[Release] anthropics/claude-code v2.1.69: v2.1.69

Claude Code v2.1.69 release adds the `/claude-api` skill for API development, expands voice STT support to 10 new languages (20 total), and introduces numerous UX improvements including effort level display, numeric keypad support, and custom session naming for remote control. The release includes significant bug fixes addressing security issues, memory leaks, plugin trust dialogs, OAuth keychain corruption, and various UI/terminal interaction problems.

Key Points

• •Added `/claude-api` skill for building applications with Claude API and Anthropic SDK integration
• •Expanded Voice STT support to 10 new languages (20 total), including Russian, Polish, Turkish, Dutch, Ukrainian, Greek, Czech, Danish, Swedish, and Norwegian
• •Enhanced bash mode with Ctrl+U exit command and numeric keypad support for interview question selection
• •Added optional name argument to `/remote-control` for custom session titles visible in claude.ai/code
• •Introduced effort level display in logo/spinner and agent name display in terminal title for better visibility of active settings
• •Fixed critical security issue where nested skill discovery could load skills from gitignored directories like `node_modules`
• •Resolved multiple memory leaks in long-running sessions (SDK/CCR, React Compiler, REPL render scopes, interactive mode hook events)
• •Fixed trust dialog behavior for MCP servers to show per-server approval dialogs instead of silently enabling all servers
• •Added new configuration options: `sandbox.enableWeakerNetworkIsolation`, `includeGitInstructions`, `oauth.authServerMetadataUrl`, and `pathPattern` for marketplace restrictions
• •Improved plugin system with `/reload-plugins` command, `git-subdir` source type support, and fixed hook firing issues after plugin operations

Concepts