Opus and Fable 1M-context sessions now compact reliably near the limit, while a broad stability pass fixes permissions, resumes, agent teams, plugins, terminals, and VS Code.
/diff/cost and the status line's prompt_cache field/reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists/advisor (/advisor, /advisor <model>, /advisor off) for the desktop app, Remote Control, and other headless (-p/Agent SDK) sessionsoidc.scope_on_refresh to the Claude apps gateway for IdPs that return an id_token on refresh only when asked for openid againdesktop policy blocks, including userPluginMarketplacesEnabled and userPluginUploadsEnabledagent({schema}) rejects a JSON Schema that can never be satisfied up front, and retry-cap errors now include the last validation failure-p / SDK) sessionsbedrock:CountTokens) instead of a one-token requestEdit(C:\dir\(name)\**), where \( is read as an escaped parenthesis rather than a path separator, to suggest an unambiguous spelling/ultrareview and claude ultrareview to wait up to 45 minutes (previously 30) for long-running cloud reviews/effort on Claude Fable 5.1 so changing effort mid-session no longer invalidates the prompt cacheEdit/Write/Read permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox, which left "read-only" folders writable[) making every file edit fail with Invalid regular expression; such a deny rule now guards the literal path it spellspermissions.blockReadsOutsideWorkingDirectories on macOS hiding the user's git config from sandboxed git and hiding a worktree-isolated sub-agent's own checkout/login/status listing a signed-in claude.ai account and a configured API key as if both were in effect; the credential not in use is now markedskillOverrides entries keyed on a bundled skill's alias (e.g. checkup for /doctor) not applying, and Skill(name) deny rules not covering a nested skill listed as <dir>:namemodel: fable agents ignoring the [1m] tag on an ANTHROPIC_DEFAULT_FABLE_MODEL pin and silently running with a 200K context window/model picker not showing Fable 5.1 for organizations that can use it, which was only accepted when typed as /model claude-fable-5-1…)/rewind and --rewind-files reporting success when checkpoint backup files were missing and nothing was actually restored/rewind leaving stale file-read tracking from the rewound-away turns, which caused "File unchanged since last read" stubs and full-file re-injection after external edits-p --resume/--continue (as used by the desktop app) failing on every retry once a session's worktree directory lost its git metadata; it now fails once, then resumes without the worktreeCLAUDE_CODE_RETRY_WATCHDOG) as retry notices evicted real messagesgitlab.com/group/subgroup/project)owner/repo#123 issue references in rendered output linking to github.com when working in a GitLab repository; they now link to the gitlab.com issueclaude-api skill so its Go, Java, and C# samples use current-generation model IDs, and clarified that cheaper worker or sub-agent models should be current-generation tooctrl+l / cmd+k in fullscreen mode to clear the transcript view like a terminal clear; scroll up to see earlier messagesBash(ls) x), which never matched anything, to be reported as invalid settings instead of being silently ignoredclaudeMd) no longer triggers the security approval dialog; hooks, shell-command, sandbox, and unsafe env settings still require approval--chrome, /chrome and the browser tools are unavailableorgPluginSettings in the list form read by Claude Desktop 1.15200.0 and later; older desktops ignore itdesktop policy misspells a field in a nested object of a managedMcpServers or orgPluginSettings entry! bash-mode prompt to run outside the sandbox even when strict sandbox mode (sandbox.allowUnsandboxedCommands: false) is on, like typing into your own terminal--kill-session-after-min to release a session that is only waiting on its user (paused, resumable on the next message) instead of killing it and reporting a failureRead() deny rules to Bash arguments; it denied npm run build under a Read(./**/build/**) rule in every mode and made cd … && grep prompt even in auto mode