Add operator YOLO training dataset tooling

docs/AI_PIPELINES.md

@@ -229,6 +229,42 @@ The multi-sample summary exposes `best_overall_by_score`,
 model-quality decisions are based on repeated persisted QA/QC evidence rather
 than one AOI.
 
+When repeated public model benchmarks remain too weak, the operator can convert
+the prepared real-data samples into a local YOLO training dataset:
+
+```bash
+docker exec -it geointel python /app/scripts/export_operator_yolo_dataset.py \
+  --manifest-path /app/storage/operator-data/operator_samples_manifest.json \
+  --output-dir /app/storage/operator-data/yolo-building-dataset \
+  --val-samples turnhout \
+  --force
+```
+
+The exporter creates a standard YOLO detection layout with `dataset.yaml`,
+`images/train`, `labels/train`, `images/val` and `labels/val`. It converts GRB
+building reference geometries to pixel-space bounding boxes for the matching
+orthophoto sample and records `yolo_dataset_summary.json`.
+
+A minimal local training smoke can then be run explicitly in an AI-enabled
+runtime:
+
+```bash
+docker exec \
+  -e OPERATOR_YOLO_DATASET_DIR=/app/storage/operator-data/yolo-building-dataset \
+  -e YOLO_BASE_MODEL_PATH=/app/models/yolov8n.pt \
+  -e TRAIN_MODEL_OUTPUT_PATH=/app/models/geointel-building-detector.pt \
+  -e TRAIN_EPOCHS=8 \
+  -e TRAIN_IMGSZ=512 \
+  -e TRAIN_BATCH=2 \
+  -e TRAIN_WORKERS=0 \
+  -e TRAIN_DEVICE=cpu \
+  geointel bash /app/scripts/train_operator_yolo_detector.sh
+```
+
+This remains operator tooling only. GeoIntel does not expose Training Studio in
+V1, does not generate labels from predictions and does not treat the trained
+artifact as useful until it passes the same real-data Detection + QA matrix.
+
 For visual error inspection, export the persisted QA evidence from a calibration
 summary:
 

docs/CODEX_EXECUTION_LOG.md

@@ -1,3 +1,35 @@
+## Sprint 129 Operator YOLO training dataset tooling (2026-07-07)
+
+Changed:
+- Added `scripts/export_operator_yolo_dataset.py` to export prepared operator samples into a local YOLO detection dataset:
+  - input manifest: `operator_samples_manifest.json`
+  - output: `dataset.yaml`, `images/train`, `labels/train`, `images/val`, `labels/val`, `yolo_dataset_summary.json`
+  - labels are derived from GRB building references with `source_name=grb` and `reference_layer_name=buildings`.
+- Added `scripts/train_operator_yolo_detector.sh` as an explicit operator/runtime wrapper around a local Ultralytics training smoke:
+  - requires `OPERATOR_YOLO_DATASET_DIR`
+  - requires an existing `YOLO_BASE_MODEL_PATH`
+  - writes a local `TRAIN_MODEL_OUTPUT_PATH`
+  - writes `training_summary.json`.
+- Added readiness coverage for exporter compile and train-wrapper shell syntax.
+- Added regression coverage in `backend/tests/test_sprint129_operator_yolo_training_dataset.py`.
+- Updated `scripts/README.md`, `backend/README.md`, `docs/AI_PIPELINES.md`, `docs/TODO.md` and `CHANGELOG.md`.
+
+Tested:
+- RED: `python -m pytest backend\tests\test_sprint129_operator_yolo_training_dataset.py -q` failed while the exporter and training wrapper contracts were incomplete.
+- `python -m pytest backend\tests\test_sprint129_operator_yolo_training_dataset.py -q` passed.
+- `python scripts\export_operator_yolo_dataset.py --help` passed without requiring local GIS dependencies.
+- `python -m py_compile scripts\export_operator_yolo_dataset.py` passed.
+- `bash -n scripts/train_operator_yolo_detector.sh` passed.
+
+Open:
+- Run the exporter and training smoke inside the AI-enabled Tower runtime, then benchmark the trained artifact through the existing multi-sample Detection + QA matrix.
+
+Limitations:
+- This is operator tooling only. It does not add Training Studio, browser training controls, provider fetching, fake detections, model auto-provisioning or API contract changes.
+
+Next recommended pass:
+- Generate the local YOLO dataset from the current Geel/Mol/Turnhout samples, train a small local model smoke from `yolov8n.pt`, and compare it against the current `yolov8s-building-segmentation-pt` benchmark.
+
 ## Sprint 128 Stronger building model runtime benchmark (2026-07-07)
 
 Changed:

docs/TODO.md

@@ -404,3 +404,5 @@ This file now starts with the current implementation status. Older preparation/b
 - [x] Render persisted QA/QC feature-level evidence as Map workspace overlays.
 - [x] Add safe local YOLO model env configuration helper for Unraid/Tower runtime activation.
 - [x] Harden configured YOLO inference for single-band raster tiles and wrapped runtime errors.
+- [x] Add operator-only YOLO dataset export and local training-smoke wrapper for real sample calibration.
+- [ ] Train/evaluate a local GeoIntel building detector from the operator samples and only activate it after QA/QC matrix improvement.