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>

tests/test_create_root_files.py

@@ -244,24 +244,3 @@ def test_run_all_caps_concurrency(tmp_path):
         concurrent += delta
         peak = max(peak, concurrent)
     assert peak <= 2
-
-
-def test_build_parser_defaults():
-    args = create_root_files.build_parser().parse_args(
-        [
-            "--executable",
-            "fake",
-            "--detector",
-            "pbwo4",
-            "--num-files",
-            "2",
-            "--events-per-file",
-            "10000",
-            "--gen",
-            "gen1",
-        ]
-    )
-    assert args.jobs == 4
-    assert args.kind == "steps"
-    assert args.dataset_root == "/ceph/lbogner/geant_steps"
-    assert args.execute is False

tests/test_dwarf.py

@@ -0,0 +1,68 @@
+from typer.testing import CliRunner
+
+from scripts.dwarf import app
+
+runner = CliRunner()
+
+
+def test_convert_rejects_jobs_below_one(tmp_path):
+    root_file = tmp_path / "shard.root"
+    root_file.touch()
+    result = runner.invoke(app, ["convert", str(root_file), "--jobs", "0"])
+    assert result.exit_code != 0
+    assert "--jobs must be >= 1" in result.output
+
+
+def test_convert_rejects_output_with_multiple_files(tmp_path):
+    a = tmp_path / "a.root"
+    b = tmp_path / "b.root"
+    a.touch()
+    b.touch()
+    result = runner.invoke(app, ["convert", str(a), str(b), "--output", "out.parquet"])
+    assert result.exit_code != 0
+    assert "--output can only be used with a single input file" in result.output
+
+
+def test_convert_rejects_output_with_parallel_jobs(tmp_path):
+    root_file = tmp_path / "shard.root"
+    root_file.touch()
+    result = runner.invoke(
+        app, ["convert", str(root_file), "--output", "out.parquet", "--jobs", "2"]
+    )
+    assert result.exit_code != 0
+    assert "--output cannot be combined with --jobs > 1" in result.output
+
+
+def test_convert_default_jobs_is_one():
+    result = runner.invoke(app, ["convert", "--help"])
+    assert result.exit_code == 0
+    assert "default: 1" in result.output
+
+
+def test_bump_gen_requires_reason():
+    result = runner.invoke(app, ["bump-gen"])
+    assert result.exit_code != 0
+    assert "reason" in result.output.lower()
+
+
+def test_create_manifest_requires_exactly_one_of_output_or_pool(tmp_path):
+    f = tmp_path / "a.parquet"
+    f.touch()
+    result = runner.invoke(app, ["create-manifest", str(f)])
+    assert result.exit_code != 0
+    assert "exactly one of --output or --pool is required" in result.output
+
+
+def test_create_manifest_requires_type_with_pool(tmp_path):
+    f = tmp_path / "a.parquet"
+    f.touch()
+    result = runner.invoke(app, ["create-manifest", "--pool", "pbwo4", str(f)])
+    assert result.exit_code != 0
+    assert "--type is required when --pool is given" in result.output
+
+
+def test_status_reports_missing_root(tmp_path):
+    missing = tmp_path / "does-not-exist"
+    result = runner.invoke(app, ["status", "--root", str(missing)])
+    assert result.exit_code != 0
+    assert "is not a directory" in result.output

tests/test_steps_to_parquet_parallel.py

@@ -1,4 +1,5 @@
 import json
+import sys
 from pathlib import Path
 
 from scripts import steps_to_parquet_parallel
@@ -40,7 +41,7 @@ def test_runs_one_job_per_file_and_reports_success(tmp_path):
     fake = _write_fake_executable(tmp_path, marker_dir)
 
     files = [str(tmp_path / f"shard-{i:03d}.root") for i in range(3)]
-    results = run_parallel(files, jobs=4, steps_to_parquet_path=fake)
+    results = run_parallel(files, jobs=4, cmd_prefix=[sys.executable, str(fake)])
 
     assert {r[0] for r in results} == set(files)
     assert all(code == 0 for _, code, _, _ in results)
@@ -53,7 +54,7 @@ def test_failures_are_reported_with_nonzero_exit_code(tmp_path):
     fake = _write_fake_executable(tmp_path, marker_dir)
 
     files = [str(tmp_path / "shard-000.root"), str(tmp_path / "shard-fail.root")]
-    results = run_parallel(files, jobs=4, steps_to_parquet_path=fake)
+    results = run_parallel(files, jobs=4, cmd_prefix=[sys.executable, str(fake)])
 
     codes = {Path(f).stem: code for f, code, _, _ in results}
     assert codes["shard-000"] == 0
@@ -66,7 +67,7 @@ def test_jobs_caps_concurrency(tmp_path):
     fake = _write_fake_executable(tmp_path, marker_dir)
 
     files = [str(tmp_path / f"shard-{i:03d}.root") for i in range(6)]
-    run_parallel(files, jobs=2, steps_to_parquet_path=fake)
+    run_parallel(files, jobs=2, cmd_prefix=[sys.executable, str(fake)])
 
     intervals = []
     for f in files:
@@ -83,11 +84,6 @@ def test_jobs_caps_concurrency(tmp_path):
     assert peak <= 2
 
 
-def test_default_jobs_is_four():
-    args = steps_to_parquet_parallel.build_parser().parse_args(["dummy.root"])
-    assert args.jobs == 4
-
-
 def test_output_for_is_passed_through_as_output_flag(tmp_path):
     marker_dir = tmp_path / "markers"
     marker_dir.mkdir()
@@ -108,7 +104,10 @@ sys.exit(0)
     root_file = str(tmp_path / "shard-000.root")
     dest = tmp_path / "processed" / "shard-000.parquet"
     run_parallel(
-        [root_file], jobs=1, steps_to_parquet_path=fake, output_for={root_file: dest}
+        [root_file],
+        jobs=1,
+        cmd_prefix=[sys.executable, str(fake)],
+        output_for={root_file: dest},
     )
     assert (marker_dir / "shard-000.txt").read_text() == str(dest)
 
@@ -171,9 +170,3 @@ def test_resolve_destination_errors_on_wrong_shape(tmp_path):
 
 def test_latest_schema_tag_returns_none_when_missing(tmp_path):
     assert latest_schema_tag(tmp_path / "does" / "not" / "exist") is None
-
-
-def test_dataset_root_and_schema_flags_default(tmp_path):
-    args = steps_to_parquet_parallel.build_parser().parse_args(["dummy.root"])
-    assert args.dataset_root == "/ceph/lbogner/geant_steps"
-    assert args.schema is None