"""HT/MS Mixin — analyze_match_htms endpoint and helpers.

Auto-extracted mixin module — split from services/single_match_orchestrator.py.
All methods here are composed into SingleMatchOrchestrator via inheritance.
`self` attributes (self.dsn, self.enrichment, self.v25_predictor, etc.) are
initialised in the main __init__.
"""

from __future__ import annotations

import json
import re
import time
import math
import os
import pickle
from collections import defaultdict
from typing import Any, Dict, List, Optional, Set, Tuple, overload

import pandas as pd
import numpy as np

import psycopg2
from psycopg2.extras import RealDictCursor

from data.db import get_clean_dsn
from schemas.prediction import FullMatchPrediction
from schemas.match_data import MatchData
from models.v25_ensemble import V25Predictor, get_v25_predictor
try:
    from models.v27_predictor import V27Predictor, compute_divergence, compute_value_edge
except ImportError:
    class V27Predictor:  # type: ignore[no-redef]
        def __init__(self): self.models = {}
        def load_models(self): return False
        def predict_all(self, features): return {}
    def compute_divergence(*args, **kwargs):
        return {}
    def compute_value_edge(*args, **kwargs):
        return {}
from features.odds_band_analyzer import OddsBandAnalyzer
try:
    from models.basketball_v25 import (
        BasketballMatchPrediction,
        get_basketball_v25_predictor,
    )
except ImportError:
    BasketballMatchPrediction = Any  # type: ignore[misc]
    def get_basketball_v25_predictor() -> Any:
        raise ImportError("Basketball predictor is not available")
from core.engines.player_predictor import PlayerPrediction, get_player_predictor
from services.feature_enrichment import FeatureEnrichmentService
from services.betting_brain import BettingBrain
from services.v26_shadow_engine import V26ShadowEngine, get_v26_shadow_engine
from services.match_commentary import generate_match_commentary
from utils.top_leagues import load_top_league_ids
from utils.league_reliability import load_league_reliability
from config.config_loader import build_threshold_dict, get_threshold_default
from models.calibration import get_calibrator


class HtmsMixin:
    def analyze_match_htms(self, match_id: str) -> Optional[Dict[str, Any]]:
        """
        HT/MS focused response for upset-hunting workflows.

        This endpoint is intentionally additive and does not mutate the
        standard /v20plus/analyze package contract.
        """
        data = self._load_match_data(match_id)
        if data is None:
            return None

        if str(data.sport or "").lower() != "football":
            return {
                "status": "skip",
                "match_id": match_id,
                "reason": "unsupported_sport",
                "engine_used": "htms_router",
            }

        is_top_league = self._is_top_league(data.league_id)
        engine_used = "v20plus_top_htms"

        # Hard gate: HT/MS upset model is trained on top leagues only.
        if not is_top_league:
            return {
                "status": "skip",
                "match_id": match_id,
                "reason": "out_of_training_scope",
                "engine_used": engine_used,
                "data_quality": {
                    "label": "LOW",
                    "flags": ["league_out_of_scope"],
                },
            }

        missing_requirements = self._missing_htms_requirements(data)
        if missing_requirements:
            return {
                "status": "skip",
                "match_id": match_id,
                "reason": "missing_critical_data",
                "missing": missing_requirements,
                "engine_used": engine_used,
                "data_quality": {
                    "label": "LOW",
                    "flags": [f"missing_{item}" for item in missing_requirements],
                },
            }

        base_package = self.analyze_match(match_id)
        if not base_package:
            return None
        data_quality = base_package.get("data_quality", {})
        market_board = base_package.get("market_board", {})
        ms_market = market_board.get("MS", {})
        ht_market = market_board.get("HT", {})
        htft_probs = market_board.get("HTFT", {}).get("probs", {})

        reversal_probs = {
            "1/2": float(htft_probs.get("1/2", 0.0)),
            "2/1": float(htft_probs.get("2/1", 0.0)),
            "X/1": float(htft_probs.get("X/1", 0.0)),
            "X/2": float(htft_probs.get("X/2", 0.0)),
        }
        top_reversal = max(reversal_probs.items(), key=lambda item: item[1])

        ms_conf = float(ms_market.get("confidence", 0.0))
        ht_conf = float(ht_market.get("confidence", 0.0))
        base_conf = (ms_conf + ht_conf) / 2.0

        confidence_cap = 100.0
        penalties: List[str] = []
        if data.lineup_source == "probable_xi":
            confidence_cap = min(confidence_cap, 72.0)
            penalties.append("lineup_probable_xi")
        if data.lineup_source == "none":
            confidence_cap = min(confidence_cap, 58.0)
            penalties.append("lineup_unavailable")
        if str(data_quality.get("label", "LOW")).upper() == "LOW":
            confidence_cap = min(confidence_cap, 55.0)
            penalties.append("low_data_quality")

        final_conf = min(base_conf, confidence_cap)

        upset_score = self._compute_htms_upset_score(
            reversal_probs=reversal_probs,
            odds_data=data.odds_data,
            is_top_league=is_top_league,
        )
        upset_threshold = 58.0 if is_top_league else 54.0
        upset_playable = (
            upset_score >= upset_threshold
            and top_reversal[1] >= 0.045
            and final_conf >= 45.0
            and "low_data_quality" not in penalties
        )

        return {
            "status": "ok",
            "engine_used": engine_used,
            "match_info": base_package.get("match_info", {}),
            "data_quality": data_quality,
            "htms_core": {
                "ms_pick": ms_market.get("pick"),
                "ms_confidence": round(ms_conf, 1),
                "ht_pick": ht_market.get("pick"),
                "ht_confidence": round(ht_conf, 1),
                "combined_confidence": round(final_conf, 1),
                "confidence_cap": round(confidence_cap, 1),
                "penalties": penalties,
            },
            "surprise_hunter": {
                "upset_score": round(upset_score, 1),
                "threshold": upset_threshold,
                "playable": upset_playable,
                "top_reversal_pick": top_reversal[0],
                "top_reversal_prob": round(top_reversal[1], 4),
                "reversal_probs": {
                    key: round(value, 4) for key, value in reversal_probs.items()
                },
            },
            "risk": base_package.get("risk", {}),
            "reasoning_factors": base_package.get("reasoning_factors", []),
        }

    def _is_top_league(self, league_id: Optional[str]) -> bool:
        if not league_id:
            return False
        return str(league_id) in self.top_league_ids

    def _missing_htms_requirements(self, data: MatchData) -> List[str]:
        missing: List[str] = []
        ms_keys = ("ms_h", "ms_d", "ms_a")
        ht_keys = ("ht_h", "ht_d", "ht_a")
        if not all(float(data.odds_data.get(k, 0.0) or 0.0) > 1.0 for k in ms_keys):
            missing.append("ms_odds")
        if not all(float(data.odds_data.get(k, 0.0) or 0.0) > 1.0 for k in ht_keys):
            missing.append("ht_odds")

        return missing

    def _compute_htms_upset_score(
        self,
        reversal_probs: Dict[str, float],
        odds_data: Dict[str, float],
        is_top_league: bool,
    ) -> float:
        ms_h = self._to_float(odds_data.get("ms_h"), 0.0)
        ms_a = self._to_float(odds_data.get("ms_a"), 0.0)
        if ms_h <= 1.0 or ms_a <= 1.0:
            favorite_gap = 0.0
        else:
            favorite_gap = abs(ms_h - ms_a)

        reversal_max = max(reversal_probs.values()) if reversal_probs else 0.0
        reversal_sum = sum(reversal_probs.values())

        # Strong favorite + reversal probability is the core upset signal.
        gap_factor = min(1.0, favorite_gap / 2.0)
        score = (
            (reversal_max * 100.0 * 0.60)
            + (reversal_sum * 100.0 * 0.25)
            + (gap_factor * 100.0 * 0.15)
        )

        if not is_top_league:
            # Non-top leagues are noisier; keep it slightly conservative.
            score *= 0.92
        return max(0.0, min(100.0, score))