Pull existing log from HF on startup to prevent overwrites on restart

app.py

@@ -55,7 +55,18 @@ def load_model():
 
 @st.cache_resource
 def get_scheduler():
+    import shutil
     LOG_DIR.mkdir(exist_ok=True)
+    # Pull existing log from HF on startup so we append instead of overwrite
+    try:
+        existing = hf_hub_download(
+            repo_id=LOG_REPO,
+            filename="logs/predictions.csv",
+            repo_type="dataset",
+        )
+        shutil.copy(existing, LOG_FILE)
+    except Exception:
+        pass  # no log yet, start fresh
     return CommitScheduler(
         repo_id=LOG_REPO,
         repo_type="dataset",