Train a URL-extraction agent in your own harness

import json
import os
import re
import time
import urllib.error
import urllib.request

from openai import OpenAI

client = OpenAI()  # reads OPENAI_BASE_URL / OPENAI_API_KEY from the env
MODEL = os.environ.get("VERI_POLICY_MODEL", "Qwen/Qwen3-4B")
MAX_TURNS = int(os.environ.get("VERI_MAX_TURNS", "8"))

SYSTEM = (
    "You find GitHub repository URLs for arXiv papers. On each turn reply with "
    "EXACTLY ONE of:\n"
    "  FETCH: <arxiv_id>   to look up the paper's page (e.g. FETCH: 2305.10601)\n"
    "  ANSWER: <url>       when you know the GitHub URL\n"
    "No other text."
)

def fetch_arxiv(arxiv_id: str) -> str:
    # The HF paper page carries the paper's linked code repositories (the
    # arXiv abstract page usually does not); links come from the raw HTML
    # hrefs so they survive the text truncation.
    arxiv_id = arxiv_id.strip().rstrip(".")
    for url in (f"https://huggingface.co/papers/{arxiv_id}", f"https://arxiv.org/abs/{arxiv_id}"):
        html = None
        for delay in (0, 5, 15):  # parallel rollouts can trip HF's 429 rate limit
            time.sleep(delay)
            try:
                req = urllib.request.Request(url, headers={"User-Agent": "veri-demo-agent/1.0"})
                with urllib.request.urlopen(req, timeout=30) as resp:
                    html = resp.read().decode("utf-8", errors="replace")
                break
            except urllib.error.HTTPError as e:
                if e.code != 429:
                    break  # hard miss (e.g. 404): fall through to the next source
            except Exception:
                break
        if html is None:
            continue
        links = sorted(set(re.findall(r"https?://(?:www\.)?github\.com/[\w.\-]+/[\w.\-]+", html)))
        text = re.sub(r"\s+", " ", re.sub(r"<[^>]+>", " ", html))[:2500]
        if links:
            text += "\nLINKS ON PAGE: " + " ".join(links[:10])
        return text
    return f"fetch failed: no page found for {arxiv_id}"

task = json.loads(os.environ["VERI_TASK_INPUT"])
messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": task}]
for turn in range(MAX_TURNS):
    resp = client.chat.completions.create(model=MODEL, messages=messages, temperature=0.7, max_tokens=512)
    content = (resp.choices[0].message.content or "").strip()
    messages.append({"role": "assistant", "content": content})
    if content.upper().startswith("ANSWER:"):
        break
    match = re.match(r"(?i)^FETCH:\s*(\S+)", content)
    observation = fetch_arxiv(match.group(1)) if match else "Reply with FETCH: <arxiv_id> or ANSWER: <url>."
    messages.append({"role": "user", "content": f"OBSERVATION:\n{observation}"})

from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model=os.environ.get("VERI_POLICY_MODEL", "Qwen/Qwen3-4B"),
    temperature=0.7,
    max_tokens=512,
)  # reads OPENAI_BASE_URL / OPENAI_API_KEY from the env

messages = [SystemMessage(content=SYSTEM), HumanMessage(content=task)]
for turn in range(MAX_TURNS):
    content = (llm.invoke(messages).content or "").strip()
    messages.append(AIMessage(content=content))
    if content.upper().startswith("ANSWER:"):
        break
    match = re.match(r"(?i)^FETCH:\s*(\S+)", content)
    observation = fetch_arxiv(match.group(1)) if match else "Reply with FETCH: <arxiv_id> or ANSWER: <url>."
    messages.append(HumanMessage(content=f"OBSERVATION:\n{observation}"))