Add coverage for router-center seeding, geometry batch reader, material topN cache, and setup-cache corruption paths

Closes the highest-value coverage gaps found via pytest-cov: pipeline.py's
EnergyRouter quantile-seeding (the roadmap's flagged fix for the failed MoE
rollout benchmark) had zero coverage, geometry.py's real parquet-batch reader
was always mocked, the material top-N-map cache-hit branch was untested
(only pdg's was), and setup_cache.py was missing malformed-cache-body and
unknown-axis error paths.

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

tests/test_geometry.py

@@ -4,6 +4,7 @@ from pathlib import Path
 from unittest.mock import patch
 
 import numpy as np
+import pandas as pd
 import pytest
 
 from giant import geometry as g
@@ -12,6 +13,76 @@ from giant import geometry as g
 pytest.importorskip("sklearn")
 
 
+def _steps_frame(n=5, with_post=True):
+    rng = np.random.default_rng(0)
+    data = {
+        "pre_x": rng.uniform(-10, 10, n),
+        "pre_y": rng.uniform(-10, 10, n),
+        "pre_z": rng.uniform(-10, 10, n),
+        "material": ["G4_AIR"] * n,
+        "layer_id": np.arange(n, dtype=np.int64),
+    }
+    if with_post:
+        data["post_x"] = rng.uniform(-10, 10, n)
+        data["post_y"] = rng.uniform(-10, 10, n)
+        data["post_z"] = rng.uniform(-10, 10, n)
+    return pd.DataFrame(data)
+
+
+def test_iter_point_batches_missing_columns_raises(tmp_path):
+    path = tmp_path / "steps.parquet"
+    pd.DataFrame({"pre_x": [0.0]}).to_parquet(path)
+    with pytest.raises(ValueError, match="missing columns"):
+        next(g._iter_point_batches(path))
+
+
+def test_iter_point_batches_without_post_columns_yields_pre_only(tmp_path):
+    path = tmp_path / "steps.parquet"
+    df = _steps_frame(n=5, with_post=False)
+    df.to_parquet(path)
+
+    (pos, mat, lay) = next(g._iter_point_batches(path))
+
+    assert pos.shape == (5, 3)
+    np.testing.assert_allclose(
+        pos, df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32)
+    )
+    assert list(mat) == ["G4_AIR"] * 5
+    np.testing.assert_array_equal(lay, np.arange(5))
+
+
+def test_iter_point_batches_with_post_columns_doubles_and_concatenates_points(
+    tmp_path,
+):
+    path = tmp_path / "steps.parquet"
+    df = _steps_frame(n=5, with_post=True)
+    df.to_parquet(path)
+
+    (pos, mat, lay) = next(g._iter_point_batches(path))
+
+    # Every step contributes both its pre_pos and post_pos, sharing the
+    # step's material/layer_id label — so batches double in length.
+    assert pos.shape == (10, 3)
+    np.testing.assert_allclose(
+        pos[:5], df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32)
+    )
+    np.testing.assert_allclose(
+        pos[5:], df[["post_x", "post_y", "post_z"]].to_numpy(dtype=np.float32)
+    )
+    assert list(mat) == ["G4_AIR"] * 10
+    np.testing.assert_array_equal(lay, np.concatenate([np.arange(5), np.arange(5)]))
+
+
+def test_iter_point_batches_respects_batch_size(tmp_path):
+    path = tmp_path / "steps.parquet"
+    df = _steps_frame(n=10, with_post=False)
+    df.to_parquet(path, row_group_size=10)
+
+    batches = list(g._iter_point_batches(path, batch_size=4))
+
+    assert [len(pos) for pos, _, _ in batches] == [4, 4, 2]
+
+
 def _box_batch(n, rng):
     """A labelled point cloud: inside a 100mm box -> PbWO4/0, else AIR/-1."""
     pos = rng.uniform(-200, 200, (n, 3)).astype(np.float32)