#!/usr/bin/env bash
# Search evaluation quick entrypoints. Run from any cwd; resolves repo root.
set -euo pipefail

ROOT="$(cd "$(dirname "$0")/../.." && pwd)"
cd "$ROOT"
PY="${ROOT}/.venv/bin/python"
TENANT_ID="${TENANT_ID:-163}"
DATASET_ID="${REPO_EVAL_DATASET_ID:-core_queries}"
RETRY_COUNT="${REPO_EVAL_RETRY_COUNT:-2}"
EXTRA_QUERY_ARGS=()
if [[ -n "${REPO_EVAL_QUERIES:-}" ]]; then
  EXTRA_QUERY_ARGS=(--queries-file "${REPO_EVAL_QUERIES}")
fi

usage() {
  echo "Usage: $0 batch|batch-rebuild|batch-rebuild-resume|serve"
  echo "  batch          — batch eval: live search every query, LLM only for missing labels (top_k=50)"
  echo "  batch-rebuild  — deep rebuild: build --force-refresh-labels (search recall pool + full-corpus rerank + batched LLM; expensive)"
  echo "  batch-rebuild-resume — resume missing queries from dataset query_builds with retry/continue-on-error"
  echo "  serve          — eval UI (default http://0.0.0.0:\${EVAL_WEB_PORT:-6010}/; also: ./scripts/start_eval_web.sh)"
  echo "Env: TENANT_ID (default 163), REPO_EVAL_DATASET_ID (default core_queries), REPO_EVAL_QUERIES (optional override), REPO_EVAL_RETRY_COUNT (default 2), EVAL_WEB_HOST, EVAL_WEB_PORT (default 6010)"
}

case "${1:-}" in
  batch)
    exec "$PY" scripts/evaluation/build_annotation_set.py batch \
      --tenant-id "$TENANT_ID" \
      --dataset-id "$DATASET_ID" \
      --top-k 50 \
      --language en \
      "${EXTRA_QUERY_ARGS[@]}"
    ;;
  batch-rebuild)
    exec "$PY" scripts/evaluation/build_annotation_set.py build \
      --tenant-id "$TENANT_ID" \
      --dataset-id "$DATASET_ID" \
      --search-depth 500 \
      --rerank-depth 10000 \
      --reset-artifacts \
      --force-refresh-rerank \
      --force-refresh-labels \
      --language en \
      "${EXTRA_QUERY_ARGS[@]}"
    ;;
  batch-rebuild-resume)
    exec "$PY" scripts/evaluation/build_annotation_set.py build \
      --tenant-id "$TENANT_ID" \
      --dataset-id "$DATASET_ID" \
      --search-depth 500 \
      --rerank-depth 10000 \
      --force-refresh-rerank \
      --force-refresh-labels \
      --resume-missing \
      --continue-on-error \
      --max-retries-per-query "$RETRY_COUNT" \
      --retry-backoff-sec 10 \
      --language en \
      "${EXTRA_QUERY_ARGS[@]}"
    ;;
  serve)
    EVAL_WEB_PORT="${EVAL_WEB_PORT:-6010}"
    EVAL_WEB_HOST="${EVAL_WEB_HOST:-0.0.0.0}"
    exec "$PY" scripts/evaluation/serve_eval_web.py serve \
      --tenant-id "$TENANT_ID" \
      --dataset-id "$DATASET_ID" \
      --host "$EVAL_WEB_HOST" \
      --port "$EVAL_WEB_PORT" \
      "${EXTRA_QUERY_ARGS[@]}"
    ;;
  *)
    usage
    exit 1
    ;;
esac