순도 게이트 — 품질 말고 출처를 확인해

_X_HOSTS = {"x.com", "www.x.com", "twitter.com",
            "www.twitter.com", "mobile.twitter.com"}


def extract_card(raw: str) -> dict:
    """Parse a sampled trend card and gate it on PROVENANCE.

    A model asked about current sentiment answers confidently whether
    or not it searched, and the two answers read identically. A real
    link to a real post is the one thing the search path produces and
    prior knowledge cannot.
    """
    card = _parse_tolerantly(raw)       # keep what we can
    if card is None:
        # Never silently dropped: the raw text is the only evidence of
        # why the run failed, and a sampler producing nothing looks
        # exactly like a quiet day.
        return {"status": "unparsed", "raw": raw}

    cited = [
        p for p in card.get("posts", [])
        if urlsplit(p.get("url", "")).netloc.lower() in _X_HOSTS
    ]
    if not cited:
        return {"status": "no_citation", "raw": raw, "card": card}

    # The gate judges PROVENANCE only. Whether the read is insightful,
    # whether the temperature is right, whether the prose is good --
    # none of that is mechanically checkable, and an instrument that
    # tries is worse than one that does not.
    card["posts"] = cited
    card["status"] = "ok"
    return card