We propose a new inventory control technique for large-scale bidirectional (or closed-loop) supply chains including repairs. It is well-known that available optimization techniques are computationally intractable for bidirectional stochastic supply chains and also necessitate several simplifying assumptions. In contrast, the proposed approach is an adaptive scheme which scales well to practically interesting large-scale multi-item supply chains. Furthermore, practical issues such as stochastic transport delays, manufacturing times, and repair times and probabilistic characterization of part repair success are handled in a unified framework. The control scheme is based on a hierarchical two-level architecture comprised of an adaptive set-point generator and a lower-level order-up-to policy. An application to aircraft supply chains involving multiple OEMs, depots, bases, squadrons, and planes is also investigated.