# models/architecture.py
import torch
import torch.nn as nn
from torch.nn import functional as F

class LocalConfig:
    def __init__(self, **kwargs):
        for key, value in kwargs.items():
            setattr(self, key, value)
        
        # Fallback defaults if not in JSON
        if not hasattr(self, 'dropout'):
            self.dropout = 0.0

class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        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=False)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=False)
        
        self.attn_dropout = nn.Dropout(config.dropout)
        self.resid_dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        B, T, C = x.size()
        qkv = self.c_attn(x)
        q, k, v = qkv.split(self.n_embd, dim=2)
        
        head_dim = C // self.n_head
        q = q.view(B, T, self.n_head, head_dim).transpose(1, 2)
        k = k.view(B, T, self.n_head, head_dim).transpose(1, 2)
        v = v.view(B, T, self.n_head, head_dim).transpose(1, 2)

        # PyTorch Flash Attention via scaled_dot_product_attention
        y = F.scaled_dot_product_attention(
            q, k, v, 
            is_causal=True, 
            dropout_p=self.config.dropout if self.training else 0.0
        )
        
        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):
        super().__init__()
        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd, bias=False)
        self.gelu = nn.GELU()
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd, bias=False)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        return self.dropout(self.c_proj(self.gelu(self.c_fc(x))))

class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.n_embd)
        self.mlp = MLP(config)

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

class CRAB(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.n_embd),
            wpe = nn.Embedding(config.block_size, config.n_embd),
            drop = nn.Dropout(config.dropout),
            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f = nn.LayerNorm(config.n_embd),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.transformer.wte.weight = self.lm_head.weight

    def forward(self, idx, targets=None):
        b, t = idx.size()
        pos = torch.arange(0, t, dtype=torch.long, device=idx.device)
        
        x = self.transformer.drop(self.transformer.wte(idx) + self.transformer.wpe(pos))
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)
        logits = self.lm_head(x)

        loss = None
        if targets is not None:
            # -100 ignore_index for Target Masking in instruction tuning
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-100)
            
        return logits, loss