#!/usr/bin/env python3
"""Parse custom bench_client.py JSONL outputs for vLLM TP=2 benchmark.

Reads JSONL files produced by bench_client.py (one request per line,
last line is the summary) and generates:
    - results.json  (appended scenarios, following the standard schema)
    - report.md     (human-readable summary)

Usage:
    python3 parse_results.py <result_root>
"""

import json
import sys
from pathlib import Path


def parse_jsonl(path: Path) -> tuple[dict | None, list[dict]]:
    """Read the summary JSON (last line) and all per-request lines."""
    requests: list[dict] = []
    summary: dict | None = None
    with open(path, "r", encoding="utf-8") as f:
        for line in f:
            line = line.strip()
            if not line:
                continue
            try:
                obj = json.loads(line)
            except json.JSONDecodeError:
                continue
            # The summary line has "completed" and "duration" keys.
            if "completed" in obj and "duration" in obj:
                summary = obj
            else:
                requests.append(obj)
    return summary, requests


def compute_metrics(summary: dict, requests: list[dict]) -> dict:
    completed = summary.get("completed", 0)
    total = len(requests)
    failed = total - completed if total > 0 else 0
    duration_s = summary.get("duration", 0.0)

    # Extract per-request metrics for percentiles.
    ttfts = [r["first_token_time_ms"] for r in requests if r.get("success")]
    tpots = [r["tpot_ms"] for r in requests if r.get("success") and r.get("output_tokens", 0) > 1]
    e2es = [r["e2e_latency_ms"] for r in requests if r.get("success")]
    itls = [r["mean_itl_ms"] for r in requests if r.get("success") and r.get("inter_token_latencies")]

    def percentile(values: list[float], p: float) -> float:
        if not values:
            return 0.0
        s = sorted(values)
        k = (len(s) - 1) * p / 100.0
        f = int(k)
        c = min(f + 1, len(s) - 1)
        return s[f] + (k - f) * (s[c] - s[f])

    return {
        "success": completed,
        "failed": failed,
        "duration_s": duration_s,
        "request_throughput": summary.get("request_throughput", 0.0),
        "input_token_throughput": summary.get("input_throughput", 0.0),
        "output_token_throughput": summary.get("output_throughput", 0.0),
        "total_token_throughput": summary.get("total_throughput", 0.0),
        "total_input_tokens": summary.get("total_input_tokens", 0),
        "total_output_tokens": summary.get("total_output_tokens", 0),
        "e2e_ms": {
            "mean": summary.get("mean_e2e_latency_ms", 0.0),
            "p50": percentile(e2es, 50),
            "p90": percentile(e2es, 90),
            "p95": percentile(e2es, 95),
            "p99": percentile(e2es, 99),
        },
        "ttft_ms": {
            "mean": summary.get("mean_ttft_ms", 0.0),
            "p50": percentile(ttfts, 50),
            "p90": percentile(ttfts, 90),
            "p95": percentile(ttfts, 95),
            "p99": percentile(ttfts, 99),
        },
        "tpot_ms": {
            "mean": summary.get("mean_tpot_ms", 0.0),
            "p50": percentile(tpots, 50),
            "p90": percentile(tpots, 90),
            "p95": percentile(tpots, 95),
            "p99": percentile(tpots, 99),
        },
        "itl_ms": {
            "mean": summary.get("mean_itl_ms", 0.0),
            "p50": percentile(itls, 50),
            "p90": percentile(itls, 90),
            "p95": percentile(itls, 95),
            "p99": percentile(itls, 99),
        },
    }


def scenario_name(concurrency: int, input_len: int, output_len: int) -> str:
    return f"c{concurrency}_i{input_len}_o{output_len}"


def slo_status(metrics: dict, ttft_limit_ms: float = 3000.0, tpot_limit_ms: float = 50.0) -> dict:
    ttft_ok = metrics["ttft_ms"]["p95"] < ttft_limit_ms
    tpot_ok = metrics["tpot_ms"]["mean"] < tpot_limit_ms
    if ttft_ok and tpot_ok:
        mark = "✅"
    elif ttft_ok or tpot_ok:
        mark = "⚠️"
    else:
        mark = "❌"
    return {
        "ttft_p95_ok": ttft_ok,
        "tpot_mean_ok": tpot_ok,
        "overall": mark,
    }


def append_scenario(results_json: Path, scenario: dict) -> None:
    with open(results_json, "r", encoding="utf-8") as f:
        data = json.load(f)
    data["scenarios"].append(scenario)
    with open(results_json, "w", encoding="utf-8") as f:
        json.dump(data, f, indent=2, ensure_ascii=False)


def generate_report(result_root: Path, scenarios: list[dict]) -> None:
    report_path = result_root / "report.md"
    with open(report_path, "w", encoding="utf-8") as f:
        f.write("# H200 vLLM TP=2 Custom Benchmark Report\n\n")
        f.write("- **Client**: `bench_client.py` (async OpenAI API, per-request timing)\n")
        f.write("- **Backend**: vLLM (TP=2, FP8 KV cache, no speculative decoding)\n")
        f.write(f"- **Result root**: `{result_root}`\n\n")

        f.write("## Results\n\n")
        f.write("| Scenario | Concurrency | Input | Output | Duration(s) | Success | Failed | Req/s | In tok/s | Out tok/s | Total tok/s | Mean TTFT(ms) | P95 TTFT(ms) | P99 TTFT(ms) | Mean TPOT(ms) | P95 TPOT(ms) | P99 TPOT(ms) | Mean E2E(ms) | P95 E2E(ms) | P99 E2E(ms) | SLO |\n")
        f.write("|---|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|---:|\n")

        for s in scenarios:
            cfg = s["config"]
            m = s["metrics"]
            slo = s.get("slo_status", {}).get("overall", "")
            f.write(
                f"| {s['name']} | {cfg['concurrency']} | {cfg['input_len']} | {cfg['output_len']} | "
                f"{m['duration_s']:.2f} | {m['success']} | {m['failed']} | {m['request_throughput']:.2f} | "
                f"{m['input_token_throughput']:.2f} | {m['output_token_throughput']:.2f} | "
                f"{m['total_token_throughput']:.2f} | "
                f"{m['ttft_ms']['mean']:.2f} | {m['ttft_ms']['p95']:.2f} | {m['ttft_ms']['p99']:.2f} | "
                f"{m['tpot_ms']['mean']:.2f} | {m['tpot_ms']['p95']:.2f} | {m['tpot_ms']['p99']:.2f} | "
                f"{m['e2e_ms']['mean']:.2f} | {m['e2e_ms']['p95']:.2f} | {m['e2e_ms']['p99']:.2f} | {slo} |\n"
            )
        f.write("\n")
        f.write("SLO: S2 tier — TTFT P95 < 3000ms, TPOT mean < 50ms. ✅ pass, ⚠️ partial, ❌ fail.\n\n")


def main() -> None:
    result_root = Path(sys.argv[1]) if len(sys.argv) > 1 else Path("results")
    raw_dir = result_root / "raw_outputs"
    results_json = result_root / "results.json"

    if not raw_dir.exists():
        raise SystemExit(f"raw_outputs directory not found: {raw_dir}")

    scenarios = []
    for jsonl_path in sorted(raw_dir.glob("vllm_*.jsonl")):
        parts = jsonl_path.stem.split("_")
        if len(parts) < 5:
            continue
        concurrency, input_len, output_len = int(parts[2]), int(parts[3]), int(parts[4])

        summary, requests = parse_jsonl(jsonl_path)
        if summary is None:
            continue

        metrics = compute_metrics(summary, requests)
        scenario = {
            "name": scenario_name(concurrency, input_len, output_len),
            "config": {
                "concurrency": concurrency,
                "input_len": input_len,
                "output_len": output_len,
                "dataset": "random",
                "num_prompts": metrics["success"] + metrics["failed"],
            },
            "metrics": metrics,
            "slo_status": slo_status(metrics),
            "raw_file": str(jsonl_path),
        }
        scenarios.append(scenario)

    if not scenarios:
        print("No benchmark outputs found to parse")
        return

    if results_json.exists():
        for s in scenarios:
            append_scenario(results_json, s)

    generate_report(result_root, scenarios)
    print(f"Parsed {len(scenarios)} scenarios into {result_root}/report.md")


if __name__ == "__main__":
    main()