One read of Claude Code CLIclaude-code-20260929T200701Z
11 pages moved out of 210 read.
Pages moved
11
significant first
Pages read
210
in this capture
Captured
20:07 UTC
Corpus hash
03cea9313dc6
corpus-hash
What this read moved
1-11 of 11artifacts Changed · +5 / -10 lines
from line 41
4141Build a dashboard artifact of last week's deploy failures by service and keep it updated as you investigate.
4242```
4343
44Unless you name a location, Claude writes the page to an HTML or Markdown file in a temporary directory outside your project, then publishes it. Publishing a new artifact goes through your session's [permission mode](/docs/en/permission-modes):
44Unless you name a location, Claude writes the page to an HTML or Markdown file in a temporary directory outside your project, then publishes it. Outside [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), a new artifact that Claude publishes in response to a prompt you type goes through without a permission prompt or classifier review, unless that publish declares runtime capabilities for the page, such as [connector calls](#pull-live-data-with-mcp-connectors) or [file downloads](#offer-a-file-download). In plan mode, Claude Code asks you before the first publish of each artifact.
4545
46* **Auto mode**: the classifier reviews the publish instead of prompting you, so Claude can publish a page without you seeing a prompt. Which mode your sessions start in depends on your plan; see [the starting permission mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode).
47* **Manual and Accept edits modes**: Claude Code asks for permission; it might say something like `Claude wants to publish deploy-failures.html, uploading it to claude.ai (Anthropic's servers) to host as the page "Deploy failures by service", private to you until you share it`. Select **Yes** to publish.
46The artifact stays private to you until you [share it](#share-an-artifact). After you share it publicly, Claude Code asks for your approval once per conversation before changing it, or in [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) has the classifier review the change.
4847
49After you approve an artifact once, Claude Code republishes it without asking, and asks again in some cases, including when:
50
51* Claude declares a runtime capability for the page, such as [connector calls](#pull-live-data-with-mcp-connectors) or [file downloads](#offer-a-file-download)
52* You have since [shared it publicly](#share-an-artifact)
53* You have since shared it with specific people or your organization with the latest version chosen as the version viewers see
48If you turned [feature-flag fetching](/docs/en/env-vars#features-that-need-feature-flag-fetching) off, Claude Code asks before the first publish of each artifact, or in auto mode has the classifier review it.
5449
5550After the first publish, Claude prints the URL, and your browser opens to the new page. If you sent the prompt through [Remote Control](/docs/en/remote-control) from claude.ai, Claude Desktop, or the Claude mobile app, no tab opens on the machine running the session. The browser opens there the next time Claude publishes the artifact from a prompt you type at the terminal. Press `Ctrl+]` at any time to reopen the session's most recent artifact.
5651
changelog Changed · +139 / -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="2.1.285" description="September 29, 2026">
10 * Added `CLAUDE_CODE_DISABLE_WEB_FETCH` environment variable to turn off the WebFetch tool
11 * Added `claude --desktop` to open the Claude desktop app on the current directory, or on a session with `--continue` / `--resume <id>`
12 * Added `claude plugin configure <plugin>` to show a plugin's options and which are unset, or save new values read from stdin with `--values-stdin`
13 * Added `<server>.<key>=<value>` to `claude plugin install --config`, so a bundled `.mcpb` MCP server's own settings can be set at install time and it starts without visiting `/plugin` → Configure
14 * Added `allowedProviders` managed setting to limit which API providers a machine may use (Anthropic API, a custom endpoint, Bedrock, Mantle, Vertex AI, Foundry, Claude Platform on AWS, or a Cloud gateway)
15 * Added `CLAUDE_CODE_NONSTREAMING_TIMEOUT_RETRIES` environment variable to cap re-sends of a non-streaming fallback request that timed out
16 * Fixed `claude -p` with `CLAUDE_CODE_FORK_SUBAGENT=1`: a subagent's own Agent call now runs in the foreground, so the subagent gets the child's result
17 * Fixed plugin and marketplace installs and updates over SSH ignoring the ssh program set in `GIT_SSH` or in your git config's `core.sshCommand`
18 * Fixed Claude Code refusing to start when the OS denies reading the managed settings file; it now warns and starts without that file's policies. Other read errors and unparseable files stop every session
19 * Fixed cloud sessions that restarted after their conversation was compacted refusing the next update to an artifact the session had already read or published
20 * Fixed `claude plugin disable` and `enable` with a full `name@marketplace` id changing a settings entry in another letter case instead of the installed plugin's own
21 * Fixed files attached to a message sent over Remote Control being left out after a single failed download; a network error, timeout or server error is now retried up to twice
22 * Fixed switching models mid-session with a `set_model` request (such as the Agent SDK's `setModel`) leaving the new model on the built-in output-token limit and auto-compact window until restart
23 * Fixed redacted logs and transcripts showing part of a URL password that contains `@`, or all of it when the URL writes its `@` as `%40`
24 * Fixed SSH passphrase and new-host prompts from worktree and `/teleport` fetches taking over the terminal; these fetches now fail fast instead of asking
25 * Fixed switching off an MCP server added mid-session in SDK and `-p` sessions leaving its tools available
26 * Fixed `claude -p --permission-prompt-tool`: a background subagent's permission request now goes to the prompt tool instead of being auto-denied
27 * Fixed `claude mcp list` and `claude mcp get`, and the not-found error of `claude mcp remove`, `login` and `logout`, printing line breaks and terminal escape sequences from MCP server names and values
28 * Fixed sandbox auto-allow asking for approval on every run of many inline scripts (`python3 -c`, `node -e`) just because they contain `=`
29 * Fixed fork subagents not keeping the session's plan mode or `dontAsk` mode: a fork now runs under its parent's permission mode and cannot exit plan mode
30 * Fixed `claude remote-control --help` saying `--[no-]chrome` defaults to the machine's `/chrome` setting; spawned sessions keep Claude in Chrome off unless `--chrome` is passed
31 * Fixed background subagents in auto mode prompting a second, redundant reply after each report
32 * Fixed cloud session creation and `/remote-env` reading only the newest 20 of an account's environments
33 * Fixed Remote Control marking a message as read as soon as it arrived instead of when Claude started on it, and losing a message still queued when the terminal quit (it now arrives on the next resume)
34 * Fixed installing a plugin with `claude plugin install` or `/plugin` putting it into an installed plugin's cache or data folder when their ids differ only in `.`, `-`, `@` or (macOS, Windows) capitals; the install is now refused
35 * Fixed hooks and SDK permission callbacks seeing a missing or outdated plan on ExitPlanMode when the plan was written in the same response
36 * Fixed the first reply in cloud sessions arriving tens of milliseconds late, a regression in 2.1.283
37 * Fixed sessions that authenticate with `ANTHROPIC_AUTH_TOKEN` against the Anthropic API never loading the organization's policy
38 * Fixed a failed `agent()`, `parallel()` or `pipeline()` call that a workflow script awaits later, or not at all, being treated as an unhandled promise rejection, which could end a background session
39 * Fixed synchronous hooks hanging Claude Code while a background process the hook started (for example `some-daemon &`) kept its output open; the hook now finishes shortly after its own process exits
40 * Fixed WebFetch reporting a rate-limited domain safety check as a network or enterprise policy block
41 * Fixed the fullscreen ctrl+o transcript freezing briefly when opened on turns with hundreds of file reads or searches; tool calls still running when the transcript opens now show their results when they finish
42 * Fixed Amazon Bedrock mid-stream `modelTimeoutException` and `serviceUnavailableException` errors showing a raw JSON body instead of the error message
43 * Fixed `/autofix-pr` and `/schedule` saying the Claude GitHub App is not installed on a repository whose install status had not been checked yet
44 * Fixed dismissing a row (x) in `/artifacts` unlinking its file from the artifact, so publishing the same file again created a new artifact instead of updating it
45 * Fixed Artifact tool publishes after a conversation rewind (Esc Esc) overwriting a file's newer content that Claude had read only in the rewound turns; the publish is now refused until Claude re-reads the file
46 * Fixed an `Artifact` allow rule ("don't ask again") letting the Artifact tool publish a file outside the working directories without asking; add the file's folder with `--add-dir` for the rule to cover it
47 * Fixed `/cost` and SDK `modelUsage` reporting a turn under the wrong model when the server answered a refusal with a different fallback model than the client expected
48 * Fixed the Artifact tool so that publishing a page no longer lets Claude overwrite its source file without re-reading it when Claude's earlier read was cut short or the file had changed since
49 * Fixed auto mode skipping its classifier for Artifact tool asset uploads and reads of someone else's artifact when you had approved that artifact earlier in another permission mode
50 * Fixed a misleading "core.worktree is set" error from `/ultrareview` when the project folder briefly could not be read
51 * Fixed `/ultrareview` on macOS and Linux failing to upload the working tree from a git worktree whose per-worktree config sets `core.longpaths`
52 * Fixed the Artifact tool sometimes reporting a publish as a conflict with another session after retrying a temporary server error, when the first attempt had actually succeeded
53 * Fixed `/ultrareview` uploads including uncommitted changes to credential files whose name has a colon before the extension, such as `server:8443.key`
54 * Fixed a rare auth failure when two sessions recover a login refresh lock left by a crashed process at the same time
55 * Fixed the PowerShell tool's permission check skipping deny and ask rules, and caching that failure for later checks, when its command parser failed to start (for example when the machine was out of memory)
56 * Fixed `/ultrareview` uploads on macOS and Linux running slowly on some unusual file names, and their credential-file check missing file or folder names with many backup or editor marks
57 * Fixed a cancelled shell command or hook still starting, and running to its end, when the cancel arrived while it was being set up
58 * Fixed vim mode: after editing in the external editor (Ctrl+G), `x` or `r` in NORMAL mode no longer breaks a pasted-text placeholder at the end of the prompt
59 * Fixed responses blocked by the API's output content filter being re-sent and retried, sometimes for minutes, instead of showing the filter's error right away
60 * Fixed plugins silently skipping a bundled `.mcpb` MCP server that still needs configuration: `/plugin`, the install message and `claude plugin install` now say so and point to Configure
61 * Fixed compacting or resuming a session failing, opening without its history, or crashing when its saved transcript holds a compaction marker or loop wakeup entry with missing or malformed fields
62 * WSL: Fixed `/ultrareview` refusing to upload a checkout on a Linux volume when a changed file's name has a colon or ends in a dot or space
63 * Fixed `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` re-running a turn that had ended at `--max-turns`
64 * Fixed sign-in that could wait forever after the browser showed success
65 * Windows: Fixed `/ultrareview` uploading a linked worktree of a repository rooted at your home folder in some cases
66 * Fixed cloud sessions reporting the uploads folder as missing before any file had been uploaded
67 * Fixed a reply sent from `claude agents` to a background session waiting on a permission prompt sometimes approving the pending command
68 * Fixed `claude attach`, `logs`, `stop`, `respawn` and `rm` starting a new session with the command name as its prompt when options came before it, such as from a shell alias
69 * Fixed `claude mcp list` leaving out WebSocket (`ws`) MCP servers; each is now listed with its URL and health status
70 * Fixed `claude mcp get` showing no Type, Command, Args, or Environment for stdio servers whose config entry omits the `type` field
71 * Fixed `.claude/settings.local.json` allow rules being held back outside a git repository when git's trace2 output is configured
72 * Fixed the `/claude-api` eval runner scaffold and report builder writing through a symlink or hard link planted at an output file
73 * Fixed the `/claude-api` eval runner scaffold counting responses cut off at `max_tokens` in the score averages; they are now marked truncated and counted separately
74 * Fixed ` ` showing as literal text in the terminal when a reply uses it to indent text, such as row labels in a markdown table
75 * Fixed a brief freeze (up to a second) partway through long sessions outside fullscreen mode, which came back after `/clear` or `/compact`
76 * Fixed an approved Edit never going through when its target is a device, such as a file symlinked to /dev/null, and the approval came from the IDE diff view or changed the edit
77 * Fixed a failing API request being retried up to 21 times when streaming kept failing; the non-streaming fallback now shares the request's retry budget instead of getting a fresh set of retries
78 * Improved Claude in Chrome: the native host now reports your computer's name, so connected browsers can be labeled by computer instead of "Browser 1" / "Browser 2"
79 * Improved Bedrock and Vertex AI sessions to switch to an older available model of the same tier, instead of failing, when an admin removes access to the default model; session titles and summaries now fall back with it
80 * Improved plugin marketplace errors to name why a git address is refused instead of citing enterprise policy
81 * Improved validation of git URLs for plugins, marketplaces and the current repository's remote
82 * Improved Artifact tool results: they now suggest publishing in the same step as writing or editing the page, which can save a round trip
83 * Improved Remote Control: a `/btw` side question asked of a session hosted by an app such as Claude Desktop now sees the turn in progress, not only the last finished one
84 * Improved pictures Claude sends as BMP, HEIC, HEIF, AVIF or TIFF files: the Claude apps now show a preview where Claude Code can convert them
85 * Improved subagents in auto mode: a subagent's run now ends as soon as it hands its report back to its caller, instead of taking extra turns that reach no one
86 * Improved Bedrock and Vertex start-up model checks: models your account cannot use are now remembered for up to a day instead of being re-checked on every launch
87 * Improved Artifact tool publish results to use fewer tokens: the note on updating an artifact is shorter, and where to find your artifacts is no longer repeated after every publish
88 * Improved SDK liveness during a non-streaming fallback request: with partial messages on, a `ping` stream event is now sent every 30 seconds on the Anthropic API, Claude Platform on AWS and gateways
89 * Improved `/resume` and `claude --resume` on a session that is running in the background: they now open that session instead of refusing, and a prompt given with `claude --resume <id> "prompt"` is sent to it as its next turn
90 * Improved per-turn performance when many permission deny rules and MCP tools are configured
91 * Improved responsiveness when leaving the ctrl+o transcript view in long sessions when fullscreen rendering is off
92 * Improved Bedrock, Vertex and Mantle start-up model checks to send the same User-Agent, x-app and session ID headers as regular requests
93 * Changed MCP tools so a tool that sets its own `_meta['anthropic/alwaysLoad']` to false stays deferred when its `--mcp-config`, Agent SDK or plugin server is set to `alwaysLoad`
94 * Changed background Bash and PowerShell commands to stop after a time limit (their `timeout` with `run_in_background`, default 30 min, max 2 h); Claude is notified when one is stopped
95 * Changed Code Review's pull request reviews and `/ultrareview` to run when `disableWorkflows` is on, unless the machine running the review has it set by its own administrator (MDM or the managed-settings file)
96 * Changed sessions behind a custom `ANTHROPIC_BASE_URL` to use the 1M context window of models that have one (Opus 4.7+, Sonnet 5+, Fable); run `/autocompact 200k` if your gateway stops at 200K
97 * Changed Team and Enterprise sessions, and sessions whose sign-in plan Claude Code can't determine, to withhold WebFetch until the organization policy loads if it couldn't be loaded at startup
98 * Changed /memory so that Auto-memory can no longer be turned on from a background session or from a session one of Claude Code's own tools started; turning it off there still works
99 * Changed the one-time offer to make auto mode your default permission mode to also show on third-party providers and with telemetry off, when your user settings default to another mode
100 * Changed `claude -p` and Python Agent SDK sessions on third-party providers or with telemetry off to start in auto mode when no permission mode is configured, like interactive sessions; `--permission-mode` still overrides it
101 * Changed Bedrock, Mantle and Claude Platform on AWS requests to a base URL with a non-default port to include the port in the SigV4-signed Host header
102 * Changed the MCP server name `widgets` to be reserved in cloud sessions and on self-hosted runners: your own server under it, or a close spelling such as `widgets_`, no longer loads, so rename it
103 * Changed `/ultrareview` on macOS and Linux to leave symbolic refs out when uploading a local checkout; a checkout whose current branch is a symbolic ref is now refused with an explanation
104 * Windows: Changed project and local settings `env` to no longer set `ALLUSERSPROFILE`, `SystemDrive`, or the `CommonProgramFiles` variables; set them in user or managed settings instead
105 * Changed `/tasks` to fold background work Claude Code runs for itself under one "System tasks" row; press Enter on it to show those tasks
106 * Changed `/ultrareview` on macOS and Linux to require git 2.31 or newer to upload a local repository; checkouts made with `--separate-git-dir` are now refused instead of being uploaded with an older method
107 * Changed `/ultrareview` uploads on macOS and Linux to send a partial clone as a working-tree snapshot on git 2.31 or newer, instead of falling back or refusing when git's version looked too old
108 * Changed `/ultrareview` uploads on macOS and Linux to refuse, instead of fetching, a partial clone missing some of its working tree's files on older git versions; a clone made without `--filter` uploads
109 * Changed Bedrock, Vertex and Mantle start-up model checks to identify themselves as Claude Code, like other Claude Code requests
110 * Changed `claude mcp get` to hide the command, arguments, and environment values of stdio MCP servers provided by plugins; variable names are still shown
111 * Changed `/claude-api` so it can no longer be run from Remote Control clients
112 * Changed `/config chrome=true` to direct you to the /config panel instead of enabling Claude in Chrome by default; `/config chrome=false` still turns it off when it was on
113 * Changed sandbox settings so project settings cannot widen or turn off an admin-required sandbox, replace the proxy behind a managed deny list, extend a strict allowlist, or reopen managed read-denies
114 * \[VSCode] Added a note under a restored tab's last message when a window reload interrupted it and no reply will follow
115 * \[VSCode] Added a plugin options form to Manage plugins: installing a plugin that has options asks for the unset ones, and a gear on its row changes them later
116 * \[VSCode] Added an on-demand diagnostics tool so Claude in the panel can read the Problems panel's current errors and warnings at any time, not only right after it edits a file
117 * \[VSCode] Fixed pressing Enter after typing a slash command running an unrelated menu item picked by fuzzy match, or doing nothing
118 * \[VSCode] Fixed an open agent transcript losing the agent's newer messages during a long session
119 * \[VSCode] Fixed a message that quotes a Claude Code or IDE tag losing the rest of its text in the chat
120 * \[VSCode] Fixed a message sent while Claude was working disappearing from the conversation after the session was reopened
121 * \[VSCode] Fixed the session list's Web tab showing the previous account's sessions after an account switch
122 * \[VSCode] Fixed restored tabs re-running an interrupted turn when VS Code was started with `CLAUDE_CODE_RESUME_INTERRUPTED_TURN` set, even with Continue After Reload off
123 * \[VSCode] Fixed Escape stopping the running turn instead of closing the command menu after clicking one of its rows
124 * \[VSCode] Fixed opening Past conversations replacing a live conversation with its saved copy
125 * \[VSCode] Fixed a Claude tab reloaded after an extension restart staying blank instead of saying how to recover
126 * \[VSCode] Fixed opening a conversation that is already open in another window or app starting a second copy of it without warning; it now asks first
127 * \[VSCode] Fixed a hook's reason for blocking or stopping a prompt disappearing after a window reload
128 * \[VSCode] Fixed tabs stuck on a conversation that can't be resumed: the error now says so and offers to start a new conversation
129 * \[VSCode] Fixed every file Read, Write and Edit stalling for ten minutes and then being skipped when the editor stops responding to the extension's automatic save before the tool runs
130 * \[VSCode] Fixed the agent map labeling a sub-agent with the session's model instead of the model it actually ran on (e.g. under `CLAUDE_CODE_SUBAGENT_MODEL_FORCE` or an agent's own `model`)
131 * \[VSCode] Fixed uninstalling a plugin from the Manage plugins dialog, which removed the wrong installation or failed for a plugin installed for the project
132 * \[VSCode] Fixed sign-in staying on the authorization-code step after going back and choosing the same sign-in method again
133 * \[VSCode] Fixed the chat panel stalling when a long session trims its oldest rows
134 * \[VSCode] Fixed the conversation disappearing from a session when many agents run
135 * \[VSCode] Fixed the editor tab keeping an old name after a session was renamed with /rename, by a SessionStart hook, or on claude.ai
136 * \[VSCode] Fixed the agent map's transcript view leaving out messages sent to a running agent
137 * \[VSCode] Improved the Manage plugins dialog: a failed plugin action now opens a popup that explains it and, where there is one, offers the fix
138 * \[VSCode] Changed the Manage plugins dialog to ask before removing a marketplace or turning off a plugin that your project's shared `.claude/settings.json` turns on
139 * \[Cloud sessions] Fixed Run now on a routine showing internal error text when the run is refused before it starts; it now shows the same explanation as the routine's failure notification
140 * \[Cloud sessions] Changed `MCP_DISCOVERY_CACHE=1`, when set in your cloud environment's variables rather than a settings file, to reuse your connectors' tool lists after a session restart; other MCP servers are no longer cached and connect at startup
141 * \[Claude Tag] Added direct messages with Claude for members on an Enterprise plan Standard or Usage-Based Chat seat who also have Cowork; a seat that includes Claude Code is no longer required
142 * \[Claude Tag] Fixed the Default model setting in admin settings and a channel's Configure page offering models your organization can't use, which made saves or new sessions fail
143 * \[Claude Tag] Fixed the note under Claude's Slack messages saying it answered on a fallback model, and why, disappearing when Claude later edited that message
144 * \[Code Review] Fixed the organization menu in Code Review's "Add a repository" dialog showing only a few of your GitHub organizations; it now loads more as you scroll
145 * \[Code Review] Improved the Code Review check run to say when your repository's REVIEW\.md wasn't applied, for example on a very large pull request or when REVIEW\.md is a symbolic link
146</Update>
147
9148<Update label="2.1.284" description="September 28, 2026">
10149 * Added Claude Sonnet 5.5 (`claude-sonnet-5-5`), now the default Sonnet model on the Anthropic API — 1M context, $2/$10 per Mtok with \$0.20/Mtok cache reads
11150 * Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones
from line 1729
15901729 * Fixed background sessions failing to start on macOS npm installs during a self-update, and on Windows when a stale daemon lock file pointed at a reused process id
15911730 * Fixed the working spinner stopping while a response streams behind a slash-command panel
15921731 * Fixed a background session's `state.json` `detail` repeating its own dispatch prompt after a scheduled wake-up
1593 * Fixed `claude agents` keeping a background session you re-prompted buried in Completed after it finished again; Completed now orders by the latest finish
1594 * Fixed `claude --bg` from a directory that was just deleted reporting "backgrounded" and leaving a crashed session row; it now prints the reason and exits 1
1595 * Fixed Remote Control connecting mid-session re-sending the Bash tool definition, causing a prompt-cache miss
1596 * Fixed a doubly-listed custom `Authorization` header overriding the configured credential on Bedrock, Mantle, Vertex, and WIF, and the Vertex setup wizard picking up a leftover Anthropic profile from `~/.config/anthropic`
1597 * Fixed Claude apps gateway sending stray host `Authorization` or profile headers to Foundry, Vertex, and Bedrock, and Foundry Entra ID upstreams not starting when `ANTHROPIC_FOUNDRY_API_KEY` is set
1598 * Fixed a leftover Anthropic API key or auth token being sent alongside your Foundry subscription key in API-key mode
1599 * Fixed `/schedule` routines whose prompt was saved without a message role and then ran with nothing to do
1600 * Fixed `claude agents` not saying that a background session is waiting for you to approve a message from another session, or who sent it
1601 * Fixed a prompt stashed with Ctrl+S inside an opened background session being lost when the session went idle or was stopped and then reopened
1602 * Fixed telemetry (OTEL) settings pushed through server-managed settings being ignored on warm starts, including desktop-app Code sessions
1603 * Fixed a teammate permission request being answered twice when the leader's mailbox write was briefly locked
1604 * Fixed a phantom duplicate slash-command row rendering below the in-flight turn while a command's auto-continued response streamed
1605 * Fixed `policyHelper` `timeoutMs` and `refreshIntervalMs` values above the timer maximum (2147483647) causing failures or re-runs every millisecond; they are now clamped
1606 * Fixed the token counter freezing or crawling after switching to another subagent's transcript, and made background subagents' and teammates' counters update live while a response streams
1607 * Fixed sandbox network hosts written with a trailing dot (`example.com.`): a `deniedDomains` entry didn't block the host inside the sandbox, and "don't ask again" for such a host kept prompting
1608 * Fixed dismissing the Remote Control consent prompt (Esc, or `n` at `claude remote-control`) counting as consent, so the next request connected without asking
1609 * Fixed `/mcp` reconnect and enable still connecting a settings-file MCP server that a managed MCP allow/deny list or `strictPluginOnlyCustomization` loaded after startup should block
1610 * Fixed `claude mcp remove` leaving a remote server's stored OAuth credentials behind when `strictPluginOnlyCustomization` locks MCP to plugin-only servers
1611 * Fixed Remote Control (`claude remote-control`) sessions started from the Claude app ignoring the selected model and running on the machine's default instead
1612 * Fixed `--disallowedTools` and session deny rules being dropped after the first settings reload when `allowManagedPermissionRulesOnly` is enabled
1613 * Fixed `--resume` listing a backgrounded conversation twice and `--continue` reopening its stalled pre-background copy; `--continue` now also opens finished background sessions
1614 * Fixed fullscreen mode not letting you click `!` shell command output to expand it
1615 * Fixed background sessions left running an older Claude Code binary piling up across auto-updates instead of being retired
1616 * Fixed `claude agents --json` briefly switching the terminal to raw mode and undoing another program's terminal settings on exit
1617 * Fixed Proactive output style sessions busy-looping with filler messages and repeated log reads instead of idling while a background command or Monitor they started is still running
1618 * Fixed subagents stopping when a response was cut off mid-stream by a computer sleep, dropped connection, or server error; they now automatically continue instead of ending with an incomplete response
1619 * Fixed `←` doing nothing in the `/btw` panel inside a `claude agents` session: it now returns to the agents list (even mid-answer), and the panel comes back when you reopen the session
1620 * Fixed sessions with an advisor model set missing the prompt cache on background requests (compaction, `/recap`, prompt suggestions) and re-sending the full conversation uncached each time
1621 * Fixed `claude -p` exiting about 5 seconds after its final result while a Monitor the model armed was still running; it now waits for the watch to fire or time out
1622 * Fixed a `permissions.ask` rule being skipped in auto mode when the matching command ran inside a compound command or subshell, letting it run without the confirmation prompt
1623 * Fixed plugins being able to read files outside their own directory through a declared command, agent, skill, hooks or other component path that is a symlink; such paths are now refused with an error
1624 * Fixed `/add-dir` rejecting a directory inside the current working directory; it now loads that directory's skills, commands, and agents like `--add-dir` does at startup
1625 * Fixed the main agent not being told when you resume a subagent you had stopped from its transcript view
1626 * Fixed a crash when pasting ANSI-colored text (e.g. a CI log) into dialogs like `/feedback`
1627 * Fixed `claude mcp add/remove` hanging or exhausting memory when the project's `.mcp.json` is a FIFO or a device-file symlink; it now fails fast with an actionable message
1628 * Fixed unbounded memory growth when non-JSONL data is piped into `claude -p --input-format stream-json`; it now fails fast with a clear error
1629 * Fixed backgrounding a turn (`←` or Ctrl+B) while a subagent or other tool was running occasionally making the background session treat that tool as rejected instead of re-running it
1630 * Fixed Bash `Read()`/`Edit()` deny rules not applying to `< file` redirects and reader commands like `tac` and `egrep`; a deny rule on any argument or redirect target now refuses the command
1631 * Fixed resuming or messaging a subagent whose transcript had grown past 5 MB (for example after reading many images) failing with "No transcript found"
1632 * Fixed worktree-isolated sessions refusing Bash loops, `$VAR` reads, `"$(…)"` and heredocs that never touch git as "too complex to verify that it stays inside the worktree"
1633 * Fixed `/model` and `/effort` showing a prompt-cache warning after rewinding a conversation back to empty
1634 * Fixed prompt-cache misses on every turn in long screenshot-heavy sessions once images exceeded the per-request size cap
1635 * Fixed the Edit permission prompt's diff view rendering emoji and multi-code-point characters with incorrect widths
1636 * Fixed WebSocket MCP server connection failures being logged as "\[object ErrorEvent]" instead of the underlying error
1637 * Fixed background sessions failing to open with "Couldn't start the background service" while another Claude Code process was downloading an npm update; the start now waits for it
1638 * Fixed background commands that detach from their shell (for example under `timeout` or `setsid`) surviving a task stop or Claude Code exit
1639 * Fixed Claude not being told when you stop a background command from the tasks panel or a connected client
1640 * Fixed stopping a background subagent leaving its monitors running
1641 * Fixed sandboxed git commands in a linked worktree losing write access to the repository's common `.git` directory after `cd` into a subdirectory
1642 * Fixed Bedrock and Bedrock Mantle requests going silent during long hidden-thinking phases on Opus 4.7 and later, which let idle timeouts cut the connection; the stream now carries progress events
1643 * Fixed launching Claude Code after a Claude apps gateway expired or revoked your session: it now says the session ended and offers `/login` instead of reporting a network error
1644 * Fixed cloud sessions losing git/GitHub credentials for the rest of the session when the session's network proxy failed to start at launch; it now retries in the background and recovers
1645 * Fixed leftover `cc-daemon-*` folders in the system temp directory after an interrupted background daemon start; the `cleanupPeriodDays` retention sweep now removes them
1646 * Fixed Bash permission checks auto-approving certain `[[ ]]` conditionals that zsh parses differently from bash; these commands now prompt for approval
1647 * Fixed the managed-settings approval prompt showing the generic warning instead of its telemetry wording when the settings also turn detailed tracing or raw API body logging off, or trace export on
1648 * Fixed agent-team teammates in tmux/iTerm2 panes sometimes staying open after acknowledging a shutdown request
1649 * Fixed the keyless Console sign-in ("Sign in with your Console account") not applying your organization's server-managed settings, and `/status` not showing the Organization for that sign-in
1650 * Improved rendering performance: less re-render work per turn in long conversations, streaming no longer slows down as the reply grows, and background-agent updates no longer re-render the whole screen
1651 * Improved prompt input responsiveness by reducing per-keystroke rendering work
1652 * Improved policy helper diagnostics — refresh failures now show in `/status`, declining the managed-settings dialog prints why Claude Code exited, and helper timeouts are reported as timeouts
1653 * Improved `/code-review --comment` to post findings on GitLab merge requests via `glab mr note` instead of reporting the target as unsupported
1654 * Improved notifications: an MCP elicitation or permission ask queued under another dialog now sends its idle desktop notification at the same delay as a visible ask
1655 * Improved verbose/transcript output: async hook completion notices that arrive together now appear on one line instead of one line per hook
1656 * Improved `claude self-hosted-runner --configure-git` to also enable git push negotiation, so the first push of a new branch from a stale clone uploads only the new commits instead of the whole tree
1657 * Improved liveness reporting to SDK hosts while a response is held open by gateway keep-alives, so long waits under a raised `CLAUDE_STREAM_IDLE_TIMEOUT_MS` are not mistaken for a hung session
1658 * Improved MCP connection and OAuth debug/error logs so credentials carried in a server's URL or request headers are redacted
1659 * Improved `/fork` to keep the original conversation's prompt cache in the new background session: its worktree briefing now arrives as a message instead of a system-prompt change
1660 * Improved emoji autocomplete to accept the remaining GitHub/Slack shortcode aliases (`:satisfied:`, `:telephone:`, `:collision:`, …)
1661 * Changed `--effort` to lift a new model's default-effort hold for that session only rather than permanently; an effort picked on claude.ai for a Remote Control session now applies during the hold
1662 * Changed a `policyHelper` in MDM or `managed-settings.json` shadowed at launch by cached server-managed settings to run (or exit) as soon as the fetch reports them removed, not at the next launch
1663 * Changed `managedSourcesBehavior: "merge"` to take `sandbox.credentials.awsPairs` and `sandbox.ripgrep` whole from the highest managed source that sets them instead of combining the sources' values
1664 * Changed gateway model discovery (`CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1`) to run even when `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC` is set, since it only queries your gateway
1665 * Changed `claude --resume <session-id> --bg` to continue that session under its own ID when nothing is running it, instead of silently starting a copy; a copy is now announced
1666 * Changed `/btw` history browsing from `←`/`→` to `Shift+←`/`Shift+→` (or `[`/`]`), stepping through your recent side questions and back to the live answer
1667 * Changed `defaultMode: "bypassPermissions"` in `.claude/settings.json` or `.claude/settings.local.json` to be ignored, like `"auto"`; set it in user or managed settings, or pass `--permission-mode`
1668 * Changed `fable` and `best` in Claude apps gateway sessions to keep resolving to Fable 5 for now, since gateways not yet configured for Fable 5.1 reject it; pick Fable 5.1 in `/model` to use it
1669 * Changed `--add-dir`, `/add-dir`, and `additionalDirectories` to refuse network paths (UNC shares, `/net/<host>` automounts) with a message before touching them; on Windows use a mapped drive letter
1670 * Changed Claude apps gateway sign-in and token refresh requests to verify the gateway's pinned TLS certificate, as the managed settings fetch already does
1671 * Changed Cowork and claude.ai cloud sessions: reading an artifact that isn't yours now always asks you first, even in auto mode
1672 * Removed the Ctrl+E command explanation on Bash and PowerShell permission prompts
1673 * \[VSCode] Added collapsible ACCOUNT & USAGE and SESSION MANAGER section headers to the session list panel, with the account email, the usage meter, and a View details link opening the usage dialog
1674 * \[VSCode] Added a model pill to the input footer that shows the current model and opens the model picker, with an Effort row and a "More models" page
1675 * \[VSCode] Added a collapse toggle to the Ungrouped section of the session list
1676 * \[VSCode] Added output style selection to the command menu, including custom styles
1677 * \[VSCode] Fixed third-party provider deployments (Bedrock, Vertex, and others) still showing claude.ai-only features (remote sessions, dictation, usage) and calling claude.ai with a leftover login
1678 * \[VSCode] Fixed the session list panel's usage meter staying blank after the panel loads; it now shows the last known usage immediately
1679 * \[VSCode] Fixed the "Enable Remote Control for all sessions" toggle so turning it on or off applies to sessions that are already open, not only to new ones
1680 * \[VSCode] Fixed screen reader announcements: a control character before a fence or heading no longer drops visible lines from speech, and bold markers spanning a heading are no longer mis-paired
1681 * \[VSCode] Changed the action menu to list slash commands in a filterable "Slash commands" dialog instead of inline; picking one runs it; the MCP servers dialog gained the same filter box
1682 * \[VSCode] Changed "Delete session" to "Archive session": archived sessions move to a collapsible "Archived sessions" group at the bottom of the list with an Unarchive action
1683</Update>
1684
1685<Update label="2.1.252" description="August 31, 2026">
1686 * Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs
1687 * Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet
1688 * Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded
1689 * Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit
1690</Update>
1691
1692<Update label="2.1.251" description="August 28, 2026">
1693 * Added `PreModelSwitch` and `PostModelSwitch` hook events (block, confirm, or annotate a model switch); `SessionStart` resume hooks now receive session staleness and the estimated re-cache cost
1694 * Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)
1695 * Added a Spend limit bar to `/usage` and a `rate_limits.spend_limit` status line field for developers behind a Claude apps gateway with spend limits
1696 * Added a per-session prompt-cache line to `/cost` (hit ratio, misses, tokens re-cached, warm/cold) and a matching `prompt_cache` object for status line scripts
1697 * Added `attach`, `logs`, `stop`, `respawn`, and `rm` to `claude --help`; the `--resume` message for a running background session now names the exact `claude attach <id>` command
1698 * Fixed file tools (Read, Write, Edit) following a symlink swapped inside the working directory after the permission check, which could read or write outside the approved location
1699 * Fixed plugin commands declared in a marketplace entry being able to point outside the plugin directory; such paths are now rejected with a path-traversal error
1700 * Fixed project settings being able to enable detailed beta tracing or raw API body logging, and a lower-scope beta tracing endpoint bypassing an OTLP collector pinned by managed settings or a host app
1701 * Fixed the Workflow tool reading (and quoting in errors) a `scriptPath` outside what the session may read before the permission check ran
1702 * Fixed Grep and Glob not applying `Read(...)` deny rules to files reached through a symlinked search path
1703 * Fixed conversations getting stuck on "text content blocks must be non-empty" errors after a turn where the model produced only thinking
1704 * Fixed the first launch on a fresh install starting in default mode instead of auto mode for accounts whose startup default is auto mode
1705 * Fixed Opus 5 requests failing with "effort … is not supported when thinking is disabled" when effort was xhigh/max and thinking was turned off; effort is now sent as `high` in that case
1706 * Fixed replying to a message Claude Desktop delivered from another session: `SendMessage` to that session id now delivers through Claude Desktop instead of failing with "not reachable"
1707 * Fixed TUI lag with many parallel subagents: per-second progress ticks now replace their predecessor instead of piling up in the transcript
1708 * Fixed agent teams: a teammate's final answer not reaching the team lead — it now arrives in the idle notification instead of a content-free "available" notice
1709 * Fixed background subagents being unable to reply to a message from an unnamed sibling or parent agent (`from` was the agent type, which is not an address)
1710 * Fixed managed-settings `disableAutoMode` arriving mid-session not moving an already-running auto-mode session back to default mode
1711 * Fixed a "switch to Opus 1M for 5x more context" tip that appeared even when the current Opus model already has a 1M context window
1712 * Fixed Claude apps gateway sessions treating a stored Anthropic profile (e.g. a Console sign-in) as active: listing it in `/status` and retrying gateway 401s with it, though requests never use it
1713 * Fixed cloud sessions telling Claude the model had changed when the host was only setting the session's initial model
1714 * Fixed Remote Control reporting a failure when an organization's policy disables it; it now shows a single quiet notice instead
1715 * Fixed `/mcp reconnect` on Remote Control showing a generic withheld-detail error instead of the real remedy when a server was disabled in another session
1716 * Fixed `--input-format stream-json`: client-injected assistant tool calls sent without a message id were merged into the first one and their results lost, including when resuming older sessions
1717 * Fixed session transcripts being silently overwritten when a directory change relocated a session onto an existing same-ID transcript
1718 * Fixed background sessions and their subagents being unable to edit files inside a git worktree they created with `git worktree add`
1719 * Fixed background sessions occasionally starting without any plugin skills (and staying that way) when another Claude Code process was refreshing the plugin marketplace at the same moment
1720 * Fixed selecting text in an opened background session inside tmux over SSH: it now copies to the tmux buffer like a foreground session instead of falling back to OSC 52
1721 * Fixed SDK and cloud sessions hanging indefinitely when an SDK MCP server's handshake acknowledgment was lost; the wait now times out after 70 seconds and marks only that server failed
1722 * Fixed self-hosted runner leaving a stuck session's Bash tool processes running after the session was force-stopped
1723 * Fixed `/usage-credits` for Team and Enterprise members whose admin set the org's usage-credit limit to \$0: it now offers to ask the admin instead of saying a cap was reached
1724 * Fixed `--worktree --tmux` with a merge-request number on a gitlab.com origin trying a doomed GitHub-style fetch first instead of fetching the GitLab ref directly
1725 * Fixed Ctrl+G failing with "Emacs quit unexpectedly" in background sessions for editors that open `/dev/tty`, such as `emacs -nw` and `micro`
1726 * Fixed an `additionalDirectories` entry containing a null byte crashing startup, or breaking `/add-dir` and later settings updates when it came from an SDK host, IDE, or hook; it is now skipped
1727 * Fixed the MCP server menu's copy shortcut: it now says how the sign-in URL was copied instead of always claiming success
1728 * Fixed italic text (such as the session recap line) rendering as highlighted blocks in GNU screen and in tmux sessions using a `screen` terminal type
1729 * Fixed `claude mcp add --header` and `claude mcp add-json` help text naming the wrong transports
1730 * Fixed `claude ultrareview` and `/ultrareview` waiting the full 30 minutes when the cloud session fails to start; they now stop early and report the reason
1731 * Fixed Bash permission checks auto-approving commands that assign an arithmetic expression to an integer shell variable (e.g. `OPTIND=1/0`, `RANDOM=2+2`); these now prompt for approval
1732 * Fixed backgrounded sessions (`←`, `/background`, `--bg`) losing a Vertex/Bedrock gateway (`ANTHROPIC_*_BASE_URL` + `CLAUDE_CODE_SKIP_*_AUTH`) exported in the shell, so every request failed
1733 * Fixed `claude --bg --model fable` on Max plans stopping to ask for usage credits while the interactive session on the same account still had Fable all
1732
communications-kit Changed · +5 / -5 lines
from line 59
5959
6060 Where your code goes: Claude Code runs in your terminal and talks directly
6161 to Anthropic's API, with no third-party servers in the loop. It asks before
62 editing files or running commands. Under our Enterprise agreement, Anthropic
62 editing files or running commands. On our Team or Enterprise plan, Anthropic
6363 does not use your code or prompts to train its models.
6464 Details: https://code.claude.com/docs/en/data-usage
6565 https://code.claude.com/docs/en/security
from line 86
8686 *First thing to try* → run `/init`, then: "the test in [file] is flaky,
8787 figure out why and fix it."
8888
89 🔒 Runs in your terminal, talks only to Anthropic's API. Under our
90 Enterprise plan your code and prompts are not used to train models.
89 🔒 Runs in your terminal, talks only to Anthropic's API. On our Team or
90 Enterprise plan, your code and prompts are not used to train models.
9191 Data usage → https://code.claude.com/docs/en/data-usage
9292
9393 📚 Quickstart · VS Code · Free 1-hr course
from line 464
464464Permission-first by design. Every file edit, shell command, and external
465465call is gated by your approval. The CLI runs in your terminal and talks
466466directly to Anthropic's API, with no third-party servers, and supports
467optional OS-level sandboxing for shell commands. Under our Enterprise plan,
467optional OS-level sandboxing for shell commands. On a Team or Enterprise plan,
468468Anthropic does not use your code or prompts to train its models.
469469
470470*Try it now:* save these two links for the next time the question comes up.
from line 504
504504| - | - |
505505| "Does it work in VS Code?" | Yes. There is a VS Code extension and a JetBrains plugin with the same features, embedded in your editor. [VS Code →](/docs/en/vs-code) |
506506| "Do I have to configure anything first?" | No. Install, then run `claude` in any repo. Run `/init` once and you're set. [Quickstart →](/docs/en/quickstart) |
507| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. Under your Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
507| "Where does my code go?" | The CLI runs in your terminal and sends context to Anthropic's API for inference, with no third-party servers. On a Team or Enterprise plan, your code and prompts are not used to train models. [Data usage →](/docs/en/data-usage) |
508508| "Can it see my whole repo?" | It reads what you give it access to. File reads inside your working directory don't prompt; permission prompts gate edits, non-read-only shell commands, and file-tool reads outside that directory. A built-in set of read-only shell commands such as `ls` and `cat` runs without prompting; restrict it with [sandbox `denyRead` rules](/docs/en/sandboxing#filesystem-isolation). [Permissions →](/docs/en/permissions) |
509509| "How is this different from Copilot?" | Copilot autocompletes lines. Claude Code is an agent that reads files, runs commands, and makes multi-file edits. [Overview →](/docs/en/overview) |
510510| "What should I try first?" | A bug you've been putting off because it's tedious. "The test in \[file] is flaky, figure out why." [Quickstart →](/docs/en/quickstart) |
desktop Changed · +10 / -2 lines
from line 816
816816
817817### Authentication and SSO
818818
819Enterprise organizations can require SSO for all users. See [authentication](/docs/en/authentication) for plan-level details and [Setting up SSO](https://support.claude.com/en/articles/13132885-setting-up-single-sign-on-sso) for SAML configuration; OIDC setup is covered in the [Claude Enterprise Administrator Guide](https://claude.com/resources/tutorials/claude-enterprise-administrator-guide).
819Team and Enterprise organizations can require SSO for all users. See [authentication](/docs/en/authentication) for plan-level details and [Setting up SSO](https://support.claude.com/en/articles/13132885-setting-up-single-sign-on-sso) for SAML configuration; OIDC setup is covered in the [Claude Enterprise Administrator Guide](https://claude.com/resources/tutorials/claude-enterprise-administrator-guide).
820820
821821### Data handling
822822
from line 839
839839
840840To move a CLI session into Desktop, run `/desktop` in the terminal. Claude saves your session and opens it in the desktop app, then exits the CLI. This command is available on macOS and x64 Windows when you are signed in with a Claude subscription. It is not available with API key authentication or on Amazon Bedrock, Google Cloud's Agent Platform, or Microsoft Foundry.
841841
842To pick up a CLI session from inside Desktop instead, type `/resume` in the prompt box. Desktop lists the sessions you started from the CLI, and you can search them by title, folder, or branch and preview where each one left off. Select a session and it continues in the app with its full conversation and context.
842You can also pick up a CLI session from inside Desktop with `/resume`. The command is available in local sessions, not in SSH, WSL, or cloud sessions.
843
844To continue a terminal session in Desktop:
845
8461. Close the session in the terminal.
8472. In the Desktop prompt box, type `/resume`. Desktop lists the sessions you started from the CLI on this computer. Search by title, folder, or branch, and preview where each one left off.
8483. Select the session. It continues in the app with its full conversation and context.
849
850Desktop continues the same session rather than a copy, so `claude --resume` in the terminal still finds it afterwards.
843851
844852<Tip>
845853 When to use Desktop vs CLI: use Desktop when you want to manage parallel sessions in one window, arrange panes side by side, or review changes visually. Use the CLI when you need scripting, automation, or prefer a terminal workflow.
keybindings Changed · +5 / -5 lines
from line 16
1616| `$docs` | Optional documentation URL |
1717| `bindings` | Array of binding blocks by context |
1818
19This example binds `Ctrl+E` to open an external editor in the chat context, and unbinds `Ctrl+U`:
19This example binds `Ctrl+E` to open an external editor in the chat context, and unbinds `Ctrl+S`:
2020
2121```json theme={null}
2222{
from line 27
2727 "context": "Chat",
2828 "bindings": {
2929 "ctrl+e": "chat:externalEditor",
30 "ctrl+u": null
30 "ctrl+s": null
3131 }
3232 }
3333 ]
from line 49
4949| `Help` | Help menu is visible |
5050| `Transcript` | Transcript viewer |
5151| `HistorySearch` | History search mode (Ctrl+R) |
52| `Task` | Background task is running |
52| `Task` | A task is running in the foreground |
5353| `ThemePicker` | Theme picker dialog |
5454| `Attachments` | Image attachment navigation in select dialogs |
5555| `Footer` | Footer indicator navigation (tasks, teams, diff, artifacts) |
from line 605
605605
606606## Validation
607607
608Claude Code validates your keybindings and shows warnings for:
608Claude Code validates your keybindings and writes a warning to the debug log for:
609609
610610* Parse errors (invalid JSON or structure)
611611* Invalid context names
from line 614
614614* Reserved shortcut conflicts
615615* Duplicate bindings in the same context
616616
617Claude Code reports warnings when the file loads and writes each one to the debug log. Start Claude Code with [`--debug`](/docs/en/cli-reference#cli-flags) to see the details.
617Start Claude Code with [`--debug`](/docs/en/cli-reference#cli-flags) to see the details.
618618
permission-modes Changed · +6 / -1 lines
from line 579
579579
580580Claude Code refuses `bypassPermissions` in a session you start with [`--restricted`](/docs/en/cli-reference#cli-flags). `--restricted` requires Claude Code v2.1.248 or later.
581581
582The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission checks. Claude Code saves your acceptance to user settings, so the dialog appears only once. If you decline, Claude Code exits. In [non-interactive mode](/docs/en/headless) no dialog is shown, and a [background session](/docs/en/agent-view) started with `--bg` is refused until you've accepted the dialog in an interactive session.
582The first time you start an interactive session with this mode enabled, Claude Code shows a warning dialog asking you to accept responsibility for actions taken without permission checks:
583
584* **If you accept**: Claude Code sets `skipDangerousModePermissionPrompt` to `true` in `~/.claude/settings.json`, so later sessions skip the dialog. To see the dialog again, remove the key from that file or set it to `false`. The [`skipDangerousModePermissionPrompt` reference](/docs/en/settings-reference#skipdangerousmodepermissionprompt) lists the other settings files where you or your organization can set it.
585* **If you decline**: Claude Code exits.
586
587In [non-interactive mode](/docs/en/headless) no dialog is shown, and a [background session](/docs/en/agent-view) started with `--bg` is refused until you've accepted the dialog in an interactive session.
583588
584589On Linux and macOS, Claude Code refuses to start in this mode when running as root or under `sudo`:
585590
web-quickstart Changed · +3 / -3 lines
### "Claude Code isn't available on your account" ### "Not available for the selected organization"
from line 207
207207
208208Cloud sessions require a connected GitHub account. Connect via the browser flow above, or run `/web-setup` from your terminal if you use the GitHub CLI. If you'd rather not connect GitHub at all, see [Remote Control](/docs/en/remote-control) to run Claude Code on your own machine and monitor it from your browser or phone.
209209
210### "Not available for the selected organization"
210### "Claude Code isn't available on your account"
211211
212Enterprise organizations may need an Owner to enable cloud sessions. Contact your Anthropic account team.
212Your seat in the selected organization doesn't include Claude Code. If you belong to another organization, click **Switch organization** on that page. Otherwise, ask an Owner of the organization to assign you a [seat that includes Claude Code](https://support.claude.com/en/articles/11845131-use-claude-code-with-your-team-or-enterprise-plan).
213213
214214### `/web-setup` says "Not signed in to Claude"
215215
github-enterprise-server Changed · +1 / -1 lines
from line 212
212212
213213### Session start fails with `Unable to get organization UUID`
214214
215Sign in with `/login` using your organization account. If you authenticate with an API key instead, cloud sessions fail earlier with a message asking you to run `/login`.
215Claude Code couldn't read a claude.ai organization from your credentials. Sign in with `/login` using an account in your Team or Enterprise organization, since GitHub Enterprise Server support is limited to those plans. See [Unable to get organization UUID](/docs/en/claude-code-on-the-web#unable-to-get-organization-uuid) for the causes and the other messages this state produces.
216216
217217## Related resources
218218
model-config Changed · +2 / -0 lines
from line 685
685685
686686Claude Code collapses thinking output by default. Press `Ctrl+O` to toggle verbose mode and see the reasoning as gray italic text. Interactive sessions on the Anthropic API receive redacted thinking blocks by default, so set `showThinkingSummaries: true` in [settings](/docs/en/settings) if you want the full summaries available when you expand. You are charged for all thinking tokens generated, even when collapsed or redacted.
687687
688<a id="extended-context-with-1m" />
689
688690### Extended context
689691
690692Fable 5.1, Fable 5, Sonnet 5 and later, Opus 4.6 and later, and Sonnet 4.6 support a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long sessions with large codebases.
remote-control Changed · +2 / -1 lines
from line 56
5656 | `--capacity <N>` | Maximum number of concurrent sessions. Default is 32. Cannot be used with `--spawn=session`. |
5757 | `--[no-]create-session-in-dir` | Pre-create one session in the current directory when the server starts, so you have somewhere to type immediately. In `worktree` mode this session stays in the current directory while on-demand sessions get isolated worktrees. On by default. If you pass `--no-create-session-in-dir` to start with none, Claude Code archives the server's sessions when you stop it, so there's nothing to [resume](#resume-sessions-after-stopping-the-server). |
5858 | `--permission-mode <mode>` | Set the starting [permission mode](/docs/en/permission-modes) for the server's sessions, such as `acceptEdits`. Accepts `manual` as an alias for `default`; an unrecognized mode stops the server at startup and lists the valid modes. |
59 | `-d`, `--debug[=<filter>]` | Turn on debug logging for the server, optionally filtered by category. Pass a filter only in the `=` form, such as `--debug=api,hooks`. Requires Claude Code v2.1.282 or later; earlier versions reject the flag as an unknown argument. |
59 | `--chrome` / `--no-chrome` | Turn [Chrome integration](/docs/en/chrome) on or off in the sessions the server creates, so Claude can use Chrome on your machine while you work from another device. Without either flag, the session the server pre-creates and any session you start yourself from claude.ai/code or the Claude app begin with Chrome off, even if you [enabled Chrome by default](/docs/en/chrome#enable-chrome-by-default). A session the server starts for one of your [project](/docs/en/claude-projects) threads follows that setting instead, except in `bypassPermissions` mode. Requires Claude Code v2.1.273 or later. |
60 | `-d`, `--debug[=<filter>]` | Turn on debug logging for the server, optionally filtered by category. Pass a filter only in the `=` form, such as `--debug=api,hooks`. Requires Claude Code v2.1.282 or later. |
6061 | `--debug-file <path>` | Write debug logs to the given file. |
6162 | `--verbose` | Show detailed connection and session logs. |
6263 | `--sandbox` / `--no-sandbox` | Enable or disable [sandboxing](/docs/en/sandboxing) for filesystem and network isolation. Off by default. |
sessions Changed · +2 / -2 lines
from line 4
44
55A session is a saved conversation tied to a project directory. Claude Code stores it locally as you work, so you can resume where you left off, branch to try a different approach, or switch between tasks.
66
7The [desktop app](/docs/en/desktop#work-in-parallel-with-sessions), [claude.ai/code](/docs/en/claude-code-on-the-web), and the [VS Code extension](/docs/en/vs-code#resume-past-conversations) each maintain their own session history. This page covers the CLI.
7The [desktop app](/docs/en/desktop#work-in-parallel-with-sessions), [claude.ai/code](/docs/en/claude-code-on-the-web), and the [VS Code extension](/docs/en/vs-code#resume-past-conversations) each keep their own session list, and the desktop app can also [resume a CLI session](/docs/en/desktop#coming-from-the-cli). This page covers the CLI.
88
99## Resume a session
1010
from line 119
119119| From claude.ai or the Claude app | Rename a [Remote Control session](/docs/en/remote-control#connect-from-another-device); Claude Code applies the same name in the CLI. Requires Claude Code v2.1.221 or later |
120120| From the desktop app | Rename a session in the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions) |
121121
122Once you name a session through a CLI route or from claude.ai, return to it with `claude --resume <name>` or `/resume <name>`; a desktop-app session resumes in the app, which keeps its own session history. See [Resume a session](#resume-a-session) for how name resolution behaves across worktrees.
122Once you name a session through a CLI route or from claude.ai, return to it with `claude --resume <name>` or `/resume <name>`; a desktop-app session resumes in the [desktop app](/docs/en/desktop#work-in-parallel-with-sessions). See [Resume a session](#resume-a-session) for how name resolution behaves across worktrees.
123123
124124When you start or resume an interactive session with a name that another live session on this machine already uses, or rename a session into such a name, Claude Code leaves the name with the session that already has it, renames yours to a variant with a two-word suffix, such as `auth-refactor-graceful-unicorn`, and tells you. Run `/rename` with a new name if you'd rather pick one yourself. Before v2.1.232, both sessions kept the name.
125125