🤖 AI Summary
This work addresses interoperability challenges in distributed systems arising from heterogeneous services, multi-version REST APIs, GraphQL endpoints, and IoT devices due to data schema mismatches. The authors propose a FastAPI-based runtime middleware that, for the first time, shifts Bass et al.’s interoperability tactics from design time to runtime. Leveraging large language models (LLMs), the approach dynamically detects structural and semantic discrepancies and implements a dual-path transformation strategy—either generating reusable adapter code or performing on-the-fly request-level conversion—through a five-stage pipeline. It also incorporates a three-tier security mechanism comprising validation, ensemble voting, and rule-based fallback. Evaluated across ten scenarios, the best configuration achieves a pass@1 accuracy of 0.90, with the CODEGEN strategy (mean 0.83) significantly outperforming DIRECT (0.77); notably, the highest-accuracy models also exhibit the lowest inference costs.
📝 Abstract
Modern distributed systems integrate heterogeneous services, REST APIs with different schema versions, GraphQL endpoints, and IoT devices with proprietary payloads that suffer from persistent schema mismatches. Traditional static adapters require manual coding for every schema pair and cannot handle novel combinations at runtime. We present SAGAI-MID, a FastAPI-based middleware that uses large language models (LLMs) to dynamically detect and resolve schema mismatches at runtime. The system employs a five-layer pipeline: hybrid detection (structural diff plus LLM semantic analysis), dual resolution strategies (per-request LLM transformation and LLM-generated reusable adapter code), and a three-tier safeguard stack (validation, ensemble voting, rule-based fallback). We frame the architecture through Bass et al.'s interoperability tactics, transforming them from design-time artifacts into runtime capabilities. We evaluate SAGAI-MID on 10 interoperability scenarios spanning REST version migration, IoT-to-analytics bridging, and GraphQL protocol conversion across six LLMs from two providers. The best-performing configuration achieves 0.90 pass@1 accuracy. The CODEGEN strategy consistently outperforms DIRECT (0.83 vs 0.77 mean pass@1), while cost varies by over 30x across models with no proportional accuracy gain; the most accurate model is also the cheapest. We discuss implications for software architects adopting LLMs as runtime architectural components.