Offset event_id per file to avoid cross-file collisions

Each input parquet file is one Geant4 job (scripts/steps_to_parquet.py),
and a job's event_id numbering always restarts from 0 — so loading
multiple files together (a directory or .manifest) let same-numbered
events from different files collapse into one during the event index
scan and train/val split, corrupting both. Every per-file event_id now
gets offset by file index * EVENT_ID_FILE_STRIDE (giant/data/loader.py),
threaded through the setup-cache event index, the streaming dataset,
and predict/rollout seeding. Bumps the setup-cache format version so
stale sidecars computed pre-fix are invalidated.

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

tests/test_loader.py

@@ -3,10 +3,16 @@ import pandas as pd
 import pytest
 
 from giant.data.loader import (
+    EVENT_ID_FILE_STRIDE,
     build_index_maps,
     build_index_maps_from_files,
     build_process_map_from_files,
+    event_id_offset,
     find_parquet_files,
+    iter_cond_chunks,
+    iter_file_chunks,
+    load_event_ids,
+    load_steps,
 )
 
 
@@ -279,3 +285,84 @@ def test_build_index_maps_from_files_matches_build_index_maps(tmp_path):
     from_files = build_index_maps_from_files([path])
     from_memory = build_index_maps({"pdg": pdg, "material": material})
     assert from_files == from_memory
+
+
+# ── event_id_offset / per-file event_id offsetting ─────────────────────────
+
+
+def _steps_df(event_ids):
+    """Minimal schema-complete steps rows (no secondaries) for _df_to_dict."""
+    return pd.DataFrame(
+        [
+            {
+                "event_id": eid,
+                "pdg": 11,
+                "pre_x": 0.0,
+                "pre_y": 0.0,
+                "pre_z": 0.0,
+                "pre_E": 100.0,
+                "pre_dx": 0.0,
+                "pre_dy": 0.0,
+                "pre_dz": 1.0,
+                "material": "G4_AIR",
+                "layer_id": 0,
+                "child_track_ids": [],
+                "e_sec": 0.0,
+                "step_length": 1.0,
+                "post_E": 90.0,
+                "edep": 10.0,
+                "post_dx": 0.0,
+                "post_dy": 0.0,
+                "post_dz": 1.0,
+                "post_x": 0.0,
+                "post_y": 0.0,
+                "post_z": 1.0,
+            }
+            for eid in event_ids
+        ]
+    )
+
+
+def test_event_id_offset_scales_by_file_index():
+    assert event_id_offset(0) == 0
+    assert event_id_offset(1) == EVENT_ID_FILE_STRIDE
+    assert event_id_offset(3) == 3 * EVENT_ID_FILE_STRIDE
+
+
+def test_load_event_ids_default_offset_is_zero(tmp_path):
+    path = tmp_path / "a.parquet"
+    pd.DataFrame({"event_id": [5, 6, 7]}).to_parquet(path)
+    np.testing.assert_array_equal(load_event_ids(path), [5, 6, 7])
+
+
+def test_load_event_ids_applies_offset(tmp_path):
+    path = tmp_path / "a.parquet"
+    pd.DataFrame({"event_id": [0, 1, 2]}).to_parquet(path)
+    offset = event_id_offset(1)
+    np.testing.assert_array_equal(
+        load_event_ids(path, offset=offset), [offset, offset + 1, offset + 2]
+    )
+
+
+def test_load_steps_applies_offset_to_event_id(tmp_path):
+    path = tmp_path / "a.parquet"
+    _steps_df([0, 1]).to_parquet(path)
+    offset = event_id_offset(2)
+    d = load_steps(path, offset=offset)
+    np.testing.assert_array_equal(d["event_id"], [offset, offset + 1])
+
+
+def test_iter_file_chunks_applies_offset(tmp_path):
+    path = tmp_path / "a.parquet"
+    _steps_df([0, 1, 2]).to_parquet(path)
+    offset = event_id_offset(1)
+    ids = np.concatenate([c["event_id"] for c in iter_file_chunks(path, offset=offset)])
+    np.testing.assert_array_equal(sorted(ids), [offset, offset + 1, offset + 2])
+
+
+def test_iter_cond_chunks_applies_offset(tmp_path):
+    path = tmp_path / "a.parquet"
+    _steps_df([0, 1]).to_parquet(path)
+    offset = event_id_offset(5)
+    ids = np.concatenate([c["event_id"] for c in iter_cond_chunks(path, offset=offset)])
+    np.testing.assert_array_equal(sorted(ids), [offset, offset + 1])