"""Utility helpers for the research engine."""
import re


def strip_thinking(text: str) -> str:
    """Remove <think>...</think> or <thinking>...</thinking> blocks from model output."""
    if not text:
        return text
    text = re.sub(r"<think(?:ing)?>[\s\S]*?</think(?:ing)?>", "", text, flags=re.I)
    return text.strip()


def is_low_quality(text: str) -> bool:
    """Return True if extracted content looks useless (too short, error page, etc.)."""
    if not text or len(text.strip()) < 50:
        return True
    low_q_patterns = [
        "access denied", "403 forbidden", "404 not found",
        "page not found", "enable javascript", "please enable cookies",
        "captcha", "robot check", "cloudflare", "just a moment",
        "no relevant information", "not relevant to",
    ]
    lower = text.lower()
    return any(p in lower for p in low_q_patterns)


EXTRACTOR_PROMPT = """\
You are extracting relevant information from a webpage to help answer a research question.

**Research goal:** {goal}

**Webpage content:**
{webpage_content}

Extract the most relevant information. Return a JSON object:
{{
  "rational": "One sentence on why this page is/isn't relevant",
  "evidence": "The specific facts, data, quotes, and info from this page relevant to the goal (up to 800 words)",
  "summary": "2-3 sentence summary of the key findings from this page"
}}

If the page has no relevant information, set evidence to "" and summary to "Not relevant."
Return ONLY valid JSON.
"""