eval: faithfulness spot-check on health subset — no regression (5.00/5)

fix(safety): make _compute_needs_vet query required; pass query in eval harness

feat(llm): migrate to google-genai SDK + quota resilience

test(eval): score the shipped safety behavior (rerank gate + server banner)

fix(eval): make LLM judge robust to 2.5-flash thinking-token truncation

feat(llm): rotate across multiple Gemini API keys to multiply free-tier quota

fix(eval): use live Gemini models in judge fallback chain

feat(rag): add cross-encoder reranker, enforce citations, external-dataset eval harness