"""Guardrail anti-duplicati e similarità pre-scrittura."""
from __future__ import annotations

import hashlib
import unicodedata
from typing import Any, Optional

from qdrant_client.http import models as qm

from config import GUARDRAIL_BLOCK_THRESHOLD, GUARDRAIL_WARN_THRESHOLD


def normalize_text(text: str) -> str:
    s = unicodedata.normalize("NFD", text.lower())
    s = "".join(c for c in s if not unicodedata.combining(c))
    return " ".join(s.split())


def text_hash(text: str) -> str:
    return hashlib.sha256(normalize_text(text).encode("utf-8")).hexdigest()


def find_similar(qdrant: Any, collection: str, text: str, vector: list[float], top_k: int = 3) -> list[dict]:
    qfilter = qm.Filter(must=[qm.IsEmptyCondition(is_empty=qm.PayloadField(key="superseded_by"))])
    hits = qdrant.query_points(collection_name=collection, query=vector, query_filter=qfilter, limit=top_k, with_payload=True).points
    return [
        {
            "memory_id": h.id,
            "score": round(float(h.score), 4),
            "text": (h.payload or {}).get("text", ""),
            "kind": (h.payload or {}).get("kind", ""),
            "project_id": (h.payload or {}).get("project_id", ""),
        }
        for h in hits
    ]


def decide(qdrant: Any, collection: str, text: str, vector: list[float], topic: Optional[str] = None, parent_id: Optional[str] = None) -> dict:
    exact_filter = qm.Filter(must=[
        qm.FieldCondition(key="text_hash", match=qm.MatchValue(value=text_hash(text))),
        qm.IsEmptyCondition(is_empty=qm.PayloadField(key="superseded_by")),
    ])
    exact = qdrant.query_points(collection_name=collection, query=vector, query_filter=exact_filter, limit=1, with_payload=True).points
    if exact:
        return {"decision": "BLOCK", "reason": "EXACT_DUPLICATE", "matches": [{"memory_id": exact[0].id, "score": 1.0}]}

    matches = find_similar(qdrant, collection, text, vector, top_k=3)
    if not matches:
        return {"decision": "ALLOW", "reason": "NO_CANDIDATE", "matches": []}
    top1 = matches[0]["score"]
    if top1 >= GUARDRAIL_BLOCK_THRESHOLD:
        if (topic or parent_id) and any(m.get("memory_id") != parent_id for m in matches):
            return {"decision": "WARN", "reason": "HIERARCHICAL_SUBTOPIC", "matches": matches}
        return {"decision": "BLOCK", "reason": "KNOWN_SOLUTION", "matches": matches}
    if top1 >= GUARDRAIL_WARN_THRESHOLD:
        return {"decision": "WARN", "reason": "MODERATE_SIMILARITY", "matches": matches}
    return {"decision": "ALLOW", "reason": "NEW_SOLUTION", "matches": matches}


def parse_ts(value: Optional[str]) -> Optional[float]:
    from datetime import datetime
    if not value:
        return None
    try:
        return datetime.fromisoformat(value.replace("Z", "+00:00")).timestamp()
    except ValueError:
        return None