print commit hash on import; fix event_id offset in multi-core steps

G4Calo.py prints the commit at import time, resolved via a
minicalo_version.py file (baked in by Docker) or git rev-parse
from the file's directory as fallback.

event_id in the Steps ntuple restarts from 0 in each subprocess;
_assemble_results_to_mini_df now accepts per-file event_id_offsets
so IDs are globally unique after merging. run_batch passes cumulative
nevents as offsets when loading the Steps tree.

Dockerfiles write minicalo_version.py before copying Python files.

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

bind/G4Calo.py

@@ -171,6 +171,27 @@ from IPython.display import Image, display
 from minipandas import MiniFrame
 
 
+def _get_commit():
+    try:
+        from minicalo_version import commit as _c
+        return _c
+    except ImportError:
+        pass
+    try:
+        r = subprocess.run(
+            ['git', 'rev-parse', '--short', 'HEAD'],
+            capture_output=True, text=True,
+            cwd=os.path.dirname(os.path.abspath(__file__))
+        )
+        if r.returncode == 0:
+            return r.stdout.strip()
+    except Exception:
+        pass
+    return 'unknown'
+
+print(f"miniCaloSim: commit {_get_commit()}")
+
+
 #### helpers #####
 
 class Stopwatch(object):
@@ -238,11 +259,14 @@ def _count_total_entries(root_paths, tree_name: str = "Hits") -> int:
             total += int(f[tree_name].num_entries)
     return total
 
-def _assemble_results_to_mini_df(root_paths, tree_name: str = "Hits"):
+def _assemble_results_to_mini_df(root_paths, tree_name: str = "Hits", event_id_offsets=None):
     """
     Returns:
       scalars: dict[col, np.ndarray]  # shape (N,)
       arrays:  dict[col, np.ndarray]  # shape (N, M[col])
+
+    event_id_offsets: optional list[int], one per file — added to the
+    'event_id' column so that IDs are globally unique across batches.
     """
     # 1) learn schema & sizes from first file
     scalar_cols, array_cols, array_sizes, dtypes_scalar, dtypes_array, _ = \
@@ -257,19 +281,22 @@ def _assemble_results_to_mini_df(root_paths, tree_name: str = "Hits"):
 
     # 4) fill by slices
     pos = 0
-    for p in root_paths:
+    for file_idx, p in enumerate(root_paths):
         with uproot.open(p) as f:
             arr = f[tree_name].arrays(library="ak")
         n = len(arr)
         sl = slice(pos, pos + n)
 
         for c in scalar_cols:
-            scalars[c][sl] = np.asarray(arr[c])
+            data = np.asarray(arr[c])
+            if c == 'event_id' and event_id_offsets is not None:
+                data = data + event_id_offsets[file_idx]
+            scalars[c][sl] = data
         for c in array_cols:
             arrays[c][sl, :] = ak.to_numpy(arr[c])  # (n, fixed_size)
 
         pos += n
-    
+
     #merge the dicts
     merged = {**scalars, **arrays}
     return MiniFrame(merged)
@@ -412,6 +439,7 @@ Example
     #print(f"Running {nEventsLastCore} events on last core")
     
     nevents = [nEventsPerCore if i < nCores - 1 else nEventsLastCore for i in range(nCores)]
+    event_id_offsets = [sum(nevents[:i]) for i in range(nCores)]
 
     if manual_seed >= 0:
         seed = manual_seed 
@@ -466,7 +494,8 @@ Example
     try:
         df = _assemble_results_to_mini_df(rp)
         if return_steps:
-            steps_df = _assemble_results_to_mini_df(rp, tree_name="Steps")
+            steps_df = _assemble_results_to_mini_df(rp, tree_name="Steps",
+                                                     event_id_offsets=event_id_offsets)
     finally:
         for f in tmpfile:
             if os.path.exists(f):

docker/Dockerfile

@@ -101,7 +101,9 @@ RUN cd  /root/minicalosim && git checkout $COMMIT && \
     mkdir -p build && cd build && rm -rf * && cmake ../ && make -j4
 
 
-RUN cp /root/minicalosim/build/minicalo* /root/minicalosim/bind/G4Calo.py /root/minicalosim/bind/minicalo_tools.py /root/minicalosim/bind/minipandas.py /usr/local/lib/python3.10/dist-packages/
+RUN echo "commit = '${COMMIT}'" > /root/minicalosim/bind/minicalo_version.py
+
+RUN cp /root/minicalosim/build/minicalo* /root/minicalosim/bind/G4Calo.py /root/minicalosim/bind/minicalo_tools.py /root/minicalosim/bind/minipandas.py /root/minicalosim/bind/minicalo_version.py /usr/local/lib/python3.10/dist-packages/
 
 RUN cp /root/minicalosim/bind/G4Calo_exec.py /usr/local/bin/
 

docker/Dockerfile-cpu

@@ -99,7 +99,8 @@ ADD minicalosim /root/minicalosim
 RUN cd  /root/minicalosim && git checkout $COMMIT && \
     git submodule update --init lib/pybind11 && \
     mkdir -p build && cd build && rm -rf * && cmake ../ && make -j$(nproc) &&\
-    cp minicalo* ../bind/G4Calo.py /usr/local/lib/python3.8/dist-packages/
+    echo "commit = '${COMMIT}'" > ../bind/minicalo_version.py && \
+    cp minicalo* ../bind/G4Calo.py ../bind/minicalo_version.py /usr/local/lib/python3.8/dist-packages/
 
 
 

docker/Dockerfile-mini

@@ -52,9 +52,11 @@ RUN cd /root/minicalosim && git checkout $COMMIT && \
     cmake --build build --parallel $(nproc) && \
     cp build/minicalo*.so /usr/local/lib/python3.10/dist-packages/
 
-RUN cp /root/minicalosim/bind/G4Calo.py \
+RUN echo "commit = '${COMMIT}'" > /root/minicalosim/bind/minicalo_version.py && \
+    cp /root/minicalosim/bind/G4Calo.py \
        /root/minicalosim/bind/minicalo_tools.py \
        /root/minicalosim/bind/minipandas.py \
+       /root/minicalosim/bind/minicalo_version.py \
        /usr/local/lib/python3.10/dist-packages/ && \
     install -m 755 /root/minicalosim/bind/G4Calo_exec.py /usr/local/bin/G4Calo_exec.py