{"version":"1.0.28","anchor":"new-features","canonical_anchor":"new-features","heading":"New Features","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/1.0.28\/e\/new-features","release_url":"https:\/\/changelogs.core-directive.com\/v\/1.0.28","markdown":"### New Features\n\nModel Selection Command Menu\n\n- Added new interactive model selection functionality that allows users to switch between different Claude models during a session\n- When invoked, users can navigate through available models and select their preferred model\n- Includes keyboard shortcuts: ESC key to cancel and keep current model\n- The selected model is displayed in bold text for clarity\n- Example usage: The menu will show available models and allow selection via arrow keys\n\nEnhanced MCP (Model Context Protocol) Support\n\n- Added `MAX_MCP_OUTPUT_TOKENS` environment variable to control the maximum tokens for MCP output\n- Default value: 25,000 tokens (configurable via environment variable)\n- Example: `export MAX_MCP_OUTPUT_TOKENS=50000` to increase the limit\n\nImproved Resume Command\n\n- Refactored the `resume` command to use a more robust component-based architecture\n- Better error handling when loading conversations\n- Async loading with proper state management\n- Shows loading state while fetching conversations\n- Filters out sidechain conversations automatically"}