Added skip logic - Based on random sampling, when disk_space_mb=0, it is safe to entirely skip it

spruce/cli.py

@@ -122,6 +122,17 @@ def parse_args() -> argparse.Namespace:
             "and report how many were re-queued. Run before resuming after a crash."
         ),
     )
+    p.add_argument(
+        "--max-tiles",
+        type=int,
+        default=None,
+        metavar="N",
+        help=(
+            "Download at most N tiles per scan (default: all). "
+            "Pass 1 to probe a single tile — useful for quickly checking "
+            "whether a scan has real imagery or only placeholder responses."
+        ),
+    )
     p.add_argument(
         "--verbose",
         "-v",
@@ -145,6 +156,9 @@ def main() -> None:
     if args.list_scans_first_page_only and not args.list_scans:
         sys.exit("--list-scans-first-page-only requires --list-scans")
 
+    if args.scan_id is not None and args.scan_id <= 0:
+        sys.exit("--scan-id must be a positive integer")
+
     # --list-machines doesn't need credentials
     if args.list_machines:
         base_url = "http://205.149.147.131:8010/"
@@ -270,6 +284,7 @@ def main() -> None:
                 mosaic_only=args.mosaic_only,
                 metadata_only=args.metadata_only,
                 scan_id_filter=args.scan_id,
+                max_tiles=args.max_tiles,
             )
             totals.merge(stats)
     finally:
@@ -331,6 +346,22 @@ def _print_summary(
                 )
         if not metadata_only and not mosaic_only:
             log.info(row("Tiles downloaded:", str(totals.tiles_downloaded)))
+            if totals.scans_probe_skipped:
+                log.info(
+                    row(
+                        "Probe-skipped scans:",
+                        str(totals.scans_probe_skipped),
+                        "probe tile was 404 or placeholder; tile pool skipped",
+                    )
+                )
+        if not metadata_only and totals.scans_disk_space_skipped:
+            log.info(
+                row(
+                    "Zero-disk-space skipped:",
+                    str(totals.scans_disk_space_skipped),
+                    "disk_space_mb=0; mosaic and tiles not attempted",
+                )
+            )
         if not dry_run and not metadata_only:
             log.info(
                 row(