JADE — A VS Code plugin for automatically repairing static analysis warnings using local LLMs.
Model comparison protocol
JADE includes an official reproducible benchmark battery for comparing Deepseek and Qwen through Ollama.
Run JADE: Run Model Comparison to execute the fixed benchmark.
Results are written to the open workspace in model-comparison-results/.
Run JADE: Compare Models on Open Java File to compare Deepseek and Qwen against the currently open Java file. These results are written to model-comparison-results/open-file/.
Run JADE: Export Model Comparison Samples to copy the official Java samples, expected findings, and protocol document into the open workspace for inspection.
The benchmark always reads the official samples packaged with the extension. Exporting samples is for auditability and documentation; it does not mutate the packaged benchmark battery.
Open-file comparison has no fixed ground truth, so it records model outputs and response metrics without treating suggestions as academically validated false positives.
