You can now stop Claude Code compacting a long conversation while you sit idle by setting idleCompaction to false. The CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS variable sets how large a conversation must be before idle compaction starts. A new --proactivity flag picks how much Claude does on its own when it starts. CLAUDE_CODE_DISABLE_PROACTIVITY turns that choice off. Running claude remote-control with --allow-unattended-tool-calls lets cloud sessions use the current folder for one run. Remote sessions now read the SDK address from CLAUDE_CODE_REMOTE_SDK_URL when --sdk-url is not given.
This release has 7 entries in the build that are not switched on yet. One would let you attach more PDFs as a reference when their page count is known. Another would let an MCP server that needs you to sign in keep its saved tools. Claude Code could also tell the model that you pay per token and what a Bash call costs. Live-update connections could learn to spot a proxy answering in place of the real server. Each of these waits on a switch that is off by default.
Among this release's fixes, a cancel sent from outside the terminal no longer throws away every prompt you had queued. Plugin names that version 2.1.287 changed now match the installed plugins again. Synced skills now keep the text that sits above their main body. A plugin's hook error handler now still runs if the worker running those hooks is replaced mid-event. Stopping a remotely served background command now returns without waiting for it to end.
Written by our agent from the shipped bundle, not by Anthropic.
A new remote-control option lets auto-mode cloud sessions run commands in your folder without asking, sandboxed, with status messages showing what is allowed
Sessions & agentsA new --proactivity <level> option, hidden from help, sets how much Claude does on its own, and a remote session started from Claude Code is sent the same level
New idleCompaction setting can stop idle compaction, and CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS overrides its minimum token threshold
Sessions & agentsA --proactivity flag picks the proactivity level when Claude Code starts, and CLAUDE_CODE_DISABLE_PROACTIVITY turns the selector off
Setting CLAUDE_CODE_REMOVE_PROMPT_STRINGS to a JSON list removes those strings from the prompts Claude Code sends to the model
Sessions & agentsWant the reasoning? Read walks the 61 entries that probably matter to you, each one opening to what changed and why.
Read this release → Every row →Anything you can use today, anything that visibly changes, and anything worth poking at. One line each, open for detail.
Channels now also need a server allow_channels verdict besides tengu_harbor, and that verdict is denied for HIPAA policy (HIPAA-R71)
When reads are restricted, instruction files that a Read deny rule covers or that lie outside your working folders are skipped, with the reason logged
Unclear What the new options do, and how AGENTS.md is handled, is not clear.
Remote sessions now check attached apps against a device trust policy and refuse ones that fall below it
Unclear Which policy values apply and whether the check is enforced by default are not settled.
The code review part of the suggestion shown before a commit now appears only when includeCodeReviewSuggestion is true
Unclear It is not clear whether the code review suggestion was already hidden by default before this change.
With sources set to personAndPolicy, the proxy auth helper is skipped under folder trust or else runs from another folder
Unclear What sets the sources value, and which folder the helper now runs from, are not settled.
What would fix it?
Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.
28 more of these are in What probably matters to you, above.
Remote and Cowork sessions ignore Claude in Chrome's enabled-by-default setting, and project settings can no longer turn it on
Unclear How Claude Code decides that a session counts as remote or Cowork is not shown.
MCP tools that may act on the session's desktop now ask every time, and remote-session MCP tools cannot be always-allowed
Unclear What the "arbiter" mode corresponds to for users is unclear.
Resumed sessions set to ask before edits no longer come back in auto mode, and spawned teammates now receive the leader's --proactivity level
Unclear The exact check that decides when the downgrade applies is not clear.
The git bundle uploaded for cloud sessions and teleport is now checked first, and many unusual or tampered setups get a specific refusal message
Unclear It is unclear whether the bundle check runs for every upload or only on some upload paths.
Attaching to a cloud session can now re-send home settings, and refuses when the settings copies cannot be kept
Unclear How often the host consent is set to forward settings is not known.
A background worker in bypassPermissions mode falls back to default unless skipDangerousModePermissionPrompt is true in ~/.claude/settings.json
Unclear It is not clear whether this fallback is newly enforced or whether only the message is new.
Some Claude in Chrome tools now ask for your permission rather than running at once, even with a whole-tool allow rule
Unclear Which Chrome tools are on the list that asks for permission is not stated.
PermissionRequest hooks are now blocked from approving a hosted session's desktop tools, and a broken hook command gets a clearer error
Unclear Which tools count as a hosted session's desktop tools is not stated.
Remote sessions refuse interface requests from clients below a trust level, or when the policy or the list of who may write is unreadable or stale
Unclear Whether these checks always apply or only under a policy is not known.
Account memory prompts now stay in the terminal instead of going to Remote Control, and outgoing events pass through a redaction step
Unclear It is not clear what the redaction step removes.
Before replying to an artifact comment unattended, Claude Code now does a fuller check when a quick rules check allows it
Unclear It is not clear what controls this behaviour or what a user sees differently.
Claude Code now knows safe values for three Chrome variables, can clear them, and keeps a new unattended-tools variable out of child processes
Unclear What triggers the clearing of these variables, and what sets them in the first place, is not settled.
Incoming channel notifications are now dropped unless a check passes, where before they were always queued
Unclear What the check tests is not known.
When a hook runs for an account memory tool, its output is replaced with a placeholder instead of entering the conversation
Unclear When this placeholder is used is not established.
A turn handoff held over 30 minutes now fails as expired, the handler now gets the handoff's age, and handoff validation was reworked
Unclear Only the description of the error was seen, not the code that enforces the 30-minute limit.
The built-in gh stand-in no longer takes the GitHub host from GH_HOST or GH_REPO; pass --hostname instead
Unclear It is not clear which condition decides whether the "as GH_HOST" wording appears.
With claude --cloud, hooks from files the cloud session can change are withheld with a notice, and hook warnings and errors are reworded
/code-review medium now runs the high-effort recipe on most models#On every model without its own /code-review row, Opus 5.5 included, medium now runs the eight-angle high recipe instead of a single pass. high, xhigh and Opus 5 are unchanged.
If a plugin named without a marketplace cannot be fetched, Claude Code installs the official marketplace's copy instead of failing
Unclear Which marketplaces count as official, and exactly when the fallback applies, is not stated.
EnterWorktree now checks first and refuses to switch into an existing worktree where the agent would not have write access
A command allowed only once its output redirection is removed is now rechecked as written, and refused if the full form is not allowed
Unclear It is unclear whether the redirection recheck always applies or depends on a switch that could not be identified.
When Claude Code reads a repository's git config file, it now returns nothing if the content fails a check, instead of always using it
Unclear It is not clear what content the check rejects.
--allow-dangerously-skip-permissions without recorded consent#Background sessions now ignore --allow-dangerously-skip-permissions unless bypass consent is in your user or policy settings
Tool calls served to a remote session are now refused when a read-deny rule matches the path, or when the rules cannot be checked
Unclear Exactly which tools these checks cover is not clear.
Remotely hosted tool calls now refuse over-long paths and settings-file edits, deny on a rule-check crash, and use up approvals that arrive too late
Unclear It is not clear which of these checks apply in every setup and which depend on a setting or remote switch.
Remote Control now replaces or drops account memory content before sending session events and history to remote clients
Unclear Whether the filter is controlled by a remote setting, and what decides when it is switched off, is not known.
Permission rules with wildcards are now checked against a tool's name and its other names, replacing the old ** handling
Unclear Exactly which rules now match differently than before is not clear.
The git check before uploading a folder to a cloud session now refuses reftable or GIT_REFERENCE_BACKEND repos, names its reasons and hides git's own output
Unclear It is not clear which feature runs this check or what Claude Code does when a repository is treated as tampered.
Cancelling a permission prompt from a remote subagent running in the background now denies the request instead of stopping the turn
Unclear It is not clear what decides whether the answer is reported to Anthropic.
An organisation's MCP allowlist now refuses claude.ai connectors it cannot find or does not admit, and matches them by their real name
Unclear What makes a connector count as admitted is not settled.
Claude Code's check for PreToolUse hooks now matches against a wider list of names worked out from an extra tool name, not just one
Unclear It is not clear what the extra names are or what bypassCapabilityNotification does.
The web search cap is now a budget that refills each hour, and in some modes it counts per turn instead of per session
Unclear What decides whether the limit counts per turn or per session is not settled.
WebSearch is limited by an hourly refilling budget instead of a simple count, adjustable with CLAUDE_CODE_WEB_SEARCH_REFILLS_PER_HOUR
Unclear The actual limits and what turns refilling on by default are not stated.
When a resumed session was still in plan mode, Claude Code can now switch plan mode back on
Unclear It is not clear what switches this on or whether it applies only to remote sessions.
Plugins, mcp add and MCP config files now reject the claudeai-proxy server type, and claude.ai connectors wait to reconnect after an account switch
Claude Code now also protects Windows profile credential files reached through WSL's /mnt paths and through Windows short file names
Unclear Which part of this the tengu_ticklish_pnueli flag controls is not clear.
Installing a plugin can now stop with the not_found failure code when a check on that plugin matches
Unclear What the check looks up, and which plugins it matches, is not clear.
rm commands with variables set in front now ask first#Claude Code now rechecks rm commands with variables set before a declaration, and asks you when it cannot check them all
Unclear Which part of the new checking each of the two server flags controls is not clear.
For MCP tool calls in remote sessions, Claude Code now keeps its own stricter decision over a plugin's looser one
Unclear What the switch controlling this defaults to is not clear.
If a PermissionRequest hook approves a web fetch but attaches arguments WebFetch can't check, Claude Code now denies the fetch
Unclear Exactly which hook replies cause a fetch to be denied is not settled.
Claude Code now checks the shell commands inside a skill first, and runs none of them if one is invalid
Claude Code now caps the total size of a streamed response and pauses briefly when reading it has taken more than 8 milliseconds
Unclear What the total size limit is set to is not known.
Environment variables from your settings are now added before Claude Code filters the environment it passes to programs it starts
Unclear Exactly which settings variables now reach child programs that did not before, or the reverse, is not settled.
Claude Code refuses to install a plugin marketplace whose name looks like Anthropic's own, and marks such names in the marketplace list
Unclear How Claude Code decides that a name looks like Anthropic's is not stated.
Skills with over-long display names are not loaded, and MCP commands with over-long names or aliases are not listed
Unclear The character limit itself is not known.
Dropping or pasting an image file path now runs a permission check, and a refused path is passed on as plain text instead of read
Unclear The exact rule that decides whether the image may be read is not clear.
Claude Code now caps MCP HTTP response sizes, unpacks gzip and deflate itself, and refuses responses compressed with br or zstd
Unclear The size limits are not known, and it is not settled in which cases Claude Code does the unpacking itself.
Messages sent to a starting background session are no longer queued if they are slash commands, and replies may return a new code
Unclear How ENOREPLY is shown to the user is unclear.
disableClaudeAiMcp now also blocks claude.ai servers you add yourself#With disableClaudeAiMcp set, a claude.ai proxy server passed by --mcp-config or the SDK mcpServers option no longer connects either
Unclear Only the setting's description is known to have changed; the code that enforces it was not examined.
Claude Code's saved shell setup now takes its PATH from a new source, falling back to your own, and always adds a guard on pkill
Unclear It is not clear what the new PATH value contains or when it differs from your own.
A handoff the session service held for too long is now rejected and its calls are not run
Unclear The time limit and which feature these handoffs belong to are not settled.
The path-safety check now resolves relative file names given to MCP tools, considers mount points, and describes /proc links, overlong paths and unknown home folders
Unclear It is not clear what switches the handling of relative names on, or whether it applies in every session.
Bash commands with $ followed by non-ASCII text, and some redirect and loop forms, are now too complex to check and prompt you
A path check now rejects entries containing the Unicode replacement character, the � that marks garbled text
Unclear Which feature uses this path check is not known.
{fd}>file now ask for your approval#Shell redirects that store a file number in a variable, such as {fd}>file, are now treated as too complex to run without asking
A file write that leads to a Claude Code settings file through a symbolic link now triggers a permission prompt and cannot be auto-approved
Adding a plugin marketplace now fails if its name matches the download folder of a GitHub marketplace you already have
In worktree sessions, git commands are now refused if a word the shell fills in at run time comes before git's subcommand
A plansDirectory setting containing a backslash may now be rejected, and the error message says so
Unclear Whether paths with a backslash are also rejected on Windows is not clear.
awk and find commands now ask for permission first#Claude Code now asks before running awk or find commands that trip an extra wildcard check, not only ones with unquoted wildcards
Unclear What the second wildcard check looks for is not clear.
Before running git, Claude Code now clears a wider fixed set of git environment variables, not just GIT_CONFIG and GIT_ATTR_SOURCE
Unclear Which additional variables are removed is not known.
When preparing files for upload, Claude Code now refuses symlinks that lead outside their folder and reports links that have moved
Claude Code's Bash command checker now treats text after a heredoc, {fd}> redirects and variables set before export differently
Unclear Exactly which commands are newly approved or newly sent to a prompt is not settled.
Claude Code recognises more ways of handing a shell an inline script, including PowerShell options like -EncodedCommand, in any capitalisation
Unclear Whether this check is used for permission decisions was not confirmed.
$$ now ask for permission#Shell commands using patterns like $$[ are now treated as too complex to judge and prompt for permission
Unclear The exact commands that now prompt when they did not before are not fully stated.
Claude Code now refuses to load or refresh a saved marketplace whose name fails its look-alike check, even if it was added earlier
Unclear Exactly which names the look-alike check refuses is not stated.
Claude Code's shell permission checks changed for sudo shell flags, += variable prefixes, command -v and backslashes
Unclear The overall effect on any particular command is not clear.
Published verbatim by Anthropic for v2.1.290. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.
Of these 190 bullets, 30 name something an entry on this page also names, 67 name something no entry here does, and 93 name nothing specific enough to line up either way. The pairings are made on names both sides wrote down, a flag or a setting or a slash command, so read one as probably the same thing rather than as a fact, and read the middle number as candidates rather than as a miss count.
serverToolUses to the result of a mod's turn.step hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end
No entry names this agentId to the tool.check event of plugin hooks, so a hook can tell a subagent's permission check from the main session's
No entry names this ceiling to the question and verdict a mod's tool.check hook reads, naming the approval an organization requires for a tool
No entry names this ThemeKey and Color types to the plugin hooks typings, so an editor lists the theme colors a mod's drawing can name
No entry names this claude plugin validate: each hook a mod registers at a gating site is listed with whether it has a .catch (gatingHooks under --json)
No entry names this claude attach <name> and claude logs <name>: part of a session name works in place of the id
No entry names this /claude-api managed-agents-onboard <url> to set up the Managed Agents pattern a page describes as ant apply files
Probably bundled-claude-api-skill-adds-managed-agents-quickstarts /claude-api managed-agents-onboard <quickstart-name> to build a Console quickstart template, such as deep-researcher, with the ant CLI
Probably bundled-claude-api-skill-adds-managed-agents-quickstarts offset to read on
Nothing to match on #95127[BUG] WebFetch truncation is invisible to the model — absent from the tool description, unmarked in the result, and the web-fetch subagent can neither detect nor recover from it Open
/rewind not listing a prompt sent while Claude was still working
No entry names this /loop with an interval, reminders) silently not coming back on resume once the conversation was compacted; covers compactions made from this version on
No entry names this /background hand-off, and recurring ones firing an extra run on every resume, respawn or fork
No entry names this #96531[BUG] /loop scheduled task stops firing on its own after the session is backgrounded — fires only right after a user turn Open
--json-schema runs exiting non-zero with is_error: true on a success result when the connection dropped after the structured output was already delivered
No entry names this CLAUDE.md, rule or AGENTS.md symlinked outside the working directories loading under permissions.blockReadsOutsideWorkingDirectories or a Read deny rule
Probably instruction-file-loading-de-duplicated-via-a-held-set-and, edit-tool-results-carry-gitdiffread-flag-sealed-path-case, sandbox-read-blocking-and-wsl-mount-parsing-rework, withheld-memory-files-now-shown-as-a-startup-warning, instruction-files-claudemd-rules-held-outside-the-workin, plan-exit-dialog-hides-clear-context-option-for-ask-proactiv, startupresume-telemetry-adds-store-confirm-and-system-promp, home-settings-seeded-to-cloud-sessions-ccr, hooks-module-fsancestors-reads-agentsmd-with-a-held-outs xn-- host label matching differently from one process to the next
Probably url-permission-patterns-reject-punycode-wildcard-hosts /ultrareview dropping uncommitted changes without a warning on Windows when git stash create failed, and refusing them after a git add -N file was deleted or moved
No entry names this plansDirectory setting's project-root check for paths that contain a backslash on macOS and Linux
Probably plansdirectory-rejects-backslashes-off-windows claude daemon run and claude daemon logs; they now show as \uXXXX escapes
No entry names this .catch being unloaded, and its .catch skipped, when the hook kept the hooks worker busy on a prompt or tool call
Nothing to match on turn.step result listing a tool call that a mid-response model fallback had discarded
No entry names this claude plugin validate and plugin loading refusing a hooks module that destructures an option named like one of its top-level functions
No entry names this /ultrareview failing to upload uncommitted changes when core.safecrlf=true is set in git's configuration
No entry names this ! shell blocks in skills and commands failing when the file is saved with CRLF line endings
Nothing to match on /permissions tab was clicked while searching in fullscreen mode
No entry names this answer on turn.complete for a subagent that hands its report back in auto mode
No entry names this prompt.submit hook that drops a prompt after calling next(e) being ignored silently: the hook is now reported as failed, by name
No entry names this disableClaudeAiConnectors and allowedMcpServers URL rules not being applied to some MCP entries declared in .mcp.json, plugins or agents
No entry names this @-mention under the read block or --restricted being able to read a file outside the working directories through a link changed mid-read
Probably attachment-paths-are-displayed-in-a-normalized-form-in-error, safe-mode-is-now-evaluated-lazily-and-uses-the-same-check /loop run count, countdown and live status line after the session enters a worktree that it creates
No entry names this claude agents sessions in manual permission mode asking for approval to read an image pasted into a reply or a new agent's prompt
No entry names this declare, typeset, export or readonly
Nothing to match on language setting
Nothing to match on #99232[FEATURE] "You should know" mod: respect the `language` setting instead of always writing in English Open
claude respawn re-sending an earlier message to a backgrounded session that has no saved transcript instead of starting it with an empty conversation
No entry names this n: or Ctrl+F search in the agents view moving focus to a section header, where Ctrl+X twice would delete every session in the section
Nothing to match on claude agents saving a slash command it could not deliver to a stopped session and then running it by itself the next time that session restarted
No entry names this /ultrareview uploading uncommitted changes unfiltered for files under a git filter driver named unset or unspecified; the upload now stops and asks you to rename the driver
No entry names this claude --teleport and /teleport deleting the files in a folder that had replaced a tracked file of the same name when you chose to stash: the stash is now refused, and says why
No entry names this /loop run count freezing and its countdown disappearing after /clear; the count now restarts with the new conversation
Probably bridge-remote-control-peers-can-run-effort-model-rena --channels permission relay: a reply ID that repeats within a session is now ignored instead of approving a different prompt
Probably channels-banner-shows-a-waiting-for-your-organizations-pol /chrome "Reconnect extension" not restoring browser tools after a failed Chrome connection, and added an explanation when it can't (anthropics/claude-code#98135)
Probably project-settings-can-no-longer-turn-on-claude-in-chrome-a-w, chrome-disabled-session-notice-tells-the-model-not-to-use-br, chrome-menu-reports-live-connection-state-and-reconnect-act #98135/chrome Reconnect never registers claude-in-chrome MCP tools when a session starts with the bridge down (survives --resume) Closed
ANTHROPIC_BASE_URL with ANTHROPIC_AUTH_TOKEN) and have no Anthropic account
No entry names this claude agents just after a background session crashed being refused after 2 seconds: they are now retried for up to 12 seconds while the session restarts
No entry names this claude agents could not deliver to a running session being saved and sent by themselves the next time it was restarted
No entry names this cat <<EOF | python3) asking for approval on every run
No entry names this claude agents failing with "Couldn't restart the background service" and background sessions stopping after a Homebrew upgrade (takes effect from the upgrade after this one)
No entry names this #84827Daemon self-respawn after a Homebrew cask upgrade targets the purged versioned path (ENOENT), killing every background session Open
rg or git grep) whose arguments the shell would still expand as wildcards; these now prompt for approval
No entry names this claude plugin test refusing to run after an upgrade because of an out-of-date saved setting
Probably claude-plugin-test-rollout-flag-hold-and-file-form git clone option keeping the sandbox exemption from a git pattern such as git * in sandbox.excludedCommands; it is now treated like the long form
No entry names this /ultrareview of a local branch silently leaving uncommitted work out of the upload in a repository that keeps its branches outside .git (git 2.54+); it now refuses with an explanation
No entry names this /loop wakeup or scheduled task; Claude is now told and can schedule it again
No entry names this store.postgres_url can't be parsed; the error now names the setting and says what the URL may hold
Probably gateway-gives-a-clear-error-for-an-invalid-storepostgres-ur /sandbox Config tab on Linux and WSL when a sandbox read rule such as ~/**/.env covers a large folder
No entry names this #98023[BUG] 2.1.284 freezes on first Enter: new sandbox glob expander synchronously walks all of ~ for "~/**/…" denyRead patterns (follows symlinks, unbounded memory); 2.1.280 fine Open
claude -p run from the Bash tool)
No entry names this --continue or --resume <session-id> in the terminal
Probably cloud-sessions-print-a-claude-cloud-resume-hint, resume-with-resume-print-drop-turn-guard-adds-an-attach, background-job-respawn-can-fork-a-resume, remote-control-gains-allow-unattended-tool-calls-and-a-for /rewind) freezing for hundreds of milliseconds per keypress when the conversation contains a very large pasted stack trace or source file
No entry names this CLAUDE_CODE_USER_DIALOG_TIMEOUT_MS=5m being read as 5 ms and cancelling remote dialogs at once; values with a unit suffix now fall back to dialogExpiry
Probably chrome-permission-env-defaults-and-remote-tools-unattended-h --restricted (and CLAUDE_CODE_RESTRICTED=1) sessions opening the cross-session messaging socket
Probably attachment-paths-are-displayed-in-a-normalized-form-in-error, safe-mode-is-now-evaluated-lazily-and-uses-the-same-check --allow-dangerously-skip-permissions on respawn without the bypass-permissions disclaimer having been accepted
Probably background-sessions-ignore-allow-dangerously-skip-permissi, new-proactivity-startup-level-gated-by-tengu-proactivity, new-relaunchproactivity-env-vars-added-to-a-scrub-list-no claude auth login or with a credentials file already in the config directory
Probably cloud-session-auth-error-reworded-to-point-at-claude-auth-l /login reporting success when the keychain refused the new login and kept an old one it could not remove
Probably onboarding-sign-in-skip-tracked-login-prompt-kept, trusted-device-error-text-reworded, cloud-session-auth-error-reworded-to-point-at-claude-auth-l, chrome-menu-reports-live-connection-state-and-reconnect-act --include-partial-messages seeing a reply stay open after the turn ended when its stream was cut, interrupted or fell back to non-streaming
No entry names this ConfigChange hooks and reloading settings mid-command when .claude/settings.json or .claude/settings.local.json does not exist
Probably background-worker-bypass-permission-mode-requires-consent-in, background-sessions-ignore-allow-dangerously-skip-permissi, cloud-session-settings-review-now-covers-user-settings-with /loop and other recurring session-only scheduled tasks running an extra time after a sandboxed Bash command on Linux or after .claude/scheduled_tasks.json was deleted
No entry names this plugin-authoring skill: Claude now gives the one command another person runs to install a mod you made, and writes it in a README's install section
No entry names this /plugin in the desktop app's Code tab: it now says where to install and manage plugins there
Probably plugin-marketplace-names-that-imitate-anthropics-are-refuse, plugin-in-desktop-app-returns-guidance-text claude auth login and /login and no longer blames API-key authentication
Probably onboarding-sign-in-skip-tracked-login-prompt-kept, trusted-device-error-text-reworded, cloud-session-auth-error-reworded-to-point-at-claude-auth-l, chrome-menu-reports-live-connection-state-and-reconnect-act /ultrareview upload: it is about half as long and says what kind of file is the problem
No entry names this /ultrareview upload refuses a checkout: each known cause now has its own message, with a way to fix it
No entry names this browser_batch call now gets 90 seconds, up from 60, before it is reported as timed out
Probably browser-batch-gets-its-own-tool-call-timeout CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC to also skip the startup connection warm-up
No entry names this --chrome, /chrome or your user settings
Probably claude-in-chrome-enabled-by-default-is-ignored-in-remote-a, project-settings-can-no-longer-turn-on-claude-in-chrome-a-w, chrome-disabled-session-notice-tells-the-model-not-to-use-br, chrome-menu-reports-live-connection-state-and-reconnect-act pyright, which is no longer treated as a read-only command
Nothing to match on $.process.spawn rejects with when another mod denies it after the child ran: it now says the call ran and a plugin withheld its result
No entry names this ! shell command that contains raw control characters other than tab and newline, with a message that shows where they are
Nothing to match on /artifacts: opening an artifact in your browser now closes the list
No entry names this ps command ask for approval instead of running without asking
Nothing to match on /ultrareview upload fails at a git step: they name the step and what to try, and no longer repeat git's own error text
No entry names this /code-review at medium effort to also report cleanup and CLAUDE.md conventions findings on models without tuned review settings, including Opus 5.5 and Sonnet 5.5
Probably medium-and-high-effort-now-map-to-a-different-measured-profi agent_id in Agent results to its agent ID (its name@team address stays in teammate_id); TeammateIdle hooks no longer fire from its subagents or forks
Probably teammate-agent-id-now-uses-resumable-id, teammate-ambiguity-message-wording, agent-spawn-result-reports-agent-id, taskstop-description-now-covers-background-agents-spawned-wi /loop): they are now left running through updates and low memory, where being restarted or shut down could silently lose the wakeup
No entry names this /model, /effort and /rename sent from claude agents to a busy background session to apply right away, without a confirmation, instead of when the turn ends
Probably effort-commands-log-from-level-and-route, medium-and-high-effort-now-map-to-a-different-measured-profi, bridge-remote-control-peers-can-run-effort-model-rena CLAUDE_CODE_WEB_SEARCH_REFILLS_PER_HOUR sets the rate, 0 turns it off) instead of ending after 200 calls
Probably websearch-gets-a-refilling-token-bucket-budget CLAUDE_CODE_DISABLE_ATTACHMENTS so a repository's .claude/settings.json or .claude/settings.local.json can no longer set it; shell, user and managed settings still can
Probably background-worker-bypass-permission-mode-requires-consent-in, background-sessions-ignore-allow-dangerously-skip-permissi, cloud-session-settings-review-now-covers-user-settings-with, new-proactivity-startup-level-gated-by-tengu-proactivity, proactivity-opt-in-restored-across-worker-epochs, new-relaunchproactivity-env-vars-added-to-a-scrub-list-no claude plugin update on a plugin loaded from a directory to print just its reason, without the "Failed to update plugin" prefix, as for built-in plugins
No entry names this gh api in cloud sessions: a host other than github.com set in GH_HOST or GH_REPO is now refused (use --hostname or a full URL), and stderr notes requests to other hosts
Probably gh-api-hostname-help-text-varies, new-gh-host-gh-repo-guidance-when-the-host-differs, gh-style-endpoint-repo-resolution-tightened, gh-tool-description-gh-host-and-gh-repo-host-text claude-api skill's Managed Agents examples to turn off the web tools unless the agent needs them and to use the auto permission policy
Probably bundled-claude-api-skill-adds-managed-agents-quickstarts claude --environment <id> to create its session through the current Sessions API; printed and JSON session ids keep their session_… form
No entry names this !fast to switch a thread to fast mode, moving it to Opus if needed, and !fast off to switch back; replies show (fast) while it's on
No entry names this A model matched these bullets to the GitHub issues they fix, so a link can be wrong.
1 of 27 tool descriptions changed. 1 of 25 tool schemas changed. The appended system-reminder blocks moved: 2 lines added, 1 line removed.
Claude Code, interactive mode
15 prompt changes in this release could not be quoted from the build, so no entry on this page describes them.
334 documentation changes were recorded within 24 hours either side of this release, nearest first. The closest 12 are below. They're here because they happened near this release in time. That's not a claim that this release caused the edit, or that the page documents anything in it.
The 70 literal strings found in the bundle, with the number of entries that name each one. Picking one searches for it. A name is here because this build's code mentions it, which is not the same as it working or being finished.
What's wrong with this entry?