"""
Self-contained 63.8M Parameter GPT-Style Decoder Transformer
- Pre-LayerNorm Architecture
- Flash Attention via PyTorch F.scaled_dot_product_attention
- Tied Token Embedding & LM Head Weights
"""

import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from config import GPTConfig


class CausalSelfAttention(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        assert config.d_model % config.n_head == 0, "d_model must be divisible by n_head"
        self.n_head = config.n_head
        self.d_model = config.d_model
        self.head_dim = config.d_model // config.n_head
        self.dropout_p = config.dropout

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

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        B, T, C = x.size()
        qkv = self.c_attn(x)
        q, k, v = qkv.split(self.d_model, dim=2)

        k = k.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
        q = q.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
        v = v.view(B, T, self.n_head, self.head_dim).transpose(1, 2)

        dropout_p = self.dropout_p if self.training else 0.0
        y = F.scaled_dot_product_attention(
            q, k, v, attn_mask=None, dropout_p=dropout_p, is_causal=True
        )

        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.resid_dropout(self.c_proj(y))


class MLP(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.c_fc = nn.Linear(config.d_model, config.d_ffn, bias=config.bias)
        self.gelu = nn.GELU()
        self.c_proj = nn.Linear(config.d_ffn, config.d_model, bias=config.bias)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        return self.dropout(self.c_proj(self.gelu(self.c_fc(x))))


class TransformerBlock(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.d_model, elementwise_affine=config.bias)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.d_model, elementwise_affine=config.bias)
        self.mlp = MLP(config)

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = x + self.attn(self.ln_1(x))
        x = x + self.mlp(self.ln_2(x))
        return x


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

        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.d_model),
            wpe = nn.Embedding(config.context_length, config.d_model),
            drop = nn.Dropout(config.dropout),
            h = nn.ModuleList([TransformerBlock(config) for _ in range(config.n_layer)]),
            ln_f = nn.LayerNorm(config.d_model, elementwise_affine=config.bias),
        ))
        self.lm_head = nn.Linear(config.d_model, config.vocab_size, bias=False)

        # Weight tying: token embeddings and LM head share weights
        self.transformer.wte.weight = self.lm_head.weight

        # Weight initialization
        self.apply(self._init_weights)
        for pn, p in self.named_parameters():
            if pn.endswith('c_proj.weight'):
                torch.nn.init.normal_(p, mean=0.0, std=0.02 / math.sqrt(2 * config.n_layer))

    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: torch.Tensor, targets: torch.Tensor = None):
        b, t = idx.size()
        pos = torch.arange(0, t, dtype=torch.long, device=idx.device)

        tok_emb = self.transformer.wte(idx)
        pos_emb = self.transformer.wpe(pos)
        x = self.transformer.drop(tok_emb + pos_emb)

        for block in self.transformer.h:
            x = block(x)

        x = self.transformer.ln_f(x)

        if targets is not None:
            logits = self.lm_head(x)
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
        else:
            logits = self.lm_head(x[:, [-1], :])
            loss = None

        return logits, loss

    def get_num_params(self) -> int:
        return sum(p.numel() for p in self.parameters())

    def configure_optimizers(self, weight_decay: float, learning_rate: float, betas: tuple, device_type: str):
        decay_params = [p for n, p in self.named_parameters() if p.requires_grad and p.dim() >= 2]
        nodecay_params = [p for n, p in self.named_parameters() if p.requires_grad and p.dim() < 2]

        optim_groups = [
            {'params': decay_params, 'weight_decay': weight_decay},
            {'params': nodecay_params, 'weight_decay': 0.0}
        ]

        fused_available = 'fused' in torch.optim.AdamW.__init__.__code__.co_varnames
        use_fused = fused_available and device_type == 'cuda'
        extra_args = dict(fused=True) if use_fused else dict()
        return torch.optim.AdamW(optim_groups, lr=learning_rate, betas=betas, eps=1e-8, **extra_args)

    @torch.no_grad()
    def generate(self, idx: torch.Tensor, max_new_tokens: int = 80, temperature: float = 0.8, top_k: int = 40) -> torch.Tensor:
        self.eval()
        for _ in range(max_new_tokens):
            idx_cond = idx if idx.size(1) <= self.config.context_length else idx[:, -self.config.context_length:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / max(temperature, 1e-5)

            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)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, idx_next), dim=1)

        return idx


# Alias
GPT = SmallGPT