Big stability pass: resumed sessions keep extended thinking, 400 errors from undecryptable web search or redacted_thinking blocks are fixed, and managed settings get tighter.
maxProseWidth setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width/status and claude doctor entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry offallowClaudeInChromeWithManagedMcp managed setting to let claude --chrome run alongside an exclusive managed-mcp.json; the error shown when Chrome is blocked now names itstore.readiness_grace_seconds to the Claude apps gateway so /readyz can stay ready through a short Postgres outage such as a database failover/feedback drafts list in fullscreen mode; it appears while the mouse is over the list/artifacts: titles line up in one column, details are dropped whole instead of cut mid-word, and the list supports PgUp/PgDn, Home/End, the mouse wheel and clicks--continue, --resume) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning/model, /rename, /artifacts or another immediate slash command was used while Claude was working--tools list that leaves out a built-in tool offered earlier in the conversationdata in redacted_thinking block" API error; Claude Code now drops the conversation's thinking blocks and retries once/model with a full Fable model id stopping at an API error instead of opening the usage-credits prompt when the plan needs usage credits that aren't turned on yet/Network via .. or a /.vol-style kernel path, or a rules link to macOS's /home being listed:* being skipped in settings files while --allowedTools honored them; they now work from every source, with a startup warning on how they matchdisableClaudeAiConnectors or allowManagedPermissionRulesOnly; the lock now applies and startup names the keypermissions, autoMode, worktree and attribution settings being ignored entirely when one nested value was invalid; the rest of the block now still applies--add-dir skills, commands and skills-directory plugin manifests pre-approving their own tools via allowed-tools under managed allowManagedPermissionRulesOnlySessionStart hookclaude remote-control --debug failing with "Unknown argument: --debug", although Remote Control's own eligibility error says to run with --debug/install-github-app saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done/ in /skills moving the skill list instead of reaching the search box/skills search box to the skill list while typing, which could hide the caret and put IME input in the wrong place/skills and /mcp, being two columns narrower outside fullscreen mode, where the scrollbar can never appear · separator in the /tasks dialog footer when the stop-all-agents shortcut is unbound in keybindings.json>> indenting empty lines, r with a count longer than the line changing text, 2J joining one line too many, and a count on the last line (2dd, 2>>) shifting or deleting itdd, dj, dG or a whole-line p/P it lands on the first non-blank, yy no longer moves it, and Esc after an emoji no longer leaves it inside the emoji. when repeating x, s, p, d or c, and whole-line p/P, o, O, J, >> and << acting on the wrong line when a line above wrapsx did nothingclaude-api skill: pre-output refusal billing now links to the How refusals are billed docs, mid-stream refusals bill at normal rates, and pre-output refusals count against rate limitsclaude-api skill to recommend ant apply for keeping Managed Agents resources as version-controlled filesCLAUDE_CODE_AUTO_MODE_SERVER=0 opts out)sandbox.excludedCommands to ignore project and local settings entries when managed settings or --settings set allowUnsandboxedCommands: false, or managed allowManagedDomainsOnly: trueCLAUDE_CODE_ENABLE_TELEMETRY and OTEL_LOG_*managed-settings.json) keeps user-writable HKCU and WSL /etc/claude-code from applyingSkill(anthropic-skills:*) and Skill(claude-ai:*) allow rules to cover only skills synced from claude.ai, not plugins or other skills that merely use such a nameanthropic-skills or claude-ai namespace to no longer load; a plugin so named still loads but yields name ties to synced skillsanthropic-skills or claude-ai to list no skills or prompts (their tools still work); rename the server in your MCP configuration to list them againultracode visuals in /effort and the prompt input to plain styling (no ripple, border flourish or keyword glimmer) and removed the dynamic-workflows spinner tip