Massive stability pass: 3 multi-GB memory leaks squashed (images, /usage, long-running tools), --resume crash fixed, plus new /skills search and alwaysLoad MCP option.
alwaysLoad option to MCP server config — when true, all tools from that server skip tool-search deferral and are always availableclaude plugin prune to remove orphaned auto-installed plugin dependencies; plugin uninstall --prune cascades/skills so you can find a skill in long lists without scrolling/usage leaking up to ~2GB of memory on machines with large transcript histories--resume crashing on startup in external builds--resume failing on large sessions when a transcript line was corrupted by an unclean shutdown — the corrupt line is now skippedthinking.type.enabled is not supported error when using Bedrock application inference profile ARNsprompt parameterNO_PROXY not being respected for all HTTP clients when set via managed-settings.json under the native build/usage returning "rate limited" after a stale OAuth token — now refreshes automaticallysettings.json invalidating the entire settings file/usage dialog content being clipped when no-flicker mode is off/focus showing "Unknown command" when the fullscreen renderer is off — now explains how to enable it--dangerously-skip-permissions no longer prompts for writes to .claude/skills/, .claude/agents/, and .claude/commands/hookSpecificOutput.updatedToolOutput (previously MCP-only)claude -p: CLAUDE_CODE_FORK_SUBAGENT=1 now works in non-interactive sessions/terminal-setup now enables iTerm2's "Applications in terminal may access clipboard" setting so /copy works, including from tmuxlanguage settingmcp_authenticate now supports redirectUri for custom scheme completion and claude.ai connectorsstop_reason, gen_ai.response.finish_reasons, and user_system_prompt (gated behind OTEL_LOG_USER_PROMPTS) to LLM request spansaccessibility.voice.speechLanguage setting when no Claude Code language is configured/context now opens a native token usage dialogfind in the Bash tool on large directory trees