Add split promotion preflight

scripts/run_split_background_promotion_workflow.sh

@@ -10,7 +10,7 @@ Usage:
   QUALITY_TILE_SIZES="512" \
   QUALITY_TILE_OVERLAPS="64" \
   QUALITY_THRESHOLDS="0.35 0.15" \
-  bash scripts/run_split_background_promotion_workflow.sh [base_url]
+  bash scripts/run_split_background_promotion_workflow.sh [--preflight-only] [base_url]
 
 Optional environment:
   BACKGROUND_SPLIT_OUTPUT_DIR                 Split matrix output directory.
@@ -22,6 +22,7 @@ Optional environment:
   PROMOTION_MAX_BACKGROUND_DETECTIONS_PER_SAMPLE  Default: 0.
   PROMOTION_DEFAULT_POSITIVE_TILE_SIZE        Optional fallback for legacy positive portfolios.
   PROMOTION_DEFAULT_POSITIVE_TILE_OVERLAP     Optional fallback for legacy positive portfolios.
+  GE_INTEL_BASE_URL                           Default base URL when no argument is supplied.
 
 Runs the split background matrix, then builds a split-aware promotion report.
 The pure-empty background summary is the strict default gate. Sparse-context
@@ -35,11 +36,24 @@ EOF
 ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 cd "$ROOT"
 
-BASE_URL="${1:-${GE_INTEL_BASE_URL:-http://localhost:1202}}"
-if [ "${BASE_URL}" = "-h" ] || [ "${BASE_URL}" = "--help" ]; then
-  usage
-  exit 0
-fi
+BASE_URL="${GE_INTEL_BASE_URL:-http://localhost:1202}"
+PREFLIGHT_ONLY=0
+
+while [ "$#" -gt 0 ]; do
+  case "$1" in
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    --preflight-only)
+      PREFLIGHT_ONLY=1
+      ;;
+    *)
+      BASE_URL="$1"
+      ;;
+  esac
+  shift
+done
 
 if [ -z "${PROMOTION_POSITIVE_PORTFOLIO_PATH:-}" ]; then
   echo "PROMOTION_POSITIVE_PORTFOLIO_PATH is required" >&2
@@ -52,6 +66,17 @@ if [ ! -s "${PROMOTION_POSITIVE_PORTFOLIO_PATH}" ]; then
   exit 1
 fi
 
+if [ -z "${OPERATOR_SAMPLE_MANIFEST_PATH:-}" ]; then
+  echo "OPERATOR_SAMPLE_MANIFEST_PATH is required" >&2
+  usage
+  exit 1
+fi
+
+if [ ! -s "${OPERATOR_SAMPLE_MANIFEST_PATH}" ]; then
+  echo "Operator sample manifest is not readable: ${OPERATOR_SAMPLE_MANIFEST_PATH}" >&2
+  exit 1
+fi
+
 if [ -n "${PYTHON_BIN:-}" ]; then
   PYTHON_BIN="${PYTHON_BIN}"
 else
@@ -69,6 +94,49 @@ if [ -z "${PYTHON_BIN}" ]; then
   exit 1
 fi
 
+if ! command -v curl >/dev/null 2>&1; then
+  echo "curl is required for split-background promotion preflight" >&2
+  exit 1
+fi
+
+"${PYTHON_BIN}" - "${OPERATOR_SAMPLE_MANIFEST_PATH}" <<'PY'
+import json
+import sys
+from pathlib import Path
+
+manifest_path = Path(sys.argv[1])
+payload = json.loads(manifest_path.read_text(encoding="utf-8-sig"))
+samples = payload.get("samples") or payload.get("items") or []
+if not isinstance(samples, list) or not samples:
+    raise SystemExit(f"Operator sample manifest has no samples: {manifest_path}")
+
+background_categories = {
+    str(sample.get("background_category") or "")
+    for sample in samples
+    if str(sample.get("sample_role") or "") == "background_candidate"
+}
+missing = {"pure_empty_negative", "sparse_building_context"} - background_categories
+if missing:
+    raise SystemExit(
+        "Operator sample manifest is missing background categories "
+        f"{sorted(missing)}; found {sorted(background_categories)}"
+    )
+PY
+
+api_response="$(curl -fsS "${BASE_URL%/}/api/v1/projects" 2>/dev/null || true)"
+if ! printf '%s' "${api_response}" | grep -q '"data"'; then
+  echo "Runtime API proxy is not reachable or did not return the canonical envelope: ${BASE_URL%/}/api/v1/projects" >&2
+  exit 1
+fi
+
+if [ "${PREFLIGHT_ONLY}" = "1" ]; then
+  echo "Split-background promotion preflight passed"
+  echo "Base URL: ${BASE_URL}"
+  echo "Positive portfolio: ${PROMOTION_POSITIVE_PORTFOLIO_PATH}"
+  echo "Operator sample manifest: ${OPERATOR_SAMPLE_MANIFEST_PATH}"
+  exit 0
+fi
+
 stamp="$(date -u +%Y%m%dT%H%M%SZ)"
 BACKGROUND_SPLIT_OUTPUT_DIR="${BACKGROUND_SPLIT_OUTPUT_DIR:-artifacts/detection-hard-negatives/background-split/${stamp}}"
 PROMOTION_OUTPUT_DIR="${PROMOTION_OUTPUT_DIR:-artifacts/detection-model-promotion/split-aware/${stamp}}"