Add detection calibration sweep

CHANGELOG.md

@@ -7,6 +7,13 @@
 
 # Changelog
 
+## Sprint 124 Detection calibration sweep tooling (2026-07-07)
+
+- Added `scripts/run_detection_calibration_sweep.sh` to run the existing real-data detection + QA workflow across multiple configured-YOLO confidence thresholds.
+- The sweep writes per-threshold logs and a `calibration_summary.json` with persisted detection count, QA score, precision, recall, F1, mean IoU, matches, false positives and false negatives.
+- Added readiness syntax coverage and static regression coverage for the calibration sweep contract.
+- No new model dependencies, provider fetching, fake detections, API contracts or product UI behavior were introduced.
+
 ## Sprint 123 YOLO class and tile CRS normalization (2026-07-07)
 
 - Fixed configured-YOLO class filtering so model labels such as `Building` match operator/domain filters such as `building`.

backend/README.md

@@ -374,6 +374,21 @@ manifests generated for AI handoff include source CRS metadata so pixel-space
 model outputs can be transformed to WGS84 GeoJSON coordinates. Current V1 upload
 support is limited to GeoTIFF-style rasters and GeoJSON/JSON reference vectors.
 
+For model-quality calibration, run the confidence sweep wrapper:
+
+```bash
+REAL_RASTER_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_orthophoto_wms_512.tif \
+REAL_REFERENCE_VECTOR_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_grb_gbg_buildings.geojson \
+CALIBRATION_THRESHOLDS="0.50 0.35 0.25 0.15" \
+bash scripts/run_detection_calibration_sweep.sh http://192.168.10.150:1202
+```
+
+The sweep creates one real persisted workflow run per threshold, fetches the
+persisted `QualityCheck`/`Metric` rows and writes a `calibration_summary.json`
+with detection count, score, precision, recall, F1, mean IoU and false
+positive/negative counts. It is intended to tune confidence/IoU/model choices,
+not to add new inference behavior.
+
 ### Run backend
 
 ```bash

backend/tests/test_sprint124_detection_calibration_sweep.py

@@ -0,0 +1,29 @@
+from pathlib import Path
+
+
+ROOT = Path(__file__).resolve().parents[2]
+
+
+def test_detection_calibration_sweep_reuses_real_data_workflow_and_reports_qa_metrics() -> None:
+    script_path = ROOT / "scripts" / "run_detection_calibration_sweep.sh"
+    readiness = (ROOT / "scripts" / "run_readiness_check.sh").read_text(encoding="utf-8")
+
+    assert script_path.exists()
+    script = script_path.read_text(encoding="utf-8")
+
+    assert "bash -n scripts/run_detection_calibration_sweep.sh" in readiness
+    assert "verify_real_data_detection_qa_workflow.sh" in script
+    assert "CALIBRATION_THRESHOLDS" in script
+    assert "REAL_CONFIDENCE_THRESHOLD" in script
+    assert "REAL_RASTER_PATH" in script
+    assert "REAL_REFERENCE_VECTOR_PATH" in script
+    assert "/api/v1/projects/${project_id}/quality-checks" in script
+    assert "quality_check_id" in script
+    assert "false_positives" in script
+    assert "false_negatives" in script
+    assert "quality_score" in script
+    assert "best_by_score" in script
+    assert "calibration_summary.json" in script
+    assert "demo/workflow" not in script
+    assert "fixture_mode" not in script
+    assert "will_download_models" not in script

docs/AI_PIPELINES.md

@@ -167,6 +167,21 @@ download model weights. A zero detection count is valid as runtime evidence only
 when the selected model genuinely returns no usable detections after canonical
 class filtering; it does not prove the model is useful for the target imagery.
 
+For confidence-threshold calibration, use the sweep wrapper:
+
+```bash
+REAL_RASTER_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_orthophoto_wms_512.tif \
+REAL_REFERENCE_VECTOR_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_grb_gbg_buildings.geojson \
+CALIBRATION_THRESHOLDS="0.50 0.35 0.25 0.15" \
+bash scripts/run_detection_calibration_sweep.sh http://192.168.10.150:1202
+```
+
+The sweep runs the real-data workflow once per threshold and then reads the
+persisted project quality-check list to build `calibration_summary.json`.
+Results are honest QA/QC evidence from persisted detections and persisted
+reference `vector_features`; no demo detections, live provider fetches or model
+downloads are introduced by the calibration tool.
+
 ### Sprint 8C detection visualization and QA status
 
 Sprint 8C makes persisted detections reviewable:

docs/CODEX_EXECUTION_LOG.md

@@ -1,3 +1,30 @@
+## Sprint 124 Detection calibration sweep tooling (2026-07-07)
+
+Changed:
+- Added `scripts/run_detection_calibration_sweep.sh` as an operator-facing confidence-threshold sweep for the configured-YOLO real-data path.
+- The sweep reuses `scripts/verify_real_data_detection_qa_workflow.sh` once per threshold, so each row is backed by persisted Project, Dataset, AnalysisRun, Detection, QualityCheck, Metric and export records.
+- The sweep fetches project `quality-checks` after each run and writes per-threshold summaries plus `calibration_summary.json` with detection count, QA score, precision, recall, F1, mean IoU, matches, false positives and false negatives.
+- Registered the sweep in `scripts/run_readiness_check.sh` as a syntax check.
+- Added regression coverage in `backend/tests/test_sprint124_detection_calibration_sweep.py`.
+- Updated `scripts/README.md`, `backend/README.md`, `docs/AI_PIPELINES.md`, `docs/TODO.md` and `CHANGELOG.md`.
+
+Validation:
+- RED: `python -m pytest backend/tests/test_sprint124_detection_calibration_sweep.py -q` failed because `scripts/run_detection_calibration_sweep.sh` did not exist.
+- `python -m pytest backend/tests/test_sprint124_detection_calibration_sweep.py -q` passed.
+- `bash -n scripts/run_detection_calibration_sweep.sh` passed.
+- `bash scripts/run_detection_calibration_sweep.sh --help` passed.
+- Missing-input guard printed usage and did not start a live workflow.
+
+Open:
+- Run the sweep on Tower with the Geel operator sample and record the observed threshold metrics.
+
+Limitations:
+- The sweep is intentionally mutating and creates one real workflow run per threshold.
+- It is calibration tooling only; it does not change inference, add model downloads, fetch providers, seed demo detections or change API/UI behavior.
+
+Next recommended pass:
+- Run the Tower sweep for the current Geel sample, then repeat on additional operator-provided orthophoto/reference samples before choosing V1 default confidence/IoU guidance.
+
 ## Sprint 123 YOLO class and tile CRS normalization (2026-07-07)
 
 Changed:

docs/TODO.md

@@ -95,6 +95,7 @@ This file now starts with the current implementation status. Older preparation/b
 - [x] Validate the configured building model on a real georeferenced Kempen orthophoto/GeoTIFF with persisted reference vectors and QA/QC metrics.
 - [x] Fix configured-YOLO mixed-case class labels so `Building` model output matches `building` domain filters.
 - [x] Persist CRS metadata in raster tile manifests so AI detections can be transformed to WGS84 GeoJSON correctly.
+- [x] Add real-data detection calibration sweep tooling for confidence-threshold and QA/QC metric comparison.
 - [ ] Calibrate confidence, IoU and model selection against persisted Geel detections and additional local orthophoto/reference samples.
 
 ## Sprint 8 status

scripts/README.md

@@ -189,6 +189,24 @@ operationally only when the selected model genuinely returns no usable
 detections after class filtering; it must be interpreted as model/data quality
 evidence rather than as a successful building extraction result.
 
+Run a confidence-threshold calibration sweep against the same real-data path:
+
+```bash
+REAL_RASTER_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_orthophoto_wms_512.tif \
+REAL_REFERENCE_VECTOR_PATH=/mnt/user/appdata/geointel/storage/operator-data/geel_grb_gbg_buildings.geojson \
+CALIBRATION_THRESHOLDS="0.50 0.35 0.25 0.15" \
+bash scripts/run_detection_calibration_sweep.sh http://192.168.10.150:1202
+```
+
+The sweep reuses `verify_real_data_detection_qa_workflow.sh` once per
+threshold, so every row is backed by persisted Project, Dataset, AnalysisRun,
+Detection, QualityCheck, Metric and export records. It writes per-threshold
+logs plus `calibration_summary.json` under
+`artifacts/detection-calibration/<timestamp>` unless
+`CALIBRATION_OUTPUT_DIR` is set. This is a calibration/benchmarking tool only:
+it does not seed demo data, enable fixture detections, fetch external data or
+download model weights.
+
 Docker images install only the GIS runtime by default. To build a local/Tower
 image with PyTorch/Ultralytics available for the configured-YOLO preflight and
 runtime path, set:

scripts/run_detection_calibration_sweep.sh

@@ -0,0 +1,235 @@
+#!/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 \
+  CALIBRATION_THRESHOLDS="0.50 0.35 0.25 0.15" \
+  bash scripts/run_detection_calibration_sweep.sh [base_url]
+
+or:
+  bash scripts/run_detection_calibration_sweep.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:
+  CALIBRATION_THRESHOLDS       Space/comma separated confidence thresholds, default: 0.50 0.35 0.25 0.15.
+  CALIBRATION_OUTPUT_DIR       Output directory, default: artifacts/detection-calibration/<timestamp>.
+  REAL_MODEL_ASSET_ID          Specific /api/v1/detection/model-assets id to use.
+  REAL_TILE_SIZE               Raster tile size passed to the underlying real-data workflow.
+  REAL_TILE_OVERLAP            Raster tile overlap passed to the underlying real-data workflow.
+  REAL_IOU_THRESHOLD           QA IoU threshold, default inherited by the underlying workflow.
+EOF
+}
+
+ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+cd "$ROOT"
+
+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:-}}"
+CALIBRATION_THRESHOLDS="${CALIBRATION_THRESHOLDS:-0.50 0.35 0.25 0.15}"
+CALIBRATION_OUTPUT_DIR="${CALIBRATION_OUTPUT_DIR:-artifacts/detection-calibration/$(date -u +%Y%m%dT%H%M%SZ)}"
+
+if [ "${BASE_URL}" = "-h" ] || [ "${BASE_URL}" = "--help" ]; then
+  usage
+  exit 0
+fi
+
+if [ -z "${REAL_RASTER_PATH}" ] || [ -z "${REAL_REFERENCE_VECTOR_PATH}" ]; then
+  usage
+  exit 2
+fi
+
+if ! command -v curl >/dev/null 2>&1; then
+  echo "curl is required for detection calibration sweep verification" >&2
+  exit 1
+fi
+
+if [ -n "${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 "${PYTHON_BIN}" ]; then
+  echo "A Python interpreter is required for JSON parsing" >&2
+  exit 1
+fi
+
+thresholds_normalized="$(printf '%s' "${CALIBRATION_THRESHOLDS}" | tr ',' ' ')"
+mkdir -p "${CALIBRATION_OUTPUT_DIR}"
+
+"${PYTHON_BIN}" - "${thresholds_normalized}" <<'PY'
+import sys
+
+raw = sys.argv[1].split()
+if not raw:
+    raise SystemExit("CALIBRATION_THRESHOLDS must contain at least one threshold")
+for value in raw:
+    try:
+        threshold = float(value)
+    except ValueError as exc:
+        raise SystemExit(f"Invalid confidence threshold: {value}") from exc
+    if threshold < 0.0 or threshold > 1.0:
+        raise SystemExit(f"Confidence threshold must be between 0 and 1: {value}")
+PY
+
+echo "== GeoIntel detection calibration sweep =="
+echo "Base URL: ${BASE_URL}"
+echo "Raster: ${REAL_RASTER_PATH}"
+echo "Reference vector: ${REAL_REFERENCE_VECTOR_PATH}"
+echo "Thresholds: ${thresholds_normalized}"
+echo "Output: ${CALIBRATION_OUTPUT_DIR}"
+
+run_index=0
+for threshold in ${thresholds_normalized}; do
+  run_index=$((run_index + 1))
+  threshold_label="$(printf '%s' "${threshold}" | tr '.-' 'pm')"
+  run_log="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}.log"
+  quality_response="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}_quality_checks.json"
+  run_summary="${CALIBRATION_OUTPUT_DIR}/threshold_${threshold_label}_summary.json"
+
+  echo "-- Threshold ${threshold} (${run_index}) --"
+  if ! REAL_PROJECT_NAME="GeoIntel Detection Calibration ${threshold}" \
+      REAL_CONFIDENCE_THRESHOLD="${threshold}" \
+      bash scripts/verify_real_data_detection_qa_workflow.sh "${BASE_URL}" "${REAL_RASTER_PATH}" "${REAL_REFERENCE_VECTOR_PATH}" \
+      >"${run_log}" 2>&1; then
+    echo "Calibration threshold ${threshold} failed. Log: ${run_log}" >&2
+    tail -n 80 "${run_log}" >&2 || true
+    exit 1
+  fi
+
+  project_id="$(sed -n 's/^Project: //p' "${run_log}" | tail -n 1)"
+  analysis_run_id="$(sed -n 's/^Analysis run: //p' "${run_log}" | tail -n 1)"
+  quality_check_id="$(sed -n 's/^Quality check: //p' "${run_log}" | tail -n 1)"
+  detection_count="$(sed -n 's/^Detections: //p' "${run_log}" | tail -n 1)"
+
+  if [ -z "${project_id}" ] || [ -z "${analysis_run_id}" ] || [ -z "${quality_check_id}" ]; then
+    echo "Calibration threshold ${threshold} did not print project/run/quality ids. Log: ${run_log}" >&2
+    exit 1
+  fi
+
+  curl -fsS "${BASE_URL%/}/api/v1/projects/${project_id}/quality-checks?limit=200" > "${quality_response}"
+
+  "${PYTHON_BIN}" - \
+    "${quality_response}" \
+    "${run_summary}" \
+    "${threshold}" \
+    "${project_id}" \
+    "${analysis_run_id}" \
+    "${quality_check_id}" \
+    "${detection_count}" \
+    "${run_log}" <<'PY'
+import json
+import sys
+
+quality_path, output_path, threshold, project_id, analysis_run_id, quality_check_id, detection_count, run_log = sys.argv[1:9]
+with open(quality_path, "r", encoding="utf-8") as handle:
+    payload = json.load(handle)
+if "data" not in payload:
+    raise SystemExit("Quality-check list is not a canonical GeoIntel data envelope")
+items = payload["data"].get("items") or []
+quality_check = next((item for item in items if str(item.get("id")) == quality_check_id), None)
+if quality_check is None:
+    raise SystemExit(f"Quality check not found in project list: {quality_check_id}")
+metrics = {
+    metric.get("metric_key"): metric.get("metric_value")
+    for metric in quality_check.get("metrics", [])
+    if metric.get("metric_key")
+}
+findings = quality_check.get("findings_json") or {}
+summary = {
+    "threshold": float(threshold),
+    "project_id": project_id,
+    "analysis_run_id": analysis_run_id,
+    "quality_check_id": quality_check_id,
+    "detection_count": int(detection_count),
+    "quality_status": quality_check.get("status"),
+    "quality_score": quality_check.get("score"),
+    "precision": metrics.get("precision"),
+    "recall": metrics.get("recall"),
+    "f1_score": metrics.get("f1_score"),
+    "mean_iou": metrics.get("mean_iou"),
+    "matches": findings.get("matches"),
+    "false_positives": findings.get("false_positives"),
+    "false_negatives": findings.get("false_negatives"),
+    "run_log": run_log,
+}
+with open(output_path, "w", encoding="utf-8") as handle:
+    json.dump(summary, handle, indent=2, sort_keys=True)
+print(
+    "threshold={threshold} detections={detections} score={score} "
+    "precision={precision} recall={recall} f1={f1} matches={matches} fp={fp} fn={fn}".format(
+        threshold=summary["threshold"],
+        detections=summary["detection_count"],
+        score=summary["quality_score"],
+        precision=summary["precision"],
+        recall=summary["recall"],
+        f1=summary["f1_score"],
+        matches=summary["matches"],
+        fp=summary["false_positives"],
+        fn=summary["false_negatives"],
+    )
+)
+PY
+done
+
+"${PYTHON_BIN}" - "${CALIBRATION_OUTPUT_DIR}" "${BASE_URL}" "${thresholds_normalized}" <<'PY'
+import glob
+import json
+import os
+import sys
+from datetime import datetime, timezone
+
+output_dir, base_url, thresholds = sys.argv[1:4]
+items = []
+for path in sorted(glob.glob(os.path.join(output_dir, "threshold_*_summary.json"))):
+    with open(path, "r", encoding="utf-8") as handle:
+        items.append(json.load(handle))
+
+ranked = [
+    item
+    for item in items
+    if item.get("quality_score") is not None
+]
+best_by_score = max(ranked, key=lambda item: item["quality_score"], default=None)
+summary = {
+    "generated_at": datetime.now(timezone.utc).isoformat(),
+    "base_url": base_url,
+    "thresholds": [float(value) for value in thresholds.split()],
+    "best_by_score": best_by_score,
+    "items": items,
+}
+summary_path = os.path.join(output_dir, "calibration_summary.json")
+with open(summary_path, "w", encoding="utf-8") as handle:
+    json.dump(summary, handle, indent=2, sort_keys=True)
+
+print("")
+print("Detection calibration summary")
+print("threshold\tdetections\tscore\tprecision\trecall\tf1\tmatches\tfp\tfn")
+for item in items:
+    print(
+        "{threshold:.2f}\t{detection_count}\t{quality_score}\t{precision}\t{recall}\t{f1_score}\t{matches}\t{false_positives}\t{false_negatives}".format(
+            **item
+        )
+    )
+print("")
+print(f"Summary: {summary_path}")
+if best_by_score:
+    print(
+        "best_by_score threshold={threshold:.2f} score={quality_score} f1={f1_score} detections={detection_count}".format(
+            **best_by_score
+        )
+    )
+PY

scripts/run_readiness_check.sh

@@ -55,6 +55,7 @@ bash -n scripts/verify_demo_raster_workflow.sh
 bash -n scripts/verify_ai_handoff_interactions.sh
 bash -n scripts/verify_model_asset_detection_workflow.sh
 bash -n scripts/verify_real_data_detection_qa_workflow.sh
+bash -n scripts/run_detection_calibration_sweep.sh
 bash -n scripts/verify_workbench_default_state.sh
 bash -n scripts/verify_workbench_interactions.sh
 bash -n scripts/verify_gis_runtime.sh