geointel/scripts/verify_real_data_detection_qa_workflow.sh

#!/usr/bin/env bash
set -euo pipefail

usage() {
  cat >&2 <<'EOF'
Usage:
  REAL_RASTER_PATH=/path/to/orthophoto.tif \
  REAL_REFERENCE_VECTOR_PATH=/path/to/reference-buildings.geojson \
  bash scripts/verify_real_data_detection_qa_workflow.sh [base_url]

or:
  bash scripts/verify_real_data_detection_qa_workflow.sh [base_url] /path/to/orthophoto.tif /path/to/reference-buildings.geojson

Required inputs:
  REAL_RASTER_PATH             Georeferenced .tif/.tiff/.geotiff raster.
  REAL_REFERENCE_VECTOR_PATH   EPSG-aware .geojson/.json reference vector with building polygons.

Optional environment:
  REAL_PROJECT_NAME            Project name for the validation run.
  REAL_PROJECT_REGION          Persisted project region, default: Kempen.
  REAL_PROJECT_ID              Existing project id to reuse instead of creating a validation project.
  REAL_AREA_NAME               Persisted AOI name when REAL_AREA_BBOX is set.
  REAL_AREA_BBOX               Optional EPSG:4326 minx,miny,maxx,maxy AOI bounds.
  REAL_DATASET_NAME_PREFIX     Safe filename prefix for raster/reference uploads in a reused project.
  REAL_MODEL_ASSET_ID          Specific /api/v1/detection/model-assets id to use.
  REAL_TILE_SIZE               Raster tile size, default 640.
  REAL_TILE_OVERLAP            Raster tile overlap, default 64.
  REAL_CONFIDENCE_THRESHOLD    Detection confidence threshold, default 0.5.
  REAL_IOU_THRESHOLD           QA IoU threshold, default 0.5.
EOF
}

BASE_URL="${1:-${GE_INTEL_BASE_URL:-http://localhost:1202}}"
REAL_RASTER_PATH="${2:-${REAL_RASTER_PATH:-}}"
REAL_REFERENCE_VECTOR_PATH="${3:-${REAL_REFERENCE_VECTOR_PATH:-}}"
REAL_PROJECT_NAME="${REAL_PROJECT_NAME:-GeoIntel Real Data Validation}"
REAL_PROJECT_REGION="${REAL_PROJECT_REGION:-Kempen}"
REAL_PROJECT_ID="${REAL_PROJECT_ID:-}"
REAL_AREA_NAME="${REAL_AREA_NAME:-${REAL_PROJECT_NAME} AOI}"
REAL_AREA_BBOX="${REAL_AREA_BBOX:-}"
REAL_DATASET_NAME_PREFIX="${REAL_DATASET_NAME_PREFIX:-}"
REAL_TILE_SIZE="${REAL_TILE_SIZE:-640}"
REAL_TILE_OVERLAP="${REAL_TILE_OVERLAP:-64}"
REAL_CONFIDENCE_THRESHOLD="${REAL_CONFIDENCE_THRESHOLD:-0.5}"
REAL_IOU_THRESHOLD="${REAL_IOU_THRESHOLD:-0.5}"
REAL_MODEL_ASSET_ID="${REAL_MODEL_ASSET_ID:-}"
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "${TMP_DIR}"' EXIT

if [ "${BASE_URL}" = "-h" ] || [ "${BASE_URL}" = "--help" ]; then
  usage
  exit 0
fi

if [ -z "${REAL_RASTER_PATH}" ] || [ -z "${REAL_REFERENCE_VECTOR_PATH}" ]; then
  usage
  exit 2
fi

if [ ! -f "${REAL_RASTER_PATH}" ]; then
  echo "REAL_RASTER_PATH does not point to a readable file: ${REAL_RASTER_PATH}" >&2
  exit 2
fi
if [ ! -f "${REAL_REFERENCE_VECTOR_PATH}" ]; then
  echo "REAL_REFERENCE_VECTOR_PATH does not point to a readable file: ${REAL_REFERENCE_VECTOR_PATH}" >&2
  exit 2
fi

case "${REAL_DATASET_NAME_PREFIX}" in
  *[!a-zA-Z0-9._-]*)
    echo "REAL_DATASET_NAME_PREFIX may contain letters, numbers, dot, underscore and dash only" >&2
    exit 2
    ;;
esac

case "${REAL_RASTER_PATH,,}" in
  *.tif|*.tiff|*.geotiff) ;;
  *)
    echo "REAL_RASTER_PATH must be a .tif, .tiff or .geotiff file for the current V1 raster upload flow." >&2
    exit 2
    ;;
esac

case "${REAL_REFERENCE_VECTOR_PATH,,}" in
  *.geojson|*.json) ;;
  *)
    echo "REAL_REFERENCE_VECTOR_PATH must be .geojson or .json for the current V1 vector upload flow." >&2
    exit 2
    ;;
esac

if ! command -v curl >/dev/null 2>&1; then
  echo "curl is required for real data detection/QA workflow verification" >&2
  exit 1
fi

if [ -n "${PYTHON_BIN:-}" ]; then
  PYTHON_BIN="${PYTHON_BIN}"
else
  PYTHON_BIN=""
  for candidate in python3 python.exe python; do
    if command -v "${candidate}" >/dev/null 2>&1 && "${candidate}" -c "import json, sys" >/dev/null 2>&1; then
      PYTHON_BIN="${candidate}"
      break
    fi
  done
fi

if [ -z "${PYTHON_BIN}" ]; then
  echo "A Python interpreter is required for JSON parsing" >&2
  exit 1
fi

json_field() {
  local file_path="$1"
  local expression="$2"
  "${PYTHON_BIN}" - "$file_path" "$expression" <<'PY'
import json
import sys

path, expression = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as handle:
    payload = json.load(handle)
value = payload
for part in expression.split("."):
    if part:
        value = value[part]
print(value)
PY
}

require_json_data() {
  local file_path="$1"
  "${PYTHON_BIN}" - "$file_path" <<'PY'
import json
import sys

with open(sys.argv[1], "r", encoding="utf-8") as handle:
    payload = json.load(handle)
if "data" not in payload:
    raise SystemExit("Response is not a canonical GeoIntel data envelope")
PY
}

echo "== GeoIntel real data detection + QA workflow verification =="
echo "Base URL: ${BASE_URL}"
echo "Raster: ${REAL_RASTER_PATH}"
echo "Reference vector: ${REAL_REFERENCE_VECTOR_PATH}"

if [ -n "${REAL_PROJECT_ID}" ]; then
  curl -fsS "${BASE_URL%/}/api/v1/projects/${REAL_PROJECT_ID}" > "${TMP_DIR}/project.json"
  require_json_data "${TMP_DIR}/project.json"
  project_id="$(json_field "${TMP_DIR}/project.json" "data.id")"
  if [ "${project_id}" != "${REAL_PROJECT_ID}" ]; then
    echo "Existing project lookup returned the wrong project id" >&2
    exit 1
  fi
else
  "${PYTHON_BIN}" - "${TMP_DIR}/project_request.json" "${REAL_PROJECT_NAME}" "${REAL_PROJECT_REGION}" <<'PY'
import json
import sys
from datetime import datetime, timezone

path, project_name, project_region = sys.argv[1:4]
stamp = datetime.now(timezone.utc).strftime("%Y%m%dT%H%M%SZ")
payload = {
    "name": f"{project_name} {stamp}",
    "description": "Operator-provided real data validation: raster upload, reference vector upload, configured YOLO detection, QA/QC and GeoJSON export.",
    "region": project_region,
}
with open(path, "w", encoding="utf-8") as handle:
    json.dump(payload, handle)
PY

  curl -fsS -X POST "${BASE_URL%/}/api/v1/projects" \
    -H "Content-Type: application/json" \
    --data-binary "@${TMP_DIR}/project_request.json" > "${TMP_DIR}/project.json"
  require_json_data "${TMP_DIR}/project.json"
  project_id="$(json_field "${TMP_DIR}/project.json" "data.id")"
  if [ -z "${project_id}" ] || [ "${project_id}" = "None" ] || [ "${project_id}" = "null" ]; then
    echo "Project creation did not return a project id" >&2
    exit 1
  fi
fi

area_id=""
if [ -n "${REAL_AREA_BBOX}" ]; then
  "${PYTHON_BIN}" - "${TMP_DIR}/area_request.json" "${REAL_AREA_NAME}" "${REAL_AREA_BBOX}" <<'PY'
import json
import sys

path, area_name, bbox_raw = sys.argv[1:4]
try:
    minx, miny, maxx, maxy = [float(value.strip()) for value in bbox_raw.split(",")]
except (TypeError, ValueError) as exc:
    raise SystemExit("REAL_AREA_BBOX must contain four numeric EPSG:4326 values: minx,miny,maxx,maxy") from exc
if minx >= maxx or miny >= maxy:
    raise SystemExit("REAL_AREA_BBOX minimum values must be smaller than maximum values")
if not (-180 <= minx <= 180 and -180 <= maxx <= 180 and -90 <= miny <= 90 and -90 <= maxy <= 90):
    raise SystemExit("REAL_AREA_BBOX is outside EPSG:4326 longitude/latitude bounds")
ring = [[minx, miny], [maxx, miny], [maxx, maxy], [minx, maxy], [minx, miny]]
payload = {
    "name": area_name,
    "crs": "EPSG:4326",
    "geometry": {"type": "MultiPolygon", "coordinates": [[ring]]},
}
with open(path, "w", encoding="utf-8") as handle:
    json.dump(payload, handle)
PY
  curl -fsS -X POST "${BASE_URL%/}/api/v1/projects/${project_id}/areas" \
    -H "Content-Type: application/json" \
    --data-binary "@${TMP_DIR}/area_request.json" > "${TMP_DIR}/area.json"
  require_json_data "${TMP_DIR}/area.json"
  area_id="$(json_field "${TMP_DIR}/area.json" "data.id")"
  if [ -z "${area_id}" ] || [ "${area_id}" = "None" ] || [ "${area_id}" = "null" ]; then
    echo "Area creation did not return an area id" >&2
    exit 1
  fi
fi

area_upload_args=()
if [ -n "${area_id}" ]; then
  area_upload_args=(-F "area_id=${area_id}")
fi

raster_form_file="file=@${REAL_RASTER_PATH}"
reference_form_file="file=@${REAL_REFERENCE_VECTOR_PATH}"
if [ -n "${REAL_DATASET_NAME_PREFIX}" ]; then
  raster_extension="${REAL_RASTER_PATH##*.}"
  reference_extension="${REAL_REFERENCE_VECTOR_PATH##*.}"
  raster_form_file="${raster_form_file};filename=${REAL_DATASET_NAME_PREFIX}_orthophoto.${raster_extension}"
  reference_form_file="${reference_form_file};filename=${REAL_DATASET_NAME_PREFIX}_grb_buildings.${reference_extension}"
fi

curl -fsS -X POST "${BASE_URL%/}/api/v1/projects/${project_id}/datasets/upload" \
  -F "${raster_form_file}" \
  -F "dataset_type=raster" \
  -F "source=user_upload" \
  -F "dataset_role=source" \
  -F "source_name=manual" \
  -F 'source_metadata_json={"validation_workflow":"real_data_detection_qa","input_kind":"orthophoto"}' \
  -F 'provenance_metadata_json={"operator_supplied":true,"no_external_fetch":true}' \
  "${area_upload_args[@]}" \
  > "${TMP_DIR}/raster_upload.json"
require_json_data "${TMP_DIR}/raster_upload.json"
raster_dataset_id="$(json_field "${TMP_DIR}/raster_upload.json" "data.id")"

"${PYTHON_BIN}" - "${TMP_DIR}/raster_upload.json" <<'PY'
import json
import sys

with open(sys.argv[1], "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("dataset_type") != "raster":
    raise SystemExit(f"Uploaded raster returned wrong dataset_type: {data.get('dataset_type')}")
if data.get("status") != "ready":
    raise SystemExit(f"Uploaded raster is not ready: {data.get('status')}")
if not data.get("crs"):
    raise SystemExit("Uploaded raster does not expose CRS metadata; refusing geospatial AI validation")
if not data.get("bounds_json"):
    raise SystemExit("Uploaded raster does not expose bounds metadata; refusing geospatial AI validation")
PY

curl -fsS -X POST "${BASE_URL%/}/api/v1/projects/${project_id}/datasets/upload" \
  -F "${reference_form_file}" \
  -F "dataset_type=vector" \
  -F "source=user_upload" \
  -F "dataset_role=reference" \
  -F "source_name=manual" \
  -F "reference_layer_name=buildings" \
  -F 'source_metadata_json={"validation_workflow":"real_data_detection_qa","input_kind":"reference_buildings"}' \
  -F 'provenance_metadata_json={"operator_supplied":true,"no_external_fetch":true}' \
  "${area_upload_args[@]}" \
  > "${TMP_DIR}/reference_upload.json"
require_json_data "${TMP_DIR}/reference_upload.json"
reference_dataset_id="$(json_field "${TMP_DIR}/reference_upload.json" "data.id")"

"${PYTHON_BIN}" - "${TMP_DIR}/reference_upload.json" <<'PY'
import json
import sys

with open(sys.argv[1], "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("dataset_type") != "vector":
    raise SystemExit(f"Uploaded reference returned wrong dataset_type: {data.get('dataset_type')}")
if data.get("dataset_role") != "reference":
    raise SystemExit("Uploaded reference did not persist dataset_role=reference")
if data.get("reference_layer_name") != "buildings":
    raise SystemExit("Uploaded reference did not persist reference_layer_name=buildings")
if data.get("status") != "ready":
    raise SystemExit(f"Uploaded reference is not ready: {data.get('status')}")
if int(data.get("feature_count") or 0) < 1:
    raise SystemExit("Uploaded reference has no persisted features; QA would be meaningless")
PY

curl -fsS "${BASE_URL%/}/api/v1/projects/${project_id}/datasets/${raster_dataset_id}/raster/inspect" > "${TMP_DIR}/raster_inspect.json"
require_json_data "${TMP_DIR}/raster_inspect.json"
"${PYTHON_BIN}" - "${TMP_DIR}/raster_inspect.json" "${raster_dataset_id}" <<'PY'
import json
import sys

path, raster_id = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("dataset_id") != raster_id:
    raise SystemExit("Raster inspect returned the wrong dataset id")
if data.get("ready") is not True:
    raise SystemExit("Raster inspect did not report ready=true")
metadata = data.get("metadata") or {}
if not metadata.get("crs"):
    raise SystemExit("Raster inspect metadata has no CRS")
if int(metadata.get("width") or 0) < 1 or int(metadata.get("height") or 0) < 1:
    raise SystemExit("Raster inspect metadata has invalid dimensions")
PY

curl -fsS "${BASE_URL%/}/api/v1/projects/${project_id}/datasets/${reference_dataset_id}/vector/summary" > "${TMP_DIR}/reference_summary.json"
require_json_data "${TMP_DIR}/reference_summary.json"
"${PYTHON_BIN}" - "${TMP_DIR}/reference_summary.json" <<'PY'
import json
import sys

with open(sys.argv[1], "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if int(data.get("feature_count") or 0) < 1:
    raise SystemExit("Reference vector summary reports no features")
geometry_types = set(data.get("geometry_types") or [])
if not geometry_types.intersection({"Polygon", "MultiPolygon"}):
    raise SystemExit(f"Reference vector does not expose polygonal building geometries: {sorted(geometry_types)}")
PY

curl -fsS -X POST "${BASE_URL%/}/api/v1/projects/${project_id}/datasets/${raster_dataset_id}/raster/tile" \
  -H "Content-Type: application/json" \
  -d "{\"tile_size\":${REAL_TILE_SIZE},\"overlap\":${REAL_TILE_OVERLAP},\"output_name\":\"real_data_detection_tiles\"}" > "${TMP_DIR}/tile.json"
require_json_data "${TMP_DIR}/tile.json"
manifest_path="$(json_field "${TMP_DIR}/tile.json" "data.result_json.manifest_path")"
if [ -z "${manifest_path}" ] || [ "${manifest_path}" = "None" ] || [ "${manifest_path}" = "null" ]; then
  echo "Raster tile response did not include a manifest_path" >&2
  exit 1
fi
"${PYTHON_BIN}" - "${TMP_DIR}/tile.json" "${raster_dataset_id}" <<'PY'
import json
import sys

path, raster_id = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as handle:
    job = json.load(handle)["data"]
if job.get("job_type") != "raster.tile":
    raise SystemExit(f"Unexpected tile job type: {job.get('job_type')}")
if job.get("status") not in {"success", "completed"}:
    raise SystemExit(f"Raster tile job did not complete: {job.get('status')}")
result = job.get("result_json") or {}
if result.get("dataset_id") != raster_id:
    raise SystemExit("Raster tile result returned the wrong dataset id")
if result.get("ready") is not True:
    raise SystemExit("Raster tile result did not report ready=true")
manifest = result.get("manifest") or {}
tiles = manifest.get("tiles") or []
if not tiles:
    raise SystemExit("Raster tile manifest has no tiles")
if manifest.get("source_dataset_id") != raster_id:
    raise SystemExit("Raster tile manifest source_dataset_id drifted")
PY

curl -fsS "${BASE_URL%/}/api/v1/detection/model-assets" > "${TMP_DIR}/model_assets.json"
require_json_data "${TMP_DIR}/model_assets.json"
model_asset_id="$("${PYTHON_BIN}" - "${TMP_DIR}/model_assets.json" "${REAL_MODEL_ASSET_ID}" <<'PY'
import json
import sys

path, requested = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
items = data.get("items") or []
if not items:
    raise SystemExit("No local model assets are available. Mount a local .pt/.onnx/.engine file before running this smoke.")
for item in items:
    if item.get("will_download_models") is not False:
        raise SystemExit("Model asset catalog must never report automatic model downloads")
if requested:
    matches = [item for item in items if item.get("model_asset_id") == requested]
    if not matches:
        raise SystemExit(f"Requested REAL_MODEL_ASSET_ID was not found: {requested}")
    selected = matches[0]
else:
    selected = next((item for item in items if item.get("active")), items[0])
print(selected["model_asset_id"])
PY
)"

curl -fsS -G "${BASE_URL%/}/api/v1/detection/yolo/preflight" \
  --data-urlencode "tile_manifest_path=${manifest_path}" \
  --data-urlencode "model_asset_id=${model_asset_id}" > "${TMP_DIR}/preflight.json"
require_json_data "${TMP_DIR}/preflight.json"
"${PYTHON_BIN}" - "${TMP_DIR}/preflight.json" "${model_asset_id}" <<'PY'
import json
import sys

path, expected_model_asset_id = sys.argv[1], sys.argv[2]
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("model_asset_id") != expected_model_asset_id:
    raise SystemExit("YOLO preflight did not use the selected model_asset_id")
if data.get("will_download_models") is not False:
    raise SystemExit("YOLO preflight must never download model weights")
if data.get("will_run_inference") is not False:
    raise SystemExit("YOLO preflight must remain read-only")
if data.get("status") != "ready":
    raise SystemExit(f"YOLO preflight is not ready: {data.get('status')} {data.get('message')}")
checks = data.get("checks") or {}
if checks.get("manifest_valid") is not True:
    raise SystemExit("YOLO preflight did not validate the raster tile manifest")
if checks.get("model_file_exists") is not True:
    raise SystemExit("YOLO preflight did not confirm the local model file")
PY

"${PYTHON_BIN}" - "${TMP_DIR}/run_request.json" "${project_id}" "${raster_dataset_id}" "${model_asset_id}" "${manifest_path}" "${REAL_CONFIDENCE_THRESHOLD}" <<'PY'
import json
import sys

path, project_id, dataset_id, model_asset_id, tile_manifest_path, confidence = sys.argv[1:7]
payload = {
    "project_id": project_id,
    "dataset_id": dataset_id,
    "model_id": "yolo-configured",
    "model_asset_id": model_asset_id,
    "confidence_threshold": float(confidence),
    "class_filter": ["building"],
    "tile_manifest_path": tile_manifest_path,
    "parameters_json": {
        "workflow": "real_data_detection_qa",
        "operator_supplied_inputs": True,
    },
}
with open(path, "w", encoding="utf-8") as handle:
    json.dump(payload, handle)
PY

curl -fsS -X POST "${BASE_URL%/}/api/v1/detection/run" \
  -H "Content-Type: application/json" \
  --data-binary "@${TMP_DIR}/run_request.json" > "${TMP_DIR}/detection_run.json"
require_json_data "${TMP_DIR}/detection_run.json"
"${PYTHON_BIN}" - "${TMP_DIR}/detection_run.json" <<'PY'
import json
import sys

with open(sys.argv[1], "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("model_id") != "yolo-configured":
    raise SystemExit("Detection run did not use yolo-configured")
if not data.get("analysis_run_id") or not data.get("job_id"):
    raise SystemExit("Detection run did not return persisted run/job ids")
if data.get("status") != "success":
    raise SystemExit(f"Detection run failed: {data.get('error_code')} {data.get('message')}")
if int(data.get("detection_count") or 0) < 0:
    raise SystemExit("Detection count cannot be negative")
PY
analysis_run_id="$(json_field "${TMP_DIR}/detection_run.json" "data.analysis_run_id")"
detection_count="$(json_field "${TMP_DIR}/detection_run.json" "data.detection_count")"

curl -fsS "${BASE_URL%/}/api/v1/detection/runs/${analysis_run_id}/detections" > "${TMP_DIR}/detections.json"
require_json_data "${TMP_DIR}/detections.json"
"${PYTHON_BIN}" - "${TMP_DIR}/detections.json" "${detection_count}" <<'PY'
import json
import sys

path, expected_count = sys.argv[1], int(sys.argv[2])
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
items = data.get("items") or []
if int(data.get("total") or 0) != expected_count:
    raise SystemExit("Detection list total does not match run detection_count")
if len(items) != expected_count:
    raise SystemExit("Detection list item count does not match run detection_count")
for item in items:
    if not item.get("source_tile_path"):
        raise SystemExit("Persisted detection is missing source_tile_path provenance")
PY

curl -fsS "${BASE_URL%/}/api/v1/detection/runs/${analysis_run_id}/geojson" > "${TMP_DIR}/detection_geojson.json"
require_json_data "${TMP_DIR}/detection_geojson.json"
"${PYTHON_BIN}" - "${TMP_DIR}/detection_geojson.json" "${detection_count}" <<'PY'
import json
import sys

path, expected_count = sys.argv[1], int(sys.argv[2])
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("type") != "FeatureCollection":
    raise SystemExit("Detection GeoJSON response is not a FeatureCollection")
if len(data.get("features") or []) != expected_count:
    raise SystemExit("Detection GeoJSON feature count does not match detection_count")
PY

"${PYTHON_BIN}" - "${TMP_DIR}/qa_request.json" "${reference_dataset_id}" "${REAL_IOU_THRESHOLD}" "${REAL_CONFIDENCE_THRESHOLD}" <<'PY'
import json
import sys

path, reference_dataset_id, iou_threshold, confidence = sys.argv[1:5]
payload = {
    "reference_dataset_id": reference_dataset_id,
    "iou_threshold": float(iou_threshold),
    "class_name": "building",
    "min_confidence": float(confidence),
}
with open(path, "w", encoding="utf-8") as handle:
    json.dump(payload, handle)
PY

curl -fsS -X POST "${BASE_URL%/}/api/v1/detection/runs/${analysis_run_id}/qa/reference" \
  -H "Content-Type: application/json" \
  --data-binary "@${TMP_DIR}/qa_request.json" > "${TMP_DIR}/qa.json"
require_json_data "${TMP_DIR}/qa.json"
"${PYTHON_BIN}" - "${TMP_DIR}/qa.json" "${analysis_run_id}" "${reference_dataset_id}" <<'PY'
import json
import sys

path, analysis_run_id, reference_dataset_id = sys.argv[1:4]
with open(path, "r", encoding="utf-8") as handle:
    data = json.load(handle)["data"]
if data.get("analysis_run_id") != analysis_run_id:
    raise SystemExit("Detection QA returned the wrong analysis_run_id")
if data.get("reference_dataset_id") != reference_dataset_id:
    raise SystemExit("Detection QA returned the wrong reference_dataset_id")
if not data.get("quality_check_id"):
    raise SystemExit("Detection QA did not persist a quality_check_id")
if int(data.get("reference_feature_count") or 0) < 1:
    raise SystemExit("Detection QA reference feature count is empty")
coverage = data.get("coverage") or {}
if coverage.get("applied") is not True:
    raise SystemExit("Detection QA did not apply persisted tile-manifest coverage")
if coverage.get("mode") != "persisted_tile_manifest_union":
    raise SystemExit("Detection QA returned an unexpected coverage mode")
if int(coverage.get("tile_count") or 0) < 1:
    raise SystemExit("Detection QA coverage did not report persisted tiles")
if int(coverage.get("reference_raw_count") or 0) < int(coverage.get("reference_evaluated_count") or 0):
    raise SystemExit("Detection QA evaluated more references than the raw population")
diagnostics = data.get("box_to_footprint_diagnostics") or {}
if diagnostics.get("diagnostic_only") is not True:
    raise SystemExit("Detection QA did not return box-to-footprint diagnostics")
if diagnostics.get("canonical_method") != "candidate_polygon_vs_reference_footprint_iou":
    raise SystemExit("Detection QA canonical matching method changed unexpectedly")
for key in ("matches", "false_positives", "false_negatives"):
    if int(data.get(key) or 0) < 0:
        raise SystemExit(f"Detection QA returned a negative {key}")
PY
quality_check_id="$(json_field "${TMP_DIR}/qa.json" "data.quality_check_id")"

"${PYTHON_BIN}" - "${TMP_DIR}/export_request.json" "${analysis_run_id}" <<'PY'
import json
import sys

path, analysis_run_id = sys.argv[1], sys.argv[2]
payload = {
    "export_kind": "detection_run",
    "analysis_run_id": analysis_run_id,
    "name": "real-data-detection-run",
}
with open(path, "w", encoding="utf-8") as handle:
    json.dump(payload, handle)
PY

curl -fsS -X POST "${BASE_URL%/}/api/v1/exports/geojson" \
  -H "Content-Type: application/json" \
  --data-binary "@${TMP_DIR}/export_request.json" > "${TMP_DIR}/export.json"
require_json_data "${TMP_DIR}/export.json"
export_id="$(json_field "${TMP_DIR}/export.json" "data.export_id")"
if [ -z "${export_id}" ] || [ "${export_id}" = "None" ] || [ "${export_id}" = "null" ]; then
  echo "Detection GeoJSON export did not return an export_id" >&2
  exit 1
fi

curl -fsS "${BASE_URL%/}/api/v1/exports/${export_id}/content" > "${TMP_DIR}/export_content.json"
require_json_data "${TMP_DIR}/export_content.json"
"${PYTHON_BIN}" - "${TMP_DIR}/export_content.json" "${detection_count}" <<'PY'
import json
import sys

path, expected_count = sys.argv[1], int(sys.argv[2])
with open(path, "r", encoding="utf-8") as handle:
    content = json.load(handle)["data"]["content"]
if content.get("type") != "FeatureCollection":
    raise SystemExit("Detection export content is not a FeatureCollection")
if len(content.get("features") or []) != expected_count:
    raise SystemExit("Detection export feature count does not match detection_count")
PY

echo "Real data detection + QA workflow verification passed"
echo "Project: ${project_id}"
echo "Area: ${area_id}"
echo "Raster dataset: ${raster_dataset_id}"
echo "Reference dataset: ${reference_dataset_id}"
echo "Model asset: ${model_asset_id}"
echo "Manifest: ${manifest_path}"
echo "Analysis run: ${analysis_run_id}"
echo "Detections: ${detection_count}"
echo "Quality check: ${quality_check_id}"
echo "Detection export: ${export_id}"