Unify dataset/tooling scripts into a single dwarf Typer CLI

Replace the five separately-hyphenated uv entry points (steps-to-parquet,
steps-to-parquet-parallel, migrate-geant-steps, bump-dataset-version,
create-root-files) plus the unregistered hparam_scan.py with one `dwarf`
command exposing convert/migrate/bump-gen/bump-schema/status/
update-manifest/create-manifest/make-root/hparam-scan as subcommands.

Each scripts/*.py module now only holds argparse-free business logic;
scripts/dwarf.py wires it up with Typer, matching giant/cli.py's style.
`dwarf convert` merges the old serial/parallel conversion scripts behind
a --jobs flag (default 1: sequential with plain -o; >1: dataset-layout
fan-out via subprocess).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

scripts/migrate_geant_steps.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 """One-time migration of /ceph/lbogner/geant_steps into the versioned layout:
 
     raw/<kind>/<gen>/<detector>/shard-NNN.root
@@ -13,12 +12,13 @@ up pool membership from POOL_ASSIGNMENT — decoupling "where it sits today" fro
 "which pool it belongs to".
 
 Defaults to a dry run (prints the planned moves and manifest contents). Pass
---execute to actually move files and write manifests. Pass --copy as well to
-copy instead of move, leaving the original files in place — e.g. if another
-process is still reading them from their current location.
+execute=True to actually move files and write manifests, and copy=True to copy
+instead of move, leaving the original files in place — e.g. if another process
+is still reading them from their current location.
+
+See `uv run dwarf migrate --help` for the CLI.
 """
 
-import argparse
 import os
 import re
 import shutil
@@ -181,39 +181,18 @@ def plan_manifests(src_root: Path) -> dict[Path, list[str]]:
     }
 
 
-def main() -> None:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "root",
-        nargs="?",
-        default="/ceph/lbogner/geant_steps",
-        help="Dataset root to migrate in place (default: /ceph/lbogner/geant_steps)",
-    )
-    parser.add_argument(
-        "--execute",
-        action="store_true",
-        help="Actually move files and write manifests (default: dry run / print plan only)",
-    )
-    parser.add_argument(
-        "--copy",
-        action="store_true",
-        help="Copy instead of move, leaving the originals in place "
-        "(e.g. if another process is still reading them). Implies the legacy "
-        "train/ etc. directories are left as-is too, since they won't be empty.",
-    )
-    args = parser.parse_args()
-
-    src_root = Path(args.root)
+def run_migration(root: str, execute: bool, copy: bool) -> None:
+    src_root = Path(root)
     if not src_root.is_dir():
-        parser.error(f"{src_root} is not a directory")
+        raise SystemExit(f"error: {src_root} is not a directory")
 
     moves, unrecognized = plan_moves(src_root)
     manifests = plan_manifests(src_root)
 
-    verb = "COPY" if args.copy else "MOVE"
-    print(f"=== {'EXECUTING' if args.execute else 'DRY RUN'} ({verb}): {src_root} ===\n")
+    verb = "COPY" if copy else "MOVE"
+    print(f"=== {'EXECUTING' if execute else 'DRY RUN'} ({verb}): {src_root} ===\n")
 
-    print(f"-- {len(moves)} file {'copy' if args.copy else 'move'}(s) --")
+    print(f"-- {len(moves)} file {'copy' if copy else 'move'}(s) --")
     for src, dst in moves:
         print(f"  {src.relative_to(src_root)}  ->  {dst.relative_to(src_root)}")
 
@@ -228,11 +207,11 @@ def main() -> None:
         for path in unrecognized:
             print(f"  {path.relative_to(src_root)}")
 
-    if not args.execute:
+    if not execute:
         print("\nDry run only — pass --execute to apply.")
         return
 
-    transfer = shutil.copy2 if args.copy else shutil.move
+    transfer = shutil.copy2 if copy else shutil.move
     for src, dst in moves:
         if dst.exists():
             raise FileExistsError(f"refusing to overwrite existing file: {dst}")
@@ -257,7 +236,7 @@ def main() -> None:
     # empty since their contents were classified by filename, not location —
     # remove them, but only if a move actually emptied them. In --copy mode the
     # originals are still there by design, so leave these alone entirely.
-    if not args.copy:
+    if not copy:
         for stale_dir in ("train", "sampling_train/small", "sampling_train"):
             d = src_root / stale_dir
             if d.is_dir() and not any(d.iterdir()):
@@ -265,7 +244,3 @@ def main() -> None:
                 print(f"removed now-empty directory: {d.relative_to(src_root)}")
 
     print("\nDone.")
-
-
-if __name__ == "__main__":
-    main()