"""Code read-out rescue for the deliberation module. When the thinking of a code task hits the budget, the module closes it and lets the model answer. On hard problems the model then writes an editorial-style "Solution Explanation" with pseudo-code and runs out of space before the program (LCB v6: 37 of 112 budget read-outs had no Python block at all). Rescue: if the answer generated at the budget contains no program that compiles, generate it again with the code block already opened ("```python" right after ). Other records are copied unchanged, so the comparison with the source run is exactly paired. Tokens of the discarded answer stay counted. usage: code_rescue.py --src results/lcb_dm/lcb.jsonl --items data/lcb/lcb6.jsonl --out results/lcb_dmr/lcb.jsonl """ import argparse import json import os import sys import time import urllib.request import zlib from concurrent.futures import ThreadPoolExecutor from transformers import AutoTokenizer sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) from grade import extract_code # noqa: E402 THINK_END = 124902 PREFILL = "```python\n" CODE_TASKS = {"code_io", "humaneval", "mbpp", "code_fn", "lcb"} SAMPLING = {"temperature": 0.6, "top_p": 0.95, "top_k": 50, "min_p": 0.0, "repeat_penalty": 1.0, "samplers": ["top_k", "top_p", "temperature"]} def runnable(text): code = extract_code(text or "") if not code: return False try: compile(code, "", "exec") return True except Exception: return False def close_block(content): text = PREFILL + content return text if "```" in content else text.rstrip() + "\n```" def post(port, body): for attempt in range(5): try: req = urllib.request.Request(f"http://localhost:{port}/completion", data=json.dumps(body).encode(), headers={"Content-Type": "application/json"}) return json.loads(urllib.request.urlopen(req, timeout=3600).read()) except Exception: if attempt == 4: raise time.sleep(5) if __name__ == "__main__": ap = argparse.ArgumentParser() ap.add_argument("--src", required=True) ap.add_argument("--items", nargs="+", required=True) ap.add_argument("--out", required=True) ap.add_argument("--reserve", type=int, default=4096) ap.add_argument("--workers", type=int, default=32) ap.add_argument("--port", type=int, default=8080) ap.add_argument("--tokenizer", default="models/LFM3-1.7B") args = ap.parse_args() tok = AutoTokenizer.from_pretrained(args.tokenizer) pre_ids = tok(PREFILL, add_special_tokens=False)["input_ids"] items = {} for path in args.items: for l in open(path, encoding="utf-8"): r = json.loads(l) items[r["id"]] = r def process(rec): it = items[rec["id"]] c = rec["completion"] if it["task"] not in CODE_TASKS or rec.get("module") != "fallback" or "" not in c: return rec thinking, final = c[len(""):].split("", 1) if runnable(final): return rec ids = tok.apply_chat_template([{"role": "user", "content": it["prompt"]}], tokenize=True, add_generation_prompt=True, return_dict=False) gen = tok(thinking, add_special_tokens=False)["input_ids"] seed = zlib.crc32(rec["id"].encode()) % 1000003 * 7 + rec.get("sample", 0) + 31 r = post(args.port, {"prompt": ids + gen + [THINK_END] + pre_ids, "n_predict": args.reserve, "seed": seed, "cache_prompt": False, "return_tokens": True, **SAMPLING}) text = close_block(r["content"]) return {**rec, "completion": "" + thinking + "" + text, "n_tokens": rec["n_tokens"] + len(pre_ids) + len(r["tokens"]), "module": "fallback_rescue", "rescued": runnable(text)} recs = [json.loads(l) for l in open(args.src, encoding="utf-8")] t0 = time.time() with ThreadPoolExecutor(args.workers) as ex: out = list(ex.map(process, recs)) os.makedirs(os.path.dirname(args.out), exist_ok=True) with open(args.out, "w", encoding="utf-8") as f: for r in out: f.write(json.dumps(r, ensure_ascii=False) + "\n") res = [r for r in out if r.get("module") == "fallback_rescue"] print(f"{len(out)} records, {len(res)} read-outs without a runnable program regenerated, " f"{sum(r['rescued'] for r in res)} now have one, {(time.time() - t0) / 60:.1f} min")