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


class KairoGPTConfig:
    def __init__(self, vocab_size, block_size=4096, n_layer=14, n_head=14, n_embd=896, dropout=0.1):
        self.vocab_size = vocab_size
        self.block_size = block_size
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_embd = n_embd
        self.dropout = dropout


class CausalSelfAttention(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        assert cfg.n_embd % cfg.n_head == 0
        self.qkv = nn.Linear(cfg.n_embd, 3 * cfg.n_embd)
        self.proj = nn.Linear(cfg.n_embd, cfg.n_embd)
        self.attn_drop_p = cfg.dropout
        self.resid_drop = nn.Dropout(cfg.dropout)
        self.n_head = cfg.n_head

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

        y = F.scaled_dot_product_attention(
            q, k, v,
            dropout_p=self.attn_drop_p if self.training else 0.0,
            is_causal=True,
        )
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.resid_drop(self.proj(y))


class Block(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.ln1 = nn.LayerNorm(cfg.n_embd)
        self.attn = CausalSelfAttention(cfg)
        self.ln2 = nn.LayerNorm(cfg.n_embd)
        self.mlp = nn.Sequential(
            nn.Linear(cfg.n_embd, 4 * cfg.n_embd),
            nn.GELU(),
            nn.Linear(4 * cfg.n_embd, cfg.n_embd),
            nn.Dropout(cfg.dropout),
        )

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


class KairoGPT(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.cfg = cfg
        self.tok_emb = nn.Embedding(cfg.vocab_size, cfg.n_embd)
        self.pos_emb = nn.Parameter(torch.zeros(1, cfg.block_size, cfg.n_embd))
        self.drop = nn.Dropout(cfg.dropout)
        self.blocks = nn.Sequential(*[Block(cfg) for _ in range(cfg.n_layer)])
        self.ln_f = nn.LayerNorm(cfg.n_embd)
        self.head = nn.Linear(cfg.n_embd, cfg.vocab_size, bias=False)
        self.apply(self._init_weights)

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

    def forward(self, idx, targets=None):
        B, T = idx.shape
        x = self.drop(self.tok_emb(idx) + self.pos_emb[:, :T, :])
        x = self.blocks(x)
        x = self.ln_f(x)
        logits = self.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, temperature=0.8, top_k=40):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.cfg.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / temperature
            if top_k is not None:
                v, _ = torch.topk(logits, top_k)
                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)
        return idx

    @torch.no_grad()
    def generate_stream(self, idx, max_new_tokens, temperature=0.8, top_k=40):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.cfg.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / temperature
            if top_k is not None:
                v, _ = torch.topk(logits, top_k)
                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)
            yield next_id.item()