"""Autoregressive inference for the paper-version Samudra model."""

try:
    from ._bootstrap import ROOT
except ImportError:
    from _bootstrap import ROOT

import argparse
from pathlib import Path

import numpy as np
import torch
import yaml

from model.samudra import build_model

STATE_CHANNELS = 77
BOUNDARY_CHANNELS = 4


def load_data(path: str | Path) -> tuple[np.ndarray, np.ndarray]:
    """Load and validate native Samudra time-major arrays."""
    with np.load(path) as data:
        prognostic = np.asarray(data["prognostic"], dtype=np.float32)
        boundary = np.asarray(data["boundary"], dtype=np.float32)
    if prognostic.ndim != 4 or prognostic.shape[1] != STATE_CHANNELS:
        raise ValueError("prognostic must have shape [time, 77, lat, lon]")
    if boundary.ndim != 4 or boundary.shape[1] != BOUNDARY_CHANNELS:
        raise ValueError("boundary must have shape [time, 4, lat, lon]")
    if prognostic.shape[0] != boundary.shape[0] or prognostic.shape[2:] != boundary.shape[2:]:
        raise ValueError("prognostic and boundary time/grid dimensions must match")
    return prognostic, boundary


def load_checkpoint(model: torch.nn.Module, path: str, device: torch.device) -> None:
    try:
        checkpoint = torch.load(path, map_location=device, weights_only=True)
    except TypeError:
        checkpoint = torch.load(path, map_location=device)
    state = checkpoint.get("model", checkpoint.get("state_dict", checkpoint))
    model.load_state_dict(state)


@torch.no_grad()
def rollout(model, prognostic, boundary, steps, device):
    # Training uses one consecutive boundary frame for each recurrent pass.
    available_steps = boundary.shape[0] - 1
    if prognostic.shape[0] < 2 or available_steps < 1:
        raise ValueError(
            "rollout requires at least two states and two boundary time samples"
        )
    if steps > available_steps:
        raise ValueError(
            f"requested {steps} model steps, but input data provides only {available_steps}; "
            f"use --steps <= {available_steps} or provide a longer data file"
        )
    previous = torch.from_numpy(prognostic[0]).to(device)
    current = torch.from_numpy(prognostic[1]).to(device)
    predictions = []
    for step in range(steps):
        forcing = torch.from_numpy(boundary[step + 1]).to(device)
        inputs = torch.cat((previous, current, forcing), dim=0).unsqueeze(0)
        prediction = model(inputs).squeeze(0)
        previous, current = prediction[:STATE_CHANNELS], prediction[STATE_CHANNELS:]
        predictions.extend((previous.cpu().numpy(), current.cpu().numpy()))
    return np.stack(predictions)


def main() -> None:
    parser = argparse.ArgumentParser()
    parser.add_argument("--config", default="./conf/config.yaml")
    parser.add_argument("--data", default="./data/test.npz")
    parser.add_argument("--checkpoint", default=None)
    parser.add_argument("--output", default=None)
    parser.add_argument("--steps", type=int, default=None)
    parser.add_argument("--device", default=None)
    args = parser.parse_args()
    if args.steps is not None and args.steps < 1:
        raise ValueError("--steps must be positive")
    with open(args.config, encoding="utf-8") as handle:
        config = yaml.safe_load(handle)
    device = torch.device(args.device or ("cuda" if torch.cuda.is_available() else "cpu"))
    model = build_model(config).to(device)
    checkpoint = args.checkpoint or config["inference"].get("checkpoint") or "./data/checkpoints/model_bak.pth"
    output_path = args.output or config["inference"].get("output_dir", "./result/output")
    if Path(output_path).suffix != ".npz":
        output_path = str(Path(output_path) / "prediction.npz")
    load_checkpoint(model, checkpoint, device)
    model.eval()
    prognostic, boundary = load_data(args.data)
    configured_steps = int(config["inference"].get("rollout_steps", 1))
    if configured_steps < 1:
        raise ValueError("inference.rollout_steps must be positive")
    available_steps = boundary.shape[0] - 1
    steps = args.steps if args.steps is not None else min(configured_steps, available_steps)
    if args.steps is None and steps < configured_steps:
        print(
            f"input data supports {available_steps} model steps; "
            f"using rollout_steps={steps}"
        )
    predictions = rollout(model, prognostic, boundary, steps, device)
    output = Path(output_path)
    output.parent.mkdir(parents=True, exist_ok=True)
    np.savez_compressed(output, predictions=predictions, forcing=boundary[1 : steps + 1])
    print(f"saved predictions: {output} shape={predictions.shape}")


if __name__ == "__main__":
    main()