Claude Code changelog changedchangelog
Nearest release: v2.1.301, published 5 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 15 Oct 2026 19:53 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 15 Oct 2026 20:07 UTC.
Upstream edited
Recorded here
Lines+65added
Lines−0removed
From line
6
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits70to this page, all time
The whole hunk
from line 6, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 6
66
77Run `claude --version` to check your installed version.
88
9<Update label="2.1.301" description="October 15, 2026">
10 **Added**
11
12 * Added `CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS` so unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`) ends a request at a usage limit that resets too far away instead of waiting
13 * Added OpenTelemetry tracing guidance to the `claude-api` skill, including setting up trace destinations with the `ant` CLI
14 * Added the `%` motion to vim mode: jump to the matching bracket, alone or with d/c/y
15 * Added `rows` to a mod's `Input`: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line
16 * Added `classifier_verdict` and `permission_mode` to OpenTelemetry `tool_decision` events, so auto mode classifier decisions can be told apart from permission rules
17 * Added `classifier_category` to OpenTelemetry `tool_decision` events, naming the built-in rule a classifier block matched, when `OTEL_LOG_TOOL_DETAILS=1`
18 * \[VSCode] Added LaTeX math rendering in Claude's responses, including `$$` and multi-line `\[ … \]` blocks and inline `$…$` and `\(…\)` math
19 * \[VSCode] Added a "Get more usage" link to the usage-limit banner for Pro and Max plans in the VS Code and JetBrains panels
20
21 **Changed**
22
23 * Changed a mod hook's `.catch` handler to run only when the hook throws or times out; events raised beneath the hook's own calls now skip that hook without asking its `.catch`
24 * Changed a mod's `$.env.set` to resolve with `{}` once the variable is set or unset, or with `{ deny }` saying why when the write is not made
25
26 **Improved**
27
28 * Improved switching to a model with a smaller context window: a conversation too long for the new model is now summarized by the previous model first
29 * Improved rendering performance while a long-running subagent works: its progress trail now updates incrementally instead of being reprocessed in full on every render
30 * Improved artifacts: pages Claude writes now paint the band above a sticky header, so scrolled text no longer shows there in the mobile apps
31 * Improved mods: in VS Code and the desktop and mobile apps, a tree drawn above the question dialog can now hold Markdown and up to 48 rows; the terminal keeps 12 plain rows
32
33 <Expandable title="37 bug fixes">
34 - Fixed quitting removing a worktree made by a `WorktreeCreate` hook without asking when it may hold unpushed commits
35 - Fixed the `fable` (and `best`) model alias erroring on the Anthropic API when the newest Fable model is not available to your organization: Claude Code now retries once on the previous Fable model
36 - Fixed a misleading "Please run /login" error when a full disk keeps the login from being refreshed; the error now names the disk and says to delete files
37 - Fixed Grep and Glob reporting no matches when the search program failed unexpectedly before returning any results; they now return an error saying the search failed
38 - Fixed workflow agents sometimes skipping their step, and the run still reporting success, after reading the harness note that their task text carries no user authority
39 - Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call
40 - Fixed skills and commands with very many or very long argument names stalling for seconds when invoked; only the first 64 names, each up to 64 characters, are now filled in
41 - Fixed skills, commands and hooks using very large amounts of memory when their arguments fill many placeholders
42 - Fixed stray characters such as `>0q` covering the folder trust prompt, and `>4m` before the shell prompt at exit, in terminals built on VTE older than 0.53 such as MATE Terminal on RHEL 8
43 - Fixed stray `GOK` text appearing in the prompt at startup in some versions of iTerm2
44 - Fixed switching to a model whose name contains `application-inference-profile` running your `awsAuthRefresh` command and delaying model-switch hooks when the provider is not Bedrock
45 - Fixed sign-in refresh timeouts and unexpected sign-outs after a short command such as `claude auth status` or `claude plugin list` exited in the middle of a token refresh
46 - Fixed a tool call cut off by a message sent mid-turn during its permission check being reported to the model as rejected by the user
47 - Fixed a case where switching to a model with a smaller context window could spend usage credits on a summary by the previous model without asking first
48 - Fixed conversations being compacted over and over, on a model you didn't pick, behind an LLM gateway whose responses name a different model than the one requested
49 - Fixed vim mode sometimes staying in INSERT after Escape on a slow or busy machine
50 - Fixed Esc discarding a typed AskUserQuestion answer in vim mode: the free-text field now supports vim NORMAL mode, and Esc cancels only from NORMAL
51 - Fixed the Read tool reading binary files such as .xlsm, .parquet, .epub and .heic as text
52 - Fixed a Markdown table with only a header row drawing nothing when too wide for the terminal, including in plans on the plan approval card
53 - Fixed the /claude-api skill saying CMEK external-key endpoints aren't available on Claude Platform on AWS
54 - Fixed skills no longer being listed to the model after using `/rewind`
55 - Fixed the compaction row in a resumed session offering ctrl+o for history that is not loaded; it now says where the earlier messages are saved, and also shows in fullscreen
56 - Fixed the "new task? /clear to save tokens" hint coming back right after you interrupt a response
57 - Fixed the permission prompt for a plugin or skill hook's `ask` decision not showing which plugin or skill the hook comes from
58 - Fixed `/diff` not noticing a conflicted cherry-pick or revert in reftable repositories when one of its git checks timed out or failed
59 - Fixed workflow scripts asking for permission or being refused when read, edited or re-run after a Bash `cd` in the same session
60 - Fixed dim text on the dark ANSI theme and 16-color terminals: faint inside filled boxes, not faint under selection and search highlights, and list descriptions dimmed like other secondary text
61 - Fixed a mod's `$.model.fork` returning `nothing-to-fork` when called before the first response of a new Claude Code process had finished, as in `claude -p` runs and cloud sessions
62 - Fullscreen mode: Fixed `/compact` and auto-compact briefly freezing the UI while the visible transcript is rebuilt
63 - Self-hosted runner: Fixed sessions started from Slack being unable to find or attach a repository when managed settings restrict MCP servers; use `deniedMcpServers` to keep those tools off
64 - Self-hosted runner: Fixed sessions being reported as having a deleted source branch, and not retried, when an unrelated setup or session failure quoted git's missing-ref wording
65 - Self-hosted runner: Fixed the log promising a retry of a failed or declined session release for a session that is ending; repeated failures now show a count
66 - Windows: Fixed stopped background PowerShell commands missing the closing `[killed]` line in their output file
67 - \[VSCode] Fixed a conversation that crashes or freezes the panel being reopened on every reload
68 - \[VSCode] Fixed the chat panel slowing down during long thinking: it no longer re-parses the whole thinking text on every update
69 - \[VSCode] Fixed diagnostics showing "\[object Object]" instead of the rule code (e.g. MD013) for some language servers
70 - \[VSCode] Fixed the native dictation audio module being loaded, to check microphone permission, where dictation is not offered (non-claude.ai sign-ins, remote windows)
71 </Expandable>
72</Update>
73
974<Update label="2.1.300" description="October 14, 2026">
1075 **Added**
1176
from line 1917
18521917 - Improved keyboard navigation in tabbed dialogs such as `/permissions` and `/usage`: ↑/↓ move focus between the tab row and the content, and a list responds to keys only while it has focus
18531918 - Improved `/help` and `/sandbox`: ←/→ and Tab switch tabs from inside a tab's list, and ↓ on an empty Custom commands tab in `/help` no longer leaves the keys stuck until Esc
18541919 - Improved `/install-github-app`, `/desktop`, the `/permissions` auto mode environment prompts, and the `/plugin` "Add marketplace?" and "Run this command?" prompts: they now use the standard dialog frame with key hints, and Ctrl+C or Ctrl+D cancels them on the second press like other dialogs
1855 - Improved the `/workflows` and `/mcp` lists: they page (PgUp/PgDn, Home/End) and take j/k and the mouse like other lists, their arrows follow `select:previous`/`select:next` rebinds, and `x` in `/workflows` stops the run the pointer is on
1856 - Improved the `/plugin` plugin and marketplace details menus and the `/remote-control` already-connected menu: they now support Home/End and clicking a row
1857 - Improved the background workflow row below the prompt: it now shows the name, a progress bar, the agent count on wide terminals, elapsed time, total tokens, and the large-workflow warning
1858 - Improved the /plugin Installed list: rows now line up in columns (status, name, type, details) across every section
1859 - Improved `/skills`: each row now leads with the skill's name, with ✔ or ◯ alone showing on or off, and stays on one line in narrow terminals
1860 - Improved narrow list rows (`/skills`, `/workflows`, `/feedback`): a name keeps 20 columns beside its first detail, and details are shown whole or not at all
1861 - Improved `/diff`: a scrollbar shows where you are in a long list of changed files, and long paths no longer wrap their rows
1862 - Improved `/hooks`: a hook's detail screen now says what kind of hook it is and where to change it, instead of always pointing at settings.json, and the hooks-disabled, safe mode and managed-hooks-only notices each say what is happening in one plain sentence
1863 - Improved screen-reader output in `/mcp`: a disabled server is read as "off" instead of "pending"
1864 - Improved the Remote Control confirmation: its options are briefly inactive again after the terminal window regains focus, so a key pressed while switching back cannot answer it
1865 - \[Claude Code on the web] Improved the file card shown when a cloud session can't open a file: it now says whether the file no longer exists or the session's permission settings block reading it
1866 </Expandable>
1867
1868 <Expandable title="112 bug fixes">
1869 * Fixed a crash ("unrecoverable interface error") that could end a session while an API request was being retried
1870 * Fixed a turn that could retry indefinitely, ignoring `--max-turns`, when the model alternated unparseable tool calls and output-limit truncation
1871 * Fixed resumed sessions re-sending earlier turns in a changed form (a parallel tool-call turn, an MCP tool call's input or a tool-search result while its server was still reconnecting, or a tool-search result whose loading turn was interrupted), which could make the API drop the conversation's prior reasoning
1872 * Fixed resuming a very large session sometimes restoring only its last few messages
1873 * Fixed a session resumed after a restart during a pending permission prompt sending a different history than before, which broke the prompt cache from that point
1874 * Fixed resuming a session that ended during a tool call: Claude now sees the call and is told its outcome is unknown, and a manual resume no longer adds a hidden "Continue" message
1875 * Fixed sessions with an earlier advisor result the API could no longer read failing one request every turn and repeatedly losing earlier reasoning; the history is now repaired once
1876 * Fixed the prompt cache being lost when an MCP server disconnects mid-conversation, or is still connecting after a resume, while tool search is off (for example behind a proxy or gateway)
1877 * Fixed responses cut short by a proxy or gateway that closes the stream cleanly being shown as complete with no warning, and tool calls running twice on duplicated stream events
1878 * Fixed responses failing with "Content block not found" when a proxy drops a stream event mid-response; the partial response is now kept, and web search keeps results that already arrived
1879 * Fixed an empty completed response being requested twice when the connection dropped before the stream's final event
1880 * Fixed the stop reason being lost when a proxy sends a trailing usage-only frame
1881 * Fixed `CLAUDE_CODE_RETRY_WATCHDOG` sessions failing on the first 5xx or dropped connection after a run of 429/529 waits, and sleeping uncapped and silently on a long `Retry-After` from a 5xx
1882 * Fixed fast mode retrying rate-limited requests back to back when the server sent `Retry-After: 0`
1883 * Fixed a tool that returned an oversized image leaving sibling tool calls unanswered and still running, or ending the turn with no final message
1884 * Fixed conversations getting permanently stuck on "tool\_use.name: String should have at most 200 characters" after the model called a tool by an overlong name
1885 * Fixed tool calls failing with "Failed to get memory usage", or being reported as failed after they ran, when Claude Code cannot read its own memory usage, for example when it has run out of file descriptors
1886 * Fixed `--input-format stream-json` sessions (Agent SDK, VS Code extension) and scheduled cloud sessions failing every turn with an error when an earlier assistant message had plain-string content
1887 * Fixed non-interactive sessions (`-p`, Agent SDK) failing on the next turn after the directory they were started in was deleted mid-session
1888 * Fixed headless sessions with host-side (SDK) MCP servers stalling on the first message when the host stops responding mid-handshake; remote sessions now wait a few seconds at most
1889 * Fixed interactive startup waiting on the managed-settings network request (about 80 ms, 17+ seconds when the network is unreachable) when no MCP servers or plugins are configured
1890 * Fixed a delay of up to two minutes before responding when reading or @-mentioning a PDF larger than 3 MB
1891 * Fixed an interrupted Read of specific PDF pages leaving its page render running for up to two minutes
1892 * Fixed permission dialogs and attachment checks reading a path under macOS's `/.vol`, `/.nofollow` or `/.resolve` (which can reach a network mount) before approval
1893 * Fixed a recursive `rm` whose target is only command-substitution output, such as `rm -rf "$(pwd)"`, running unprompted in auto and `--dangerously-skip-permissions` mode; it now asks even with a Bash allow rule, unless run with `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT=1`
1894 * Fixed a permission rule containing a NUL byte being expanded into a wildcard match; such a rule now matches nothing
1895 * Fixed sandbox `excludedCommands` entries not matching `git rev-parse --git-dir`, programs named like shell builtins, and commit messages containing `[WIP]` or `#` lines
1896 * Fixed sandboxed Bash commands being unable to write to `$TMPDIR` when `CLAUDE_CODE_TMPDIR` is set
1897 * Fixed `claude --bg` starting a background session, and running its project hooks, in a directory that had not passed the workspace trust prompt; it now asks for trust first, or exits when not run interactively
1898 * Fixed `--setting-sources` (and SDK `settingSources`) not being forwarded to spawned sessions: teammates, `/bg`, `claude agents` sessions and `--worktree --tmux` now start with the parent's restriction
1899 * Fixed Read, Write, Edit and NotebookEdit: a file path containing a null byte now fails that tool call with a clear error instead of ending the whole turn
1900 * Fixed Write refusing a call that gives the file path or content twice under two parameter names with identical values
1901 * Fixed CLAUDE.md and rules files from an `--add-dir` directory inside the working directory being sent to the model twice in headless and SDK sessions
1902 * Fixed remote sessions staying on "needs approval" with a stale prompt after a permission prompt and a sandbox network-access prompt overlapped and both were answered
1903 * Fixed cloud sessions not telling Claude about background agents that finished just before a worker restart
1904 * Fixed scheduled routine and notification turns in remote sessions not receiving turn-start notices (newly available tools, MCP changes, date, todos) until after the first tool call
1905 * Fixed scheduled tasks and `/loop` wakeups being fired again every secon
1920 - Improved the `/workflows` and `/mcp` lists: they page (PgUp/PgDn, Home/End) and take j/k and the mouse like other lists, their arrows follow `select:previous`/`select:next` rebinds, and
No line in this hunk matches that.