import os
import sys
import time
import torch

# Add recipe path to sys.path
_RECIPE_ROOT = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, _RECIPE_ROOT)

from modeling_aha_qwen3 import AHAQwen3ForCausalLM, AHAQwen3Config
from router_training_utils import RowWiseAdamW

def main():
    AHAQwen3Config.register_for_auto_class()
    AHAQwen3ForCausalLM.register_for_auto_class("AutoModelForCausalLM")

    # The repo root is the parent directory of recipe
    model_path = os.path.dirname(_RECIPE_ROOT)

    print("Loading model in BF16...", flush=True)
    model = AHAQwen3ForCausalLM.from_pretrained_qwen3(
        model_path,
        aha_window_size=128,
        aha_lambda=3e-4,
        aha_distill_weight=0.0,
        aha_ce_weight=1.0,
        aha_gate_target=1.0,
        aha_reg_weight=0.01,
        aha_mode="dynamic",
        aha_router_granularity="token",
        duo_sink_size=64,
        duo_recent_size=256,
        duo_alpha_init=1.0,
        torch_dtype=torch.bfloat16,
        attn_implementation="sdpa",
    )

    # Freeze embeddings and LM head as in stage 2 SFT training
    for param in model.model.embed_tokens.parameters():
        param.requires_grad = False
    for param in model.lm_head.parameters():
        param.requires_grad = False

    print("Moving model to CUDA...", flush=True)
    model = model.to("cuda")

    # Configure RowWiseAdamW optimizer
    num_heads = model.config.num_attention_heads
    head_dim = getattr(model.config, "head_dim", model.config.hidden_size // num_heads)
    q_rows = num_heads * head_dim
    q_row_scale = 3e-7 / 3e-6  # backbone_lr / gate_lr

    gate_params = []
    gate_param_ids = set()
    row_scales = []
    for layer in model.model.layers:
        q_proj = layer.self_attn.q_proj
        for p in (q_proj.weight, q_proj.bias):
            if p is None or not p.requires_grad:
                continue
            gate_params.append(p)
            gate_param_ids.add(id(p))
            row_scales.append((p, q_rows, q_row_scale))

    backbone_params = [
        p for p in model.parameters()
        if p.requires_grad and id(p) not in gate_param_ids
    ]

    param_groups = [{"params": gate_params, "lr": 3e-6}]
    if backbone_params:
        param_groups.append({"params": backbone_params, "lr": 3e-7})

    optimizer = RowWiseAdamW(
        param_groups,
        row_scales=row_scales,
        weight_decay=0.0,
    )

    # Allocate a batch of seq_len=8192
    seq_len = 8192
    print(f"Allocating dummy batch: batch_size=1, seq_len={seq_len}", flush=True)
    input_ids = torch.randint(0, model.config.vocab_size, (1, seq_len), device="cuda")
    labels = input_ids.clone()

    # Enable gradient checkpointing
    model.gradient_checkpointing_enable(gradient_checkpointing_kwargs={"use_reentrant": False})

    # Warmup step (GPU caching, model trace creation, etc.)
    print("Warmup step...", flush=True)
    outputs = model(input_ids=input_ids, labels=labels)
    loss = outputs.loss
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

    # Reset peak memory stats and time the next step
    print("Starting measured smoke test step...", flush=True)
    torch.cuda.reset_peak_memory_stats()
    torch.cuda.synchronize()
    start_time = time.time()

    outputs = model(input_ids=input_ids, labels=labels)
    loss = outputs.loss
    loss.backward()
    optimizer.step()
    optimizer.zero_grad()

    torch.cuda.synchronize()
    step_time = time.time() - start_time

    peak_mem = torch.cuda.max_memory_allocated() / (1024 ** 3)
    reserved_mem = torch.cuda.memory_reserved() / (1024 ** 3)

    print("=== SMOKE TEST RESULTS ===", flush=True)
    print(f"Peak VRAM: {peak_mem:.4f} GB", flush=True)
    print(f"Reserved VRAM: {reserved_mem:.4f} GB", flush=True)
    print(f"Step time: {step_time:.4f} seconds", flush=True)
    print("==========================", flush=True)

if __name__ == '__main__':
    main()