"""Cloud vector store — wraps Pinecone (default) or Qdrant.

Vectors are pre-encrypted blobs from the client.  The backend stores them
alongside a deterministic 32-dim float representation derived from the blob's
SHA-256 hash.  Semantic ANN search is not meaningful on encrypted data — this
is a known trade-off documented in the backend plan.

Isolation: Pinecone uses ``namespace=user_id``; Qdrant filters by
``user_id`` payload field on a shared collection.
"""

from __future__ import annotations

import base64
import hashlib
from typing import Any

from pinecone import Pinecone
from qdrant_client import QdrantClient
from qdrant_client.models import FieldCondition, Filter, MatchValue, PointIdsList, PointStruct

from app.config.settings import settings
from app.schemas import VectorItem, VectorSearchResult

_QDRANT_COLLECTION = "adiuva_vectors"


def _blob_to_vector(blob: bytes) -> list[float]:
    """Derive a 32-dim float vector from *blob* for storage purposes only.

    Uses SHA-256 to produce a deterministic 32-byte fingerprint, then
    normalises each byte to the range [-1.0, 1.0].  This vector carries no
    semantic meaning on encrypted data.
    """
    return [(b - 128) / 128.0 for b in hashlib.sha256(blob).digest()]


class VectorStore:
    """Thin wrapper around Pinecone or Qdrant.

    The backend to use is selected at runtime:
    - Pinecone: when ``settings.PINECONE_API_KEY`` is non-empty.
    - Qdrant: otherwise (requires ``settings.QDRANT_URL``).
    """

    def _use_pinecone(self) -> bool:
        return bool(settings.PINECONE_API_KEY)

    # ── Pinecone helpers ──────────────────────────────────────────────

    def _pinecone_index(self) -> Any:
        pc = Pinecone(api_key=settings.PINECONE_API_KEY)
        return pc.Index(settings.PINECONE_INDEX)

    # ── Qdrant helpers ────────────────────────────────────────────────

    def _qdrant_client(self) -> Any:
        return QdrantClient(
            url=settings.QDRANT_URL,
            api_key=settings.QDRANT_API_KEY or None,
        )

    # ── Public API ────────────────────────────────────────────────────

    async def upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
        """Store encrypted vectors in the backend.

        Each ``VectorItem.blob`` is base64-encoded and kept in metadata/payload
        so it can be returned verbatim during search.

        Args:
            user_id: Used as Pinecone namespace or Qdrant payload field.
            vectors: List of encrypted vector items from the client.
        """
        if self._use_pinecone():
            await self._pinecone_upsert(user_id, vectors)
        else:
            await self._qdrant_upsert(user_id, vectors)

    async def search(
        self,
        user_id: str,
        query_blob: bytes,
        top_k: int,
    ) -> list[VectorSearchResult]:
        """Query the vector store and return encrypted result blobs.

        The query vector is derived from *query_blob* using the same
        deterministic mapping as upsert.

        Args:
            user_id:    Scopes the search to this user's namespace.
            query_blob: Encrypted query from the client.
            top_k:      Maximum number of results to return.

        Returns:
            List of ``VectorSearchResult`` with ``id``, ``score``, and ``blob``.
        """
        if self._use_pinecone():
            return await self._pinecone_search(user_id, query_blob, top_k)
        return await self._qdrant_search(user_id, query_blob, top_k)

    async def delete(self, user_id: str, vector_ids: list[str]) -> None:
        """Remove vectors by ID, scoped to *user_id*.

        Args:
            user_id:    Namespace / payload filter to prevent cross-user deletion.
            vector_ids: List of vector IDs to remove.
        """
        if self._use_pinecone():
            await self._pinecone_delete(user_id, vector_ids)
        else:
            await self._qdrant_delete(user_id, vector_ids)

    # ── Pinecone implementation ───────────────────────────────────────

    async def _pinecone_upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
        index = self._pinecone_index()
        records = [
            {
                "id": v.id,
                "values": _blob_to_vector(v.blob),
                "metadata": {
                    "blob": base64.b64encode(v.blob).decode(),
                    "checksum": v.checksum,
                    "user_id": user_id,
                },
            }
            for v in vectors
        ]
        index.upsert(vectors=records, namespace=user_id)

    async def _pinecone_search(
        self, user_id: str, query_blob: bytes, top_k: int
    ) -> list[VectorSearchResult]:
        index = self._pinecone_index()
        query_vector = _blob_to_vector(query_blob)
        response = index.query(
            vector=query_vector,
            top_k=top_k,
            namespace=user_id,
            include_metadata=True,
        )
        results: list[VectorSearchResult] = []
        for match in response.get("matches", []):
            blob_bytes = base64.b64decode(match["metadata"]["blob"])
            results.append(
                VectorSearchResult(
                    id=match["id"],
                    score=match["score"],
                    blob=blob_bytes,
                )
            )
        return results

    async def _pinecone_delete(self, user_id: str, vector_ids: list[str]) -> None:
        index = self._pinecone_index()
        index.delete(ids=vector_ids, namespace=user_id)

    # ── Qdrant implementation ─────────────────────────────────────────

    async def _qdrant_upsert(self, user_id: str, vectors: list[VectorItem]) -> None:
        client = self._qdrant_client()
        points = [
            PointStruct(
                id=v.id,
                vector=_blob_to_vector(v.blob),
                payload={
                    "blob": base64.b64encode(v.blob).decode(),
                    "checksum": v.checksum,
                    "user_id": user_id,
                },
            )
            for v in vectors
        ]
        client.upsert(collection_name=_QDRANT_COLLECTION, points=points)

    async def _qdrant_search(
        self, user_id: str, query_blob: bytes, top_k: int
    ) -> list[VectorSearchResult]:
        client = self._qdrant_client()
        query_vector = _blob_to_vector(query_blob)
        hits = client.search(
            collection_name=_QDRANT_COLLECTION,
            query_vector=query_vector,
            query_filter=Filter(
                must=[FieldCondition(key="user_id", match=MatchValue(value=user_id))]
            ),
            limit=top_k,
        )
        return [
            VectorSearchResult(
                id=str(hit.id),
                score=hit.score,
                blob=base64.b64decode(hit.payload["blob"]),
            )
            for hit in hits
        ]

    async def _qdrant_delete(self, user_id: str, vector_ids: list[str]) -> None:
        client = self._qdrant_client()
        client.delete(
            collection_name=_QDRANT_COLLECTION,
            points_selector=PointIdsList(points=vector_ids),
        )