style: fix ruff lint — import sorting, line length

fix: address remaining review issues (3/5)

feat: infrastructure sprint — vLLM/Modal, Helm, Terraform (#8)

fix: eliminate redundant stream_complete() call in run_stream

feat: add streaming responses via SSE endpoint

test: add sliding window reset test with mocked time

test: fix rate limiter test gaps

feat: add provider retry with backoff and API rate limiting

fix: cross-request state bleed, metadata accuracy, empty question validation

feat: Day 6 — serving layer with FastAPI app, routes, middleware