#!/usr/bin/env python3
"""Cache exact Qwen2.5-Omni AV pieces for Thinker LoRA training.

For every source-aligned 2-second block this script caches ten causal phases:
0.2, 0.4, ..., 2.0 seconds.  The 2.0-second phase is reused as completed
history; phases 0.2--1.8 are used only for the current partial block.  No
future samples enter a phase.

The optional verification compares a full-sequence reconstruction from the
cache with the existing open-stream KV replay.  Run this 24-second pilot before
caching a full EasyCom session.
"""

from __future__ import annotations

import argparse
import math
import platform
from pathlib import Path
from typing import Any, Sequence

import numpy as np
import torch
import torch.nn.functional as F
from tqdm.auto import tqdm

import streaming_turn_model as core
from easycom_head import NUM_HORIZONS
from omni_cached_av import (
    SCHEMA_VERSION,
    CachedBlockStore,
    anchor_intervals,
    cache_block_filename,
    cache_size_bytes,
    forward_last_state,
    make_anchor,
    pieces_to_cache,
    reconstruct_open_stream_sequence,
    save_json,
)
from streaming_turn_model_directly import CausalSourceAV, _easycom_directory_specs


def parse_args(argv: Sequence[str] | None = None) -> argparse.Namespace:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--model-id", required=True)
    parser.add_argument("--easycom-session-dir", type=Path, required=True)
    parser.add_argument("--target", type=Path, required=True)
    parser.add_argument("--output-dir", type=Path, required=True)
    parser.add_argument(
        "--end",
        type=float,
        default=24.0,
        help="Dense session endpoint in seconds; use 24 for the first pilot",
    )
    parser.add_argument("--step-seconds", type=float, default=0.2)
    parser.add_argument("--native-block-seconds", type=float, default=2.0)
    parser.add_argument("--memory-seconds", type=float, default=8.0)
    parser.add_argument("--video-fps", type=float, default=2.0)
    parser.add_argument("--video-min-pixels", type=int, default=64 * 28 * 28)
    parser.add_argument("--video-max-pixels", type=int, default=128 * 28 * 28)
    parser.add_argument("--frame-cache-size", type=int, default=64)
    parser.add_argument("--decoder", choices=("decord", "pynvcodec"), default="decord")
    parser.add_argument("--decoder-gpu-id", type=int, default=0)
    parser.add_argument("--decoder-threads", type=int, default=1)
    parser.add_argument("--max-open-readers", type=int, default=1)
    parser.add_argument(
        "--dtype",
        choices=("auto", "bfloat16", "float16", "float32"),
        default="bfloat16",
    )
    parser.add_argument("--device", default="cuda:0")
    parser.add_argument("--flash-attention-2", action="store_true")
    parser.add_argument(
        "--verify-every",
        type=int,
        default=10,
        help="Compare every Nth 5-Hz state with exact KV replay; 0 disables",
    )
    parser.add_argument(
        "--minimum-cosine",
        type=float,
        default=0.999,
        help="Fail if cached full-forward/reference KV cosine is below this",
    )
    parser.add_argument(
        "--overwrite",
        action="store_true",
        help="Overwrite this cache's known block/static/manifest files",
    )
    return parser.parse_args(argv)


def _integer_ratio(numerator: float, denominator: float, name: str) -> int:
    ratio = numerator / denominator
    rounded = round(ratio)
    if not math.isclose(ratio, rounded, rel_tol=0.0, abs_tol=1e-6):
        raise ValueError(f"{name} must be integral, got {ratio}")
    return int(rounded)


def _load_targets(path: Path) -> np.ndarray:
    targets = np.load(path, mmap_mode="r")
    if targets.ndim != 2 or targets.shape[1] != 3:
        raise ValueError(f"Expected target [T,3], got {targets.shape}: {path}")
    return targets


def _safe_output_path(path: Path, overwrite: bool) -> None:
    if path.exists() and not overwrite:
        raise FileExistsError(f"Refusing to overwrite {path}; pass --overwrite")


def _model_device(model: torch.nn.Module) -> torch.device:
    try:
        return next(model.parameters()).device
    except StopIteration as exc:
        raise RuntimeError("Model has no parameters") from exc


@torch.inference_mode()
def _cache_blocks(
    *,
    extractor: core.OpenStreamReplayExtractor,
    model: torch.nn.Module,
    output_dir: Path,
    num_steps: int,
    steps_per_block: int,
    step_seconds: float,
    block_seconds: float,
    overwrite: bool,
) -> list[dict[str, Any]]:
    num_blocks = math.ceil(num_steps / steps_per_block)
    records: list[dict[str, Any]] = []
    input_embeddings = model.get_input_embeddings()
    for block_index in tqdm(range(num_blocks), desc="cache AV blocks", unit="block"):
        first_step = block_index * steps_per_block
        phase_count = min(steps_per_block, num_steps - first_step)
        block_start = block_index * block_seconds
        variants: dict[str, dict[str, torch.Tensor]] = {}
        token_lengths: dict[str, int] = {}
        for tail_steps in range(1, phase_count + 1):
            interval_end = block_start + tail_steps * step_seconds
            pieces = extractor._prepare_pieces(
                video_path=None,
                audio_path=None,
                interval=(block_start, interval_end),
                use_audio_in_video=True,
            )
            closure_embeddings = input_embeddings(pieces.closure_ids)
            cached = pieces_to_cache(
                pieces,
                closure_embeddings=closure_embeddings,
                floating_dtype=torch.bfloat16,
            )
            variants[str(tail_steps)] = cached
            token_lengths[str(tail_steps)] = int(
                cached["prefix_embeddings"].shape[1]
                + cached["payload_embeddings"].shape[1]
                + cached["closure_embeddings"].shape[1]
            )
        path = output_dir / cache_block_filename(block_index)
        _safe_output_path(path, overwrite)
        torch.save(
            {
                "schema_version": SCHEMA_VERSION,
                "block_index": block_index,
                "start_seconds": block_start,
                "end_seconds": min(
                    block_start + block_seconds, num_steps * step_seconds
                ),
                "variants": variants,
            },
            path,
        )
        records.append(
            {
                "block_index": block_index,
                "path": path.name,
                "phase_count": phase_count,
                "token_lengths_without_query": token_lengths,
                "size_bytes": path.stat().st_size,
            }
        )
    return records


@torch.inference_mode()
def _verify_cache(
    *,
    model: torch.nn.Module,
    extractor: core.OpenStreamReplayExtractor,
    cache_dir: Path,
    static: dict[str, Any],
    anchors: list[dict[str, Any]],
    verify_every: int,
    minimum_cosine: float,
    block_seconds: float,
    step_seconds: float,
) -> list[dict[str, float]]:
    if verify_every <= 0:
        return []
    selected = [
        anchor
        for anchor in anchors
        if (int(anchor["step_index"]) + 1) % verify_every == 0
    ]
    if anchors and anchors[-1] not in selected:
        selected.append(anchors[-1])
    store = CachedBlockStore(cache_dir, max_blocks=max(2, int(static["memory_blocks"])))
    device = _model_device(model)
    checks: list[dict[str, float]] = []
    for anchor in tqdm(selected, desc="verify cached replay", unit="state"):
        embeddings, positions = reconstruct_open_stream_sequence(
            store=store, static=static, anchor=anchor
        )
        embeddings = embeddings.unsqueeze(0).to(device=device, dtype=model.dtype)
        positions = positions.unsqueeze(1).to(device=device)
        attention_mask = torch.ones(
            1, embeddings.shape[1], dtype=torch.long, device=device
        )
        cached_state = forward_last_state(
            model.model,
            inputs_embeds=embeddings,
            position_ids=positions,
            attention_mask=attention_mask,
            readout_indices=torch.tensor(
                [embeddings.shape[1] - 1], dtype=torch.long, device=device
            ),
        )
        exact_state = extractor.state_from_scratch(
            video_path=None,
            audio_path=None,
            intervals=anchor_intervals(
                anchor,
                block_seconds=block_seconds,
                step_seconds=step_seconds,
            ),
            use_audio_in_video=True,
        )
        cached_float = cached_state.float()
        exact_float = exact_state.float()
        check = {
            "time_seconds": float(anchor["time_seconds"]),
            "cosine": float(
                F.cosine_similarity(cached_float, exact_float, dim=-1).item()
            ),
            "mean_abs": float((cached_float - exact_float).abs().mean().item()),
            "max_abs": float((cached_float - exact_float).abs().max().item()),
        }
        checks.append(check)
        print(
            f"verify t={check['time_seconds']:.1f}s "
            f"cosine={check['cosine']:.8f} "
            f"mean_abs={check['mean_abs']:.6f} "
            f"max_abs={check['max_abs']:.6f}",
            flush=True,
        )
        if check["cosine"] < minimum_cosine:
            raise RuntimeError(
                "Cached full-sequence reconstruction disagrees with open-stream "
                f"KV replay at t={check['time_seconds']:.1f}s: "
                f"cosine={check['cosine']:.8f} < {minimum_cosine:.8f}"
            )
    return checks


def main(argv: Sequence[str] | None = None) -> None:
    args = parse_args(argv)
    core._configure_qwen_logging()
    if args.end <= 0:
        raise ValueError("--end must be positive")
    steps_per_block = _integer_ratio(
        args.native_block_seconds, args.step_seconds, "native block / step"
    )
    memory_blocks = _integer_ratio(
        args.memory_seconds, args.native_block_seconds, "memory / native block"
    )
    num_steps = _integer_ratio(args.end, args.step_seconds, "end / step")
    targets = _load_targets(args.target)
    if num_steps > len(targets):
        raise ValueError(
            f"Requested {num_steps} cached steps but target has only {len(targets)}"
        )

    output_dir = args.output_dir.expanduser().resolve()
    output_dir.mkdir(parents=True, exist_ok=True)
    manifest_path = output_dir / "manifest.json"
    static_path = output_dir / "static.pt"
    _safe_output_path(manifest_path, args.overwrite)
    _safe_output_path(static_path, args.overwrite)

    config = core.StreamConfig(
        step_seconds=args.step_seconds,
        native_block_seconds=args.native_block_seconds,
        memory_seconds=args.memory_seconds,
        video_fps=args.video_fps,
        video_min_pixels=args.video_min_pixels,
        video_max_pixels=args.video_max_pixels,
    )
    config.validate()
    specs = _easycom_directory_specs(args.easycom_session_dir)
    media = CausalSourceAV(
        specs,
        output_fps=args.video_fps,
        required_duration=args.end,
        frame_cache_size=args.frame_cache_size,
        decoder_backend=args.decoder,
        decoder_gpu_id=args.decoder_gpu_id,
        decoder_threads=args.decoder_threads,
        max_open_readers=args.max_open_readers,
    )
    print(
        f"Direct media ready: duration={args.end:.1f}s, "
        f"grid={media.expected_grid_frames} frames, audio={len(media.audio)} samples"
    )

    model, processor = core.load_qwen_omni(
        args.model_id,
        dtype=args.dtype,
        device_map=args.device,
        use_flash_attention_2=args.flash_attention_2,
    )
    model.requires_grad_(False)
    extractor = core.OpenStreamReplayExtractor(
        model, processor, config, fixed_grid_av=media
    )
    with torch.inference_mode():
        query_ids = extractor.query_ids
        query_embeddings = model.get_input_embeddings()(query_ids)
    positions_per_chunk = core._tmrope_positions_per_chunk(model)
    static = {
        "schema_version": SCHEMA_VERSION,
        "steps_per_block": steps_per_block,
        "memory_blocks": memory_blocks,
        "positions_per_chunk": positions_per_chunk,
        "query_ids": query_ids.detach().cpu().long(),
        "query_embeddings": query_embeddings.detach().cpu().to(torch.bfloat16),
    }
    torch.save(static, static_path)

    block_records = _cache_blocks(
        extractor=extractor,
        model=model,
        output_dir=output_dir,
        num_steps=num_steps,
        steps_per_block=steps_per_block,
        step_seconds=args.step_seconds,
        block_seconds=args.native_block_seconds,
        overwrite=args.overwrite,
    )
    anchors = [
        make_anchor(
            step_index=step_index,
            steps_per_block=steps_per_block,
            memory_blocks=memory_blocks,
            step_seconds=args.step_seconds,
            num_target_steps=len(targets),
            num_horizons=NUM_HORIZONS,
        )
        for step_index in range(num_steps)
    ]
    checks = _verify_cache(
        model=model,
        extractor=extractor,
        cache_dir=output_dir,
        static=static,
        anchors=anchors,
        verify_every=args.verify_every,
        minimum_cosine=args.minimum_cosine,
        block_seconds=args.native_block_seconds,
        step_seconds=args.step_seconds,
    )

    manifest = {
        "schema_version": SCHEMA_VERSION,
        "cache_kind": "qwen2.5-omni-frozen-av-open-stream-phases",
        "session": args.easycom_session_dir.resolve().name,
        "model_id": args.model_id,
        "target_path": str(args.target.expanduser().resolve()),
        "target_steps": int(len(targets)),
        "cached_steps": num_steps,
        "cached_end_seconds": args.end,
        "hidden_size": int(query_embeddings.shape[-1]),
        "floating_dtype": "bfloat16",
        "step_seconds": args.step_seconds,
        "native_block_seconds": args.native_block_seconds,
        "memory_seconds": args.memory_seconds,
        "steps_per_block": steps_per_block,
        "memory_blocks": memory_blocks,
        "positions_per_chunk": positions_per_chunk,
        "video_fps": args.video_fps,
        "video_min_pixels": args.video_min_pixels,
        "video_max_pixels": args.video_max_pixels,
        "use_audio_in_video": True,
        "interval_convention": "half_open_[start,end)",
        "phase_policy": "cache_0.2_to_2.0s;_2.0s_is_completed_history",
        "label_policy": "target[i+1:i+11]",
        "static_path": static_path.name,
        "blocks": block_records,
        "anchors": anchors,
        "verification": checks,
        "media": media.metadata(),
        "software": {
            "python": platform.python_version(),
            "torch": torch.__version__,
        },
    }
    save_json(manifest_path, manifest)
    size = cache_size_bytes(
        [static_path, *[output_dir / record["path"] for record in block_records]]
    )
    print(
        f"Saved {len(block_records)} blocks / {len(anchors)} anchors to {output_dir}"
    )
    print(f"Cache tensor size: {size / (1024 ** 3):.3f} GiB")
    if checks:
        print(
            "Verification: "
            f"lowest cosine={min(item['cosine'] for item in checks):.8f}, "
            f"worst max_abs={max(item['max_abs'] for item in checks):.6f}"
        )


if __name__ == "__main__":
    main()