Large Language Models (LLMs) have demonstrated significant potential in story generation and role-playing, enabling the creation and exploration of novel content based on existing stories. However, previous interactive storytelling systems have shown limitations in immersion and agency. To address these challenges, we propose ECHIDNA, a novel two-stage framework designed around three core dimensions of interactive narrative systems: author intent, character autonomy, and player modeling. We employ Perturbation-Driven Branching to expand the interactive space in the generation stage and introduce the GM-NPC architecture to enable dynamic character responses and state management during the interactive narrative phase. The evaluation results show that ECHIDNA achieves superior performance in creating diverse branching narratives and providing engaging interactive experiences compared to existing methods. Our code and prompts are available at https://github.com/MoidzzZ/Echidna.