesses so gh can attribute traffic to Claude Code claude plugin validate now accepts $schema, version, and description at the top level of marketplace.json and $schema in plugin.json auto (lowercase, no token count) instead of a misleading token value /rewind and other interactive overlays not responding to keyboard input after launching with claude --resume DISABLE_TELEMETRY / CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC not suppressing usage metrics telemetry for API and enterprise users /plugin marketplace failing to load when one entry uses an unrecognized source format — that entry is shown but installing it prompts you to update /usage now opens the native Account & Usage dialog instead of returning plain-text session cost language setting in ~/.claude/settings.json find in the Bash tool exhausting open file descriptors on large directory trees, causing host-wide crashes (macOS/Linux native builds) Update Jun 4, 2026 tracked by Updatify
/config settings (theme, editor mode, verbose, etc.) now persist to ~/.claude/settings.json and participate in project/local/policy override precedence prUrlTemplate setting to point the footer PR badge at a custom code-review URL instead of github.com CLAUDE_CODE_HIDE_CWD environment variable to hide the working directory in the startup logo --from-pr now accepts GitLab merge-request, Bitbucket pull-request, and GitHub Enterprise PR URLs --print mode now honors the agent’s tools: and disallowedTools: frontmatter, matching interactive-mode behavior --agent <name> now honors the agent definition’s permissionMode for built-in agents PostToolUse and PostToolUseFailure hook inputs now include duration_ms (tool execution time, excluding permission prompts and PreToolUse hooks) owner/repo#N shorthand links in output now use your git remote’s host instead of always pointing at github.com blockedMarketplaces now correctly enforces hostPattern and pathPattern entries tool_result and tool_decision events now include tool_use_id; tool_result also includes tool_input_size_bytes effort.level and thinking.enabled PostToolUse hooks that emit no response payload writing empty entries to the session transcript ENABLE_TOOL_SEARCH) @-file Tab completion replacing the entire prompt when used inside a slash command with an absolute path p character appearing at the prompt on startup in macOS Terminal.app via Docker or SSH ${ENV_VAR} placeholders in headers for HTTP/SSE/WebSocket MCP servers not being substituted before requests --client-secret not being sent during token exchange for servers requiring client_secret_post /skills Enter key closing the dialog instead of pre-filling /<skill-name> in the prompt /agents detail view mislabeling built-in tools unavailable to subagents as “Unrecognized” /export showing the current default model instead of the model the conversation actually used /usage progress bars overlapping with their “Resets …” labels ${user_config.*} references an optional field left blank /plan and /plan open not acting on the existing plan when entering plan mode /reload-plugins and /doctor reporting load errors for disabled plugins isolation: "worktree" reusing stale worktrees from prior sessions /status TaskList returning tasks in arbitrary filesystem order instead of sorted by ID gh output contained PR titles mentioning “rate limit” read_file not correctly enforcing size cap on growing files /doctor warning about MCP server entries overridden by a higher-precedence scope Update Jun 4, 2026 tracked by Updatify
v) and visual-line mode (V) with selection, operators, and visual feedback /cost and /stats into /usage — both remain as typing shortcuts that open the relevant tab /theme, or hand-edit JSON files in ~/.claude/themes/; plugins can also ship themes via a themes/ directory type: "mcp_tool" DISABLE_UPDATES env var to completely block all update paths including manual claude update — stricter than DISABLE_AUTOUPDATER wslInheritsWindowsSettings policy key "$defaults" in autoMode.allow, autoMode.soft_deny, or autoMode.environment to add custom rules alongside the built-in list instead of replacing it claude plugin tag to create release git tags for plugins with version validation --continue/--resume now find sessions that added the current directory via /add-dir /color now syncs the session accent color to claude.ai/code when Remote Control is connected /model picker now honors ANTHROPIC_DEFAULT_*_MODEL_NAME/_DESCRIPTION overrides when using a custom ANTHROPIC_BASE_URL gateway /doctor and the /plugin Errors tab /mcp menu hiding OAuth Authenticate/Re-authenticate actions for servers configured with headersHelper, and HTTP/SSE MCP servers with custom headers being stuck in “needs authentication” after a transient 401 expires_in requiring re-authentication every hour insufficient_scope 403 names a scope the current token already has ~/.claude/.credentials.json /login having no effect in a session launched with CLAUDE_CODE_OAUTH_TOKEN — the env token is now cleared so disk credentials take effect /plugin badges --dangerously-skip-permissions Stop or SubagentStop prompt hooks re-firing on tool calls made by an agent-hook verifier subagent /fork writing the full parent conversation to disk per fork — now writes a pointer and hydrates on read model setting in ~/.claude/settings.json / plugin install on an already-installed plugin not re-resolving a dependency installed at the wrong version SendMessage not restoring the explicit cwd they were spawned with Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_FORK_SUBAGENT=1 mcpServers are now loaded for main-thread agent sessions via --agent /model: selections now persist across restarts even when the project pins a different model, and the startup header shows when the active model comes from a project or managed-settings pin /resume command now offers to summarize stale, large sessions before re-reading them, matching the existing --resume behavior plugin install on an already-installed plugin now installs any missing dependencies instead of stopping at “already installed” claude plugin marketplace add now auto-resolves missing dependencies from configured marketplaces blockedMarketplaces and strictKnownMarketplaces are now enforced on plugin install, update, refresh, and autoupdate /compact cleanupPeriodDays retention sweep now also covers ~/.claude/tasks/, ~/.claude/shell-snapshots/, and ~/.claude/backups/ user_prompt events now include command_name and command_source for slash commands; cost.usage, token.usage, api_request, and api_error now include an effort attribute when the model supports effort levels. Custom/MCP command names are redacted unless OTEL_LOG_TOOL_DETAILS=1 is set Glob and Grep tools are replaced by embedded bfs and ugrep available through the Bash tool — faster searches without a separate tool round-trip (Windows and npm-installed builds unchanged) where.exe executable lookups per process for faster subprocess launches high (was medium) WebFetch hanging on very large HTML pages by truncating input before HTML-to-markdown conversion TypeError /login having no effect when launched with CLAUDE_CODE_OAUTH_TOKEN env var and that token expires Ctrl+_) doing nothing immediately after typing, and skipping a state on each undo step NO_PROXY not being respected for remote API requests when running under Bun reload_plugins reconnecting all user MCP servers serially elicitation/create requests auto-cancelling in print/SDK mode when the server finishes connecting mid-turn /context percentages and autocompacting too early — Claude Code was computing against a 200K context window instead of Opus 4.7’s native 1M Update Jun 4, 2026 tracked by Updatify
/resume on large sessions is significantly faster (up to 67% on 40MB+ sessions) and handles sessions with many dead-fork entries more efficiently resources/templates/list is now deferred to first @-mention /terminal-setup now configures the editor’s scroll sensitivity /config search now matches option values (e.g. searching “vim” finds the Editor mode setting) /doctor can now be opened while Claude is responding, without waiting for the current turn to finish /reload-plugins and background plugin auto-update now auto-install missing plugin dependencies from marketplaces you’ve already added gh commands hit GitHub’s API rate limit, so agents can back off instead of retrying hooks: now fire when running as a main-thread agent via --agent rm/rmdir targeting /, $HOME, or other critical system directories https://downloads.claude.ai/claude-code-releases instead of https://storage.googleapis.com/claude-code-dist-86c565f3-f756-42ad-8dfa-d59b1c096819/claude-code-releases npx, bun run) /branch rejecting conversations with transcripts larger than 50MB /resume silently showing an empty conversation on large session files instead of reporting the load error /plugin Installed tab showing the same item twice when it appears under Needs attention or Favorites /update and /tui not working after entering a worktree mid-session Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
sandbox.network.deniedDomains setting to block specific domains even when a broader allowedDomains wildcard would otherwise permit them Ctrl+A and Ctrl+E now move to the start/end of the current logical line in multiline input, matching readline behavior Ctrl+Backspace now deletes the previous word /loop: pressing Esc now cancels pending wakeups, and wakeups display as “Claude resuming /loop wakeup” for clarity /extra-usage now works from Remote Control (mobile/web) clients @-file autocomplete suggestions /ultrareview: faster launch with parallelized checks, diffstat in the launch dialog, and animated launching state cd <current-directory> && git … no longer triggers a permission prompt when the cd is a no-op /private/{etc,var,tmp,home} paths are now treated as dangerous removal targets under Bash(rm:*) allow rules env/sudo/watch/ionice/setsid and similar exec wrappers Bash(find:*) allow rules no longer auto-approve find -exec/-delete Ctrl+U to once again delete from the cursor to the start of the line /copy “Full response” not aligning markdown table columns for pasting into GitHub, Notion, or Slack dangerouslyDisableSandbox running commands outside the sandbox without a permission prompt /effort auto confirmation — now says “Effort level set to max” to match the status bar label /insights crashing with EBUSY on Windows CLAUDE_CODE_EXTRA_BODY output_config.effort causing 400 errors on subagent calls to models that don’t support effort and on Vertex AI NO_COLOR is set ToolSearch ranking so pasted MCP tool names surface the actual tool instead of description-matching siblings plugin install succeeding when a dependency version conflicts with an already-installed plugin — now reports range-conflict thinking.type.enabled is not supported 400 error when using Opus 4.7 via a Bedrock Application Inference Profile ARN Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
xhigh effort level for Opus 4.7, sitting between high and max. Available via /effort, --effort, and the model picker; other models fall back to high /effort now opens an interactive slider when called without arguments, with arrow-key navigation between levels and Enter to confirm /theme /less-permission-prompts skill — scans transcripts for common read-only Bash and MCP tool calls and proposes a prioritized allowlist for .claude/settings.json /ultrareview for running comprehensive code review in the cloud using parallel multi-agent analysis and critique — invoke with no arguments to review your current branch, or /ultrareview <PR#> to fetch and review a specific GitHub PR --enable-auto-mode CLAUDE_CODE_USE_POWERSHELL_TOOL. On Linux and macOS, enable with CLAUDE_CODE_USE_POWERSHELL_TOOL=1 (requires pwsh on PATH) ls *.ts) and commands starting with cd <project-dir> && no longer trigger a permission prompt claude <word> is invoked with a near-miss typo (e.g. claude udpate → “Did you mean claude update?”) fix-auth-race-snug-otter.md) instead of purely random words /setup-vertex and /setup-bedrock to show the actual settings.json path when CLAUDE_CONFIG_DIR is set, seed model candidates from existing pins on re-run, and offer a “with 1M context” option for supported models /skills menu now supports sorting by estimated token count — press t to toggle Ctrl+U now clears the entire input buffer (previously: delete to start of line); press Ctrl+Y to restore Ctrl+L now forces a full screen redraw in addition to clearing the prompt input [ (dump to scrollback) and v (open in editor) shortcuts --output-format stream-json now includes plugin_errors on the init event when plugins are demoted for unsatisfied dependencies OTEL_LOG_RAW_API_BODIES environment variable to emit full API request and response bodies as OpenTelemetry log events for debugging @ file suggestions re-scanning the entire project on every turn in non-git working directories, and showing only config files in freshly-initialized git repos with no tracked files /resume immediately resuming an arbitrary titled session instead of showing the session picker /context grid rendering with extra blank lines between rows /clear dropping the session name set by /rename, causing statusline output to lose session_name plugin update; plugin install now recovers from interrupted prior installs commit skill and showing “Unknown skill: commit” for users without a custom /commit command CLAUDE_ENV_FILE and SessionStart hook environment files now apply (previously a no-op) Update Jun 4, 2026 tracked by Updatify
/tui command and tui setting — run /tui fullscreen to switch to flicker-free rendering in the same conversation Ctrl+O to toggle between normal and verbose transcript only; focus view is now toggled separately with the new /focus command autoScrollEnabled config to disable conversation auto-scroll in fullscreen mode Ctrl+G external editor (enable via /config) /plugin Installed tab — items needing attention and favorites appear at the top, disabled items are hidden behind a fold, and f favorites the selected item /doctor to warn when an MCP server is defined in multiple config scopes with different endpoints --resume/--continue now resurrects unexpired scheduled tasks /context, /exit, and /reload-plugins now work from Remote Control (mobile/web) clients TRACEPARENT/TRACESTATE from the environment for distributed trace linking DISABLE_TELEMETRY). Opt out via /config or CLAUDE_CODE_ENABLE_AWAY_SUMMARY=0. plugin.json when the marketplace entry omits them; /plugin install now lists auto-installed dependencies disable-model-invocation: true failing when invoked via /<skill> mid-message --resume sometimes showing the first prompt instead of the /rename name for sessions still running or exited uncleanly /tui, provider setup wizards) PermissionRequest hooks returning updatedInput not being re-checked against permissions.deny rules; setMode:'bypassPermissions' updates now respect disableBypassPermissionsMode PreToolUse hook additionalContext being dropped when the tool call fails CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC or CLAUDE_CODE_DISABLE_TERMINAL_TITLE is set /skills menu not scrolling when the list overflows the modal in fullscreen mode Update Jun 4, 2026 tracked by Updatify
Update Jun 4, 2026 tracked by Updatify
ENABLE_PROMPT_CACHING_1H env var to opt into 1-hour prompt cache TTL on API key, Bedrock, Vertex, and Foundry (ENABLE_PROMPT_CACHING_1H_BEDROCK is deprecated but still honored), and FORCE_PROMPT_CACHING_5M to force 5-minute TTL /config and manually invocable with /recap; force with CLAUDE_CODE_ENABLE_AWAY_SUMMARY if telemetry disabled. /init, /review, and /security-review via the Skill tool /undo is now an alias for /rewind /model to warn before switching models mid-conversation, since the next response re-reads the full history uncached /resume picker to default to sessions from the current directory; press Ctrl+A to show all projects Ctrl+O) DISABLE_PROMPT_CACHING* environment variables /login code prompt (regression in 2.1.105) DISABLE_TELEMETRY falling back to 5-minute prompt cache TTL instead of 1 hour CLAUDE_ENV_FILE (e.g. ~/.zprofile) ends with a # comment line claude --resume <session-id> losing the session’s custom name and color set via /rename --teleport /feedback retry: pressing Enter to resubmit after a failure now works without first editing the description --teleport and --resume <id> precondition errors (e.g. dirty git tree, session not found) exiting silently instead of showing the error message --resume truncating sessions when the transcript contained a self-referencing message language setting is configured Update Jun 4, 2026 tracked by Updatify
path parameter to the EnterWorktree tool to switch into an existing worktree of the current repository {"decision":"block"} monitors manifest key that auto-arms at session start or on skill invoke /proactive is now an alias for /loop /doctor layout with status icons; press f to have Claude fix reported issues /config labels and descriptions for clarity WebFetch to strip <style> and <script> contents from fetched pages so CSS-heavy pages no longer exhaust the content budget before reaching actual text jq for JSON, computed Read chunk sizes for text) rich/loguru logging) package.json and lockfile not having dependencies installed automatically after install/update /resume, --worktree, or /branch /model picker on AWS Bedrock in non-US regions persisting invalid us.* model IDs to settings.json when inference profile discovery is still in-flight /help dropping the tab bar, Shortcuts heading, and footer at short terminal heights keybindings.json being silently loaded instead of rejected with a clear error CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC in one project’s settings permanently disabling usage metrics for all projects on the machine acceptEdits permission mode when exiting plan mode would downgrade from a higher permission level Update Jun 4, 2026 tracked by Updatify
/team-onboarding command to generate a teammate ramp-up guide from your local Claude Code usage CLAUDE_CODE_CERT_STORE=bundled to use only bundled CAs) /ultraplan and other remote-session features now auto-create a default cloud environment instead of requiring web setup first claude -p --resume <name> to accept session titles set via /rename or --name settings.json no longer causes the entire file to be ignored allowManagedHooksOnly is set /plugin and claude plugin update to show a warning when the marketplace could not be refreshed, instead of silently reporting a stale version OTEL_LOG_USER_PROMPTS, OTEL_LOG_TOOL_DETAILS, and OTEL_LOG_TOOL_CONTENT; sensitive span attributes are no longer emitted unless opted in query() to clean up subprocess and temp files when consumers break from for await or use await using which fallback used by LSP binary detection --resume/--continue losing conversation context on large sessions when the loader anchored on a dead-end branch instead of the live conversation --resume chain recovery bridging into an unrelated subagent conversation when a subagent message landed near a main-chain write gap --resume when a persisted Edit/Write tool result was missing its file_path API_TIMEOUT_MS permissions.deny rules not overriding a PreToolUse hook’s permissionDecision: "ask" — previously the hook could downgrade a deny into a prompt --setting-sources without user causing background cleanup to ignore cleanupPeriodDays and delete conversation history older than 30 days ANTHROPIC_AUTH_TOKEN, apiKeyHelper, or ANTHROPIC_CUSTOM_HEADERS set an Authorization header claude -w <name> failing with “already exists” after a previous session’s worktree cleanup left a stale directory mktemp: No such file or directory after a fresh boot claude mcp serve tool calls failing with “Tool execution failed” in MCP clients that validate outputSchema RemoteTrigger tool’s run action sending an empty body and being rejected by the server /resume picker issues: narrow default view hiding sessions from other projects, unreachable preview on Windows Terminal, incorrect cwd in worktrees, session-not-found errors not surfacing in stderr, terminal title not being set, and resume hint overlapping the prompt input rg and self-heals mid-session /btw writing a copy of the entire conversation to disk on every use /context Free space and Messages breakdown disagreeing with the header percentage name: frontmatter, /plugin update failing with ENAMETOOLONG, Discover showing already-installed plugins, directory-source plugins loading from a stale version cache, and skills not honoring context: fork and agent frontmatter fields /mcp menu offering OAuth-specific actions for MCP servers configured with headersHelper; Reconnect is now offered instead to re-invoke the helper script ctrl+], ctrl+\, and ctrl+^ keybindings not firing in terminals that send raw C0 control bytes (Terminal.app, default iTerm2, xterm) /login OAuth URL rendering with padding that prevented clean mouse selection settings.json env values are numbers instead of strings /add-dir --remember, /config) not refreshing the in-memory snapshot, preventing removed directories from being revoked mid-session ~/.claude/keybindings.json) not loading on Bedrock, Vertex, and other third-party providers claude --continue -p not correctly continuing sessions created by -p or the SDK /remote-control failing over SSH when only CLAUDE_CODE_ORGANIZATION_UUID is set /insights sometimes omitting the report file link from its response Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_PERFORCE_MODE env var: when set, Edit/Write/NotebookEdit fail on read-only files with a p4 edit hint instead of silently overwriting them CLAUDE_CODE_SUBPROCESS_ENV_SCRUB is set, and CLAUDE_CODE_SCRIPT_CAPS env var to limit per-session script invocations --exclude-dynamic-system-prompt-sections flag to print mode for improved cross-user prompt caching workspace.git_worktree to the status line JSON input, set whenever the current directory is inside a linked git worktree TRACEPARENT env var to Bash tool subprocesses when OTEL tracing is enabled, so child-process spans correctly parent to Claude Code’s trace tree clientInfo in the initialize request LANG, TZ, NO_COLOR, etc.) /dev/tcp/... or /dev/udp/... not prompting instead of auto-allowing Retry-After — exponential backoff now applies as a minimum oauth.authServerMetadataUrl config override not being honored on token refresh after restart, affecting ADFS and similar IdPs --dangerously-skip-permissions being silently downgraded to accept-edits mode after approving a write to a protected path via Bash permissions.additionalDirectories changes not applying mid-session — removed directories lose access immediately and added ones work without restart additionalDirectories revoking access to the same directory passed via --add-dir Bash(cmd:*) and Bash(git commit *) wildcard permission rules failing to match commands with extra spaces or tabs Bash(...) deny rules being downgraded to a prompt for piped commands that mix cd with other segments cut -d /, paste -d /, column -s /, awk '{print $1}' file, and filenames containing % toString) causing settings.json to be silently ignored --dangerously-skip-permissions --resume when the edited file was larger than 10KB /resume picker issues: --resume <name> opening uneditable, filter reload wiping search state, empty list swallowing arrow keys, cross-project staleness, and transient task-status text replacing conversation summaries /export not honoring absolute paths and ~, and silently rewriting user-supplied extensions to .txt /effort max being denied for unknown or future model IDs name is a YAML boolean keyword _meta["anthropic/maxResultSizeChars"] not bypassing the token-based persist layer DISABLE_AUTOUPDATER not fully suppressing the npm registry version check and symlink modification on npm-based installs grep -f FILE / rg -f FILE not prompting when reading a pattern file outside the working directory sandbox.network.allowMachLookup not taking effect on macOS /resume filter hint labels and added project/worktree/branch names in the filter indicator /agents with a tabbed layout: a Running tab shows live subagents, and the Library tab adds Run agent and View running instance actions /reload-plugins to pick up plugin-provided skills without requiring a restart j/k in NORMAL mode now navigate history and select the footer pill at the input boundary --debug /claude-api skill to cover Managed Agents alongside Claude API CLAUDE_CODE_GIT_BASH_PATH is set or Git is installed at a default location CLAUDE_CODE_MAX_CONTEXT_TOKENS to honor DISABLE_COMPACT when it is set. /compact hints when DISABLE_COMPACT is set. Update Jun 4, 2026 tracked by Updatify
Ctrl+O) in NO_FLICKER mode showing prompt, one-line tool summary with edit diffstats, and final response refreshInterval status line setting to re-run the status line command every N seconds workspace.git_worktree to the status line JSON input, set when the current directory is inside a linked git worktree ● N running indicator in /agents next to agent types with live subagent instances .cedar, .cedarpolicy) --dangerously-skip-permissions being silently downgraded to accept-edits mode after approving a write to a protected path toString) causing settings.json to be silently ignored permissions.additionalDirectories changes in settings not applying mid-session settings.permissions.additionalDirectories revoking access to the same directory passed via --add-dir oauth.authServerMetadataUrl not being honored on token refresh after restart, fixing ADFS and similar IdPs Retry-After — exponential backoff now applies as a minimum /resume picker issues: --resume <name> opening uneditable, Ctrl+A reload wiping search, empty list swallowing navigation, task-status text replacing conversation summary, and cross-project staleness --resume when the edited file was larger than 10KB --resume cache misses and lost mid-turn input from attachment messages not being saved to the transcript Stop/SubagentStop hooks failing on long sessions, and hook evaluator API errors displaying “JSON validation failed” instead of the actual message cwd: override leaking their working directory back to the parent session’s Bash tool claude plugin update reporting “already at the latest version” for git-based marketplace plugins when the remote had newer commits name is a YAML boolean keyword NO_FLICKER mode inserting spaces at line breaks NO_FLICKER mode when running inside zellij NO_FLICKER mode when hovering over MCP tool results NO_FLICKER mode memory leak where API retries left stale streaming state NO_FLICKER mode on Windows Terminal NO_FLICKER mode on terminals shorter than 24 rows NO_FLICKER mode AWS_BEARER_TOKEN_BEDROCK or ANTHROPIC_BEDROCK_BASE_URL are set to empty strings (as GitHub Actions does for unset inputs) LANG=C rm foo, timeout 5 mkdir out) sandbox.network.allowMachLookup now takes effect on macOS @-mention completion to trigger after CJK sentence punctuation, so Japanese/Chinese input no longer requires a space before / or @ TRACEPARENT env var when tracing is enabled /claude-api skill to cover Managed Agents alongside the Claude API Update Jun 4, 2026 tracked by Updatify
403 "Authorization header is missing" when using AWS_BEARER_TOKEN_BEDROCK or CLAUDE_CODE_SKIP_BEDROCK_AUTH (regression in 2.1.94) Update Jun 4, 2026 tracked by Updatify
CLAUDE_CODE_USE_MANTLE=1 /effort) Slacked #channel header with a clickable channel link for Slack MCP send-message tool calls keep-coding-instructions frontmatter field support for plugin output styles hookSpecificOutput.sessionTitle to UserPromptSubmit hooks for setting the session title "skills": ["./"] now use the skill’s frontmatter name for the invocation name instead of the directory basename, giving a stable name across install methods claude doctor diagnoses the fix CLAUDE_PLUGIN_ROOT was not set ${CLAUDE_PLUGIN_ROOT} resolving to the marketplace source directory instead of the installed cache for local-marketplace plugins on startup ❯ caret instead of under the text FORCE_HYPERLINK environment variable being ignored when set via settings.json env us. inference profile ID --resume to resume sessions from other worktrees of the same repo directly instead of printing a cd command settings.json files fail to parse, so users know their permission rules are not being applied Update Jun 4, 2026 tracked by Updatify
forceRemoteSettingsRefresh policy setting: when set, the CLI blocks startup until remote managed settings are freshly fetched, and exits if the fetch fails (fail-closed) /cost for subscription users /release-notes is now an interactive version picker myhost-graceful-unicorn), overridable with --remote-control-session-name-prefix ok:false, and restored preventContinuation:true semantics for non-Stop prompt-type hooks claude-code → stable, claude-code@latest → latest) ctrl+e jumping to the end of the next line when already at end of line in multiline prompts &/$) /tag command /vim command (toggle vim mode via /config → Editor mode) apply-seccomp helper in both npm and native builds, restoring unix-socket blocking for sandboxed commands