初始化项目，由ModelHub XC社区提供模型

Model: bk1dr/qwen3-8b-code-pkpo
Source: Original Platform

shipped_tool.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+"""Standalone agentic coding tool for OpenAI-compatible endpoints."""
+from __future__ import annotations
+
+import argparse
+import os
+import subprocess
+import sys
+
+from openai import OpenAI
+
+from agent_core import coding_task_message, openai_generate_fn, run_episode
+
+
+def run_bash(cmd: str, timeout_s: int = 30) -> str:
+    cp = subprocess.run(
+        cmd,
+        shell=True,
+        text=True,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.STDOUT,
+        timeout=timeout_s,
+    )
+    out = cp.stdout[-12000:]
+    return f"Exit code: {cp.returncode}\n{out}"
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--base-url", default=os.environ.get("OPENAI_BASE_URL", "http://127.0.0.1:8000/v1"))
+    ap.add_argument("--model", default=os.environ.get("MODEL", "bk1dr/qwen3-8b-code-pkpo"))
+    ap.add_argument("--api-key", default=os.environ.get("OPENAI_API_KEY", "EMPTY"))
+    ap.add_argument("--max-turns", type=int, default=1,
+                    help="One-turn deployment default used for training and evaluation.")
+    ap.add_argument("--cp", action="store_true", help="Wrap stdin as a competitive-programming task.")
+    ap.add_argument("--starter-code", default="")
+    args = ap.parse_args()
+
+    prompt = sys.stdin.read()
+    if args.cp:
+        first = coding_task_message(prompt, starter_code=args.starter_code, max_turns=args.max_turns)
+    else:
+        first = prompt
+
+    client = OpenAI(base_url=args.base_url, api_key=args.api_key)
+    generate = openai_generate_fn(client, args.model)
+    ep = run_episode(generate, run_bash, first, max_turns=args.max_turns)
+    if ep.final_answer is not None:
+        print(ep.final_answer)
+    else:
+        print(f"Episode ended without final answer: {ep.end_reason}", file=sys.stderr)
+        return 2
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())