core/parse.py

import json
import re


def _strip_fences(text: str) -> str:
    text = text.strip()
    text = re.sub(r"^```(?:json)?\s*\n?", "", text, flags=re.MULTILINE)
    text = re.sub(r"\n?```\s*$", "", text, flags=re.MULTILINE)
    return text.strip()


def _extract_first_json(text: str):
    """Try to pull the first {...} or [...] block from noisy text."""
    for pattern in (r"\{[\s\S]*\}", r"\[[\s\S]*\]"):
        match = re.search(pattern, text)
        if match:
            try:
                return json.loads(match.group())
            except json.JSONDecodeError:
                pass
    return None


def parse_json(text: str):
    """
    Defensively parse model JSON output.
    Returns parsed dict/list, or {"error": "...", "raw": "..."} on failure.
    Never raises.
    """
    cleaned = _strip_fences(text)

    try:
        return json.loads(cleaned)
    except json.JSONDecodeError:
        pass

    recovered = _extract_first_json(cleaned)
    if recovered is not None:
        return recovered

    return {"error": "Could not parse model output as JSON.", "raw": text[:600]}