Add local model asset catalog

docs/API_CONTRACTS.md

@@ -636,12 +636,51 @@ Returns object-detection model capability descriptors.
 }
 ```
 
+### GET `/api/v1/detection/model-assets`
+
+Returns local runtime model files discovered in the configured model directory.
+This is a read-only catalog. GeoIntel never downloads, creates, mutates or
+deletes model weights from this endpoint.
+
+The backend scans `YOLO_MODELS_DIR` (default `/app/models`) and reports
+supported local model files such as `.pt`, `.onnx` and `.engine`. The active
+model is the file matching `YOLO_MODEL_PATH`.
+
+Response data:
+
+```json
+{
+  "items": [
+    {
+      "model_asset_id": "building-detector-pt",
+      "filename": "building-detector.pt",
+      "display_name": "building-detector",
+      "model_path": "/app/models/building-detector.pt",
+      "suffix": ".pt",
+      "framework": "ultralytics/pytorch",
+      "task_type": "object_detection",
+      "size_bytes": 123456,
+      "sha256": "sha256hex",
+      "active": true,
+      "status": "available",
+      "limitation_message": "Local runtime model asset. GeoIntel will not download or mutate model weights.",
+      "will_download_models": false
+    }
+  ],
+  "total": 1,
+  "model_directory": "/app/models"
+}
+```
+
 ### GET `/api/v1/detection/yolo/preflight`
 
 Returns a canonical envelope with read-only configured-YOLO runtime preflight
 state. Optional query parameters:
 
 - `tile_manifest_path`: existing raster tile manifest path to validate.
+- `model_asset_id`: optional local model asset ID from
+  `GET /api/v1/detection/model-assets`; when supplied, preflight validates that
+  asset path instead of the default `YOLO_MODEL_PATH`.
 - `check_model_load`: default `false`; when `true`, explicitly loads only the
   configured local model file for compatibility smoke. It never downloads
   weights and never runs inference.
@@ -651,6 +690,7 @@ Response data:
 ```json
 {
   "model_id": "yolo-configured",
+  "model_asset_id": null,
   "model_path": null,
   "tile_manifest_path": null,
   "status": "not_configured",
@@ -693,6 +733,7 @@ Request:
   "project_id": "uuid",
   "dataset_id": "uuid",
   "model_id": "yolo-placeholder",
+  "model_asset_id": null,
   "confidence_threshold": 0.5,
   "class_filter": ["building"],
   "tile_manifest_path": null,
@@ -707,6 +748,12 @@ Sprint 8B configured YOLO mode uses `model_id: "yolo-configured"`. It requires:
 - backend optional AI dependencies installed with `geointel-backend[ai]`
 - `tile_manifest_path` pointing to an existing raster tile manifest generated by the raster tile operation
 
+`model_asset_id` may be supplied with `model_id: "yolo-configured"` to select a
+specific local model file from the read-only model asset catalog. The backend
+resolves the ID to a file inside the configured model directory and persists the
+asset ID, path and SHA-256 in the job and analysis-run parameters for
+reproducibility. Clients must not submit arbitrary model paths.
+
 GeoIntel does not download model weights automatically. Configured YOLO runs read existing tile files from the manifest, convert YOLO pixel-space boxes to EPSG:4326 detection polygons and persist detections as first-class records.
 
 Unavailable model response:
@@ -729,6 +776,7 @@ Validation errors:
 
 - `INVALID_DATASET_TYPE` when the dataset is not raster.
 - `DETECTION_MODEL_NOT_FOUND` when the model id is unknown.
+- `DETECTION_MODEL_ASSET_NOT_FOUND` when `model_asset_id` is not present in the configured model directory.
 - `FIXTURE_MODE_REQUIRED` when `manual-fixture-detector` is requested without `parameters_json.fixture_mode=true`.
 - `DETECTION_TILE_MANIFEST_REQUIRED` when `yolo-configured` is requested without `tile_manifest_path`.
 - `DETECTION_TILE_MANIFEST_NOT_FOUND` when the provided manifest path does not exist.