giant/analysis/sources.py

@@ -106,18 +106,27 @@ def open_side(source: str | Path | pl.LazyFrame, side: Side) -> pl.LazyFrame:
     can push their own narrow projection into the parquet read — the single
     biggest lever on a larger-than-RAM file. ``pl.LazyFrame`` inputs pass straight
     through (used by tests).
+
+    ``pdg`` is cast to a canonical ``Int64`` here: the rollout writer and the
+    reference file's upstream ROOT→parquet conversion don't agree on integer
+    width, and an uncast mismatch only surfaces later as a ``pl.concat``
+    ``SchemaError`` (e.g. in ``build_context``'s pdg-count merge).
     """
     if isinstance(source, pl.LazyFrame):
-        return source
+        return source.with_columns(pl.col("pdg").cast(pl.Int64))
     path = Path(source)
     if side is Side.rollout:
         _check_rollout_metadata(path)
-        return pl.scan_parquet(path)
-    # The reference (a rollout's seed `dataset`) may be a directory of parquet
-    # shards rather than a single file — scan them all.
-    if path.is_dir():
-        return pl.scan_parquet(str(path / "**/*.parquet"))
-    return pl.scan_parquet(path)
+        lf = pl.scan_parquet(path)
+    else:
+        # The reference (a rollout's seed `dataset`) may be a directory of
+        # parquet shards rather than a single file — scan them all.
+        lf = (
+            pl.scan_parquet(str(path / "**/*.parquet"))
+            if path.is_dir()
+            else pl.scan_parquet(path)
+        )
+    return lf.with_columns(pl.col("pdg").cast(pl.Int64))
 
 
 def physical_steps(lf: pl.LazyFrame, side: Side) -> pl.LazyFrame: