#!/usr/bin/env python3
"""Compare recorded scheduling timings with real read-only context checks."""
import contextlib
import io
import json
from pathlib import Path
import statistics
import tempfile

from wbv2_autopilot import Autopilot, CONTROL, POLICY, ROOT, read_json, write_json
from wbv2_timing import timing_report


def main():
    policy = read_json(ROOT / POLICY)
    before = timing_report(ROOT / CONTROL)
    samples = []
    with tempfile.TemporaryDirectory(prefix="wbv2-timing-") as temporary:
        root = Path(temporary)
        runner = Autopilot(root, policy)
        with contextlib.redirect_stdout(io.StringIO()):
            for script in ["check-task-context.mjs", "check-context-governance.mjs"]:
                for iteration in range(3):
                    result = runner.run_process(["node", str(ROOT / "tools/web" / script)], root, root / f"{script}-{iteration}.log", 30, phase="context_check")
                    if result["exitCode"] != 0:
                        raise RuntimeError(f"context benchmark failed: {script}")
                    samples.append({"script": script, "seconds": result["durationSeconds"]})
    old = [row["seconds"] for row in before["steps"] if row["phase"] == "context_check"]
    median_old = statistics.median(old)
    median_new = statistics.median(sample["seconds"] for sample in samples)
    report = {
        "schemaVersion": 1,
        "operation": "AUTOPILOT_PERFORMANCE_OPTIMIZATION",
        "observedAt": timing_report(ROOT / CONTROL)["observedAt"],
        "timezone": "Asia/Shanghai",
        "labelPrecision": "minute",
        "baseline": before,
        "benchmark": {
            "scope": "Same read-only context entrypoints: historical observed baseline versus three current samples per entrypoint; not whole-project throughput.",
            "samples": samples,
            "baselineMedianMinutes": round(median_old / 60, 6),
            "optimizedMedianMinutes": round(median_new / 60, 6),
            "observedSpeedup": round(median_old / median_new, 2),
            "observedReductionPercent": round((1 - median_new / median_old) * 100, 2),
        },
        "providerPolicy": {key: policy[key] for key in ["modelStartTimeoutSeconds", "modelIdleTimeoutSeconds", "providerBackoffSeconds", "providerMaxBackoffSeconds", "maxProviderFailures"]},
        "sourcePolicy": {"driver": policy["strategy"], "authority": policy["sourceAuthority"], "sourceFirst": policy["sourceFirst"]},
        "limitations": ["Provider availability/account concurrency is external; these changes do not remove upstream limits.", "No source capability completion or inventory increment is claimed.", "Legacy JSONL lacks per-item timestamps; new runs record observed per-item intervals separately."],
    }
    destination = ROOT / "tests/golden/WBV2-P1424-001/performance-optimization-report.json"
    write_json(destination, report)
    print(json.dumps({"report": str(destination.relative_to(ROOT)), "observedAt": report["observedAt"], **report["benchmark"]}, indent=2))


if __name__ == "__main__":
    main()