#!/usr/bin/env python3
"""CASAN H6 hallucination signal detector.

Reads the quoted keyword markers from hallucination-tracking.yaml plus a set of
generic uncertainty markers, scans the agent output, and reports how many
hallucination signals were found. This turns hallucination-tracking.yaml from
dead config into a real, populated metric written to metrics.jsonl.

Usage: hallucination-scan.py <hallucination-tracking.yaml> <output-file>
Output (stdout): line 1 = integer signal count, line 2 = JSON list of matches.
"""
import json
import re
import sys

GENERIC_MARKERS = [
    "maybe", "might be incorrect", "i am not sure", "uncertain",
    "i think", "probably", "as far as i know",
]


def load_keywords(path):
    keywords = []
    try:
        with open(path, encoding="utf-8") as fh:
            for line in fh:
                # Quoted list items are the hallucination keyword markers
                # (unquoted list items are structured signal names, not text).
                m = re.match(r'\s*-\s*"(.+)"\s*$', line)
                if m:
                    keywords.append(m.group(1))
    except OSError:
        pass
    return keywords


def main():
    if len(sys.argv) < 3:
        print(0)
        print("[]")
        return
    keywords = load_keywords(sys.argv[1]) + GENERIC_MARKERS
    try:
        with open(sys.argv[2], encoding="utf-8") as fh:
            text = fh.read().lower()
    except OSError:
        print(0)
        print("[]")
        return
    matched = []
    for kw in keywords:
        k = kw.lower()
        if not k:
            continue
        count = text.count(k)
        if count:
            matched.append({"marker": kw, "count": count})
    total = sum(m["count"] for m in matched)
    print(total)
    print(json.dumps(matched))


if __name__ == "__main__":
    main()