Releases: marckrenn/claude-code-changelog
Release list
v2.1.241
2.1.241
Highlights:
- CLI bug fixes and reliability improvements reduce crashes and make commands more stable
CLI changelog
- Bug fixes and reliability improvements
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21241
Metadata
-
Time since 2.1.240 release: 17h 39m 9s
-
Bundle file size: +96.9 kB (+0.2%)
-
Prompt files: +3 (+4.8%)
-
Prompt tokens: +12,102 (+4.9%)
Prompt token mix by kind:
- system: 71.3%→70.9%
- tools: 28.7%→29.1%
Files:
v2.1.240
2.1.240
Highlights:
- Bug fixes and reliability improvements to the CLI to reduce crashes and improve error messages
- CLI fixes reduce crashes and improve command consistency, leading to fewer interruptions and steadier results
CLI changelog
- Bug fixes and reliability improvements
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21240
Metadata
-
Time since 2.1.239 release: 1d 0h 27m 9s
-
Bundle file size: -69.3 kB (-0.1%)
-
Prompt files: +3 (+5.0%)
-
Prompt tokens: +11,921 (+5.1%)
Prompt token mix by kind:
- system: 71.8%→71.3%
- tools: 28.2%→28.7%
Files:
v2.1.239
2.1.239
Highlights:
- Cost estimates (/cost, status, --max-budget-usd) add 1.1× US-only premium so budgets reflect residency costs
- Fixed Bedrock streaming behind proxies that stripped Content-Type, preventing replays that doubled API charges
- Synced plugins from claude.ai appear as name@synced, can be enabled/disabled, and won't override local plugins
CLI changelog
- Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and other previously excluded setups; new installs there now start in fullscreen
- Added /claude-api upgrade to migrate Python projects from anthropic 0.x to 1.x, and updated the skill's Python reference for 1.x (timeouts use anthropic.Timeout, not httpx.Timeout)
- Fixed Bedrock streaming behind proxies that strip the response Content-Type header, which silently doubled billed API calls by re-running every turn non-streaming
- Fixed Claude Code hanging at startup behind an HTTPS proxy when using Bedrock with an SSO profile and awsAuthRefresh — the credential pre-check now honors HTTPS_PROXY
- Fixed a raw crash dump when starting Claude Code from a directory that no longer exists; it now prints a clear message
- Fixed Edit and Write calls pausing for about 5 seconds in JetBrains IDE terminals when the Claude Code plugin is connected
- Fixed a race where pressing Esc with a prompt queued could let the next turn finish early, leaving the session idle while Claude was still working and letting a later resubmit repeat actions
- Fixed WebFetch retaining expired page content in memory for the whole session instead of the intended 15 minutes
- Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) resuming out of plan mode after an idle worker restart
- Fixed MCP elicitation forms taller than the terminal being clipped in fullscreen mode: the form now fits the window, with hidden fields reachable by scrolling and Accept/Decline always visible
- Fixed remote MCP servers staying failed after a transient 5xx on a mid-session reconnect in cloud sessions or via SDK setMcpServers()
- Fixed custom session titles disappearing from /resume after more than ~64 KB of conversation was written following the rename
- … +47 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21239
Metadata
-
Time since 2.1.238 release: 13h 32m 3s
-
Bundle file size: +238.6 kB (+0.5%)
-
Prompt files: +3 (+5.3%)
-
Prompt tokens: +11,753 (+5.3%)
Prompt token mix by kind:
- system: 72.3%→71.8%
- tools: 27.7%→28.2%
Files:
v2.1.238
2.1.238
Highlights:
- Plugin headersHelper now runs only at install/update and prompts [y/N], stopping silent header minting
- Subagent tool results released once out of view to stop unbounded memory growth in long sessions
- Self-hosted runner defers SIGTERM for a set interval, keeping attached sessions alive to avoid abrupt loss
CLI changelog
- Added a keybindingFlavor setting: set it to "readline" to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ("classic") is unchanged
- Added claude self-hosted-runner --defer-shutdown-max-min : on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit
- Added claude self-hosted-runner --proxy-authorization-command / --proxy-authorization-file for egress proxies that require a freshly issued Proxy-Authorization header on every connection
- Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window
- Fixed custom, project, and plugin output styles drifting back to the default voice mid-session
- Fixed CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=true not keeping prompt suggestions on when your account is near, but not over, its usage limit
- Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none
- Fixed self-hosted runners occasionally being removed by the server after a single slow or lost poll request, handing their healthy session to another runner
- Fixed MCP elicitation dialogs showing nothing for URLs longer than 4,096 characters, and permission prompts dropping the "don't ask again" option when the project path didn't fit the terminal width
- Fixed leftover /tmp/claude-*-cwd files when a Bash command is killed, times out, or is interrupted
- Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)
- Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped
- … +27 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21238
Metadata
-
Time since 2.1.237 release: 16h 52m 49s
-
Bundle file size: +554.4 kB (+1.1%)
-
Prompt files: +3 (+5.6%)
-
Prompt tokens: +11,598 (+5.5%)
Prompt token mix by kind:
- system: 72.8%→72.3%
- tools: 27.2%→27.7%
Files:
v2.1.237
2.1.237
Highlights:
- Fixed prompt caching for sessions using LLM gateways or custom base URLs to prevent stale prompts
- Added a built-in 'Concise' output style that leads with results and skips preamble for short focused replies
CLI changelog
- Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output style in /config.
- Fixed prompt caching for sessions using an LLM gateway or custom base URL
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21237
Metadata
-
Time since 2.1.236 release: 5h 50m 7s
-
Bundle file size: +30.0 kB (+0.1%)
-
Prompt files: +3 (+5.9%)
-
Prompt tokens: +11,456 (+5.8%)
Prompt token mix by kind:
- system: 73.3%→72.8%
- tools: 26.7%→27.2%
Files:
v2.1.236
2.1.236
Highlights:
- ANTHROPIC_DEFAULT_MODEL sets the model new sessions start on, while /model still overrides and persists
- macOS sandbox: wildcard read-deny now override allowed regions and prevent renames bypassing matched paths
- SendMessage adds notify_when_idle to request one-off opt-in idle notice from another session, no polling
CLI changelog
- Added ANTHROPIC_DEFAULT_MODEL environment variable: sets the model new sessions start on, while a /model pick still overrides it and persists across restarts (unlike ANTHROPIC_MODEL)
- Added notify_when_idle to cross-session SendMessage: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no polling (macOS and Linux)
- Fixed clipboard copy, background housekeeping, background sessions, and local MCP logs breaking after the directory a session had switched into was removed (since 2.1.229)
- Fixed the fullscreen renderer failing permanently after a single failed start: it now falls back to the classic renderer instead of exiting on every subsequent launch
- Fixed the /model picker rendering taller than the terminal: it now shows only as many models as fit the window, with the rest reachable by scrolling
- Fixed SendMessage calls being rejected when a malformed closing tag left the message text inside the summary field
- Fixed unhandled promise rejections when a subprocess fails to start, for example powershell.exe on WSL with Windows interop disabled (regression in 2.1.234)
- Fixed fullscreen mode sometimes not showing a newly sent message until the next update after the terminal was resized
- Fixed a blank band that could remain above the prompt after clearing a multi-line prompt, and panes not repainting after resizing the terminal away and back, in fullscreen mode
- Fixed the managed-settings approval prompt sometimes not appearing at startup while still capturing the first keypress as approval
- Fixed terminal tab titles jumping in tmux (iTerm tmux integration): the title is now written only when its text changes instead of animating every 960ms
- Fixed an unclear error when the cloud environments list came back empty or malformed
- … +21 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21236
Metadata
-
Time since 2.1.235 release: 1d 14h 57m 50s
-
Bundle file size: +435.0 kB (+0.9%)
-
Prompt files: +3 (+6.2%)
-
Prompt tokens: +11,327 (+6.1%)
Prompt token mix by kind:
- system: 73.8%→73.3%
- tools: 26.2%→26.7%
Files:
v2.1.235
2.1.235
Highlights:
- Optional spellcheck underlines typos in prompts via local aspell/hunspell/ispell, improving prompt accuracy
- SendMessage now rejects messages too large for cross-session delivery up front, preventing lost output
- Dialogs show exact grant text and add 'withhold - don't ask again' when hidden, preventing accidental grants
CLI changelog
- Added an optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell
- Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session
- Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI
- Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts
- Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field
- Fixed the Agent tool advertising a general-purpose default in sessions where that agent is unavailable: an omitted subagent_type there now gets a clear error listing the available agents
- Fixed notebook cell delete/replace approval dialogs silently omitting the existing cell content when the notebook or cell could not be read; the dialog now says why
- Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters
- Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update
- Fixed the expanded task list (ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks
- Improved memory and CPU usage while cloud sessions such as /ultrareview or /autofix-pr run in the background — their event streams are no longer re-scanned and re-rendered on every update
- Improved permission dialogs: display text and "don't ask again" options now always match what a grant would cover, and "don't ask again" is withheld when contents cannot be fully displayed
- … +7 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21235
Metadata
-
Time since 2.1.234 release: 1d 0h 7m 3s
-
Bundle file size: +352.8 kB (+0.7%)
-
Prompt files: +3 (+6.7%)
-
Prompt tokens: +11,211 (+6.4%)
Prompt token mix by kind:
- system: 74.3%→73.8%
- tools: 25.7%→26.2%
Files:
v2.1.234
2.1.234
Highlights:
- Claude Code automatically resumes sessions when a claude.ai usage limit resets, avoiding session interruptions
- Account email used only for ID and not sent to unrelated services unless requested, preventing sharing
- Remote reads, session restore and uploads now reject NT-namespace (??) paths, blocking NT-path access
CLI changelog
- Added the optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory
- Added the selection:clear keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view
- Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states
- Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted
- Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts
- Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field
- Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences
- Fixed SendMessage rejecting a recipient copied from ListAgents when the session name is at the 200-character cap or emoji-heavy
- Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host
- Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured ${VAR} form, and connection-failure details show only the server origin
- Fixed strictKnownMarketplaces allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to
- Fixed modal text such as the /login OAuth URL losing characters when copied in fullscreen
- … +39 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21234
Metadata
-
Time since 2.1.233 release: 2d 7h 58m 50s
-
Bundle file size: +543.8 kB (+1.1%)
-
Prompt files: +3 (+7.1%)
-
Prompt tokens: +11,095 (+6.7%)
Prompt token mix by kind:
- system: 74.9%→74.3%
- tools: 25.1%→25.7%
Files:
v2.1.233
2.1.233
Highlights:
- Added opt-in memory cgroup via CLAUDE_CODE_TOOL_MEMORY_LIMIT to keep Bash tool runs from stalling sessions
- GitLab MR URLs accepted by --worktree and shown as !N in claude agents, enabling MR linking/navigation
- Windows path handling blocks ??\ NT path bypass and revalidates UNC paths to prevent NTLM credential leaks
CLI changelog
- Added GitLab merge request URL support to the --worktree flag and the claude agents view (where MRs display as !N)
- Added an opt-in forward_user_identity apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user
- Added opt-in memory cgroup support for Bash tool commands on Linux (CLAUDE_CODE_TOOL_MEMORY_LIMIT) so a runaway build can't stall the session
- Added CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)
- Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt
- Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)
- Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code
- Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled
- Fixed bundled skill aliases like /checkup and /review reporting "Unknown command" in -p mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill
- Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers
- Fixed Windows paths spelled with the NT ??\ device prefix bypassing UNC path validation, closing an NTLM credential-leak vector
- Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway
- … +8 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21233
Metadata
-
Time since 2.1.232 release: 1d 0h 36m 21s
-
Bundle file size: +113.0 kB (+0.2%)
-
Prompt files: +2 (+5.0%)
-
Prompt tokens: +10,771 (+7.0%)
Prompt token mix by kind:
- system: 75.3%→74.9%
- tools: 24.7%→25.1%
Files:
v2.1.232
2.1.232
Highlights:
- Subagent forking now default; forked subagents inherit convo+prompt cache so spawned agents retain context
- GitLab token prefixes (glrt, gloas, glptt, glagent, etc.) redacted; routable glpat/gldt removed to avoid leaks
- Prompt @name mentions send SendMessage directly to the named Claude session, enabling cross-session messaging
CLI changelog
- Added /config rows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse)
- Added secret redaction for GitLab token families (glrt-, gloas-, glptt-, glagent-, glimt-, glsoat-, glcbt-, glft-, glffct-) and full redaction of routable glpat-/gldt- tokens; the glab CLI config store gets the same sandbox and credential-path protection as gh
- Added GitLab support to plugin marketplaces: bare gitlab.com repo URLs (including nested subgroups) now clone like github.com URLs, and clone auth-failure hints name your actual git host
- Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite $PSDefaultParameterValues and redirect later commands' file access
- Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval
- Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation
- Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe
- Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials
- Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one
- Fixed Remote Control sessions appearing unreachable to newly attached clients while idle
- Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts
- Fixed Cloud gateway /login exiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown
- … +37 more CLI changelog entries
Source: https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md#21232
Metadata
-
Time since 2.1.231 release: 9h 20m 0s
-
Bundle file size: +1,373.9 kB (+3.0%)
-
Prompt files: +2 (+5.3%)
-
Prompt tokens: +10,771 (+7.5%)
Prompt token mix by kind:
- system: 75.8%→75.3%
- tools: 24.2%→24.7%
Files: