Riedl, Saretto, and Young (2003) describes narrative mediation, a plan-based technique for addressing human user actions that conflict with the story structure maintained by computer-controlled agents within interactive narrative environments. This technique is used to generate real-time system responses to unanticipated user actions while balancing user freedom with story coherence. Narrative mediation has previously only been used for a single plan representing an entire story. A high amount of computation is required to monitor user actions and, in response, replan as appropriate to avoid a threat to the story's consistency. Toward the goal of maintaining plan consistency, use of a single planner is limited in that it can process only a single user's actions. To handle multiple users, distributing the planning burden across several planners requires collaborative communication to maintain global consistency. We propose a method that extends Riedl, Saretto and Young's mediation techniques to allow for mediation of exceptional user actions within a narrative environment consisting of many users.