Add giant.analysis module for notebook-based model quality diagnostics

Provides stratified marginal comparisons, joint-structure checks (correlation
matrices, physically-coupled pairwise plots, direction alignment), and
physical-constraint validation (unit-norm directions, non-negative raw
targets) for a trained model's generated samples, building on the aggregate
marginal/KL check already in giant.validate.

Supports two entry points: live sampling against a checkpoint + val data
(load_model_bundle/collect_samples), or loading a precomputed
`giant predict --coord local` parquet directly (load_predicted_local) without
needing the checkpoint at all. Predict output is now tagged with parquet
schema metadata so the loader can verify a file's format and reject
coord=global or untagged files with a clear error instead of guessing from
column names.

Also extends the config git-hash mismatch warning (added for --config
loading) to checkpoint loading: both `giant predict` and
analysis.load_model_bundle now look for a config.toml next to the checkpoint
and warn (without failing) if it was generated from a different git commit.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

giant/cli.py

@@ -11,7 +11,12 @@ import pyarrow as pa
 import pyarrow.parquet as pq
 
 from giant import config as gconfig
-from giant.constants import LOCAL_TARGET_NAMES
+from giant.constants import (
+    LOCAL_TARGET_NAMES,
+    PREDICT_COORD_METADATA_KEY,
+    PREDICT_SCHEMA_VERSION,
+    PREDICT_SCHEMA_VERSION_KEY,
+)
 from giant.data.loader import (
     find_parquet_files,
     iter_file_chunks,
@@ -135,6 +140,7 @@ def predict(
     model.load_state_dict(ckpt["model"])
     model.to(_device).eval()
     typer.echo(f"loaded checkpoint: {checkpoint}")
+    gconfig.warn_if_checkpoint_config_mismatch(checkpoint)
 
     # --- Output path ---
     if out is None:
@@ -234,6 +240,11 @@ def predict(
                     "post_z":       post_pos_world[:, 2],
                 })
 
+            table = table.replace_schema_metadata({
+                PREDICT_COORD_METADATA_KEY: coord.value,
+                PREDICT_SCHEMA_VERSION_KEY: PREDICT_SCHEMA_VERSION,
+            })
+
             if writer is None:
                 writer = pq.ParquetWriter(out, table.schema)
             writer.write_table(table)