"""
AILO Model for HuggingFace Transformers - Matching original architecture
"""

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
from typing import Optional, Tuple, Union

from transformers import PreTrainedModel
from transformers.generation import GenerationMixin
from transformers.modeling_outputs import CausalLMOutputWithPast

try:
    from .configuration_ailo import AILOConfig
except ImportError:
    from configuration_ailo import AILOConfig


class RotaryPositionalEmbedding(nn.Module):
    """Rotary Position Embedding (RoPE)."""
    
    def __init__(self, dim: int, max_seq_len: int = 512, base: int = 10000):
        super().__init__()
        inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float() / dim))
        self.register_buffer("inv_freq", inv_freq)
        self.max_seq_len = max_seq_len
        
    def forward(self, x: torch.Tensor, seq_len: int) -> Tuple[torch.Tensor, torch.Tensor]:
        t = torch.arange(seq_len, device=x.device).type_as(self.inv_freq)
        freqs = torch.einsum("i,j->ij", t, self.inv_freq)
        emb = torch.cat((freqs, freqs), dim=-1)
        return emb.cos(), emb.sin()


def apply_rotary_pos_emb(q, k, cos, sin):
    """Apply rotary position embedding."""
    def rotate_half(x):
        x1, x2 = x[..., :x.shape[-1]//2], x[..., x.shape[-1]//2:]
        return torch.cat((-x2, x1), dim=-1)
    
    q_embed = (q * cos) + (rotate_half(q) * sin)
    k_embed = (k * cos) + (rotate_half(k) * sin)
    return q_embed, k_embed


class AILOAttention(nn.Module):
    """Multi-head attention matching original structure."""
    
    def __init__(self, config: AILOConfig):
        super().__init__()
        self.n_heads = config.num_attention_heads
        self.head_dim = config.hidden_size // config.num_attention_heads
        self.scale = self.head_dim ** -0.5
        
        # Match original: separate q, k, v projections
        self.q_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
        self.k_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
        self.v_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
        self.out_proj = nn.Linear(config.hidden_size, config.hidden_size, bias=False)
        
        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
        self.rotary = RotaryPositionalEmbedding(self.head_dim, config.max_position_embeddings)
        
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        B, T, C = x.shape
        
        q = self.q_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
        k = self.k_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
        v = self.v_proj(x).view(B, T, self.n_heads, self.head_dim).transpose(1, 2)
        
        cos, sin = self.rotary(x, T)
        cos, sin = cos.unsqueeze(0).unsqueeze(0), sin.unsqueeze(0).unsqueeze(0)
        q, k = apply_rotary_pos_emb(q, k, cos, sin)
        
        attn = (q @ k.transpose(-2, -1)) * self.scale
        
        # Causal mask
        causal_mask = torch.triu(torch.ones(T, T, device=x.device), diagonal=1).bool()
        attn = attn.masked_fill(causal_mask.unsqueeze(0).unsqueeze(0), float('-inf'))
        
        attn = F.softmax(attn, dim=-1)
        attn = self.dropout(attn)
        
        out = (attn @ v).transpose(1, 2).reshape(B, T, C)
        return self.out_proj(out)


class AILOMLP(nn.Module):
    """Feed-forward with SwiGLU - matching original w1, w2, w3 structure."""
    
    def __init__(self, config: AILOConfig):
        super().__init__()
        # Match original: w1 [3072, 768], w2 [768, 3072], w3 [3072, 768]
        self.w1 = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
        self.w2 = nn.Linear(config.intermediate_size, config.hidden_size, bias=False)
        self.w3 = nn.Linear(config.hidden_size, config.intermediate_size, bias=False)
        self.dropout = nn.Dropout(config.hidden_dropout_prob)
        
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        # SwiGLU: w2(silu(w1(x)) * w3(x))
        return self.dropout(self.w2(F.silu(self.w1(x)) * self.w3(x)))


class AILOBlock(nn.Module):
    """Transformer block matching original structure."""
    
    def __init__(self, config: AILOConfig):
        super().__init__()
        self.ln1 = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
        self.attn = AILOAttention(config)
        self.ln2 = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
        self.ff = AILOMLP(config)
        
    def forward(self, x: torch.Tensor) -> torch.Tensor:
        x = x + self.attn(self.ln1(x))
        x = x + self.ff(self.ln2(x))
        return x


class AILOPreTrainedModel(PreTrainedModel):
    """Base class for AILO models."""
    
    config_class = AILOConfig
    base_model_prefix = "ailo"
    
    def _init_weights(self, module):
        if isinstance(module, nn.Linear):
            nn.init.normal_(module.weight, mean=0.0, std=0.02)
        elif isinstance(module, nn.Embedding):
            nn.init.normal_(module.weight, mean=0.0, std=0.02)


class AILOForCausalLM(AILOPreTrainedModel, GenerationMixin):
    """AILO model for causal language modeling - matching original structure."""
    
    def __init__(self, config: AILOConfig):
        super().__init__(config)
        
        # Match original naming: tok_emb, blocks, ln_f, head
        self.tok_emb = nn.Embedding(config.vocab_size, config.hidden_size)
        self.blocks = nn.ModuleList([AILOBlock(config) for _ in range(config.num_hidden_layers)])
        self.ln_f = nn.LayerNorm(config.hidden_size, elementwise_affine=True, bias=False)
        self.head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
        
        # Weight tying
        self.head.weight = self.tok_emb.weight
        
        self.post_init()
    
    def forward(
        self,
        input_ids: torch.LongTensor,
        attention_mask: Optional[torch.Tensor] = None,
        labels: Optional[torch.LongTensor] = None,
        **kwargs
    ) -> CausalLMOutputWithPast:
        x = self.tok_emb(input_ids)
        
        for block in self.blocks:
            x = block(x)
        
        x = self.ln_f(x)
        logits = self.head(x)
        
        loss = None
        if labels is not None:
            shift_logits = logits[..., :-1, :].contiguous()
            shift_labels = labels[..., 1:].contiguous()
            loss = F.cross_entropy(shift_logits.view(-1, shift_logits.size(-1)), shift_labels.view(-1))
        
        return CausalLMOutputWithPast(loss=loss, logits=logits)
    
    def prepare_inputs_for_generation(self, input_ids, **kwargs):
        return {"input_ids": input_ids}
    
    @torch.no_grad()
    def generate(
        self,
        input_ids: torch.LongTensor,
        max_new_tokens: int = 100,
        temperature: float = 0.8,
        top_k: int = 50,
        top_p: float = 0.95,
        **kwargs
    ) -> torch.LongTensor:
        """Generate text tokens."""
        for _ in range(max_new_tokens):
            idx_cond = input_ids[:, -512:]  # Max context
            outputs = self(idx_cond)
            logits = outputs.logits[:, -1, :] / temperature
            
            # Top-k
            if top_k > 0:
                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
                logits[logits < v[:, [-1]]] = float('-inf')
            
            # Top-p
            if top_p < 1.0:
                sorted_logits, sorted_indices = torch.sort(logits, descending=True)
                cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)
                sorted_indices_to_remove = cumulative_probs > top_p
                sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
                sorted_indices_to_remove[..., 0] = 0
                indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
                logits[indices_to_remove] = float('-inf')
            
            probs = F.softmax(logits, dim=-1)
            next_token = torch.multinomial(probs, num_samples=1)
            input_ids = torch.cat([input_ids, next_token], dim=1)
            
            if next_token.item() == self.config.eos_token_id:
                break
        
        return input_ids