feat: add baseline evaluation script, update documentation with benchmark details, and remove smoke test script

fix: standardize port to 7860 and update API server defaults

chore: clean up repository by removing context files and updating README

refactor(server): migrate FastAPI app to server module and enhance robustness

feat(api): enhance endpoint validation, thread safety, and testing infrastructure

fixed inference and used interface instead of env calling

Phase 0 changes

test suite initialised

structure initialised