"""Compare benchmark results between PD-combined and PD-separated modes.

Reads summary JSON files and per-request metrics to produce a detailed
comparison report including TTFT, TPOT, E2E, cache hit ratio, and
throughput analysis.

Usage:
    python scripts/compare_results.py \
        --combined outputs/combined_1000req/metrics.summary.json \
        --separated outputs/separated_1000req/metrics.summary.json
"""

from __future__ import annotations

import argparse
import json
import sys
from pathlib import Path


def load_summary(path: Path) -> dict:
    return json.loads(path.read_text())


def load_metrics(path: Path) -> list[dict]:
    rows = []
    with path.open() as fh:
        for line in fh:
            rows.append(json.loads(line))
    return rows


def fmt_stat(stat: dict | None, unit: str = "s") -> str:
    if stat is None:
        return "N/A"
    return (f"mean={stat['mean']:.3f}{unit} "
            f"p50={stat['p50']:.3f}{unit} "
            f"p90={stat['p90']:.3f}{unit} "
            f"p99={stat['p99']:.3f}{unit}")


def compare(combined: dict, separated: dict) -> None:
    print("=" * 70)
    print("PD-Combined vs PD-Separated Performance Comparison")
    print("=" * 70)

    for label, s in [("PD-Combined", combined), ("PD-Separated", separated)]:
        print(f"\n--- {label} ---")
        print(f"  Requests: {s['request_count']} (success: {s['success_count']}, errors: {s['error_count']})")
        print(f"  Wall clock: {s.get('wall_clock_s', 0):.1f}s")
        print(f"  TTFT:    {fmt_stat(s.get('ttft_stats_s'))}")
        print(f"  TPOT:    {fmt_stat(s.get('tpot_stats_s'))}")
        print(f"  E2E:     {fmt_stat(s.get('latency_stats_s'))}")
        hit_ratio = s.get('prefix_cache_hit_ratio', 0)
        print(f"  Prefix cache hit ratio: {hit_ratio*100:.1f}%")
        queries = s.get('prefix_cache_queries_tokens', 0)
        hits = s.get('prefix_cache_hits_tokens', 0)
        print(f"    ({hits}/{queries} tokens)")

    print("\n--- Comparison (Separated vs Combined) ---")
    for metric_key, label in [
        ("ttft_stats_s", "TTFT"),
        ("tpot_stats_s", "TPOT"),
        ("latency_stats_s", "E2E"),
    ]:
        c = combined.get(metric_key, {})
        s = separated.get(metric_key, {})
        if c and s:
            for pct in ["mean", "p50", "p90", "p99"]:
                cv, sv = c.get(pct, 0), s.get(pct, 0)
                if cv > 0:
                    change = (sv - cv) / cv * 100
                    direction = "slower" if change > 0 else "faster"
                    print(f"  {label} {pct}: {abs(change):.1f}% {direction} "
                          f"({cv:.3f}s → {sv:.3f}s)")

    c_ratio = combined.get("prefix_cache_hit_ratio", 0)
    s_ratio = separated.get("prefix_cache_hit_ratio", 0)
    print(f"  Cache hit ratio: {c_ratio*100:.1f}% → {s_ratio*100:.1f}%")

    c_wall = combined.get("wall_clock_s", 1)
    s_wall = separated.get("wall_clock_s", 1)
    c_tput = combined["success_count"] / c_wall
    s_tput = separated["success_count"] / s_wall
    print(f"  Throughput: {c_tput:.1f} → {s_tput:.1f} req/s "
          f"({(s_tput/c_tput - 1)*100:+.1f}%)")


def main():
    p = argparse.ArgumentParser(description=__doc__,
                                formatter_class=argparse.RawDescriptionHelpFormatter)
    p.add_argument("--combined", type=Path, required=True)
    p.add_argument("--separated", type=Path, required=True)
    args = p.parse_args()

    combined = load_summary(args.combined)
    separated = load_summary(args.separated)
    compare(combined, separated)


if __name__ == "__main__":
    main()