/fast on Opus 5.5 drops its research-preview label; new /auto-mode-setup and Code Review depth levels, plus a big fix pass for worktree data loss, hangs and startup timeouts.
decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be askede.isReadOnly to a mod's tool.check event, set when the tool call is read-only/auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled sessions/claude-api managed-agents-secure, which compares a Managed Agents agent's settings with Anthropic's published security guide, without changing anything/usage to say when a rate limit on usage data ends instead of "try again in a moment"alwaysLoad: trueclaude -p invalid-settings warning: a file that did not load lists only what stopped it, and long lists are capped per fileANTHROPIC_API_KEY at startup or switching "Use custom API key" in /configsandbox.filesystem.denyRead glob contains brackets that are not a character class, such as a [user-id] route folderrm -r of a mounted drive or a folder at its top level (/Volumes, /media, WSL's /mnt/c) not getting the safety prompt that rm -rf /Applications getsCLAUDE_CODE_TRANSCRIPT_LOCAL_GC dropping messages from the saved transcript when the disk filled up while the file was being trimmed--max-turns, Stop, or ended input by spawning subagents or re-running a finished onekey were redrawn unchangedplugin-authoring skill stopping at the secret scan on machines with managed settings and on Team and Enterprise plans../../…; they now show ~/… or the full pathcontext_management: Extra inputs are not permitted errors behind LLM gateways; Claude Code now resends the request without that field/privacy-settings offering choices that may not apply to you after a network or server errorclaude --help text for --tools, --resume, --debug, --json-schema, --disable-slash-commands, --system-prompt-snapshot and claude update to match actual behaviorclaude --worktree removing the worktree and its branch without asking at exit when HEAD was detached or on another branch, which could lose commits/effort status, /effort ultracode and the prompt's effort indicator showing a guessed effort level when CLAUDE_CODE_EFFORT_LEVEL is auto or unset and no level is sent/loop wakeups scheduled at the 1-hour maximum firing just after the 1-hour prompt cache expired, so those wakeups no longer re-read the conversation uncachedonce hook also removing another skill's identical hook after it ran{ and } landing the prompt on an inconsistent row, or off screen, instead of the transcript's first rowCLAUDE_CODE_AUTO_COMPACT_WINDOW=200k silently setting a 100K window: the variable now accepts k and M suffixes like --autocompact, and warns when a value is out of range or ignoredclaudeCode.claudeProcessWrapper is set@Claude !fork typed outside a thread getting no visible reply; Claude now shows you a private note saying to run it from inside a threadsettings.read hooks to receive each settings layer and rewrite the merged settings, so a managed mod can make an organization's setting a ceiling, including the cleanupPeriodDays the retention sweep uses/artifacts delete confirmation to show numbered choices: 1 or Enter keeps the artifact, 2 deletes it, and y, n and Esc still workANTHROPIC_BASE_URL; a 400 or 422 from the gateway is retried without it/reload-skills now sends only new or changed skillsallowed-toolsant CLI on Claude Platform on AWS instead of falling back to the SDK or curlclaude plugin validate that predicted where a mod's hooks would run/fast dialog title on Opus 5.5