Add giant predict command

- iter_cond_chunks: column-projected row-group streaming; post-step
  variables are never read from disk during inference
- build_cond_features: assembles conditioning arrays without any target
  or post-step fields
- inv_local_frame_rotation: Rodrigues R^T (negative angle) to rotate
  predicted post_dir back from local frame to world frame
- giant predict: loads checkpoint, streams input, runs flow matching
  sampler, inverse-normalises and inverse-rotates outputs, writes
  predictions incrementally as parquet via PyArrow ParquetWriter
- train now saves model_config in checkpoint so predict can reconstruct
  the architecture without extra CLI flags

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

giant/data/loader.py

@@ -49,6 +49,34 @@ def iter_file_chunks(path: str | Path) -> Iterator[dict[str, np.ndarray]]:
         yield _df_to_dict(pf.read_row_group(i).to_pandas())
 
 
+_COND_COLS = [
+    "event_id", "pdg",
+    "pre_x", "pre_y", "pre_z", "pre_energy",
+    "pre_dir_x", "pre_dir_y", "pre_dir_z",
+    "material_id", "layer_id", "n_secondaries",
+]
+
+
+def _cond_df_to_dict(df: pd.DataFrame) -> dict[str, np.ndarray]:
+    return {
+        "event_id": df["event_id"].to_numpy(),
+        "pdg": df["pdg"].to_numpy(dtype=np.int32),
+        "pre_pos": df[["pre_x", "pre_y", "pre_z"]].to_numpy(dtype=np.float32),
+        "pre_energy": df["pre_energy"].to_numpy(dtype=np.float32),
+        "pre_dir": df[["pre_dir_x", "pre_dir_y", "pre_dir_z"]].to_numpy(dtype=np.float32),
+        "material": df["material_id"].to_numpy(dtype=np.int32),
+        "layer_id": df["layer_id"].to_numpy(dtype=np.int32),
+        "n_sec": df["n_secondaries"].to_numpy(dtype=np.int32),
+    }
+
+
+def iter_cond_chunks(path: str | Path) -> Iterator[dict[str, np.ndarray]]:
+    """Yield conditioning-only row-groups (no post-step columns read from disk)."""
+    pf = pq.ParquetFile(path)
+    for i in range(pf.num_row_groups):
+        yield _cond_df_to_dict(pf.read_row_group(i, columns=_COND_COLS).to_pandas())
+
+
 def build_index_maps(
     data: dict[str, np.ndarray],
 ) -> tuple[dict[int, int], dict[int, int]]: