Add operator YOLO tile dataset exporter

docs/AI_PIPELINES.md

@@ -266,6 +266,25 @@ 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.
 
+If the whole-image dataset underfits or produces unusable detections, export
+overlapping tile-level samples:
+
+```bash
+docker exec -it geointel python3 /app/scripts/export_operator_yolo_tile_dataset.py \
+  --manifest-path /app/storage/operator-data/operator_samples_manifest.json \
+  --output-dir /app/storage/operator-data/yolo-building-tile-dataset \
+  --tile-size 192 \
+  --stride 96 \
+  --negative-keep-ratio 0.5 \
+  --val-samples turnhout \
+  --force
+```
+
+The tile exporter clips reference building boxes into tile-local YOLO labels
+and records the positive/negative tile counts. This gives the training smoke
+more image samples while preserving the same explicit operator-data and QA/QC
+validation boundary.
+
 For visual error inspection, export the persisted QA evidence from a calibration
 summary:
 

docs/CODEX_EXECUTION_LOG.md

@@ -1,3 +1,28 @@
+## Sprint 130 Operator YOLO tile-level dataset tooling (2026-07-07)
+
+Changed:
+- Added `scripts/export_operator_yolo_tile_dataset.py`.
+- The exporter reads `operator_samples_manifest.json`, opens each raster/reference pair, creates overlapping tile windows, clips GRB building bounding boxes into tile-local YOLO labels, writes `dataset.yaml`, and reports `yolo_tile_dataset_summary.json`.
+- Added deterministic negative tile retention through `negative_keep_ratio`.
+- Added readiness compile coverage for the tile exporter.
+- Added regression coverage in `backend/tests/test_sprint130_operator_yolo_tile_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_sprint130_operator_yolo_tile_dataset.py -q` failed while `scripts/export_operator_yolo_tile_dataset.py` did not exist.
+- `python -m pytest backend\tests\test_sprint130_operator_yolo_tile_dataset.py -q` passed.
+- `python scripts\export_operator_yolo_tile_dataset.py --help` passed without requiring local GIS dependencies.
+- `python -m py_compile scripts\export_operator_yolo_tile_dataset.py` passed.
+
+Open:
+- Run the tile exporter inside the AI-enabled Tower runtime, train a local tile-level model, and benchmark it through the existing multi-sample Detection + QA matrix.
+
+Limitations:
+- This remains 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:
+- Export the tile-level dataset on Tower with `tile-size=192`, `stride=96`, train a longer local model, and compare it against the current `yolov8s-building-segmentation-pt` baseline.
+
 ## Sprint 129 Operator YOLO training dataset tooling (2026-07-07)
 
 Changed:

docs/TODO.md

@@ -406,4 +406,6 @@ This file now starts with the current implementation status. Older preparation/b
 - [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.
 - [x] Train/evaluate a small local GeoIntel building-detector smoke from the current operator samples and reject it because QA/QC did not improve.
-- [ ] Build a larger tile-level training dataset with more AOIs, positive/negative tiles and validation splits before the next local model attempt.
+- [x] Add operator-only tile-level YOLO dataset export with overlapping windows and deterministic negative tile retention.
+- [ ] Run tile-level training on Tower and accept/reject the resulting local model through the persisted QA/QC matrix.
+- [ ] Add more AOIs after the tile-level baseline so the next local model attempt is not limited to Geel/Mol/Turnhout.