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_setup_cache.py

@@ -225,3 +225,35 @@ def test_n_train_steps_for_split_matches_full_scan():
     result = setup_cache.n_train_steps_for_split(unique_ids, counts, train_events_arr)
 
     assert result == 20 + 40 + 50
+
+
+# ── compute_event_index_from_files: cross-file event_id offsetting ─────────
+
+
+def test_compute_event_index_from_files_offsets_colliding_ids(tmp_path):
+    """Two files that each restart event_id from 0 (one Geant4 job per file)
+    must not have their same-numbered events collapsed into one by
+    np.unique — each file's ids get shifted by a distinct offset first (see
+    giant.data.loader.event_id_offset)."""
+    path_a = tmp_path / "a.parquet"
+    path_b = tmp_path / "b.parquet"
+    pd.DataFrame({"event_id": [0, 1, 2]}).to_parquet(path_a)
+    pd.DataFrame({"event_id": [0, 1, 2]}).to_parquet(path_b)
+
+    unique_ids, counts = setup_cache.compute_event_index_from_files([path_a, path_b])
+
+    assert len(unique_ids) == 6
+    assert int(counts.sum()) == 6
+    assert np.all(counts == 1)
+
+
+def test_compute_event_index_from_files_single_file_unaffected(tmp_path):
+    """A single file's ids are offset by 0 (event_id_offset(0) == 0), so a
+    single-file load's unique ids/counts are unchanged by the offsetting."""
+    path = tmp_path / "a.parquet"
+    pd.DataFrame({"event_id": [5, 5, 7]}).to_parquet(path)
+
+    unique_ids, counts = setup_cache.compute_event_index_from_files([path])
+
+    np.testing.assert_array_equal(unique_ids, [5, 7])
+    np.testing.assert_array_equal(counts, [2, 1])