What this read moved
1–6 of 6changelog Changed · +117 / -0 lines
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="2.1.280" description="September 22, 2026">
10 * Added Claude Opus 5.5 (`claude-opus-5-5`), now the default Opus model — 1M context, $4/$20 per Mtok with \$0.20/Mtok cache reads
11 * Added mouse support to more lists in fullscreen mode: the wheel scrolls the `/skills` list, and a skill's state options in `/plugin` can be clicked
12 * Added `CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH` to change the 2,048-character cap on MCP tool descriptions and server instructions for every MCP server in the session
13 * Added hook output sizes and the number of oversized outputs saved to a file to the `hook_execution_complete` OpenTelemetry event
14 * Fixed writes through a symlinked path being judged by their in-tree spelling: the prompt names where the write lands, and `acceptEdits`, allow rules and auto mode no longer approve one landing outside
15 * Fixed auto mode retrying an action over and over when a safety check declined to review it; the action is now denied once, noting that retrying won't help
16 * Fixed auto mode denying actions over and over without pause when a safety check gave no answer; retries now back off, and the turn stops with a message after ten in a row
17 * Fixed Write calls failing validation when a model sends `path`, `file_text`, `file_content` or a stray `description` instead of `file_path` and `content`
18 * Fixed Ctrl+C or Ctrl+D pressed twice in most dialogs (`/model`, `/effort`, `/config`, `/status`, `/usage`, `/plugin`, `/sandbox`, `/permissions`, `/artifacts`, `/mobile`, `/login`, `/upgrade`, `/usage-credits`, `/install-github-app`, `/setup-bedrock`, `/setup-vertex`) quitting Claude Code instead of closing the dialog
19 * Fixed a click that only brought the terminal window to the front also triggering the item under the pointer — in search pickers, tab bars, agent/workflow rows, slash-command links and suggestion dropdowns
20 * Fixed a stray `n` closing dialogs and a stray `y` confirming them; Enter and Esc accept and cancel (bind `y`/`n` to `confirm:yes`/`confirm:no` in `keybindings.json` to restore)
21 * Fixed text fields in dialogs losing a typed letter, digit or Space to a keybinding on that key
22 * Fixed the prompt line staying scrambled on Windows terminals after invisible characters were removed on Enter; the screen is now repainted so you review the exact text that will be sent
23 * Fixed the invisible-character cleanup removing the zero-width non-joiner that Persian and Arabic text uses to attach a suffix to a Latin word or number, such as the plural of "PDF"
24 * Fixed voice dictation not stopping on Ctrl+C (the prompt cleared but the microphone kept recording), Esc not cancelling while a transcript was processing, and held Space starting dictation from the transcript view and vim NORMAL mode
25 * Fixed a model switch made from a host app (Claude Desktop, VS Code, SDK) while Claude is working causing a prompt-cache miss on the next prompt
26 * Fixed resumed fork subagents rebuilding their tool list instead of re-sending the one they first used, which broke prompt caching for that agent
27 * Fixed subagent hand-back messages showing an internal provenance preamble when expanded outside verbose mode
28 * Fixed `installed_plugins.json` keeping the install-time commit after updating a plugin from a GitHub repository or git URL that tracks a branch or tag
29 * Fixed skills in `~/.claude/skills/` being moved to `~/.claude/skills/.trash/` when a `manifest.json` in that folder listed their names
30 * Fixed the session feedback survey showing no hover highlight on light and ANSI themes
31 * Fixed `/workflows` briefly showing a one-row list before opening the only run
32 * Fixed the mouse wheel not scrolling selection lists with hidden options (such as `/model` and `/permissions`) in fullscreen mode
33 * Fixed a skill you switched off showing the same red ✘ as a plugin that failed to load in `/plugin` and `/skills`; off now shows a dim ◯
34 * Fixed multi-select option descriptions being indented under the option number instead of under the label
35 * Fixed the search box in `/plugin`, `/skills` and `/mcp` losing its right border in fullscreen mode
36 * Fixed `/mcp` showing △ in the server list but ⚠ in the detail view for the same server; the list, detail views and `/plugin` now all show ⚠
37 * Fixed Home and End doing nothing in the `/config` settings list and in selection lists such as `/model`, `/memory` and permission prompts
38 * Fixed PgUp/PgDn in the `/skills` menu wrapping past the first or last skill instead of stopping there
39 * Fixed Tab silently changing the selected setting's value in the `/config` list; it now does nothing there
40 * Fixed conversations failing on every turn with a "role 'system' must precede an 'assistant' message" API error
41 * Fixed conversations with the advisor on failing every turn with API Error 400 "Input tag 'advisor\_20260301'" behind a proxy or gateway that doesn't support it; the request now retries without it
42 * Fixed a session failing on every turn and `/compact` when its saved history held a malformed notice about MCP tools that could not be loaded
43 * Fixed a crash when resuming a session whose saved transcript holds a malformed system message or a memory-saved notice without its file list
44 * Fixed one cause of long-running fullscreen sessions exiting with "Claude Code exited after an unrecoverable interface error": a damaged cached message list is now rebuilt
45 * Fixed Claude Code hanging when a settings file, or a file it re-reads after an edit, is replaced by a named pipe mid-read
46 * Fixed `/config` crashing and some on/off preferences being misread when a preference that has moved to `settings.json` still holds a value like `null` or `"false"` in `~/.claude.json`
47 * Fixed resuming a session with unfinished background agents, shells or workflows starting a model turn on its own before you typed anything
48 * Fixed messages sent to a background subagent being silently lost in headless and SDK sessions when the subagent was finishing its turn
49 * Fixed a finished subagent's report being lost when the conversation that launched it was compacted before the report was read
50 * Fixed background subagents being unable to use the LSP tool when an LSP plugin is active
51 * Fixed background shell tasks reporting benign non-zero exits (e.g. grep with no matches) as failures
52 * Fixed background sessions (`claude --bg`) being unable to run git, hooks, plugins and other helper programs when an environment variable handed to the session contained a NUL character
53 * Fixed Ctrl+C needing three or four presses to exit while background subagents are running; two presses now exit
54 * Fixed IDE selection being dropped when a sent prompt comes back into the input, such as pressing Esc to edit it, rewinding to it, or pressing Esc while startup hooks run
55 * Fixed a `!` shell-mode prompt stashed with Ctrl+S coming back as a plain prompt when restored, and `/` listing file paths right after stashing one
56 * Fixed `claude agents` showing a blank, unresponsive screen instead of an error when the temp directory is full, not writable or owned by another user
57 * Fixed an MCP server re-added under the same name after `claude mcp remove` still showing as needing authentication instead of reconnecting
58 * Fixed background plugin marketplace auto-update ignoring git credential helpers, so private-repo marketplaces were re-cloned every run or never updated
59 * Fixed `claude plugin update` clearing a plugin's recorded commit and moving it to version "unknown" when the official marketplace's snapshot file is a link or too large
60 * Fixed the Artifact tool silently disappearing when your organization's policy can't be loaded (for example behind a web proxy); Claude now says what's blocking it
61 * Fixed artifact republishes silently resetting stored database access rules or dropping the viewer profile scope when that capability was re-sent without them; they are now refused
62 * Fixed `/ultrareview` reporting a stopped cloud review as completed or as an error to retry, and waiting out the full timeout when its session was deleted or the signed-in account changed
63 * Fixed the Claude app showing a missing or stale context usage figure for Remote Control and cloud sessions right after /compact or /clear
64 * Fixed the Claude app's diff view for Remote Control and cloud sessions dropping a branch's committed files whenever there are also uncommitted changes
65 * Fixed cloud and self-hosted runner sessions failing with "Authentication failed" after waiting out a long overload during which the session's access token was rotated
66 * Fixed memory write conflicts in Cowork sessions showing Claude only the start and end of a memory file over about 10,800 characters, so the retried write dropped the middle
67 * Self-hosted runner: Fixed lifecycle-hook commits failing to sign under `--configure-git`
68 * Windows: Fixed background cleanup deleting a directory symlink or junction used to relocate `~/.claude/session-env`, `image-cache` or another cleaned-up folder
69 * Self-hosted runner: Fixed a turn that ended right at a `--retire-at` release losing its finished signal; the runner now briefly waits for the turn to be reported before stopping the session
70 * Reverted `ctrl+l` / `cmd+k` in fullscreen mode clearing the transcript view (added in 2.1.260); they redraw the screen again
71 * Improved `/permissions`: focus returns to the rule list after viewing, adding or deleting a rule, and the delete-rule and remove-directory confirmations now default to No
72 * Improved `/permissions` tab navigation: ←/→ and Tab pressed in a rule list now switch tabs without moving focus to the tab bar
73 * Improved `/cost` cache-miss causes to name thinking mode and thinking display changes
74 * Improved the Artifact tool so that when Claude cannot read an artifact link it was given, it tells the user before continuing
75 * Improved `/install-github-app`: the GitHub CLI check and repository selection steps now show "Esc to cancel"
76 * Improved the `/artifacts` and `/workflows` lists: a scrollbar at the right edge shows how much of a long list is hidden and where you are in it
77 * Improved the workflow progress tree: running agents and phases now show a dim dot instead of ⟳
78 * Improved `/plugin`'s Add Marketplace form in fullscreen: it no longer draws a box inside the pane, and its text and key hints line up with the rest of `/plugin`
79 * Improved the `/workflows` detail view in fullscreen: it no longer draws a second horizontal rule under the pane's divider
80 * Improved code blocks that don't name a language: they are now colored like inline code, so commands stand out from the surrounding text
81 * Improved `/btw` asked while a tool is still running: the side question now knows that call is in progress instead of reading it as a failed one
82 * Improved the UserPromptSubmit hook timeout notice and the debug log to name which hook command timed out
83 * Improved `@` file suggestions: a file whose name contains the query now ranks above one that only matches across its folder names
84 * Improved artifact pages: no Print buttons, confirm dialogs or device features the viewer blocks, email and phone details shown as text, and dark mode that reaches form controls and scrollbars
85 * Improved `/ultrareview` uploads: renamed copies of key files, such as `id_rsa copy` or `kubeconfig (1).yaml`, now also stay on your machine
86 * Improved the cross-session messaging startup warning to explain that `--debug-file` writes a debug log to a path you choose
87 * Changed the default model on Pro and Team Standard plans from Sonnet to Opus, matching Max, Team Premium, and Enterprise
88 * Changed an effort level saved before `/effort` became per-model to no longer apply to newly released models such as Opus 5.5; they start at their default until you pick a level
89 * Changed Opus 4.7, Opus 4.8 and Fable 5 to stop holding their launch-default effort over `/effort` in `-p` or the Agent SDK, a project, managed or `--settings` `effortLevel`, or a per-model level
90 * Changed `/autocompact`'s footer hint to name ←/→, the keys that adjust other ordered values
91 * Changed `/fast`'s footer to name Space as the toggle key
92 * Self-hosted runner: Changed git in lifecycle hooks to ignore hook folders and programs named in the runner's shared git files; local-path and `git://` remotes there now need `GIT_ALLOW_PROTOCOL`
93 * Changed plugin marketplaces whose name imitates a reserved marketplace name to be refused when added, and to stop loading if one was already added
94 * Changed `PermissionRequest` hooks: an agent-type hook no longer runs there, since its answer could never allow or deny the request; it now shows an error pointing to command or http hooks
95 * \[VSCode] Added a Status dialog, with a typed `/status`, showing the session's version, account, model and server details
96 * \[VSCode] Added a Sandbox dialog for the sandbox mode, the unsandboxed fallback and excluded commands, opened from the panel menu or by typing `/sandbox`
97 * \[VSCode] Added a Claude in Chrome dialog (extension status, the install, reconnect and permissions pages, the enabled-by-default setting), opened from the panel menu or by typing `/chrome`
98 * \[VSCode] Added Export conversation, with a typed `/export`, to copy or save the conversation as plain text
99 * \[VSCode] Added each skill's source, token estimate and on/off state to the Slash commands dialog, with a click to change the state, and a typed `/skills` that opens it
100 * \[VSCode] Added a typed `/plan` that switches to plan mode, sends a first planning prompt, or shows the session's plan
101 * \[VSCode] Improved pasted-text handling in the chat box: a paste over 800 characters or over 2 line breaks is now marked so Claude can tell it from what you typed
102 * \[VSCode] Improved prompt handling in the chat box: invisible Unicode formatting and tag characters are removed from pasted text with a notice, and from anything else before it is sent
103 * \[VSCode] Changed "Open in New Tab" to open Claude beside the editor group you are working in rather than after the last group
104 * \[VSCode] Fixed the effort chip showing a stale saved effort level instead of the level the session runs at
105 * \[VSCode] Fixed Claude Code never starting when the Python extension hangs while activating; it now starts after 60 seconds without the Python environment
106 * \[VSCode] Fixed the plan approval card never offering auto mode: when auto mode is available, its first option is now "Yes, and use auto mode", as in the terminal
107 * \[VSCode] Fixed arrow-key navigation in the session list stopping after archiving or unarchiving a session from the keyboard
108 * \[VSCode] Fixed paste marker lines showing in your own messages after reopening a session
109 * \[Claude Code on the web] Changed the admin Routines on/off setting to live under Admin settings → Capabilities → Remote sessions; the Claude Code admin page now links to it
110 * \[Claude Code on the web] Fixed `gh` and GitHub API calls inside a cloud session on a GitHub Enterprise Server repository failing after about eight hours; the token now renews automatically
111 * \[Claude Code on the web] Fixed a routine that resumes an existing session running with its old prompt and name when it was edited moments before the scheduled run started
112 * \[Claude Code on the web] Fixed file links in a cloud session transcript that point outside the session's working directory opening a file card that never loads; they're now disabled and say why
113 * \[Claude Code on the web] Fixed auto mode refusing to retry a tool call because an approval prompt that expired unanswered, or was superseded by a newer message, had been recorded as your rejection
114 * \[Claude Code on the web] Improved cloud sessions viewed in the Claude app: Claude now saves files meant for you where the app can open them
115 * \[Claude Code on the web] Removed the empty repository picker shown when starting a session on a self-hosted environment in an organization where an admin has turned GitHub off
116 * \[Claude Tag] Added Slack's native Working indicator, Stop button and thread title to Claude's threads in channels; the indicator stays up until Claude finishes, and Stop interrupts the task
117 * \[Claude Tag] Added a short notice in the Slack channel when a guest joining, or the last guest leaving, changes how Claude responds there under a Restrict or Channel only guest setting
118 * \[Claude Tag] Fixed scheduled routines silently failing to run in Slack workspaces that were connected to Claude before the workspace joined its Enterprise Grid
119 * \[Claude Tag] Fixed Claude asking you to re-upload a Slack file when a brief file-scanning outage, not the file, was the problem; it now retries the scan and is told when the scanner is down
120 * \[Claude Tag] Fixed a bullet in Claude's Slack reply whose text starts with +, - or \* rendering as an empty bullet with a stray nested item; it now shows as one bullet with the character kept
121 * \[Claude Tag] Fixed the Slack notice for a failed cloud environment setup script sometimes being a generic "mention me to retry"; it now names the setup script and says to fix it first
122 * \[Claude Tag] Improved the GitHub banner in Claude Tag admin settings to say why GitHub isn't connected: not signed in, app not linked or not installed, sign-in expired, or SSO not authorized
123 * \[Code Review] Improved the Code Review check run to say when REVIEW\.md instructions were cut or left out of a review for exceeding a size limit, naming the file and the limit
124</Update>
125
9126<Update label="2.1.278" description="September 19, 2026">
10127 * Changed auto mode for Claude API and Enterprise users, and on Bedrock, Vertex, Foundry and gateways, to default to the server-side classifier, which does not charge for classifier overhead (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out on Bedrock, Vertex, Foundry and gateways); warns on billed fallback. See [https://code.claude.com/docs/en/auto-mode-classifier-billing](https://code.claude.com/docs/en/auto-mode-classifier-billing)
11128 * Added an `Auto mode server` row to `/status` showing whether this session's auto mode classifier runs on the server
from line 1785
16681785 * Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite `$PSDefaultParameterValues` and redirect later commands' file access
16691786 * 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
16701787 * Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation
1671 * 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
1672 * Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials
1673 * 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
1674 * Fixed Remote Control sessions appearing unreachable to newly attached clients while idle
1675 * Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts
1676 * Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)
1677 * 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
1678 * Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately
1679 * Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors
1680 * Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region
1681 * Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments
1682 * Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis
1683 * Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji
1684 * Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to `known_marketplaces.json`
1685 * Fixed `/update` and `/tui` refusing to restart while work that survives the relaunch was running
1686 * Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions
1687 * Fixed the consent message for interactive `--advisor fable` launches, which told you to run `/model fable` in an interactive session that had just exited
1688 * Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update
1689 * Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (`sandbox.bwrapPath`, `sandbox.socatPath`, `sandbox.ripgrep`)
1690 * `/feedback` and `/bug` now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish
1691 * `/plugin install plugin@marketplace` now refreshes the marketplace first, so newly published plugins install without a manual marketplace update
1692 * `/code-review` at high, xhigh, and max effort now runs in a background agent like the other levels
1693 * Pasted and clipboard images are read without blocking the event loop
1694 * Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour
1695 * Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run `/remote-control` there to move it
1696 * Updated agent panel: completed subagents hide immediately with a `/tasks` footer hint, and the "↓ N more" overflow indicator moved left for visibility
1697 * Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it
1698 * Bash input redirections (`< file`) are now permission-checked like their argument spellings on all platforms
1699 * Shortened the message shown when resuming a completed background agent
1700 * Cowork sessions no longer inline external @-imports from user-scope memory files
1701 * Hardened the auto-generated cross-session messaging socket directory on shared `/tmp`: a pre-planted symlink or another user's directory is now refused instead of used
1702 * Hardened the Linux filesystem sandbox against a protected-path bypass
1703 * Changed `sandbox.ripgrep` to be honored only from user, managed, and `--settings` settings; project settings can no longer override the sandbox's ripgrep binary
1704 * Removed the startup tip suggesting you create custom subagents, and the matching nudge in the `/powerup` tour
1705</Update>
1706
1707<Update label="2.1.231" description="August 13, 2026">
1708 * Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack
1709</Update>
1710
1711<Update label="2.1.229" description="August 12, 2026">
1712 * Documented `claude remote-control --continue` for resuming the most recent Remote Control session
1713 * Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior
1714 * Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams
1715 * Added plugin marketplace `command` sources: a local command (e.g. an IDE) prints the plugin directory, which is re-resolved each session and applied without a restart; `mode: "link"` uses it in place
1716 * `ListAgents` now marks disconnected Remote Control sessions as `offline` and labels your cloud sessions as `cloud`
1717 * Fixed long responses partly disappearing while streaming and being printed twice in the terminal
1718 * Fixed a crash to the error screen (including on `--resume` of the affected session) when a tool call had a non-string `glob`, `file_path`, or `command` value
1719 * Fixed a RangeError crash when a progress bar or markdown table rendered in a very narrow terminal window (could also crash `claude --continue`/`--resume` at startup)
1720 * Fixed a crash on Windows when a tool call or message referenced a file by an extended-length (`\\?\`) or UNC path
1721 * Fixed auto mode failing on every tool call for users who disable the attribution header via `CLAUDE_CODE_ATTRIBUTION_HEADER` (direct Anthropic API connections)
1722 * Fixed `/model` rejecting Sonnet/Opus 1M for claude.ai subscribers using a custom `ANTHROPIC_BASE_URL` gateway
1723 * Fixed MCP OAuth with strict authorization servers by using `127.0.0.1` instead of `localhost` in the redirect URI
1724 * Fixed Remote Control clients showing a stuck working spinner after a slash command typed in the laptop terminal
1725 * Fixed the Claude Code Review workflow generated by `/install-github-app` completing without posting its review on the pull request
1726 * Fixed multi-second UI stalls after editing a file with thousands of IDE diagnostics while the IDE extension is connected
1727 * Fixed one-shot `claude plugin` commands leaving a stray liveness file that could prevent cleanup of outdated plugin versions
1728 * Fixed dynamic workflows inside CPU-limited containers using the host machine's core count instead of the container's CPU limit
1729 * Fixed a file-watcher handle leak after atomic file replacements, and an uncaught error on Windows when the scheduled-tasks watcher failed on a network or virtual filesystem
1730 * Fixed SDK and `--input-format stream-json` sessions getting a 400 API error when a whitespace-only message was submitted
1731 * Fixed conversations whose messages alone exceed the API's 32 MB request limit retrying compaction when no images or documents can be stripped; they now fail once with a clear message
1732 * Fixed OpenTelemetry export from Claude Desktop sessions being rejected by the Desktop-managed gateway when that gateway is also the telemetry endpoint
1733 * Fixed self-hosted runner and other remote sessions exiting at startup when `managed-mcp.json` is deployed and the server delivers MCP servers; those servers are now skipped with a warning
1734 * Fixed self-hosted runner repository preparation hanging on a Git Credential Manager prompt; git now fails fast when credentials are missing
1735 * Improved workflow fan-outs to stagger same-prefix sibling agents so subsequent agents read the cached prompt prefix instead of re-paying it (`CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0` disables)
1736 * Improved "prompt is too long" errors to explain why automatic compaction could not recover instead of only suggesting `/compact`
1737 * Improved sandbox: IPv6 literals in network domain lists are now bracketed (`[::1]:443`), and ambiguous spellings are enforced fail-closed and flagged by `/doctor`
1738 * Updated `/login` to repeat the `CLAUDE_CODE_OAUTH_TOKEN` override warning after a successful login
1739 * Changed `/commit-push-pr` so git/gh commands with dangerous flags (`--force`, `--amend`, `--no-verify`, etc.) are no longer auto-approved
1740 * Changed self-hosted runner Windows startup to require an explicit `--base-dir`; there is no default checkout directory on Windows
1741 * \[VSCode] "Report a problem" and `/bug` now open the built-in feedback dialog instead of a retired survey link
1742 * \[VSCode] Made the `/btw` side-question panel resizable by dragging its boundary, in both side-docked and stacked layouts
1743 * \[VSCode] Added session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move several sessions at once
1744</Update>
1745
1746<Update label="2.1.228" description="August 11, 2026">
1747 * Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error
1748 * Fixed `git` / Git Bash not being found on Windows when Claude Code is launched from a parent folder of the git installation
1749 * Fixed `/tui` reverting the session to an earlier model when `/model` had been changed since the last response
1750 * Fixed cross-session messaging sometimes starting without an inbox in the first session after install or upgrade
1751 * Fixed Remote Control `/resume` while connected leaking the resumed conversation's title or history into the connected session
1752 * Fixed `claude self-hosted-runner` sessions failing on every fresh runner when the `checkout` hook fails for a repository the session doesn't push to; that repository is now skipped with a warning
1753 * Fixed self-hosted runners ending sessions in the gap between a background task finishing and the follow-up turn starting
1754 * Fixed session cleanup deleting contents inside a project's memory folder
1755 * Fixed background plugin-cache cleanup deleting a plugin's cache when its only version is a symlinked development checkout
1756 * Fixed a settings-merge issue where a marketplace entry redefined in a higher-precedence settings tier could inherit another tier's custom headers; marketplace entries now merge as whole entries
1757 * Fixed the deferred-tools reminder occasionally being sent to the model twice after a skill invocation
1758 * Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, their descriptions are sanitized and labeled, and on your machine their bodies don't run `!` commands or expand `@` files
1759 * Improved cross-session messages: the sender and body now display inline instead of a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender
1760 * Improved Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes
1761 * Improved compaction progress: the retry countdown and stall hint now appear during compaction instead of only a progress bar
1762 * Updated terminal title busy-spinner glyphs to reduce tab-bar jitter on some terminals
1763 * Changed the Write tool so newer models can overwrite an existing file they haven't read this session, matching the Edit tool's rules; older models still require the read first
1764 * Removed the outdated note about auto mode sessions costing slightly more from the first-use notice for Pro, Max, and Team plans
1765</Update>
1766
1767<Update label="2.1.227" description="August 10, 2026">
1768 * Fixed feature flags being evaluated without the user's subscription tier when a session started with an expired login token, which could wrongly prompt Max plan users to enable usage credits for Fable
1769 * Fixed every Bash command failing under `claude-code-action` with `allowed_non_write_users` on GitHub-hosted runners
1770 * Fixed `/tui` bringing back a conversation that had been rewound to before its first message
1771 * Improved slash-command menu: blue now marks only the selected row, matched characters are bolded instead of recolored, and emoji or accented names keep their glyphs
1772 * Improved performance: fewer event-loop stalls on file-not-found suggestions and at-mention size checks
1773</Update>
1774
1775<Update label="2.1.226" description="August 8, 2026">
1776 * Bug fixes and reliability improvements
1777</Update>
1778
1779<Update label="2.1.225" description="August 8, 2026">
1780 * Added gateway spend-limit support to Claude Code's usage warning; the limit-reached message now names the cap, its reset time, and the operator's message (requires the gateway on 2.1.225)
1781 * Added a workspace trust prompt to `claude agents` for untrusted directories, matching the behavior of `claude`
1782 * Fixed a transient 401 replacing a long-lived `CLAUDE_CODE_OAUTH_TOKEN` with a stored login's short-lived token, breaking headless sessions until restart
1783 * Fixed MCP OAuth servers on macOS intermittently failing with a burst of 401 errors, as if never authenticated, after a keychain read timed out
1784 * Fixed auto mode counting a safety-filter refusal of its own permission check toward the consecutive-block limit; the action is still denied, but the model is now told to move on rather than retry
1785 * Fixed cross-session messages staying parked without a notice or expiry in headless sessions and during startup
1786 * Fixed conversation history breaking on Remote Control session resume after very large conversations were compacted
1787 * Fixed hovering over a session in another project in the agents list changing the directory the next agent starts in
1788 * Fixed `claude self-hosted-runner` registering and then failing every session when `--base-dir` cannot be created or written; it now exits at startup with a clear error
1789 * Fixed Claude Code on the web sessions being misreported as stuck, re-sending a growing event backlog on every reconnect
1790 * Improved Remote Control: photos attached from the Claude app are now shown to Claude directly instead of being read from disk with a separate tool call
1791 * \[VSCode] Fixed Focus view folding away the latest to-do list, a pending question's context, and settled answers; thinking-only folds show "Thought for Ns" and re-collapse when their turn completes
1792 * SendMessage can now start a conversation with your Remote Control sessions on other machines by name (`ListAgents` shows them as `name [ref]`), instead of only replying after they message you first
1793 * SendMessage: a Remote Control recipient you already confirmed is never swapped for a same-named session on this machine when its own list couldn't be checked
1794</Update>
1795
1796<Update label="2.1.224" description="August 7, 2026">
1797 * Added self-hosted environments: `claude self-hosted-runner` turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run, on Team and Enterprise plans
1798 * Added `archive` plugin source: install plugins from a zip over HTTPS without git or npm, with optional SHA-256 pinning
1799 * Added a cancel-and-confirm step when removing an unavailable paste changes a command's text
1800 * Added `ANTHROPIC_BEDROCK_REGION_PREFIX` env var for Bedrock to prefer a specific cross-region inference profile over the `AWS_REGION`-derived one
1801 * Added `crossSessionInbound` and `dialogExpiry` settings: cross-session messages sent to a session running with bypassed permissions are held for your approval, and messages to other sessions auto-deliver
1802 * Added sandbox credential-masking options: `extract` and `onExtractNoMatch` for structured env values, `decode: "jwt"` with `maskClaims` for JWT-aware masking, and `awsPairs`/`sigv4` for AWS SigV4 re-signing; these need `network.tlsTerminate` and are honored only from user, managed, or `--settings` settings
1803 * Added cross-session `SendMessage`: Claude Code sessions can now message each other, on any of your machines, with `ListAgents` to discover them (macOS and Linux)
1804 * Fixed long (>200 char) project paths resolving to another project's session directory under a shared sanitized prefix; session list, rename, fork, delete and `/resume` no longer cross projects
1805 * Fixed `SendMessage` reporting "Message sent" when the write to a teammate's inbox had actually failed; failed deliveries are now reported as errors
1806 * Fixed sandbox filesystem deny entries written with a trailing slash (e.g. `denyRead: "~/.aws/"`) being silently bypassable on Linux and macOS
1807 * Fixed sandbox violation details never appearing in Bash tool results; Claude now sees which file or network access was denied and why
1808 * Fixed MCP tools that connect mid-turn being deferred for tool search without their names announced to the model
1809 * Fixed plugin install records being silently corrupted when the same plugin is installed in multiple projects
1810 * Fixed recalled or restored paste content occasionally attaching wrong data or silently losing text when the paste had aged out or placeholder numbers collided
1811 * Fixed copy-on-select on Wayland
1788 * Fixed MCP connections hanging
hooks Changed · +3 / -2 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
Nothing in the body moved in this read. What changed is above.
memory Changed · +10 / -9 lines
from line 380
380380* You're on a Claude Code version before v2.1.277
381381* Your session doesn't [fetch feature flags from Anthropic](/docs/en/env-vars#features-that-need-feature-flag-fetching), for example because you use Amazon Bedrock or another third-party provider, or you disabled telemetry. The linked section has the full list
382382* It's your [first session after you install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade) to a version with `AGENTS.md` support. Claude reads `AGENTS.md` from your next session on
383* You or your organization set [`disableAllHooks`](/docs/en/settings-reference#disableallhooks) or [`allowManagedHooksOnly`](/docs/en/settings-reference#allowmanagedhooksonly), or you disabled the built-in `agents-md` plugin in `/plugin`
383* You disabled the built-in `agents-md` plugin in `/plugin`
384384
385385To give Claude your `AGENTS.md` in these sessions, [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools).
386386
from line 388
388388
389389An `AGENTS.md` that Claude reads through the **Project instructions** setting differs from a `CLAUDE.md` in these places:
390390
391| | `CLAUDE.md` | `AGENTS.md` read through the setting |
392| :------------------------------------------------------------------------------------------------------------------------------------ | :--------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
393| `/memory` and the **Memory files** list in `/context` | Listed | Not listed. To confirm Claude read it, look for the [`AGENTS.md loaded` line](#when-claude-code-reads-agents-md) under the default value, or ask Claude what its project instructions say |
394| [`InstructionsLoaded` hooks](/docs/en/hooks#instructionsloaded) | Fire | Don't fire. They fire as usual for an `AGENTS.md` that a `CLAUDE.md` imports or symlinks to |
395| Directories you add with `--add-dir` while [`CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD`](#load-from-additional-directories) is set | Their `CLAUDE.md` loads | Their `AGENTS.md` doesn't load |
396| An `@path` import of a file outside your working directory | Claude Code asks you to approve [external imports](#import-additional-files) | Loads only if you already approved external imports for this project, with no prompt |
391| | `CLAUDE.md` | `AGENTS.md` read through the setting |
392| :------------------------------------------------------------------------------------------------------------------------------------ | :--------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------ |
393| [`InstructionsLoaded` hooks](/docs/en/hooks#instructionsloaded) | Fire | Don't fire. They fire as usual for an `AGENTS.md` that a `CLAUDE.md` imports or symlinks to |
394| Directories you add with `--add-dir` while [`CLAUDE_CODE_ADDITIONAL_DIRECTORIES_CLAUDE_MD`](#load-from-additional-directories) is set | Their `CLAUDE.md` loads | Their `AGENTS.md` doesn't load |
395| An `@path` import of a file outside your working directory | Claude Code asks you to approve [external imports](#import-additional-files) | Loads only if you already approved external imports for this project, with no prompt |
397396
398397### Remove an earlier AGENTS.md workaround
399398
from line 535
536535
537536To debug:
538537
539* Run `/context` and check the list under **Memory files** to verify your CLAUDE.md and CLAUDE.local.md files loaded. If a `CLAUDE.md` file is missing there, Claude can't see it. An `AGENTS.md` appears there only when a `CLAUDE.md` imports it, not when Claude [reads it directly](#where-agents-md-differs-from-claude-md). Use `/memory` to open and edit the files.
538* Run `/context` and check the list under **Memory files** to verify your CLAUDE.md and CLAUDE.local.md files loaded. If a `CLAUDE.md` file is missing there, Claude can't see it. Use `/memory` to open and edit the files.
540539* Check that the relevant CLAUDE.md is in a location that gets loaded for your session (see [Choose where to put CLAUDE.md files](#choose-where-to-put-claude-md-files)).
541540* Make instructions more specific. "Use 2-space indentation" works better than "format code nicely."
542541* Look for conflicting instructions across CLAUDE.md files. If two files give different guidance for the same behavior, Claude may pick one arbitrarily.
from line 557
5585573. Check whether your session is one that [can't load `AGENTS.md`](#when-agents-md-support-is-unavailable), such as a session on a third-party provider or with telemetry disabled.
5595584. Type `/config` in your session to open the settings panel and confirm **Project instructions** isn't set to `claude-md` or `managed-only`. If you don't see the setting there at all, your session is one that [can't load `AGENTS.md`](#when-agents-md-support-is-unavailable).
560559
561`AGENTS.md` doesn't appear in `/memory` or `/context` when Claude reads it directly, so check for the `AGENTS.md loaded` line or ask Claude what its project instructions say instead.
560To check whether Claude read your `AGENTS.md`, run `/memory` and look for its path in the list.
561
562Before v2.1.280, `/memory` and `/context` didn't list an `AGENTS.md` that Claude read directly. On those versions, ask Claude what its project instructions say instead.
562563
563564If you want to keep the `CLAUDE.md` you found, or your session can't load `AGENTS.md`, [add a `CLAUDE.md` next to your `AGENTS.md` that imports it](#share-one-file-with-other-coding-tools).
564565
errors Changed · +1 / -1 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
Nothing in the body moved in this read. What changed is above.
remote-control Changed · +1 / -1 lines
from line 171
171171* **Pulling a session with `/teleport`**: when you pull a [cloud session](/docs/en/claude-code-on-the-web#from-cloud-to-terminal) into your terminal with `/teleport`, the connected device doesn't receive the pulled conversation's earlier history. New messages in both directions go to and from the pulled conversation, which is now the one open in your terminal.
172172* **Messages from your other sessions**: with [cross-session messaging](/docs/en/cross-session-messaging), the same connection carries messages between your own sessions on different machines and from your [cloud sessions](/docs/en/claude-code-on-the-web), through Anthropic servers like the rest of Remote Control traffic. [Message sessions on other machines](/docs/en/cross-session-messaging#message-sessions-on-other-machines) covers the delivery rules and [Control inbound messages](/docs/en/cross-session-messaging#control-inbound-messages) covers the inbound controls. Requires Claude Code v2.1.224 or later.
173173* **Prompts you send mid-turn**: when you send a prompt from a connected device before the current turn ends, Claude Code queues it and keeps it in the device's transcript after that turn finishes.
174* **Diff of your changes**: when the session's directory is in a git repository, a connected device's diff pane shows the diff of your uncommitted changes. The device requests the diff over the connection, and Claude Code computes it on your machine. When your working tree is clean, Claude Code instead serves your branch's changes since it diverged from the default branch. Before v2.1.247, Claude Code reported the diff to connected devices only in sessions served by `claude remote-control`.
174* **Diff of your changes**: when the session's directory is in a git repository, a connected device's diff pane shows your changes. The device requests the diff over the connection, and Claude Code computes it on your machine. On a branch that has commits ahead of the repository's default branch, the pane shows the changes since the branch split from it, including your uncommitted edits. On the default branch itself, or on a branch that isn't ahead of it, the pane shows only your uncommitted changes. Before v2.1.247, Claude Code reported the diff to connected devices only in sessions served by `claude remote-control`.
175175* **Model**: when you pick a [model](/docs/en/model-config) from a connected device, Claude Code runs the session on that model. The terminal's `/model` picker, `/status`, and `/config` show that model. Requires Claude Code v2.1.238 or later.
176176 * A model you pick from the device's model control applies to the current session only. When you send `/model <name>` from the device to an interactive session, Claude Code also sets your default for new sessions.
177177 * If you send a name Claude Code doesn't recognize, such as a display name where a model ID is expected, Claude Code [refuses the pick](/docs/en/errors#model-is-not-a-recognized-model-id) and the session keeps its current model. Before v2.1.260, Claude Code saved an unrecognized pick from the device's model control, and your next message failed.
sub-agents Changed · +3 / -1 lines
from line 420
420420* `WaitForMcpServers`
421421* `Workflow`
422422
423The second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built-in tools: `Read`, `Grep`, `Glob`, `Bash`, `PowerShell`, `Edit`, `Write`, `NotebookEdit`, `WebFetch`, `WebSearch`, `TodoWrite`, `Skill`, `ToolSearch`, `EnterWorktree`, `ExitWorktree`, `Monitor`, `TaskStop`, `SendMessage`, and `Artifact`, plus [`SubagentHandback`](/docs/en/tools-reference) for a subagent that reports through it. Claude Code removes every other built-in tool from a background subagent, whether inherited or listed in the `tools` field, so the same definition can resolve to different tools in the foreground and the background. The removal reports no error unless it leaves the `tools` list [resolving to nothing](/docs/en/errors#agent-would-be-spawned-with-zero-tools).
423The second filter applies to subagents running in the background. Apart from `Agent` and `ExitPlanMode`, which follow the first filter's conditions wherever the subagent runs, a background subagent keeps every MCP tool but only these built-in tools: `Read`, `Grep`, `Glob`, `LSP`, `Bash`, `PowerShell`, `Edit`, `Write`, `NotebookEdit`, `WebFetch`, `WebSearch`, `TodoWrite`, `Skill`, `ToolSearch`, `EnterWorktree`, `ExitWorktree`, `Monitor`, `TaskStop`, `SendMessage`, and `Artifact`, plus [`SubagentHandback`](/docs/en/tools-reference) for a subagent that reports through it. Claude Code removes every other built-in tool from a background subagent, whether inherited or listed in the `tools` field, so the same definition can resolve to different tools in the foreground and the background. The removal reports no error unless it leaves the `tools` list [resolving to nothing](/docs/en/errors#agent-would-be-spawned-with-zero-tools).
424
425Before v2.1.280, background subagents couldn't use `LSP`.
424426
425427[`ListAgents`](/docs/en/cross-session-messaging) follows these filters like any built-in tool: a foreground subagent inherits it in sessions where cross-session messaging is enabled, and a background subagent doesn't keep it.
426428