package ai

import (
	"math"
	"math/rand/v2"
	"slices"

	"github.com/greyson/super-auto-pets-board-game/internal/game"
)

// sellPetPenalty converts "persistent pet value destroyed by a sell" into a
// score penalty (see the sell-candidate logic in shop.go). A pet's keepValue
// is on the order of 1–5; multiplied by this weight and the future's share of
// the blend, one junk-pet sell drops a candidate by roughly a tenth of a
// win-probability point — enough to make keeping a body the default, while
// still letting a strongly positive rollout justify a genuine reshape.
const sellPetPenalty = 0.20

// winScore converts a simulated battle outcome to a utility for mySeat:
// win 1, draw 0.5 (nobody gains ground), loss 0, plus a small margin term.
//
// The margin — your surviving pets minus the enemy's — breaks ties among
// outcomes that share a verdict: a loss where you took most of the enemy down
// beats a wipe, and a decisive win beats a squeaker. It is capped well under
// 0.25 so it can never reorder win above draw above loss; it only decides
// between moves the coarse win/draw/loss signal rates identically. That
// gradient is what makes the bot play on sensibly when every option looks
// hopeless — fielding its strongest force instead of picking at random.
func winScore(res *game.BattleResult, mySeat int) float64 {
	var base float64
	switch res.WinnerSeat {
	case mySeat:
		base = 1
	case -1:
		base = 0.5
	default:
		base = 0
	}
	// Survivors is indexed by battle side, not by seat.
	mySide := res.Side(mySeat)
	margin := 0
	for side, s := range res.Survivors {
		if side == mySide {
			margin += s
		} else {
			margin -= s
		}
	}
	return base + 0.1*math.Tanh(float64(margin)/3)
}

// winProb estimates the chance the arranged deck wins the upcoming battle by
// simulating it against every sampled opponent arrangement, simsPer times
// each (dice rerolled every time). All candidates in one decision share the
// same opponent samples, so comparisons between them are paired and fair.
func (cx *ctx) winProb(myDeck []game.Card, oppDecks [][]game.Card, simsPer int) float64 {
	if len(oppDecks) == 0 || simsPer <= 0 {
		return 0.5
	}
	total, n := 0.0, 0
	for _, opp := range oppDecks {
		for range simsPer {
			// The bot's own deck always takes scratch seat 0, so a rollout reads
			// the same however the real table happens to be seated.
			res := game.SimulateBattle(cx.v.Round, cx.simFirstSeat(), myDeck, opp, nil)
			total += winScore(res, 0)
			n++
		}
	}
	return total / float64(n)
}

// simFirstSeat picks who acts first in a rollout, with the bot at seat 0. Two
// players pass a priority token the bot can see, so it plans against the real
// one; bigger tables flip a coin for each battle, which the bot can't know in
// advance — it rolls too, and averages over both possibilities.
func (cx *ctx) simFirstSeat() int {
	if len(cx.v.Players) == 2 {
		if cx.v.PrioritySeat == cx.me.Seat {
			return 0
		}
		return 1
	}
	return rand.IntN(2)
}

// keepValue ranks a single card's worth to the bot's future: what it loses
// by selling or trading it away. Temporary cards (apples) are nearly free to
// lose — they vanish after the next battle anyway.
func keepValue(c game.Card) float64 {
	if c.Temporary {
		return 0.15
	}
	if c.IsFood() {
		if c.Perk {
			return 1.6
		}
		return 0.3
	}
	val := float64(c.Power)*0.55 + float64(c.Tier)*0.8
	if len(c.Effects) > 0 {
		val += 0.6
	}
	return val
}

// deckValue is the future-facing worth of a deck: card quality plus suit
// synergy (pairs and triples enable the Triple trade-in, the only path to
// higher-tier cards than the current round offers). Temporary cards count
// for nothing here — their value shows up in the battle rollouts instead.
func deckValue(deck []game.Card, round, maxRounds int) float64 {
	total := 0.0
	suits := map[game.Suit]int{}
	for _, c := range deck {
		if c.Temporary {
			continue
		}
		total += keepValue(c)
		if c.IsPet() {
			suits[c.Suit]++
		}
	}
	if round < maxRounds {
		for _, k := range suits {
			switch {
			case k >= 3:
				total += 1.5
			case k == 2:
				total += 0.6
			}
		}
	}
	return total
}

// normFuture squashes an unbounded deck value into (0, 1) so it can be
// blended with a win probability.
func normFuture(val float64) float64 {
	return val / (val + 15)
}

// leadScore ranks pets for early battle positions: raw power fights longest,
// faint effects want to actually faint (early), play effects fire on entry
// wherever they are but are worth protecting slightly less.
func leadScore(c game.Card) float64 {
	s := float64(c.Power)
	for _, e := range c.Effects {
		switch e.Trigger {
		case game.TriggerFaint:
			s += 1.5
		case game.TriggerPlay:
			s += 0.8
		case game.TriggerHurt:
			s += 0.5
		case game.TriggerAfterAttack:
			// Wants to survive its clashes to keep triggering (Bulldog).
			s += 0.6
		}
	}
	return s
}

// heuristicOrder arranges a deck the way a reasonable player might: pets
// sorted by leadScore, apples front-loaded, perks spread across the
// strongest pets, never a food trailing at the bottom. temp adds Gumbel
// noise to every placement — 0 gives the deterministic "book" order, higher
// values give increasingly scrambled-but-plausible alternatives (used to
// model the range of orders an opponent might pick).
func heuristicOrder(deck []game.Card, temp float64) []game.Card {
	var pets, apples, perks, otherFood []game.Card
	for _, c := range deck {
		switch {
		case c.IsPet():
			pets = append(pets, c)
		case c.Perk:
			perks = append(perks, c)
		case c.Food == game.FoodApple:
			apples = append(apples, c)
		default:
			otherFood = append(otherFood, c)
		}
	}
	noisy := func(base float64) float64 {
		if temp <= 0 {
			return base
		}
		// Gumbel-perturbed scores turn a sort into a plausibility-weighted
		// random ranking.
		return base - temp*math.Log(-math.Log(rand.Float64()))
	}
	slices.SortStableFunc(pets, func(a, b game.Card) int {
		av, bv := noisy(leadScore(a)), noisy(leadScore(b))
		switch {
		case av > bv:
			return -1
		case av < bv:
			return 1
		}
		return 0
	})
	if len(pets) == 0 {
		// No pets means an immediate loss; foods are wasted regardless.
		return append(append(append(apples, perks...), otherFood...), pets...)
	}
	// Assign foods to pet indices, then interleave.
	assign := make([][]game.Card, len(pets))
	strongest := 0
	for i, p := range pets {
		if p.Power > pets[strongest].Power {
			strongest = i
		}
	}
	for _, a := range apples {
		at := 0
		if temp > 0 && rand.Float64() < 0.4 {
			at = rand.IntN(len(pets))
		}
		assign[at] = append(assign[at], a)
	}
	// Perks one per pet, best pets first (a pet only keeps its last perk).
	perkOrder := []int{strongest}
	for i := range pets {
		if i != strongest {
			perkOrder = append(perkOrder, i)
		}
	}
	for i, p := range perks {
		at := perkOrder[min(i, len(perkOrder)-1)]
		if temp > 0 && rand.Float64() < 0.3 {
			at = rand.IntN(len(pets))
		}
		assign[at] = append(assign[at], p)
	}
	for i, f := range otherFood {
		assign[i%len(pets)] = append(assign[i%len(pets)], f)
	}
	out := make([]game.Card, 0, len(deck))
	for i, p := range pets {
		out = append(out, assign[i]...)
		out = append(out, p)
	}
	return out
}