# Copyright © 2026 Apple Inc.

from dataclasses import dataclass
from typing import Any, Dict, Optional, Union

import mlx.core as mx
import mlx.nn as nn

from .activations import swiglu
from .base import BaseModelArgs, create_attention_mask, scaled_dot_product_attention
from .rope_utils import initialize_rope


@dataclass
class ModelArgs(BaseModelArgs):
    model_type: str
    hidden_size: int
    intermediate_size: int
    max_position_embeddings: int
    num_attention_heads: int
    num_hidden_layers: int
    num_key_value_heads: int
    rms_norm_eps: float
    vocab_size: int
    rope_theta: float
    mlp_bias: bool = False
    attention_bias: bool = False
    head_dim: Optional[int] = None
    rope_scaling: Optional[Dict[str, Union[float, str]]] = None
    tie_word_embeddings: bool = False


class Telechat3Attention(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        self.num_attention_heads = args.num_attention_heads
        self.num_key_value_heads = args.num_key_value_heads

        self.head_dim = args.head_dim or args.hidden_size // args.num_attention_heads
        self.scale = self.head_dim**-0.5

        self.q_proj = nn.Linear(
            args.hidden_size,
            args.num_attention_heads * self.head_dim,
            bias=args.attention_bias,
        )
        self.k_proj = nn.Linear(
            args.hidden_size,
            args.num_key_value_heads * self.head_dim,
            bias=args.attention_bias,
        )
        self.v_proj = nn.Linear(
            args.hidden_size,
            args.num_key_value_heads * self.head_dim,
            bias=args.attention_bias,
        )
        self.o_proj = nn.Linear(
            args.num_attention_heads * self.head_dim,
            args.hidden_size,
            bias=args.attention_bias,
        )

        self.rope = initialize_rope(
            self.head_dim,
            traditional=False,
            base=args.rope_theta,
            scaling_config=args.rope_scaling,
            max_position_embeddings=args.max_position_embeddings,
        )

    def __call__(
        self,
        x: mx.array,
        mask: Optional[mx.array] = None,
        cache: Optional[Any] = None,
    ) -> mx.array:
        B, L, _ = x.shape
        queries, keys, values = self.q_proj(x), self.k_proj(x), self.v_proj(x)

        queries = queries.reshape(B, L, self.num_attention_heads, -1).transpose(
            0, 2, 1, 3
        )
        keys = keys.reshape(B, L, self.num_key_value_heads, -1).transpose(0, 2, 1, 3)
        values = values.reshape(B, L, self.num_key_value_heads, -1).transpose(
            0, 2, 1, 3
        )

        if cache is not None:
            queries = self.rope(queries, offset=cache.offset)
            keys = self.rope(keys, offset=cache.offset)
            keys, values = cache.update_and_fetch(keys, values)
        else:
            queries = self.rope(queries)
            keys = self.rope(keys)

        output = scaled_dot_product_attention(
            queries, keys, values, cache=cache, scale=self.scale, mask=mask
        )
        output = output.transpose(0, 2, 1, 3).reshape(B, L, -1)
        return self.o_proj(output)


class Telechat3MLP(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        self.gate_proj = nn.Linear(
            args.hidden_size, args.intermediate_size, bias=args.mlp_bias
        )
        self.down_proj = nn.Linear(
            args.intermediate_size, args.hidden_size, bias=args.mlp_bias
        )
        self.up_proj = nn.Linear(
            args.hidden_size, args.intermediate_size, bias=args.mlp_bias
        )

    def __call__(self, x: mx.array) -> mx.array:
        return self.down_proj(swiglu(self.gate_proj(x), self.up_proj(x)))


class Telechat3DecoderLayer(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        self.num_attention_heads = args.num_attention_heads
        self.hidden_size = args.hidden_size
        self.self_attn = Telechat3Attention(args)
        self.mlp = Telechat3MLP(args)
        self.input_layernorm = nn.RMSNorm(args.hidden_size, eps=args.rms_norm_eps)
        self.post_attention_layernorm = nn.RMSNorm(
            args.hidden_size, eps=args.rms_norm_eps
        )
        self.args = args

    def __call__(
        self,
        x: mx.array,
        mask: Optional[mx.array] = None,
        cache: Optional[Any] = None,
    ) -> mx.array:
        r = self.self_attn(self.input_layernorm(x), mask, cache)
        h = x + r
        out = h + self.mlp(self.post_attention_layernorm(h))
        return out


class Telechat3Model(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        self.args = args
        self.vocab_size = args.vocab_size
        self.num_hidden_layers = args.num_hidden_layers
        self.embed_tokens = nn.Embedding(args.vocab_size, args.hidden_size)
        self.layers = [
            Telechat3DecoderLayer(args=args) for _ in range(args.num_hidden_layers)
        ]
        self.norm = nn.RMSNorm(args.hidden_size, eps=args.rms_norm_eps)

    def __call__(
        self,
        inputs: mx.array,
        cache: Optional[Any] = None,
        input_embeddings: Optional[mx.array] = None,
    ) -> mx.array:
        if input_embeddings is not None:
            h = input_embeddings
        else:
            h = self.embed_tokens(inputs)

        if cache is None:
            cache = [None] * len(self.layers)
        mask = create_attention_mask(h, cache[0])

        for layer, c in zip(self.layers, cache):
            h = layer(h, mask, c)

        return self.norm(h)


class Model(nn.Module):
    def __init__(self, args: ModelArgs):
        super().__init__()
        self.args = args
        self.model_type = args.model_type
        self.model = Telechat3Model(args)
        if not args.tie_word_embeddings:
            self.lm_head = nn.Linear(args.hidden_size, args.vocab_size, bias=False)

    def __call__(
        self,
        inputs: mx.array,
        cache: Optional[Any] = None,
        input_embeddings: Optional[mx.array] = None,
    ) -> mx.array:
        out = self.model(inputs, cache, input_embeddings)
        if self.args.tie_word_embeddings:
            out = self.model.embed_tokens.as_linear(out)
        else:
            out = self.lm_head(out)
        return out

    @property
    def layers(self):
        return self.model.layers