[Release] anthropics/claude-code v2.1.89: v2.1.89

Claude Code v2.1.89 is a major release introducing deferred permission decisions for headless sessions, flicker-free rendering, improved MCP connection handling, and numerous bug fixes across tool execution, file handling, and UI rendering. Key improvements include named subagents, enhanced auto-mode permission workflows, and fixes for critical issues like memory leaks, LSP crashes, and prompt cache misses in long sessions.

Key Points

• •Added 'defer' permission decision to PreToolUse hooks — headless sessions can pause at tool calls and resume with `-p --resume` for re-evaluation
• •Introduced CLAUDE_CODE_NO_FLICKER=1 environment variable for flicker-free alt-screen rendering with virtualized scrollback
• •Added PermissionDenied hook that fires after auto-mode classifier denials with `{retry: true}` option for model retry
• •Implemented MCP_CONNECTION_NONBLOCKING=true for `-p` mode to skip MCP connection wait and bounded server connections at 5s timeout
• •Enhanced auto-mode denied commands to show notifications and appear in `/permissions` → Recent tab with retry capability
• •Fixed critical memory leak where large JSON inputs were retained as LRU cache keys in long-running sessions
• •Resolved StructuredOutput schema cache bug causing ~50% failure rate with multiple schemas
• •Fixed `-p --resume` hangs when deferred tool input exceeds 64KB and improved deferred tool resumption in `-p --continue`
• •Improved Bash tool to warn when formatter/linter commands modify previously-read files, preventing stale-edit errors
• •Fixed nested CLAUDE.md files being re-injected dozens of times in long sessions and prompt cache misses caused by tool schema changes

Workflow Diagram

Concepts