Harden split background promotion preflight

CHANGELOG.md

@@ -18,6 +18,7 @@
 
 - Added `--preflight-only` to `scripts/run_split_background_promotion_workflow.sh`.
 - Preflight validates local positive portfolio and operator manifest files, confirms required `pure_empty_negative` and `sparse_building_context` background categories, checks Python/curl availability and verifies the runtime API proxy returns the canonical envelope.
+- Hardened preflight compatibility for older operator manifests by deriving missing background categories from `reference_feature_count`, matching the existing matrix-runner behavior.
 - Documented the quick post-redeploy preflight command before starting long configured-YOLO matrix inference.
 - No model default, backend API, database migration, provider fetching, fake detection output or model download behavior changed.
 

backend/tests/test_sprint159_split_promotion_workflow.py

@@ -1,11 +1,32 @@
 from __future__ import annotations
 
+import json
+import os
+import shlex
+import subprocess
 from pathlib import Path
 
 
 ROOT = Path(__file__).resolve().parents[2]
 
 
+def _bash_path(path: Path) -> str:
+    raw_path = str(path)
+    if os.name != "nt":
+        return raw_path
+
+    result = subprocess.run(
+        ["bash", "-lc", f"wslpath -a {shlex.quote(raw_path)}"],
+        capture_output=True,
+        text=True,
+        timeout=10,
+        check=False,
+    )
+    if result.returncode == 0 and result.stdout.strip():
+        return result.stdout.strip()
+    return raw_path
+
+
 def test_split_background_promotion_workflow_runs_split_then_split_aware_report() -> None:
     script_path = ROOT / "scripts" / "run_split_background_promotion_workflow.sh"
     assert script_path.exists()
@@ -35,6 +56,54 @@ def test_split_background_promotion_workflow_has_safe_preflight_mode() -> None:
     assert "Split-background promotion preflight passed" in source
 
 
+def test_split_background_preflight_derives_missing_background_categories(tmp_path: Path) -> None:
+    positive_portfolio = tmp_path / "positive.json"
+    positive_portfolio.write_text('{"items":[]}', encoding="utf-8")
+    manifest = tmp_path / "operator_samples_manifest.json"
+    manifest.write_text(
+        json.dumps(
+            {
+                "samples": [
+                    {
+                        "sample_slug": "postel_bos",
+                        "sample_role": "background_candidate",
+                        "reference_feature_count": 0,
+                    },
+                    {
+                        "sample_slug": "kasterlee_bos",
+                        "sample_role": "background_candidate",
+                        "reference_feature_count": 7,
+                    },
+                ]
+            }
+        ),
+        encoding="utf-8",
+    )
+
+    api_root = tmp_path / "api-root"
+    projects_endpoint = api_root / "api" / "v1" / "projects"
+    projects_endpoint.parent.mkdir(parents=True)
+    projects_endpoint.write_text('{"data":{"items":[]}}', encoding="utf-8")
+
+    command = (
+        f"PROMOTION_POSITIVE_PORTFOLIO_PATH={shlex.quote(_bash_path(positive_portfolio))} "
+        f"OPERATOR_SAMPLE_MANIFEST_PATH={shlex.quote(_bash_path(manifest))} "
+        f"bash scripts/run_split_background_promotion_workflow.sh --preflight-only "
+        f"{shlex.quote(f'file://{_bash_path(api_root)}')}"
+    )
+    result = subprocess.run(
+        ["bash", "-lc", command],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        timeout=30,
+        check=False,
+    )
+
+    assert result.returncode == 0, result.stderr
+    assert "Split-background promotion preflight passed" in result.stdout
+
+
 def test_readiness_checks_split_background_promotion_workflow_syntax() -> None:
     readiness = (ROOT / "scripts" / "run_readiness_check.sh").read_text(encoding="utf-8")
 

docs/AI_PIPELINES.md

@@ -301,6 +301,11 @@ For a quick post-redeploy check before the long matrix starts, use
 checks local paths, required background categories and the runtime API envelope
 without running inference:
 
+Legacy operator manifests that do not yet contain explicit `background_category`
+remain supported: the preflight derives `pure_empty_negative` from
+`reference_feature_count == 0` and `sparse_building_context` from background
+samples with persisted reference features, matching the matrix runner.
+
 ```bash
 PROMOTION_POSITIVE_PORTFOLIO_PATH=artifacts/detection-quality-matrix/multi-sample/aoi1024bg512r3e50-positive/multi_sample_quality_summary.json \
 OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \

scripts/README.md

@@ -724,6 +724,11 @@ presence, required `pure_empty_negative` and `sparse_building_context`
 background categories, Python/curl availability and the frontend API proxy
 envelope without starting inference:
 
+For older operator manifests that predate explicit `background_category`,
+preflight uses the same fallback as the matrix runner: background samples with
+`reference_feature_count == 0` are treated as `pure_empty_negative`, and
+background samples with references are treated as `sparse_building_context`.
+
 ```bash
 PROMOTION_POSITIVE_PORTFOLIO_PATH=/mnt/user/appdata/geointel/artifacts/detection-quality-matrix/multi-sample/aoi1024bg512r3e50-positive/multi_sample_quality_summary.json \
 OPERATOR_SAMPLE_MANIFEST_PATH=storage/operator-data/operator_samples_manifest.json \

scripts/run_split_background_promotion_workflow.sh

@@ -110,11 +110,24 @@ 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 = {
+background_categories = set()
-    str(sample.get("background_category") or "")
+for sample in samples:
-    for sample in samples
+    if str(sample.get("sample_role") or "") != "background_candidate":
-    if str(sample.get("sample_role") or "") == "background_candidate"
+        continue
-}
+
+    category = str(sample.get("background_category") or "").strip()
+    if not category:
+        try:
+            reference_feature_count = int(sample.get("reference_feature_count") or 0)
+        except (TypeError, ValueError):
+            reference_feature_count = 0
+        category = (
+            "pure_empty_negative"
+            if reference_feature_count == 0
+            else "sparse_building_context"
+        )
+
+    background_categories.add(category)
 missing = {"pure_empty_negative", "sparse_building_context"} - background_categories
 if missing:
     raise SystemExit(