Setting CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG now stops your own skills, agents and hooks from widening permissions. In that mode, errors in your user settings file block every prompt and tool call until you fix them. You can set transcriptCacheTtl to 5m to ask for 5-minute prompt caching instead of the default 1 hour. claude mcp serve has a new --session-tunnel mode that connects through a relay. Idle conversations are now compacted shortly before their prompt cache runs out. Plugins can now send notifications through your terminal.
Several features are in this build but not switched on yet. Print mode can show each turn's text result as soon as that turn ends. MCP servers that failed with a retryable error can be retried at the start of the next turn. Images can be re-encoded as smaller WebP files when that saves space. Work on cloud sessions continues, with remote tool requests now pausing while the host computer sleeps. The fleet view can group and pin cloud sessions.
Tool search no longer freezes Claude Code when you have very many tools. A queued message that gets dropped is now handed back to you instead of being discarded. Prompts typed during a left-arrow hand-off to background agents are no longer lost. If a model rejects the 1M-token context option, Claude Code now leaves it out instead of failing every request. Plugin sync from claude.ai no longer removes plugin files that another running session is using. The end-of-turn message no longer includes token budget figures.
Written by our agent from the shipped bundle, not by Anthropic.
In cloud-remote sessions only, claude mcp serve can run over HTTP, dial a session tunnel, read tokens from a descriptor and return tool output objects
ExtensionsA host program can set CLAUDE_CODE_AUTOUPDATER_DISABLED_BY_HOST so plugin auto-updates stay off under the host's version pin
ExtensionsPlugin UI adds a ui.notify operation and Button text from children, and the Grep search now passes a searchOtherAppsData flag
Setting CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG stops your own skills, agents and hooks from widening permissions, and makes key hooks required
Settings & config
CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG mode restricts your own Claude Code filesSetting CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG starts a session that restricts your own Claude Code files, alongside the other restricted modes
Want the reasoning? Read walks the 43 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.
In cloud-remote sessions only, claude mcp serve can run over HTTP, dial a session tunnel, read tokens from a descriptor and return tool output objects
The fleet view gains a way to move to the next session, keeps cloud sessions listed when loading fails, and lets cloud rows be grouped or pinned
Unclear It is not clear whether the controls for grouping and pinning cloud rows are reachable in this build.
A host program can set CLAUDE_CODE_AUTOUPDATER_DISABLED_BY_HOST so plugin auto-updates stay off under the host's version pin
A model list now includes claude-haiku-5-5 with thinking set to medium effort, and the model appears in more places than before
Unclear It is not stated which feature uses this list or whether a remote setting controls it.
Plugin UI adds a ui.notify operation and Button text from children, and the Grep search now passes a searchOtherAppsData flag
Unclear It is not stated what other apps' data the search now covers or when that search runs.
In claude -p print mode, text results can print as each turn ends, a notice explains waits for background work, and stream events gain fields
Claude Code can start a turn on its own when an attached computer is reachable again or a stopped command's late result arrives
Unclear Besides the remote switch, one more condition decides whether this runs, and what it checks is not known.
A new way to pass MCP server metadata to plugins was added; it stays off unless switched on remotely
Setting CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG stops your own skills, agents and hooks from widening permissions, and makes key hooks required
CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG mode restricts your own Claude Code files#Setting CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG starts a session that restricts your own Claude Code files, alongside the other restricted modes
Unclear Which of your own files and settings this mode actually stops from loading is not settled.
Plugins can now send notifications through the terminal, and tool descriptions get a longer limit once a tool is loaded through tool search
A new SELF_HOSTED_RUNNER_SERVER_AUTO_MODE_LISTS setting lets self-hosted runner operators limit which server-supplied auto mode lists sessions follow
Unclear Which of the three values the runner uses when the variable is not set is not stated.
transcriptCacheTtl#Setting transcriptCacheTtl to 5m makes Claude Code ask for 5-minute caching when the default would be 1 hour
Unclear It is not stated where transcriptCacheTtl is set.
--environment now parses env_ ids and names (only ccpool_ ids work yet), cloud runs resolve an environment query, and --cloud takes piped or positional prompts
Unclear Which other input must be present for an empty --cloud to be accepted is not clear.
In a diskless session, Claude Code no longer reads skills, settings files or shell details from the disk
The summary of plugin and marketplace settings now includes a seat section with its own plugin and marketplace values
The feedback survey gains rebindable ctrl+x 1/2/3 chords for bad, fine and good, with on-screen hints that follow your bindings
The gateway's timeouts.upstream_ttfb_ms now covers non-Anthropic upstreams when you set it, upstreams take a models list, and Bedrock can count tokens
Unclear What the per-upstream models list does is not stated.
CLAUDE_CODE_POLISHED_DEWDROP now accepts drop, block or off#The CLAUDE_CODE_POLISHED_DEWDROP environment variable now overrides a setting with one of three values: drop, block or off
Unclear What behaviour this setting controls is not known.
With CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG set, errors in your user settings file block every prompt and tool call until they are fixed
A timer now compacts an idle conversation shortly before its prompt cache runs out, if it is large enough and rate limits allow
Command and http hooks accept a new onFailure field, and setting it to "block" makes a failing hook block the action
A new hook option set to block makes a hook that fails, times out or returns bad output stop the action it guards
Unclear The name of the key to put in a hook's configuration for this setting is not known.
CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS setting stops a retry check from being skipped#Setting CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS now stops Claude Code from skipping a check it otherwise skips because of the retry watchdog
Unclear Which feature this skip applies to is not stated, so the practical effect of setting the variable is unknown.
CLAUDE_RUNNER_FETCH_SERVER_PROGRESS_CAP_MS sets a time cap on server-side progress when a runner fetches a repository
Unclear It is not stated what happens when the cap is reached, or what the default cap is.
For claude-device, a note now says its chrome_ tool calls are shown as mcp__claude-in-chrome__
recheck permission decision is treated as allowed by configuration#A permission decision of recheck is now treated as allowing the action, recorded as coming from your configuration
Unclear Whether a hook you write can return recheck itself is not settled.
With CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG set, your own agents' MCP servers are skipped and launching an agent in the cloud is refused
When CLAUDE_JOB_DIR is set, Claude Code keeps what you have typed but not sent in a .prompt-draft file in that folder
If there is no logged-in email, Claude Code can now use the CLAUDE_CODE_USER_EMAIL environment variable as the email it gives the model
Unclear The two conditions that must hold before CLAUDE_CODE_USER_EMAIL is used are not described.
HTTP hooks gain an onFailure setting, and icons, stylesheets, scripts, fonts and similar files now get their own file extensions
Unclear What the new onFailure setting does and which values it accepts is not stated.
On macOS, setting CLAUDE_CODE_DISABLE_BG_STABLE_PATH makes background sessions relaunch from the running program instead of the stable path
Plugins gain a ui.notify operation for posting notifications, and each notification's screen time is now budgeted and saved
A new FeedbackSurvey keybinding context applies when the session feedback survey has been typed over
Idle and request timeouts can now be set from a config (bodyIdleTimeout, stream_idle_timeout_ms, api_timeout_ms) when the env vars are unset
Unclear Whether bodyIdleTimeout is something a user can set, and what it defaults to, is not settled.
With CLAUDE_CODE_DIAGNOSTICS_FILE set, Claude Code writes a report on how each resumed conversation was loaded from its saved transcript
Buttons in plugin-built screens can now contain plain strings and Text elements, drawn in place of the button's label
Toggling fast mode in one settings screen now also saves the choice as your default for new sessions
Unclear Which screen this applies to, and whether anything limits who gets it, is not stated.
/copy can now copy quoted passages as well as code blocks#The /copy picker now lists quoted passages from a reply alongside code blocks, so you can copy a quote on its own
Each SDK stream event between a reply's start and stop now carries an api_message_id, so programs can match events to replies
The gatewayUrl setting is now honoured from your user settings on a machine with no managed settings, not only from admin-managed ones
Unclear Only the setting's description is confirmed to have changed, not the code that applies it.
The settings screen can set the auto-update channel to latest or stable, and choosing stable can also set a minimum version
Unclear It is not confirmed that the auto-update channel row actually shows on the settings screen, or what controls whether it does.
x-should-retry: false with a 501 not supported response#The bundled gateway guide now says a 501 not supported response should send x-should-retry: false, or Claude Code retries once first
What would fix it?
Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.
19 more of these are in What probably matters to you, above.
Self-hosted runners can now write server-supplied autoMode allow, environment and soft-deny lists into sessions, with allow lists withheld by default
A new startup notice, off by default, uses a small model to judge whether your CLAUDE.md, skills or agents push heavy subagent use, and warns you
When an environment keeps its own settings, only deny and ask rules from your machine are applied, and the notice now explains what was skipped
The remote tool-host notice now tells Claude when a host that went offline is back, and warns it not to blindly resend commands
Unclear Whether or how the list of hosts that are away is shown to you is not stated.
A new diskless session mode makes Claude Code skip writing local files and skip loading skills and other files from disk
Unclear It is not known what makes Claude Code decide that no storage is available.
The usage-limit warning can now take an overageEnabled value, alongside a resume dialog trigger tag and a changed plugin enabled check
Unclear None of the three changes has a known visible effect.
Tool search is bounded and time-sliced, some built-ins cannot be deferred, and MCP servers that will retry are reported as unavailable only for now
After a session sits idle, Claude Code can offer to start a new conversation with /clear, and the idle /clear hint can now be suppressed
Turning fast mode on or off now goes through a step that can run PreModelSwitch hooks and show "Waiting for the workspace…"
Unclear It is not stated when the new step is active or what it waits for.
Seeding of home settings now also runs for runner child sessions that declare an absolute CLAUDE_CONFIG_DIR, not only managed cloud workers
Unclear How a session comes to be treated as a runner child is not stated.
A queued prompt held for screening is now returned to the input box if it is cancelled, instead of being lost
Unclear What screens a queued prompt, and whether that screening is switched on for any user, is not stated.
The mod-making skill's description now covers any change to Claude's own interface or behaviour, including slash commands
Unclear Whether the mod-making skill is available to every user is not stated.
Claude Code now checks whether the prompt cache is about to expire while you are idle and can ask you about it
Unclear It is not stated whether this prompt is switched on for everyone or controlled by a remote setting.
Claude's guidance on starting other agents now warns that they cost more than they look and can lose detail or confirm a guess
Unclear Claude Code's standard Agent tool text is recorded as unchanged in this release, so it is not clear which setups receive the rewritten guidance.
Claude Code rewrote the main system prompt it sends in its agent-claude setup
Unclear It is not clear what the rewritten prompt now says or how it changes Claude's behaviour.
In a certain session mode, Claude Code now skips skills from project folders and synced user skills, and also skips some git and config lookups
Unclear Which session mode causes project and synced skills to be skipped is not settled.
When finding autoMemoryDirectory, Claude Code now skips settings sources that fail a new check, so they cannot move the memory folder
Unclear It is not stated which settings sources fail the new check, so it is unclear whether a project-level autoMemoryDirectory is still honored.
The check that decides what auto mode may do on its own is now told whether computer use is attached to the session
Unclear How auto mode's decisions change when computer use is attached is not known.
When CLAUDE_CODE_REMOTE is set, Claude Code can now delete credential files and logs each one it removes
If you close or ignore the prompt to enable hot reload for a mod you are developing, Claude Code stops asking after a limit
The routine that clears old session data now first removes leftover claude-seed-admin folders, after checking they are safe to delete
When Claude Code runs inside a claude-code-server setup, it now sends no first-party usage events unless it was given a grant to do so
In a new personal mode, hooks from your own files can no longer change a tool call's input or certain tool results, and Claude Code says so
Unclear It is not stated when Claude Code runs in this personal mode, so it is unclear which sessions get these limits.
While you wait out a rate limit, the notice can now include a credits option and a plan upgrade suggestion
Unclear It is not shown when the credits and plan upgrade items are filled in or who sees them.
The fleet view's peek panel now shows some text dimmed instead of formatted, and can refresh its cloud entries
With CLAUDE_CODE_RESTRICT_PERSONAL_CONFIG set, launching a cloud agent is refused and you are told to use worktree isolation
For sessions that talk to people in a chat thread, waiting on a named person now counts as waiting on the user
A new switched_off status for MCP servers, now used for SDK servers, tells Claude a server was switched off rather than disabled by you
Unclear How an MCP server comes to be marked switched_off is not known.
Permission requests sent to SDK hosts now carry a title and a one_at_a_time or all_at_once value for blocked URL fetches, and pending prompts can resolve on recheck
Messages about unreachable remote machines gain a host_asleep case and variants that tell Claude whether it needs to keep checking
When a ClaudeInChromeDomain deny rule covers a site, a claude.ai-proxied connector call that needs approval now fails instead of showing an approval card
Unclear It is not clear whether the new deny-rule check sits behind the same remote switch as the approval retry.
The dialog shown when you come back to an idle session now knows when you went idle, what triggered it, and which choice to focus
Each turn now reports whether it completed, was stopped or failed, with the outcome reset on new, rewound or resumed conversations
If Claude hits its output limit while still reasoning, it is now told to reason much more briefly and continue
After a rewind, Claude Code keeps track of the host it runs on and cancels pending work when no carried-over prompt is waiting
Unclear What exactly is cancelled after a rewind is not stated.
Retries for MCP servers that failed to connect now report a result for each try, and one failed server can be retried on its own
Images opened by the Read tool can now be re-encoded as lossless WebP, and notebook cell output is checked and tidied
Unclear Whether the lossless WebP option is used for everyone or only under some switch is not known.
disableAllHooks is set#With disableAllHooks set, Claude Code can now still run hooks from your own settings under certain conditions
Unclear The internal condition that lets your own hooks keep running is not stated, so it is unclear when this applies to you.
With a gateway provider, the model list no longer requires a name containing opus, sonnet or haiku
Unclear The further check a gateway model must pass to appear is not stated.
Each web search hit can now carry an optional snippet of page text, passed to PostToolUse hooks but not into the tool result
On Amazon Bedrock in a region outside the US and Canada, Claude Code now sends a changed model ID
Unclear It is not stated how the model ID is changed for those regions.
The built-in model list moved to a newer version and one list in it now includes Haiku 4.5 set to extended thinking
Unclear Which model picker or screen uses the list the new Haiku 4.5 entry was added to is not known.
On resume, a /loop wakeup still in the future is set again, and one whose time has passed is reported as missed
On supported terminals other than WezTerm, Claude Code now tells the terminal whether it is working, blocked, done, idle or in error
MCP servers reached through claude.ai connectors now agree a protocol version automatically unless the server explicitly turns this off
Commands such as the output style command now save settings the same way /config does, so plugin hooks can change or refuse them
--tools are now withheld unless a deny rule names them#A tool missing from the session's --tools list and named by no deny rule is now withheld, with a warning
Unclear Which tools were previously still offered despite being left out of --tools is not stated.
In interactive mode, /model and its picker can pass your choice through a step that may refuse or change it, and report save failures
Unclear It is not stated what can hook into model switching, so it is unclear when this step applies.
On Bedrock gateways, count_tokens now calls AWS CountTokens with a 10-minute retry backoff, and the built-in gateway guide says the same
The instructions Claude gets for AskUserQuestion are now chosen based on which other tools are available in the session
Claude Code now identifies a request error that mentions the long context beta as that beta being rejected
Unclear What Claude Code does after it recognises this error is not stated.
Warnings about a stale or unreadable synced copy now name what was synced instead of always saying "your settings"
The keybindings.json file Claude Code generates now leaves out some interface contexts instead of listing every default shortcut
A list view that showed code snippets now also accepts quoted text, and labels those entries "quote" instead of a programming language
When a list grows past its length limit, Claude Code now trims unmanaged entries first and keeps trimming until the list fits
Unclear It is not stated which list this is or what its entries hold, so it is unclear where a reader would notice the change.
With CLAUDE_CODE_WEBSEARCH_CITATIONS set, Claude is no longer told to end web search answers with a written "Sources:" list
If your last message came from the iOS or Android app, Claude Code withholds the Chrome setup offer and reports a phone reason
Published verbatim by Anthropic for v2.1.295. 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 143 bullets, 35 name something an entry on this page also names, 32 name something no entry here does, and 76 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.
onFailure: "block" for command and HTTP hooks: a hook that can't start, times out, or exits with an unexpected code blocks the action instead of letting it through
No entry names this /copy picker, so a drafted message copies without its > markers
Probably copy-picker-now-lists-blockquotes-as-well-as-code-blocks claude plugin install, enable, disable and marketplace add when the settings file they write to does not load
Probably release-notes-bundle-for-21292, marketplace-add-warns-after-success claude -p run is waiting for when it stays open after its last turn
Probably print-mode-text-results-printed-at-each-turn-end timeouts.upstream_ttfb_ms on the Claude apps gateway's Bedrock, Vertex, Foundry and other cloud upstreams: a value you set now limits how long a stream may take to start there, after which it fails over or gets a 502
Probably gateway-upstream-ttfb-timeout-now-only-applies-when-operator, gateway-notes-upstream-ttfb-ms-now-applies-to-non-anthropic ← is waiting for the current tool to finish
No entry names this models list to every Claude apps gateway upstream: only the listed models are sent there, on failover too, and one * in an entry is a wildcard
Nothing to match on forceLoginMethod: "gateway" and forceLoginGatewayUrl in your own user settings on machines with no managed settings, so /login opens on that Claude apps gateway
No entry names this claude plugin validate when a plugin's README has no install line: it prints the line to paste and never changes the exit code, even with --strict
Probably claude-plugin-validate-adds-a-further-check-pass upstream_request_id to the Claude apps gateway's inference audit event: the request ID from Amazon Bedrock, the Anthropic API or another upstream, for support cases
Probably telemetry-additions-api-message-id-text-runs-joined-upstr $.ui.notify for mods: raises a native notification through your own notification setting and says which channel sent it
Probably plugin-uinotify-channel-and-tool-search-aware-description Button: strings and Text, so a row of a list is one pressable with a chip or a dim detail inside
No entry names this CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS to limit how long unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) waits out 429 and 529 errors
Probably retry-watchdog-skip-can-be-overridden-by-claude-code-retry-w request-id header to the Claude apps gateway's successful inference responses, so request_id in Claude Code telemetry matches the gateway's audit log
Probably gateway-forwards-upstream-request-id, telemetry-additions-api-message-id-text-runs-joined-upstr [1m] model when a gateway, Bedrock, Vertex or Foundry refuses the context-1m beta; Claude Code now resends without it
No entry names this claude -p text output dropping earlier responses when background work started another turn; each turn's response now prints when the turn ends
Probably print-mode-text-results-printed-at-each-turn-end command_description instead of description
Probably bash-tool-input-command-description-is-accepted-as-descript host:80) to plain http:// pages on that host
No entry names this /plugin's Errors tab removing a marketplace that failed to load, and uninstalling its plugins, on Enter without asking first
Probably plugin-name-read-from-pluginjson-marketplace-clone-gains-p, plugin-errors-view-asks-for-confirmation-before-removing-mar, plugin-addressed-mcp-requestresponse-metadata-gated-behind claude plugin marketplace add reporting success for a marketplace whose name no plugin can be installed under; such an add is now refused
No entry names this CLAUDE_AUTO_BACKGROUND_TASKS moving a subagent to the background while an edit or shell command waited behind it, which started that call before the subagent finished
No entry names this claude remote-control sessions right after a phone message, without the /config toggle, or when started from inside Claude Code
Probably settings-panel-auto-update-channel-and-notification-changes, config-rows-commit-through-a-shared-writer-output-style-an #92661PushNotification reports "Remote Control inactive" (no_transport) in sessions served by `claude remote-control` Open
#99781PushNotification reports "Remote Control inactive" in sessions started with claude rc Closed
/tui exiting without a message, or with a raw system error, when Claude Code could not be started again
No entry names this availableModels not appearing in the /model picker for sessions signed in to a Claude apps gateway; such a model now shows its built-in row in place of a modelPicker row added for the same model
Probably remote-model-now-checks-whether-the-default-save-failed, model-pick-now-goes-through-a-saved-model-row-commit-with-s CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC hiding the Claude apps gateway spend limit in /usage and the status line. The spend limit request goes to the gateway the session is signed in to
Probably spend-limit-and-upsell-hint-text-refactored-into-a-lookup-ta, claude-mcp-serve-gains-an-http-transport-port-and-ses ←; Claude now keeps working in the foreground
Nothing to match on --tools and --restricted not applying to built-in tools that register after launch, and deprecated tool names reaching tools outside the caller's tool set
Probably sdk-spawns-cli-with-flagvalue-form-and-guards-values-st, tools-launch-list-now-withholds-unlisted-tools, new-claude-code-restrict-personal-config-env-var-recognized /loop that was moved to the background with ←; cancelling a pending wakeup now shows a notice
Probably resume-restores-a-pending-loop-wakeup-or-reports-it-as-mis FORCE_COLOR=3, which put color escape codes into the output Claude reads
No entry names this claude agents starting a new background service as it exited when both were stopped with a session open (for example at a reboot), which could delay shutdown and restart an interrupted session
Probably background-attach-prints-exit-notice-about-sessions-stopping #99369Agent view restarts the background daemon during system shutdown; the new daemon holds the shutdown for 90 s Open
worker being shown as "Agent" in auto-mode denial notices and in the activity lists of task detail views
No entry names this TaskStop, which can never be the cause
No entry names this /loop stopping without notice when its next wakeup came due while the session's process was down; the session now says so and Claude is told
Probably resume-restores-a-pending-loop-wakeup-or-reports-it-as-mis /advisor dialog showing a checkmark on a saved advisor model that is no longer available; it now opens on "No advisor"
No entry names this ~ moving the cursor past the last character of a line, so x after it did nothing, and 3~ running on into the next line
Nothing to match on .catch; such calls are now refused
Nothing to match on claude plugin test passing a session.append hook that removes tool call, tool result or thinking blocks that a real session keeps
No entry names this cat ran without printing it
Nothing to match on constructor or prototype always reading as their default and never reloading the plugin when edited
Nothing to match on /reload-plugins or session start was reading the mod's files
No entry names this /model, /fast and /output-style saving their setting without asking a plugin's config.set hook
Probably fast-mode-toggle-wrapped-for-remote-sessions-with-pre-switch, remote-model-now-checks-whether-the-default-save-failed, model-pick-now-goes-through-a-saved-model-row-commit-with-s claude mcp serve background Bash results not naming the output file, and its tool description promising a notification that never arrives
Probably mcp-tool-server-registers-extra-capabilities-when-serving-in, claude-mcp-serve-gains-an-http-transport-port-and-ses, mcp-serve-session-tunnel-and-tool-output-protocol #99934[BUG] `claude mcp serve`: Bash run_in_background output is unreachable since TaskOutput was removed (2.1.277) Open
CLAUDE_ENV_FILE not reaching the Bash tool after an in-app /resume or /branch
Probably restart-failure-messages #98933[BUG] CLAUDE_ENV_FILE env lost after in-app /resume — hook writes to startup session dir, Bash reads resumed dir (still on 2.1.287; #40391, #24775 auto-closed) Open
allowed-tools and effort being dropped when the Skill tool finished before the response stream ended, which denied the skill's Bash commands in -p runs
Probably new-claude-code-restrict-personal-config-mode-limits-what-a #99353[BUG] Skill allowed-tools rule is dropped when the Skill tool finishes before the response stream ends (2.1.289) Open
--plugin-dir plugin's folder in -p and SDK sessions; they are now written only where a mod is being developed
No entry names this /model saying a Max effort pick was saved as your default for new sessions; Max applies to the current session only
Probably remote-model-now-checks-whether-the-default-save-failed, model-pick-now-goes-through-a-saved-model-row-commit-with-s #99350[BUG] Clarify /model confirmation wording: max effort applies only to the current session Closed
pages parameter instead of treating it as omitted
Nothing to match on #98651[BUG] Read: `pages: ""` on a non-PDF file fails validation, and PreToolUse hooks can't work around it (still on 2.1.286) Closed
plugin install and uninstall at project or local scope on Windows missing the install record, or adding a second one, when only the drive letter's case differs
Probably release-notes-bundle-for-21292, plugin-install-lookup-refactored-into-a-shared-helper, plugin-install-records-matched-across-path-spellings-on-wind #92121Project-scope plugin installs are auto-created, never updated, and unreachable via --scope project (Windows drive-case duplicates) Open
↑ or Esc just after ←: prompt history now keeps it
Probably gateway-login-developer-sourced-url-and-esc-wording prompt.submit hook rewrote or dropped still being saved as typed to prompt history and to the transcript's queued-prompt records
No entry names this claude_code.auth OpenTelemetry login event not being emitted on Claude apps gateway sign-in. The event is exported when OpenTelemetry is configured on the machine or the session is already signed in to the gateway
No entry names this ~/.claude/seed-admin by an interrupted /ultrareview upload never being removed by the retention cleanup
No entry names this disableAutoMode was removed from settings
No entry names this /rewind being lost, and the removed turns coming back, when the session was moved to the background or resumed after being killed
Probably spend-limit-and-upsell-hint-text-refactored-into-a-lookup-ta session.receive hook asked for permission before passing a message on
No entry names this setMcpServers() as your own
No entry names this /config saving before a plugin's config.set hook was asked
Probably settings-panel-auto-update-channel-and-notification-changes, config-rows-commit-through-a-shared-writer-output-style-an /context and large file reads use: the gateway now gets them from AWS's CountTokens API instead of a one-token model request. Grant bedrock:CountTokens to use it
Probably bedrock-count-tokens-now-uses-aws-counttokens-with-backoff mcp__server__tool identifier
Probably auto-mode-resolves-toolaliases-for-mcp-tools-behind-tengu-so models: in Amazon Bedrock regions outside AWS's US geography. AWS always refused those requests; the gateway now tries the model in your own region, and a refusal names the model to add
Nothing to match on rate_limit_event usage-limit warnings to say whether the account has extra usage turned on
No entry names this plugin-authoring skill: it no longer tells a session with no terminal to run terminal commands, and explains sharing a mod only when asked
No entry names this -l, -c or -r flag now runs instead of failing the call
Nothing to match on claude plugin validate and plugin loading: when a hooks module is refused over a rebound top-level var, the error now names the line that rebinds it, the cause, and a fix
Probably claude-plugin-validate-adds-a-further-check-pass scriptPath refusal: it now says to pass the script inline via script, the route that works in sessions without a Read tool
No entry names this skills field, each once; a subagent with the Skill tool can still invoke the rest
Nothing to match on /loop wakeup alone, so pressing it twice detaches and the loop keeps running; press Esc to stop it
Probably resume-restores-a-pending-loop-wakeup-or-reports-it-as-mis claude agents stopped with its background service (macOS, or Linux without the service installed): running sessions now stop in about a minute unless it is run again, and a notice says so
Probably background-attach-prints-exit-notice-about-sessions-stopping MCP_PROTOCOL_NEGOTIATION=legacy opts out
No entry names this desktop policy key its bundled Claude Desktop schema doesn't know, so new Desktop settings need no gateway upgrade
Nothing to match on ws) MCP servers: a message over 16 MiB is no longer parsed and closes the connection, the limit the other transports already have
Nothing to match on CCR_AUTO_MODE_ALLOW, CCR_AUTO_MODE_ENVIRONMENT and CCR_AUTO_MODE_SOFT_DENY into a session's environment
Probably runner-spawns-child-with-ccr-auto-mode-env-vars-cleared CLAUDE_RUNNER_FETCH_SERVER_PROGRESS_CAP_MS tunes or turns off the wait
Probably git-fetch-gets-a-server-progress-stall-cap-env-var @Claude !restart had already confirmed the restart
No entry names this agent hook evaluations taking much longer at xhigh and max effort
Nothing to match on A model matched these bullets to the GitHub issues they fix, so a link can be wrong.
1 added and 1 removed, of 218 lines, about 22 words, in the prompt 14 of 27 arms receive. 4 other prompts also changed. The appended system-reminder blocks moved: 1 line added, 1 line removed.
Claude Code, interactive mode
13 prompt changes in this release could not be quoted from the build, so no entry on this page describes them.
550 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 78 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?