Record independent benchmark child exits without scientific retries

models/male-cns-lif/conditioning-acceleration-v1/launch_job.py

@@ -0,0 +1,36 @@
+"""Write new engineering child-process exit receipts; never retry a job."""
+import argparse
+from datetime import datetime, timezone
+import json
+import os
+from pathlib import Path
+import re
+import subprocess
+import time
+
+p = argparse.ArgumentParser()
+p.add_argument('--label', required=True)
+p.add_argument('--timeout', type=int, default=900)
+p.add_argument('command', nargs=argparse.REMAINDER)
+a = p.parse_args()
+assert re.fullmatch(r'[a-z0-9-]+', a.label)
+assert a.command
+out = Path('/home/qishizhe/phase4ar-v100-acceleration-20261001') / 'jobs'
+out.mkdir(exist_ok=True)
+start = time.perf_counter()
+receipt = dict(command=a.command, label=a.label, started_utc=datetime.now(timezone.utc).isoformat(),
+               original_experiment_resumed=False)
+with (out / (a.label + '.start.json')).open('x') as f:
+    json.dump(receipt, f, indent=2)
+with (out / (a.label + '.stdout.log')).open('x') as stdout, (out / (a.label + '.stderr.log')).open('x') as stderr:
+    try:
+        result = subprocess.run(a.command, stdout=stdout, stderr=stderr,
+            env={**os.environ, 'PYTHONDONTWRITEBYTECODE': '1'}, timeout=a.timeout)
+        receipt.update(exit_code=result.returncode, observed_exit=True, timed_out=False)
+    except subprocess.TimeoutExpired:
+        receipt.update(exit_code=None, observed_exit=False, timed_out=True)
+receipt.update(wall_seconds=time.perf_counter()-start, finished_utc=datetime.now(timezone.utc).isoformat())
+with (out / (a.label + '.exit.json')).open('x') as f:
+    json.dump(receipt, f, indent=2)
+print(json.dumps(receipt), flush=True)
+raise SystemExit(receipt['exit_code'] if receipt['observed_exit'] else 124)