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/create_root_files.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 """Generate new ROOT shards by running a minicalosim executable (e.g.
 run_pbwo4, run_sampling) and filing the output into the dataset's raw/ tree:
 
@@ -15,19 +14,11 @@ appear there, and moves it to the next free shard index for that detector
 (existing shards are never overwritten).
 
 --gen must already exist under raw/<kind>/ — create one first with
-bump_dataset_version.py bump-gen.
+`dwarf bump-gen`.
 
-Usage:
-    create_root_files.py --executable build/run_pbwo4 --detector pbwo4 \\
-        --gen gen1 --num-files 4 --events-per-file 10000 --execute
-
-    create_root_files.py --executable build/run_sampling \\
-        --detector sampling_pb_scint:pb_scint \\
-        --detector sampling_fe_scint:fe_scint \\
-        --gen gen1 --num-files 4 --events-per-file 10000 --jobs 8 --execute
+See `uv run dwarf make-root --help` for the CLI.
 """
 
-import argparse
 import os
 import re
 import shutil
@@ -192,78 +183,48 @@ def run_all(
     return results
 
 
-def build_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "--executable", required=True, type=Path, help="Built minicalosim run_* executable"
-    )
-    parser.add_argument(
-        "--detector",
-        action="append",
-        required=True,
-        metavar="NAME[:CONFIG]",
-        help="Dataset detector label, optionally with ':CONFIG' to pass as the "
-        "executable's config-name argument (e.g. sampling_pb_scint:pb_scint). "
-        "Omit ':CONFIG' for executables that take no config selector (e.g. run_pbwo4). "
-        "Repeatable.",
-    )
-    parser.add_argument(
-        "--num-files", type=int, required=True, help="New shards to create per detector"
-    )
-    parser.add_argument(
-        "--events-per-file", type=int, required=True, help="nEvents passed to the executable"
-    )
-    parser.add_argument("--kind", default="steps", help="steps | hits | ... (default: steps)")
-    parser.add_argument("--gen", required=True, help="Existing gen tag under raw/<kind>/, e.g. gen1")
-    parser.add_argument(
-        "--dataset-root",
-        default="/ceph/lbogner/geant_steps",
-        help="Dataset root (default: /ceph/lbogner/geant_steps)",
-    )
-    parser.add_argument(
-        "-j", "--jobs", type=int, default=4, help="Parallel simulation runs (default: 4)"
-    )
-    parser.add_argument(
-        "--execute", action="store_true", help="Actually run jobs (default: dry run / print plan)"
-    )
-    return parser
+def run_make_root(
+    executable: Path,
+    detector: list[str],
+    num_files: int,
+    events_per_file: int,
+    kind: str,
+    gen: str,
+    dataset_root: str,
+    jobs: int,
+    execute: bool,
+) -> None:
+    if jobs < 1:
+        raise SystemExit("error: --jobs must be >= 1")
+    if num_files < 1:
+        raise SystemExit("error: --num-files must be >= 1")
+    if events_per_file < 1:
+        raise SystemExit("error: --events-per-file must be >= 1")
+    if not executable.is_file() or not os.access(executable, os.X_OK):
+        raise SystemExit(f"error: {executable} is not an executable file")
 
-
-def main() -> None:
-    parser = build_parser()
-    args = parser.parse_args()
-
-    if args.jobs < 1:
-        parser.error("--jobs must be >= 1")
-    if args.num_files < 1:
-        parser.error("--num-files must be >= 1")
-    if args.events_per_file < 1:
-        parser.error("--events-per-file must be >= 1")
-    if not args.executable.is_file() or not os.access(args.executable, os.X_OK):
-        parser.error(f"{args.executable} is not an executable file")
-
-    dataset_root = Path(args.dataset_root)
+    dataset_root_path = Path(dataset_root)
     try:
-        jobs = plan_jobs(args.detector, args.num_files, dataset_root, args.kind, args.gen)
+        planned_jobs = plan_jobs(detector, num_files, dataset_root_path, kind, gen)
     except PlanError as exc:
-        parser.error(str(exc))
+        raise SystemExit(f"error: {exc}")
 
-    print(f"=== {'EXECUTING' if args.execute else 'DRY RUN'} ===")
-    print(f"executable: {args.executable}")
-    for job in jobs:
-        cmd = [str(args.executable)] + ([job.config] if job.config else []) + [str(args.events_per_file)]
-        dest = dataset_root / "raw" / args.kind / args.gen / job.detector / f"shard-{job.shard_index:03d}.root"
+    print(f"=== {'EXECUTING' if execute else 'DRY RUN'} ===")
+    print(f"executable: {executable}")
+    for job in planned_jobs:
+        cmd = [str(executable)] + ([job.config] if job.config else []) + [str(events_per_file)]
+        dest = dataset_root_path / "raw" / kind / gen / job.detector / f"shard-{job.shard_index:03d}.root"
         print(f"  {' '.join(cmd)}  ->  {dest}")
 
-    if not args.execute:
+    if not execute:
         print("\nDry run only — pass --execute to apply.")
         return
 
-    tmp_root = dataset_root / ".sim-tmp"
+    tmp_root = dataset_root_path / ".sim-tmp"
     tmp_root.mkdir(parents=True, exist_ok=True)
     results = run_all(
-        jobs, args.executable, args.events_per_file, dataset_root, args.kind, args.gen,
-        max_workers=args.jobs, tmp_root=tmp_root,
+        planned_jobs, executable, events_per_file, dataset_root_path, kind, gen,
+        max_workers=jobs, tmp_root=tmp_root,
     )
     if tmp_root.is_dir() and not any(tmp_root.iterdir()):
         tmp_root.rmdir()
@@ -273,10 +234,6 @@ def main() -> None:
         print(f"\n{len(failures)} of {len(results)} job(s) failed:", file=sys.stderr)
         for r in failures:
             print(f"  {r.job.detector} shard-{r.job.shard_index:03d}: {r.message}", file=sys.stderr)
-        sys.exit(1)
+        raise SystemExit(1)
 
     print(f"\nAll {len(results)} job(s) completed.")
-
-
-if __name__ == "__main__":
-    main()