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.
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
Unclear It is not clear what decides whether the option is shown and available, or whether it is live for all users.
New idleCompaction setting can stop idle compaction, and CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS overrides its minimum token threshold
A new OfferChromeSetup tool lets Claude offer one-time Claude in Chrome setup mid-task when the browser extension is not connected
Unclear It is not clear what decides whether this tool is available to Claude.
Claude Code adds us_election_info to its web tool names, an allowUnattendedToolCalls option, and trims a shell error message
Unclear It is not clear what the web tool list or the allowUnattendedToolCalls option does.
Subagents now get a computed effort level and total-token budget with a countdown reminder, and a remote value can lower their effort
Unclear What value applies when neither the server nor the environment variable provides one is not known.
A new PDF path can attach a PDF as a reference and tell Claude it may read the whole file without picking pages
Unclear What Claude is shown for a PDF attached this way is not known.
A --proactivity flag picks the proactivity level when Claude Code starts, and CLAUDE_CODE_DISABLE_PROACTIVITY turns the selector off
Unclear Whether Anthropic's server switches tengu_proactivity_selector off for some accounts is not known; it returned no value for the one account read.
Setting CLAUDE_CODE_REMOVE_PROMPT_STRINGS to a JSON list removes those strings from the prompts Claude Code sends to the model
Unclear Which prompts this removal applies to is not stated.
A new file_attachments_missing message reports attachments that did not arrive, and queued messages with attachments are no longer merged
With consent, Claude Code now uploads your ~/.claude CLAUDE.md, rules, output styles and settings to a cloud session when you create or attach to it
Unclear Whether this is switched on for anyone yet is not known.
With CLAUDE_CODE_PEWTER_OWL_TOOL set, three tools can now leave out a response ID depending on a remotely controlled switch
Unclear What this tool behaviour does, and what the other conditions test, are not known.
Setting CLAUDE_CODE_STREAMED_BUMBLEBEE_TEXT replaces the wording of the budget note given to subagents, with {N} standing for the budget
Unclear It is not clear whether the budget note is shown at all when neither the server setting nor CLAUDE_CODE_STREAMED_BUMBLEBEE is set.
Claude Code adds CLAUDE_CODE_DISABLE_PROACTIVITY and variables that pass proactivity state to a relaunched Claude Code
Programs connecting to Claude Code can opt in to tool calls from nested subagents and to showing a Claude in Chrome setup card
Unclear Which experiment flag controls the Chrome setup offer, and whether any shipped client declares either entry, is not known.
A new CLAUDE_CODE_RIPPLING_TULIP value sets the token count for the total-tokens reminder, which can be per subagent
Unclear What the number represents is not certain.
A proactivity note in the conversation tells Claude whether to ask first, act normally or act on its own for commits, pushes, pull requests and follow-ups
Channels now also need a server allow_channels verdict besides tengu_harbor, and that verdict is denied for HIPAA policy (HIPAA-R71)
HTTP MCP servers that match a toolport address are now marked ccrToolport and labelled ccr-toolport, ahead of the older ccr-proxy label
When --sdk-url is not given in a remote session, Claude Code now reads the address from the CLAUDE_CODE_REMOTE_SDK_URL environment variable
Unclear It is not clear exactly what Claude Code checks to decide that a session counts as remote.
rewind_conversation gains allow_summarized_target to rewind into compacted history and refuse_if_usage_limited to decline when a usage limit is hit
Unclear What allow_summarized_target does, and which program uses these options, is not stated.
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.
When a proactivity level other than default is set, Claude Code can choose the starting permission mode from it
The claude-api skill that ships with Claude Code now includes managed-agents reference docs, nine quickstart templates and an onboarding flow
Unclear It is not clear whether the new material is switched off for some accounts, or exactly how the onboarding flow is started.
A note can tell Claude each agent it launches has a fixed token budget, switched on by CLAUDE_CODE_STREAMED_BUMBLEBEE
Unclear What the remote switch defaults to when the server sends nothing is not known.
The instructions used to summarize a long conversation now come in four versions, chosen by an environment variable or a server setting
Unclear Which version any given account receives when the environment variable is not set is decided by the server.
Claude Code can now add an elapsed-time reminder and a proactivity note to what the model sees
Unclear Which models qualify for the elapsed-time reminder is not settled.
In headless sessions, Claude Code now keeps your proactivity opt-in when the worker restarts
Claude Code can now decline machines offered by its device listing and take remote machines only from the session's own connection
Unclear It is not clear what condition decides whether listed machines are still used, or whether that condition is met by default.
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 skill-proposal tool can now refuse a proposed SKILL.md that keeps too few lines of your current one, using a threshold set remotely
Unclear It is not clear whether the result is still reported to Anthropic when the threshold is 0 and the check is off.
Claude Code gains a set of status icons for working, needs-you, idle and failed states
Unclear Where the icons appear, and whether the new switch controls them, is not known.
Claude Code can tell the model the user pays per token and what a Bash call costs, but both notes fall back to off
Unclear Whether these notes actually reach the model, and where they are shown, is not settled.
Claude Code adds two server-controlled switches, a path for remote-session tools over MCP, and a new label for Claude.ai proxy servers
Unclear What the two switches turn on, and what uses the new remote-session path, is not known.
Claude Code now writes a grant file per process under ~/.claude/state/unattended-serving-runs and can check a token against it
Unclear Nothing is known yet about what writes these files or checks the tokens.
Setting CLAUDE_CODE_RESUME_TOLERATES_CONTEXT_SEEDS stops resume treating some final messages as an interrupted turn
Unclear What resume does with such a session instead is not shown, and the variable is not shown being documented or set anywhere.
Claude Code now recognises CCR_AGENT_PROXY_TOKEN_FILE_DESCRIPTOR as a way to receive the agent proxy credential
Unclear It is not clear what part of Claude Code reads this variable.
Programs built on the SDK can now receive tool calls and results from subagents nested inside other subagents
Unclear It is not clear which programs report that they accept nested subagent tool calls.
A hint shows the shortcut that stops background agents, and the SDK gains a request to set the proactivity level
store.postgres_url values in the gateway#The gateway now explains why a store.postgres_url with several hosts or a special-character password is rejected
An entry for approximate location now appears in a list alongside current time and other context sections
Unclear What this list controls, and whether location is ever used, is not known.
The list of capabilities that already includes mcp_read_resource_v1 now also includes register_repo_root_v1
Unclear It is not known which program reads this list or what the new capability does.
Claude Code now refers to an MCP server name, mcp__container, but nothing appears to use it yet
Unclear It is not clear whether anything in Claude Code actually uses this server name yet.
Claude Code can now hold a lease connection to its background daemon, reconnect it, and start the daemon a limited number of times
Unclear It is not clear what in Claude Code starts this lease routine, so when it actually runs is unknown.
Claude Code contains a message saying a Postgres server older than version 11 is below the supported floor
Unclear It is not clear whether anything in Claude Code can reach this code.
/run can pick up extra files and a note beyond its bundled ones#The /run skill and one other skill now add extra files from another source to their own, and can add a note to the prompt
Unclear Where the extra files and note come from is not stated.
claude plugin test now waits for its rollout setting to be saved#claude plugin test now waits until a rollout setting is saved for test files to read, and reports when that fails
Unclear Which rollout setting this is has not been identified.
In remote sessions, approval requests from subagents can now stay open when a turn ends instead of always being dismissed
Unclear It is not clear who or what sets the option that keeps subagent requests open.
With CLAUDE_AUTO_BACKGROUND_TASKS set, running foreground subagents move to the background when you have a queued message waiting
Unclear Whether the server switch controls this behaviour or something else is unclear.
In some cases Claude Code now uses a saved snapshot of managed settings before looking at administrator settings
Unclear When snapshotFirst is set is not clear.
CLAUDE_CODE_HOST_AUTH_ENV_VAR is kept when the environment is cleaned#When Claude Code removes certain environment variables, it now keeps the one named by CLAUDE_CODE_HOST_AUTH_ENV_VAR
Unclear Which variables this step removes and when it runs is not established.
A host can now list tools that must always ask before running, even ones that would normally allow themselves
claude attach and claude logs now take a background session's name, or part of it, in place of its id
A Remote Control Stop request can now name the messages it targets, and is ignored if none of them belong to the current turn
Unclear How the Remote Control service decides when to send this list is not known.
Claude Code now tells you when project hooks you haven't accepted are skipped for cloud session commands, pointing to a command to fix it
Unclear Where this message appears, and whether claude apply-project-settings is available in this release, is not stated.
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.
A set_model request now applies the model even if the server could not confirm it, and the reply says unconfirmed: true
Unclear What leaves the server unable to confirm a model is not clear.
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.
/chrome now shows the real Claude in Chrome connection state with a working Reconnect, and Claude is told to skip browser tools while it is down
Unclear It is not clear which kinds of session can reconnect directly from the /chrome dialog.
PreCompact hooks are now told when compaction was automatic#The PreCompact hook now receives a trigger of auto for automatic compaction instead of always manual
Unclear It is not clear whether automatic compaction ran these hooks through this same path before.
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.
A background shell command that goes quiet for a while can now send Claude a check-in telling it to look at the output and stop the task if stuck
Unclear What produces shell check-in notifications is not settled.
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.
Agent proxy startup can use a handed-over token instead of reading a file, and now records timings and ca_source to help diagnose slow or failed starts
Channels now stay off until your organisation's policy loads, and the startup banner explains that messages are dropped meanwhile
Copy and prompt read, fill and suggest requests from plugins now pass between attached clients in remote sessions, moving on after 5 seconds of silence
Unclear Only the event's description changed, so it is not clear whether the behaviour it describes is in place yet.
The gateway's /device sign-in page is restyled for accessibility, can now deny a sign-in request, and refuses codes already used or expired
The silent-turn reminder can now fire after a set number of silent seconds, configured by CLAUDE_CODE_SILENT_TURN_REMINDER_SECONDS or remote config
Unclear It is not clear where the remote seconds setting comes from or whether the reminder is on by default.
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.
A new check finds out whether a usable sign-in already exists, for example from CLAUDE_CODE_OAUTH_TOKEN
Unclear What part of Claude Code uses this check is not known.
Claude Code has code to ask the server whether a request would hit a usage limit before rewinding
Unclear Nothing showing where this check is called or what switches it on was found, so it may not run yet.
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.
The Background tasks dialog can show a new detail screen for local agents and a shorter list that fits the window width
Unclear It is not clear what makes the new detail screen and list appear.
Some peer replies during background review now run at once instead of waiting in a queue, and the interruption check is simpler
Unclear It is not clear what difference these changes make to what a user sees.
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.
Output from a SessionStart hook that arrives late can be set aside and passed on later instead of being lost
Unclear It is not clear what makes Claude Code set the output aside rather than deliver it straight away.
Remote Control can print a cloud sessions status line, and the first-run setup can now skip the sign-in step automatically
Unclear What causes the first-run setup to skip sign-in is not known.
@-mentioned files are now read through a new path that can carry hook context, roll back on failure and filter folder listings
Unclear What the new read step does in detail, and whether it is switched on for everyone, is not clear.
Remote tool serving gains an own-made delete check so an rm of files the session itself just created can skip the prompt, plus a new trust message
Unclear What switches this on, and whether it applies outside remote sessions, is unclear.
WebFetch gains an optional offset so Claude can read on through a page too long for one fetch instead of only seeing its start
Unclear It is not clear whether the tool already uses the offset when fetching, or only accepts it for now.
A reminder reading "Elapsed time so far" can be added to Claude's context, with the clock restarting each time you send a prompt
Unclear What the feature check falls back to when nothing is sent was not settled.
The skill listing is now built from the full list so same-named skills get distinct labels, and it takes an extra list of entries
Unclear It is not clear what the distinct labels look like.
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.
A new sandbox check can withhold files Claude Code itself creates or deletes outside the folders the sandbox allows writing to
Unclear It is not clear which parts of Claude Code use this check or when it applies.
A teammate's reported agent id is now its resumable id when one exists, falling back to the teammate id
After a cloud session restarts, Claude Code now wakes it for lost timers as well as lost background tasks
Unclear Where the list of lost timers is gathered is not known.
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.
New messages say cloud sessions cannot use this computer until its settings record can be read and saved, or when a path is too long
Programs driving Claude Code may now receive a worker's result before the first start message of a cloud session
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 has new messages for a session whose local tools run in an approved folder elsewhere, not in the current window
Unclear What causes these messages to appear is not settled.
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.
When tools are served to a remote session, calls can now be refused with a declined_magic_link code, and announced machine folders are tried
Unclear What a user sees when a call is refused this way is not clear.
Changing the permission mode or proactivity level now notifies remote clients, and a --proactivity value is recorded with --permission-mode
Unclear It is not clear how the recorded --proactivity value is used.
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 resumed non-interactive session drops its last turn, Claude Code can now add an attachment entry instead of only trimming
Unclear What the added attachment contains, and what the extra step does to restored state, is not known.
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?