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>

giant/data/setup_cache.py

@@ -22,13 +22,16 @@ import numpy as np
 
 from giant import config
 from giant.constants import COND_DIM, K_MAX, PARTICLE_PHYS_DIM, SEC_SLOT_DIM, X_DIM
-from giant.data.loader import load_event_ids
+from giant.data.loader import event_id_offset, load_event_ids
 from giant.data.transforms import Normalizer, sorted_membership
 
 # Bump manually on a change to the data-encoding semantics (e.g. a future
 # energy_simplex_encode bugfix) that doesn't also move one of _DIMS below —
 # a dims change already hard-invalidates on its own.
-_CACHE_FORMAT_VERSION = 1
+# v2: event_id is now offset per-file (see loader.event_id_offset) to avoid
+# cross-file collisions, so a v1 sidecar's event_index/normalizers were
+# computed against collided ids and must not be reused.
+_CACHE_FORMAT_VERSION = 2
 
 _DIMS = {
     "COND_DIM": COND_DIM,
@@ -263,7 +266,9 @@ def compute_event_index_from_files(files: list[Path]) -> tuple[np.ndarray, np.nd
     """Unique event ids + per-event row (step) counts, across all `files`."""
     if not files:
         return np.empty(0, dtype=np.int64), np.empty(0, dtype=np.int64)
-    all_ids = np.concatenate([load_event_ids(f) for f in files])
+    all_ids = np.concatenate(
+        [load_event_ids(f, offset=event_id_offset(i)) for i, f in enumerate(files)]
+    )
     unique_ids, counts = np.unique(all_ids, return_counts=True)
     return unique_ids, counts