from __future__ import annotations

import os
import time
from functools import lru_cache
from typing import Any, Dict, List, Tuple, Iterable, Optional

from app.config import get_settings
from app.models.dto import (
    QueryRequest, 
    QueryResponse, 
    QueryHit, 
    Explanation, 
    ScoreBreakdown, 
    Reason, 
    EdgeDTO
)
import app.core.qdrant as qdr
import app.core.qdrant_points as qp
import app.services.embeddings_client as ec
import app.core.graph_adapter as ga

try:
    import yaml  # type: ignore[import]
except Exception:  # pragma: no cover - Fallback, falls PyYAML nicht installiert ist
    yaml = None  # type: ignore[assignment]


@lru_cache
def _get_scoring_weights() -> Tuple[float, float, float]:
    """Liefert (semantic_weight, edge_weight, centrality_weight) für den Retriever.

    Priorität:
    1. Werte aus config/retriever.yaml (falls vorhanden und gültig).
    2. Fallback auf Settings.RETRIEVER_W_* (ENV-basiert).
    """
    settings = get_settings()
    sem = float(getattr(settings, "RETRIEVER_W_SEM", 1.0))
    edge = float(getattr(settings, "RETRIEVER_W_EDGE", 0.0))
    cent = float(getattr(settings, "RETRIEVER_W_CENT", 0.0))

    # YAML-Override, falls konfiguriert
    config_path = os.getenv("MINDNET_RETRIEVER_CONFIG", "config/retriever.yaml")
    if yaml is None:
        return sem, edge, cent
    try:
        if os.path.exists(config_path):
            with open(config_path, "r", encoding="utf-8") as f:
                data = yaml.safe_load(f) or {}
            scoring = data.get("scoring", {}) or {}
            sem = float(scoring.get("semantic_weight", sem))
            edge = float(scoring.get("edge_weight", edge))
            cent = float(scoring.get("centrality_weight", cent))
    except Exception:
        # Bei Fehlern in der YAML-Konfiguration defensiv auf Defaults zurückfallen
        return sem, edge, cent
    return sem, edge, cent


def _get_client_and_prefix() -> Tuple[Any, str]:
    """Liefert (QdrantClient, prefix) basierend auf QdrantConfig.from_env()."""
    cfg = qdr.QdrantConfig.from_env()
    client = qdr.get_client(cfg)
    return client, cfg.prefix


def _get_query_vector(req: QueryRequest) -> List[float]:
    """
    Liefert den Query-Vektor aus dem Request.
    """
    if req.query_vector:
        return list(req.query_vector)

    if not req.query:
        raise ValueError("QueryRequest benötigt entweder query oder query_vector")

    settings = get_settings()
    model_name = settings.MODEL_NAME

    try:
        return ec.embed_text(req.query, model_name=model_name)  # type: ignore[call-arg]
    except TypeError:
        return ec.embed_text(req.query)  # type: ignore[call-arg]


def _semantic_hits(
    client: Any,
    prefix: str,
    vector: List[float],
    top_k: int,
    filters: Dict[str, Any] | None = None,
) -> List[Tuple[str, float, Dict[str, Any]]]:
    """Führt eine semantische Suche über mindnet_chunks aus und liefert Roh-Treffer."""
    flt = filters or None
    raw_hits = qp.search_chunks_by_vector(client, prefix, vector, top=top_k, filters=flt)
    results: List[Tuple[str, float, Dict[str, Any]]] = []
    for pid, score, payload in raw_hits:
        results.append((str(pid), float(score), dict(payload or {})))
    return results


def _compute_total_score(
    semantic_score: float,
    payload: Dict[str, Any],
    edge_bonus: float = 0.0,
    cent_bonus: float = 0.0,
) -> Tuple[float, float, float]:
    """Berechnet total_score aus semantic_score, retriever_weight und Graph-Boni."""
    raw_weight = payload.get("retriever_weight", 1.0)
    try:
        weight = float(raw_weight)
    except (TypeError, ValueError):
        weight = 1.0
    if weight < 0.0:
        weight = 0.0

    sem_w, edge_w, cent_w = _get_scoring_weights()
    total = (sem_w * float(semantic_score) * weight) + (edge_w * edge_bonus) + (cent_w * cent_bonus)
    return float(total), float(edge_bonus), float(cent_bonus)


# --- WP-04b Explanation Logic ---

def _build_explanation(
    semantic_score: float,
    payload: Dict[str, Any],
    edge_bonus: float,
    cent_bonus: float,
    subgraph: Optional[ga.Subgraph],
    node_key: Optional[str]
) -> Explanation:
    """
    Erstellt ein detailliertes Explanation-Objekt für einen Treffer.
    Analysiert Scores, Typen und eingehende Kanten.
    """
    # 1. Weights & Config laden
    sem_w, edge_w, cent_w = _get_scoring_weights()
    
    try:
        type_weight = float(payload.get("retriever_weight", 1.0))
    except (TypeError, ValueError):
        type_weight = 1.0
    
    note_type = payload.get("type", "unknown")

    # 2. Score Breakdown berechnen
    breakdown = ScoreBreakdown(
        semantic_contribution=(sem_w * semantic_score * type_weight),
        edge_contribution=(edge_w * edge_bonus),
        centrality_contribution=(cent_w * cent_bonus),
        raw_semantic=semantic_score,
        raw_edge_bonus=edge_bonus,
        raw_centrality=cent_bonus,
        node_weight=type_weight
    )

    reasons: List[Reason] = []
    edges_dto: List[EdgeDTO] = []

    # 3. Semantische Gründe
    if semantic_score > 0.85:
        reasons.append(Reason(
            kind="semantic", 
            message="Sehr hohe textuelle Übereinstimmung mit der Anfrage.",
            score_impact=breakdown.semantic_contribution
        ))
    elif semantic_score > 0.75:
        reasons.append(Reason(
            kind="semantic", 
            message="Gute textuelle Übereinstimmung.",
            score_impact=breakdown.semantic_contribution
        ))

    # 4. Typ-Gründe
    if type_weight > 1.0:
        reasons.append(Reason(
            kind="type", 
            message=f"Bevorzugt aufgrund des Typs '{note_type}' (Gewicht: {type_weight}).",
            score_impact=(sem_w * semantic_score * (type_weight - 1.0)) # Delta
        ))
    elif type_weight < 1.0:
        reasons.append(Reason(
            kind="type", 
            message=f"Abgewertet aufgrund des Typs '{note_type}' (Gewicht: {type_weight}).",
            score_impact=None
        ))

    # 5. Graph-Gründe (Incoming Edges)
    if subgraph and node_key and edge_bonus > 0:
        # Wir suchen nach eingehenden Kanten, die diesen Bonus verursacht haben.
        # graph_adapter.py (v0.4.0) muss get_incoming_edges bereitstellen.
        if hasattr(subgraph, "get_incoming_edges"):
            incoming = subgraph.get_incoming_edges(node_key)
            
            # Sortieren nach Gewicht (stärkste zuerst)
            incoming_sorted = sorted(incoming, key=lambda e: e.get("weight", 0.0), reverse=True)
            
            # Top-3 Gründe extrahieren
            for idx, edge in enumerate(incoming_sorted[:3]):
                src = edge.get("source", "Unknown")
                kind = edge.get("kind", "edge")
                weight = edge.get("weight", 0.0)
                
                msg = f"Verbunden mit '{src}' via '{kind}'"
                reasons.append(Reason(
                    kind="edge",
                    message=msg,
                    score_impact=(edge_w * weight),
                    details={"source": src, "kind": kind, "weight": weight}
                ))
                
                # EdgeDTO für die API
                edges_dto.append(EdgeDTO(
                    id=f"{src}->{node_key}:{kind}", # Synthetische ID für Anzeige
                    kind=kind,
                    source=src,
                    target=node_key,
                    weight=weight,
                    direction="in"
                ))
        else:
            # Fallback, falls GraphAdapter noch alt
            reasons.append(Reason(kind="edge", message="Knoten ist im Kontext-Graphen vernetzt."))

    # 6. Centrality Gründe
    if cent_bonus > 0.05:
        reasons.append(Reason(
            kind="centrality",
            message="Knoten ist ein zentraler Hub im Kontext der Anfrage.",
            score_impact=breakdown.centrality_contribution
        ))

    return Explanation(
        breakdown=breakdown,
        reasons=reasons,
        related_edges=edges_dto if edges_dto else None
    )

# --- End Explanation Logic ---


def _extract_expand_options(req: QueryRequest) -> Tuple[int, List[str] | None]:
    """Extrahiert depth und edge_types aus req.expand."""
    expand = getattr(req, "expand", None)
    if not expand:
        return 0, None

    depth = 1
    edge_types: List[str] | None = None

    if hasattr(expand, "depth") or hasattr(expand, "edge_types"):
        depth = int(getattr(expand, "depth", 1) or 1)
        types_val = getattr(expand, "edge_types", None)
        if types_val:
            edge_types = list(types_val)
        return depth, edge_types

    if isinstance(expand, dict):
        if "depth" in expand:
            depth = int(expand.get("depth") or 1)
        if "edge_types" in expand and expand["edge_types"] is not None:
            edge_types = list(expand["edge_types"])
        return depth, edge_types

    return 0, None


def _build_hits_from_semantic(
    hits: Iterable[Tuple[str, float, Dict[str, Any]]],
    top_k: int,
    used_mode: str,
    subgraph: ga.Subgraph | None = None,
    explain: bool = False,  # WP-04b
) -> QueryResponse:
    """Baut aus Raw-Hits und optionalem Subgraph strukturierte QueryHits.
    
    WP-04b: Wenn explain=True, wird _build_explanation aufgerufen.
    """
    t0 = time.time()

    enriched: List[Tuple[str, float, Dict[str, Any], float, float, float]] = []

    for pid, semantic_score, payload in hits:
        edge_bonus = 0.0
        cent_bonus = 0.0
        node_key = payload.get("chunk_id") or payload.get("note_id")
        
        if subgraph is not None and node_key:
            try:
                edge_bonus = float(subgraph.edge_bonus(node_key))
            except Exception:
                edge_bonus = 0.0
            try:
                cent_bonus = float(subgraph.centrality_bonus(node_key))
            except Exception:
                cent_bonus = 0.0

        total, edge_bonus, cent_bonus = _compute_total_score(
            semantic_score,
            payload,
            edge_bonus=edge_bonus,
            cent_bonus=cent_bonus,
        )
        enriched.append((pid, float(semantic_score), payload, total, edge_bonus, cent_bonus))

    # Sortierung nach total_score absteigend
    enriched_sorted = sorted(enriched, key=lambda h: h[3], reverse=True)
    limited = enriched_sorted[: max(1, top_k)]

    results: List[QueryHit] = []
    for pid, semantic_score, payload, total, edge_bonus, cent_bonus in limited:
        note_id = payload.get("note_id")
        path = payload.get("path")
        section = payload.get("section") or payload.get("section_title")
        node_key = payload.get("chunk_id") or payload.get("note_id")

        # WP-04b: Explanation bauen?
        explanation_obj = None
        if explain:
            explanation_obj = _build_explanation(
                semantic_score=float(semantic_score),
                payload=payload,
                edge_bonus=edge_bonus,
                cent_bonus=cent_bonus,
                subgraph=subgraph,
                node_key=node_key
            )

        results.append(
            QueryHit(
                node_id=str(pid),
                note_id=note_id,
                semantic_score=float(semantic_score),
                edge_bonus=edge_bonus,
                centrality_bonus=cent_bonus,
                total_score=total,
                paths=None,
                source={
                    "path": path,
                    "section": section,
                },
                explanation=explanation_obj
            )
        )

    dt = int((time.time() - t0) * 1000)
    return QueryResponse(results=results, used_mode=used_mode, latency_ms=dt)


def semantic_retrieve(req: QueryRequest) -> QueryResponse:
    """Reiner semantischer Retriever (ohne Edge-Expansion)."""
    client, prefix = _get_client_and_prefix()
    vector = _get_query_vector(req)
    top_k = req.top_k or get_settings().RETRIEVER_TOP_K

    hits = _semantic_hits(client, prefix, vector, top_k=top_k, filters=req.filters)
    
    # explain Flag durchreichen
    return _build_hits_from_semantic(
        hits, 
        top_k=top_k, 
        used_mode="semantic", 
        subgraph=None,
        explain=req.explain
    )


def hybrid_retrieve(req: QueryRequest) -> QueryResponse:
    """Hybrid-Retriever: semantische Suche + optionale Edge-Expansion."""
    client, prefix = _get_client_and_prefix()

    if req.query_vector:
        vector = list(req.query_vector)
    else:
        vector = _get_query_vector(req)

    top_k = req.top_k or get_settings().RETRIEVER_TOP_K

    hits = _semantic_hits(client, prefix, vector, top_k=top_k, filters=req.filters)

    depth, edge_types = _extract_expand_options(req)
    subgraph: ga.Subgraph | None = None
    if depth and depth > 0:
        seed_ids: List[str] = []
        for _pid, _score, payload in hits:
            key = payload.get("chunk_id") or payload.get("note_id")
            if key and key not in seed_ids:
                seed_ids.append(key)

        if seed_ids:
            try:
                subgraph = ga.expand(client, prefix, seed_ids, depth=depth, edge_types=edge_types)
            except Exception:
                subgraph = None

    # explain Flag durchreichen
    return _build_hits_from_semantic(
        hits, 
        top_k=top_k, 
        used_mode="hybrid", 
        subgraph=subgraph,
        explain=req.explain
    )