The whole hunk
from line 6, old and new numbered
/
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="2.1.273" description="September 15, 2026">
10 * Added `x-claude-code-request-class`, `x-claude-code-agent-type`, `x-claude-code-prev-tool-durations`, `x-claude-code-compaction` and `x-claude-code-context-compacted` request headers for LLM gateways; opt in with `CLAUDE_CODE_GATEWAY_HINT_HEADERS=1`
11 * Added a notification when an MCP server disconnects mid-session and automatic reconnection gives up, pointing at `/mcp`
12 * Added forking a session started with `claude --remote-control` or `/remote-control` from the Claude app; the fork runs as a background session on your computer
13 * Fixed Bash commands the permission checker cannot fully analyze skipping the prompt under `permissions.blockReadsOutsideWorkingDirectories`, and a subshell hiding a dangerous `rm` in bypass mode
14 * Fixed skills synced from claude.ai staying available after your organization turns Skills off; they now move to the recoverable trash
15 * Fixed `allowManagedMcpServersOnly`, `deniedMcpServers` and `disableClaudeAiConnectors` set via MDM or `managed-settings.json` being ignored when server-managed settings are also present
16 * Fixed 401/403 errors on Bedrock, Vertex and Foundry, and Claude apps gateway 403s, telling you to run `/login`; the message now names the credential to refresh or points to your gateway administrator
17 * Fixed `/login`, `/upgrade`, and `/extra-usage` discarding earlier thinking from the conversation, which forced a full prompt-cache rewrite on the next request
18 * Fixed auto mode stopping for approval when the Artifact tool uploads a file you attached to the chat in a cloud or Remote Control session
19 * Fixed a long-running session recreating a stub `.git/info/exclude` after the repository's `.git` directory was removed or moved away
20 * Fixed the main prompt dropping a `!` typed at the start while already in shell mode, so negated commands like `! grep …` can be typed
21 * Fixed Read on macOS refusing a dragged-in screenshot, or any file the system reports under a second path, with "symlink resolution changed after permission was checked"
22 * Fixed `permissions.blockReadsOutsideWorkingDirectories`: a memory directory chosen by a repository's settings is no longer loaded into the prompt, recalled, indexed, or used by memory extraction
23 * Fixed sub-agents and background agents being reported as failed, with their result never delivered, when the final streamed reply omitted token usage or carried no model id
24 * Fixed the context meter and auto-compact counting advisor-tool turns at roughly twice their real context size, which made auto-compact fire at about half the real window
25 * Fixed `/tui` refusing to restart because of an agent-team teammate that had already finished its work and was no longer shown in the agents panel
26 * Fixed saved scheduled tasks running in the wrong session after `.claude/scheduled_tasks.json` was copied into another folder, such as a new worktree
27 * Fixed SDK and `--output-format stream-json` output dropping a subagent's remaining messages and final report after it is moved to the background mid-run (e.g. by `CLAUDE_AUTO_BACKGROUND_TASKS`)
28 * Fixed `/install-github-app` reporting a SAML single sign-on block as "admin permissions required"
29 * Fixed Remote Control clients attached to a Claude Desktop, VS Code or JetBrains session being refused when they ask for the session's context window usage
30 * Fixed the spinner showing a doubled ellipsis ("……") on compaction status lines such as "Running PreCompact hooks…"
31 * Fixed a false-positive spinner tip suggesting the frontend-design plugin after reading or publishing Artifacts
32 * Reverted a 2.1.268 change that checked Read and Edit deny rules on Bash lines the permission checker can't analyze (`eval`, `env -C`); commands like `time -p make build` prompt again instead of being denied
33 * Improved responsiveness in long sessions: hook progress and sub-agent activity no longer re-process the whole conversation on every update
34 * Improved the Artifact tool's error when a publish includes a file type artifacts don't serve: Claude is told which types are served and what to do instead, and the terminal shows one plain line
35 * Improved the Artifact tool's page read to state the capabilities and database rules the artifact service holds for the page, for anyone who can publish to it
36 * Improved artifact database writes: an update can now remove a single field instead of rewriting the whole document
37 * Improved artifact publishing: a publish whose connection drops after reaching claude.ai is now re-sent safely instead of failing or creating a duplicate version
38 * Improved the cloud-session GitHub error for an IP allow list, a suspended app installation or SAML single sign-on to show the cause instead of a generic install hint
39 * Improved `/autofix-pr`: when `gh pr view` fails it now shows gh's own error (sign-in, SAML, rate limit) instead of a generic exit-code line
40 * Improved `/autofix-pr` to say why GitHub webhook delivery couldn't be set up for the PR (for example, no linked GitHub account) instead of a generic warning
41 * Improved `/web-setup` errors: a refused GitHub token now lists the likely reasons and the fix, and a connection failure names a configured proxy or TLS certificate problem
42 * Improved the in-session SSL certificate and proxy connection errors to name the error code and what to fix, such as `NODE_EXTRA_CA_CERTS` for an untrusted corporate CA
43 * Improved the error when a cloud session can't be created because your Claude login expired or was revoked: it now tells you to run `/login`
44 * Improved the error shown when an MCP server's sign-in expires mid-session to say how to re-authenticate (`/mcp`)
45 * Changed auto mode on Bedrock, Vertex and Foundry to use the local classifier by default for now; set `CLAUDE_CODE_AUTO_MODE_SERVER=1` to use the platform's server-side classifier
46 * Changed `OTEL_LOG_TOOL_DETAILS=1` to also include real agent, skill, plugin and MCP server names on cost and token metrics
47 * Changed sign-in with a Claude account to also request access to your claude.ai plugins
48 * Changed `/bug` and `/feedback` reports to include only model-behavior params (model, system prompt, tools) from the last API request, omitting request metadata and `CLAUDE_CODE_EXTRA_BODY` fields
49 * \[VSCode] Fixed "Report a problem" still appearing, and `/bug` / `/feedback` opening a report form, for organizations that have product feedback disabled
50 * \[VSCode] Fixed a red "Claude Code process exited with code 4294967295" banner appearing after completed turns on Windows
51 * Windows: Improved the network-path permission check for UNC paths when a mapped network drive was added with `--add-dir`
52 * \[Claude Code on the web] Fixed routines losing access to an organization connector, and still calling the old one, after an admin removed and re-added that connector
53 * \[Claude Code on the web] Fixed creating a self-hosted environment from organization settings occasionally failing with a server error and leaving a half-created environment behind
54 * \[Claude Code on the web] Changed the admin "Share cloud sessions" setting to live under Data and privacy instead of the Claude Code page, where Data and privacy admins can also manage it
55 * \[Claude Code on the web] Added a "Discard unsaved changes?" confirmation before the New routine page or the Edit routine dialog throws away a routine name, prompt or edit you typed
56 * \[Claude Code on the web] Removed the full-page desktop-app download screen that new users without a cloud environment saw on Mac and Windows; they now go straight to setup
57 * \[Claude Code on the web] Improved the routine detail page: menu and rename in the breadcrumb, the on/off switch and Run now at the top, and run history beside the routine's settings
58 * \[Claude Tag] Fixed Claude going silent minutes after reinstalling the app when an Enterprise Grid was disconnected but one of its workspaces stayed connected
59 * \[Claude Tag] Fixed scheduled tasks set up in an organization-shared private Slack channel silently never posting; they now keep running in the thread they were created in
60 * \[Claude Tag] Fixed replying in an older Slack thread while Claude is mid-task sometimes restarting it from scratch and losing work it had not pushed yet
61 * \[Claude Tag] Fixed Claude occasionally dropping a message with an incorrect "couldn't find a Claude Code environment" notice right after your account token refreshed
62 * \[Claude Tag] Fixed AWS connections refusing region-less endpoints such as Budgets, Savings Plans, WAF Classic and Import/Export; Global Accelerator requests now sign correctly
63 * \[Claude Tag] Improved AWS connection failures: when a request can't be signed, such as a hostname with no region, Claude is told why and how to fix it instead of a bare error
64 * \[Claude Tag] Fixed OAuth client-credentials and JWT-bearer connections failing with providers that return a lowercase token type; requests now send the standard Bearer scheme
65 * \[Claude Tag] Fixed adding a channel manager being refused on Enterprise Grid shared channels, on channels where Claude hasn't been used yet, and on legacy private channels
66 * \[Claude Tag] Changed Claude to start watching related public channels on its own, such as an incident channel a conversation depends on, instead of only when asked
67 * \[Claude Tag] Fixed the admin Memory page not listing Slack channels Claude set up on its own even when they had saved memory; admins can now open, edit and delete that memory
68 * \[Code Review] Fixed merging the base branch into a PR whose earlier review listed "Additional findings" triggering a full re-review; these pushes now get the lighter follow-up review
69 * \[Code Review] Fixed a whole REVIEW\.md being ignored because of an @-mention, a code span wrapped across lines, or a backticked HTML tag; only lines linking to changed files are withheld
70 * \[Code Review] Improved suggested fixes to say what the fix must keep working when other code depends on the behavior being changed
71 * \[Code Review] Improved review comments that point to a second affected location to state that location's issue in a full sentence instead of a cut-off stub
72 * \[Code Review] Fixed `/ultrareview --post` so a retry after a GitHub error posts the findings comment exactly once instead of never or twice; the comment now names the reviewed commit
73 * \[Code Review] Fixed empty or content-identical pushes being re-reviewed on GitHub repositories whose owner or name contains a capital letter; these pushes are now skipped
74</Update>
75
976<Update label="2.1.272" description="September 15, 2026">
1077 * Bug fixes and reliability improvements
1178</Update>
from line 1852
17851852 * Added `--forward-subagent-text` flag and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` environment variable to include subagent text and thinking in stream-json output
17861853 * Fixed permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote characters, so tool inputs cannot visually alter the approval message
17871854 * Fixed auto mode overriding a PreToolUse hook's `ask` decision for unsandboxed Bash — a hook `ask` now floors the decision at a prompt
1788 * Fixed parallel Claude Code sessions all logging out simultaneously after wake-from-sleep when many sessions share one credential store
1789 * Fixed plugin MCP servers not reconnecting after an idle web session woke, leaving MCP calls failing until the next message
1790 * Fixed Claude Code on Vertex and Bedrock attempting the default Opus model at startup and printing a spurious fallback notice when a model is explicitly configured
1791 * Fixed subagents spawned with an explicit model override reverting to the parent's model when resumed or sent a follow-up message
1792 * Fixed nested `.claude/rules/*.md` files loading even when setting sources exclude project settings
1793 * Fixed file upload validation: filenames ending in a DOS device suffix (`.prn`) or trailing dot are now accepted, and files with multiple hard links are refused
1794 * Fixed file uploads to Claude in Chrome from remote and CLI sessions
1795 * Fixed edits that leave the input as "?" being silently swallowed and toggling the shortcuts panel
1796 * Fixed a startup hang when the Claude in Chrome extension is enabled but Chrome is not running
1797 * Fixed a 300ms delay revealing async content (Settings tabs, Stats, diff views, and other loading states)
1798 * Fixed reopening a just-stopped background session from the agents view starting a blank conversation under the same session id
1799 * Fixed `/loop` hiding the session from `/resume` after a single use
1800 * Fixed screen reader users losing the audible terminal bell after `/terminal-setup` or onboarding terminal setup
1801 * Fixed background jobs on LLM gateway auth (`ANTHROPIC_AUTH_TOKEN` + `ANTHROPIC_BASE_URL`) coming back "Not logged in" after the daemon respawns them
1802 * Fixed `claude agents` jobs becoming permanently undeletable when git no longer recognizes their worktree — the row now shows why the delete was refused instead of silently reappearing
1803 * Fixed `/clear` not resetting the session cost counter — the statusline's cost now starts at \$0 after `/clear`
1804 * Fixed Claude in Chrome setup pages failing to open in the browser on Windows
1805 * Fixed headless print-mode sessions on Windows crashing or silently exiting when stdin is unreadable
1806 * Fixed background session titles in the agents view showing the naming model's refusal text when the prompt contains a link
1807 * Fixed background agents killed by the user auto-respawning, and revived agents re-running stale prompts from old sessions
1808 * Fixed routines with no schedule reporting a next run time in the year 1
1809 * Hardened synced skill/plugin directory naming on Windows and kept CCR web fetch/search proxies working after `/clear`
1810 * Improved terminal layout and rendering performance
1811 * Improved background agent result reporting — Claude now reports the status of still-running agents and waits for the real completion instead of fabricating results
1812 * Improved the memory index over-limit warning to measure only loaded content, excluding frontmatter and HTML comments
1813 * Updated integer environment variables (timeouts, token budgets, retry counts) to accept scientific notation and digit-separator spellings like `1e6` and `64_000`
1814 * Updated documentation links to the current docs sites
1815 * Changed "always allow" permission rules to save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees
1816 * Changed `/usage-credits` to ask for confirmation before sending a request to organization admins
1817 * Changed Vim mode `s` and `S` (substitute char/line) to work in NORMAL mode, matching vim behavior
1818 * \[VSCode] Updated the Remote Control banner to describe what it does
1819 * Claude in Chrome: hardened file-upload path validation
1820 * Claude in Chrome: `save_to_disk` on screenshot actions now writes the image to disk and returns the path; previously it did nothing
1821 * Fixed a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.
1822</Update>
1823
1824<Update label="2.1.210" description="July 14, 2026">
1825 * Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck
1826 * Added a startup warning for `Write(path)`, `NotebookEdit(path)`, and `Glob(path)` permission rules — use `Edit(path)` or `Read(path)` instead
1827 * Fixed `isolation: 'worktree'` subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree
1828 * Fixed the `ultracode` keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments
1829 * Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element
1830 * Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text
1831 * Fixed `claude attach` sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes
1832 * Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element
1833 * Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait
1834 * Fixed Claude assuming a `cd` took effect after its command was moved to the background; the tool result now states the working directory is unchanged
1835 * Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session
1836 * Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot
1837 * Fixed `/doctor` skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in
1838 * Fixed Grep content mode claiming "No matches found" when paginating past the end of results
1839 * Fixed unmatched `$1`/`$2` positional placeholders in skills and commands being silently stripped; they are now preserved verbatim
1840 * Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems
1841 * Fixed background workers crash-looping when a client resets its connection to the background service
1842 * Fixed `claude agents --effort ultracode` not reaching dispatched sessions; the value was silently dropped
1843 * Fixed pressing ← to open the agents view dropping the task tracker when returning to the session
1844 * Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted
1845 * Fixed killed background sessions leaving a permanent `git worktree lock` behind; the periodic sweep now releases locks whose owning process is gone
1846 * Fixed SDK MCP servers registered via an `initialize` control request waiting until the next turn to start connecting
1847 * Fixed returning to the agents view from a session leaving overlapping ghost frames with `CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1`
1848 * Fixed late-appearing `.claude/*` symlinks not being reconciled into the sandbox deny-write list
1849 * Hardened the Agent tool against indirect prompt injection via content a subagent read
1850 * Improved the Bash/PowerShell tool message when a command hits its timeout and is auto-backgrounded, so the model can distinguish a hang from an explicit background request
1851 * Improved auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the session's first request and pinned for the session
1852 * Improved the bundled dataviz skill's chart color validation with perceptual OKLab color difference and recalibrated color-blindness thresholds
1853 * Memory writes that leave a MEMORY.md index over its read limit now produce an explicit error instead of silent truncation
1854 * Screen reader mode now announces permission mode changes aloud when cycling modes with Shift+Tab
1855 * The agents footer hint now shows how many background agents are waiting on your input, with a brief color emphasis when the count changes
1856 * Agent view: the session you pressed ← from stays visibly marked even after mouse hover or arrow keys move the selection
1857 * Fable temporarily shows as unavailable in the advisor picker while a server-side issue causing Fable advisor failures is fixed
1858</Update>
1859
1860<Update label="2.1.209" description="July 14, 2026">
1861 * Fixed /model and other dialogs being blocked in `claude agents` background sessions (reverts an overly broad guard)
1862</Update>
1863
1864<Update label="2.1.208" description="July 14, 2026">
1865 * Added screen reader mode: opt-in plain-text rendering for screen reader users. Run `claude --ax-screen-reader`, set CLAUDE\_AX\_SCREEN\_READER=1, or add "axScreenReader": true to settings.
1866 * Added `vimInsertModeRemaps` setting: map two-key insert-mode sequences like `jj` to Escape in vim mode
1867 * Added `CLAUDE_CODE_PROCESS_WRAPPER`: agent view and the background service now honor a corporate launcher by running every Claude Code self-spawn through a required wrapper executable
1868 * Added mouse-click support for multi-select menus and "Other" input rows in fullscreen mode
1869 * Changed the Fable 5 usage-credits consent prompt to start with the decline option focused
1870 * Fixed fast mode staying off after switching back to a model that supports it — it now restores automatically when enabled in settings
1871 * Fixed replies typed to a background agent being lost when delivery fails — the text is now saved and delivered when the session restarts
1872 * Fixed background-session attach failing permanently ("Couldn't start the background daemon") after an update replaced the binary a running `claude agents` process was launched from
1873 * Fixed the context window (and auto-compact indicator) briefly resetting to 200k after the CLI auto-updates, causing a false "100% context used" when resuming long-context sessions
1874 * Fixed supervised and background sessions crashing when a server closed an HTTP/2 connection with a GOAWAY while requests were in flight
1875 * Fixed truncated stream-json/JSON output and missing result message when piping large responses from `claude -p`
1876 * Fixed `CLAUDE_CODE_MAX_OUTPUT_TOKENS` and similar env vars silently using the mantissa of scientific-notation values (`1e6` became `1`)
1877 * Fixed very large markdown tables stalling rendering or using excessive memory; tables over 200 rows show the first 200 with a "… N more rows" notice
1878 * Fixed the Edit tool failing on files modified after reading when the target text still matches uniquely
1879 * F
1855 * Fixed parallel Claude Code sessions al