{"version":"2.0.0","anchor":"extended-thinking-improvements","canonical_anchor":"extended-thinking-improvements","heading":"Extended Thinking Improvements","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.0.0\/e\/extended-thinking-improvements","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.0.0","markdown":"### Extended Thinking Improvements\n\n**What:** Simplified thinking trigger system with new programmatic control\n\n**How to use:**\n\n`# Use \"ultrathink\" anywhere in your prompt for maximum thinking claude > Please ultrathink about this architectural design # Toggle thinking with tab key during interactive sessions # Or use \/t command` **Details:**\n\n- Streamlined from multilingual pattern matching to single \"ultrathink\" keyword\n- Binary mode: ULTRATHINK (31,999 tokens) or NONE\n- New `thinkingMetadata` API for programmatic control without text triggers\n- Removed complex multi-level system (HIGHEST\/MIDDLE\/BASIC) in favor of simpler on\/off\n- Thinking state notifications show \"Thinking on\/off (tab to toggle)\"\n- **Evidence**: Pattern at line 363628, functions `Y61()` at line 363667, `Y09()` at line 363644, `le1()` at line 363671, metadata handling at line 363649 in v2.0.0"}