fix(ignore): whitelist data/demo.db in git and docker ignore rules

fix(ui): remove all mock/Spider fallbacks and route queries to real backend only

docs(readme): revamp and polish README for production showcase

feat(core): stabilize benchmark pipeline with accurate latency tracking, retry-empty handling, and refined plots

fix(core): non-zero generator timing + one-shot EMPTY retry; post-verify drop LIMIT to recover EM when ExecAcc=1

perf(planner): trim relevant tables (+cache) to cut latency; keep repair loop & rich traces

refactor(core): trace schema upgrade, verifier/executor sync, benchmark plot polish

feat(trace): enrich StageTrace (sql_length/row_count/verified/error_type/repair_attempts/skipped) and propagate in normalization; tag EmptySQL; annotate repair attempts

feat(bench): gold-aware EM/SM/ExecAcc + p50/p95; write per-stage means; richer plots

feat(core): refine pipeline & verifier; improve Spider benchmark accuracy

feat(bench): auto-detect latest run and plot per-stage latency + metrics summary

chore(factory): safely load .env via dotenv (with fallback under CI)

chore(factory): safely load .env via dotenv (with fallback under CI)

fix(grafana): move nl2sql.json into provisioning folder and fix dashboard mount path

feat(benchmarks): add pro evaluator with EM, structural match, execution accuracy, and safety consistency metrics

feat(benchmarks): align Spider eval with config-driven Pipeline and native Safety; log per-stage trace; add CSV summary

feat(benchmarks): align Spider eval with config-driven Pipeline and native Safety; log per-stage trace; add CSV summary

style: format code with ruff

fix(types): resolve mypy errors and make pytest pass

build(mypy): fix type errors and add safety guards for None values

Fix some typo

style: format code with ruff

style: format code with ruff

init: NL2SQL Copilot base with API and Dockerfile

Add more advanced metrics

Add first benchmark