import math
from dataclasses import dataclass

import torch
import torch.nn as nn
import torch.nn.functional as F


@dataclass
class GPTConfig:
    name: str = "yuspec-gamedev-10m-v0.1"
    vocab_size: int = 16000
    block_size: int = 1024
    n_layer: int = 8
    n_head: int = 4
    n_embd: int = 256
    dropout: float = 0.1
    bias: bool = False


class CausalSelfAttention(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        assert config.n_embd % config.n_head == 0

        self.n_head = config.n_head
        self.n_embd = config.n_embd

        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd, bias=config.bias)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
        self.attn_dropout = nn.Dropout(config.dropout)
        self.resid_dropout = nn.Dropout(config.dropout)

        mask = torch.tril(torch.ones(config.block_size, config.block_size))
        self.register_buffer("mask", mask.view(1, 1, config.block_size, config.block_size))

    def forward(self, x):
        batch, seq_len, channels = x.size()

        q, k, v = self.c_attn(x).split(channels, dim=2)
        head_dim = channels // self.n_head

        q = q.view(batch, seq_len, self.n_head, head_dim).transpose(1, 2)
        k = k.view(batch, seq_len, self.n_head, head_dim).transpose(1, 2)
        v = v.view(batch, seq_len, self.n_head, head_dim).transpose(1, 2)

        att = (q @ k.transpose(-2, -1)) / math.sqrt(head_dim)
        att = att.masked_fill(self.mask[:, :, :seq_len, :seq_len] == 0, float("-inf"))
        att = F.softmax(att, dim=-1)
        att = self.attn_dropout(att)

        y = att @ v
        y = y.transpose(1, 2).contiguous().view(batch, seq_len, channels)
        return self.resid_dropout(self.c_proj(y))


class MLP(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.fc = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
        self.proj = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        x = self.fc(x)
        x = F.gelu(x)
        x = self.proj(x)
        return self.dropout(x)


class Block(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.ln1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln2 = nn.LayerNorm(config.n_embd)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln1(x))
        x = x + self.mlp(self.ln2(x))
        return x


class GPT(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.config = config

        self.token_embedding = nn.Embedding(config.vocab_size, config.n_embd)
        self.position_embedding = nn.Embedding(config.block_size, config.n_embd)
        self.dropout = nn.Dropout(config.dropout)
        self.blocks = nn.ModuleList([Block(config) for _ in range(config.n_layer)])
        self.ln_f = nn.LayerNorm(config.n_embd)
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.lm_head.weight = self.token_embedding.weight

        self.apply(self._init_weights)

        total_params = sum(p.numel() for p in self.parameters())
        print(f"Parameters: {total_params / 1e6:.2f}M")

    def _init_weights(self, module):
        if isinstance(module, nn.Linear):
            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
            if module.bias is not None:
                torch.nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)

    def forward(self, idx, targets=None):
        _, seq_len = idx.size()
        if seq_len > self.config.block_size:
            raise ValueError(f"Sequence length {seq_len} exceeds block_size {self.config.block_size}")

        pos = torch.arange(0, seq_len, dtype=torch.long, device=idx.device)
        tok_emb = self.token_embedding(idx)
        pos_emb = self.position_embedding(pos)
        x = self.dropout(tok_emb + pos_emb)

        for block in self.blocks:
            x = block(x)

        x = self.ln_f(x)
        logits = self.lm_head(x)

        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))

        return logits, loss

    @torch.no_grad()
    def generate(self, idx, max_new_tokens=256, temperature=0.8, top_k=50, eos_id=None, vocab_limit=None):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.config.block_size :]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / max(temperature, 1e-6)

            if vocab_limit is not None and vocab_limit < logits.size(-1):
                logits[:, vocab_limit:] = -float("inf")

            if top_k is not None:
                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
                logits[logits < v[:, [-1]]] = -float("inf")

            probs = F.softmax(logits, dim=-1)
            next_id = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, next_id), dim=1)

            if eos_id is not None and torch.all(next_id == eos_id):
                break

        return idx