feat: setup dataset enrichment app codebase and scripts

scripts/auto_pull.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+"""Auto-pull service: monitors origin/main and pulls new commits automatically."""
+
+import os
+import subprocess
+import sys
+import time
+
+INTERVAL_SECONDS = int(os.environ.get("AUTO_PULL_INTERVAL", 30))
+REPO_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+def run_git(args):
+    res = subprocess.run(["git"] + args, cwd=REPO_DIR, capture_output=True, text=True)
+    return res.returncode == 0, res.stdout.strip(), res.stderr.strip()
+
+def check_and_pull():
+    # Fetch latest remote changes quietly
+    ok, _, err = run_git(["fetch", "origin", "main"])
+    if not ok:
+        print(f"[Auto-Pull] Git fetch error: {err}")
+        return
+
+    _, incoming_commits, _ = run_git(["log", "HEAD..origin/main", "--oneline"])
+
+    if incoming_commits:
+        print(f"[Auto-Pull] Incoming commits detected:\n{incoming_commits}")
+        ok, out, err = run_git(["pull", "origin", "main"])
+        if ok:
+            print(f"[Auto-Pull] Successfully pulled:\n{out}")
+            print("[Auto-Pull] Restarting app services...")
+            restart_script = os.path.join(REPO_DIR, "scripts", "restart_app.sh")
+            subprocess.run(["bash", restart_script], cwd=REPO_DIR)
+        else:
+            print(f"[Auto-Pull] Pull failed:\n{err}")
+
+def main():
+    print(f"🔄 Auto-pull background poller started (Interval: {INTERVAL_SECONDS}s)")
+    while True:
+        try:
+            check_and_pull()
+        except Exception as exc:
+            print(f"[Auto-Pull] Error: {exc}")
+        time.sleep(INTERVAL_SECONDS)
+
+if __name__ == "__main__":
+    main()