As human-agent medical collaboration evolves with the rapid ad-vancement of AI systems, careful trust considerations are needed to overcomebarriers to adoption and usability. Although human-automation interaction andinterface design have been widely studied from the perspective of human→agenttrust, effective medical collaboration requires mutual trust. Transdisciplinary ef-forts are needed to design medical systems and user interfaces (UIs) that considerhuman↔agent trust as a fundamental part of the interaction.The design of medical systems for astronaut-agent teaming on long-durationhuman spaceflight (LDHSF) represents a well-defined and focused edge case thatallows for specifying key aspects for mutual justifiable trust-informed interactiondesign and offers opportunities for broader applications. While astronaut-agentcollaboration and the integration of emerging technologies could enable crew in-dependence from ground medical support, effective teaming requires the agentto be aware when the human is unable to perform a task or requires assistanceadaptation.Applying a human-centered design approach, we conducted qualitative inter-views, stakeholder meetings, and design workshop sessions. The Subject MatterExperts (SMEs) represented diverse fields, including astronauts, space medicine,human factors, computing, human-computer interaction, engineering, and spacesystems.In this paper, we discuss key insights related to trust challenges and opportu-nities of astronaut-agent medical interfaces, presenting selected outputs from co-design sessions related to medical interaction during LDHSF. We illustrate prac-tical examples from a case study development of a trust-driven, trust-adaptiveExploration Medical Ecosystem Design Interface (ExMEDI), and highlight op-portunities for future work.