VoxelForge/Standalone/Research/WorldAssemblerM3/Linux31/RunCostL31.py

#!/usr/bin/env python3
"""Run five interleaved W12 whole-view pairs against the final L30 binary."""
import re
import statistics
import subprocess
import time
from pathlib import Path


ROOT = Path(__file__).resolve().parents[4]
OUT = ROOT / "Saved/Linux/l31"
OUT.mkdir(parents=True, exist_ok=True)
BINARIES = {
    "l30": ROOT / "Saved/Linux/l30/bin/VoxelForgeCoreHeadless-linux30-speed-fade",
    "l31": OUT / "bin/VoxelForgeCoreHeadless-linux31-clang",
}
ORDERS = (("l30", "l31"), ("l31", "l30"), ("l30", "l31"),
          ("l31", "l30"), ("l30", "l31"))
READY = re.compile(r"\bwhole_view_ready=([0-9.]+)s")
rows = []
failed = False

for recipe in ("surface-world", "floating-islands"):
    for pair, order in enumerate(ORDERS, 1):
        for build in order:
            name = f"cost-{recipe}-pair{pair}-{build}"
            logfile = OUT / f"{name}.log"
            command = [
                str(BINARIES[build]), str(ROOT / "Standalone/data/owner_world.json"),
                "--workers=12", "--world-assembler-prototype", "--stream-benchmark",
                "--stream-pipeline", "--force-generate", "--clip-radius=3",
                "--max-clip-level=8", "--max-level=-1", f"--recipe={recipe}",
            ]
            started = time.monotonic()
            try:
                with logfile.open("w", encoding="utf-8") as stream:
                    result = subprocess.run(command, stdout=stream, stderr=subprocess.STDOUT,
                                            timeout=1800, check=False)
            except subprocess.TimeoutExpired:
                result = None
            elapsed = time.monotonic() - started
            text = logfile.read_text(encoding="utf-8", errors="replace")
            matches = READY.findall(text)
            if build == "l31":
                stamps = re.findall(
                    r"^\[WorldAssemblerRecipeAudit\] requested=([^ ]+) actual=([^ ]+).*status=([^ ]+)$",
                    text, re.M)
                actual_recipe = stamps[0][1] if len(stamps) == 1 else "missing"
                stamp_ok = stamps == [(recipe, recipe, "PASS")]
            else:
                configured = re.findall(
                    r"^\[HeadlessConfig\].*\brecipe=([^\s]+)", text, re.M)
                actual_recipe = configured[0] if len(configured) == 1 else "missing"
                floating_plan = "[FloatingIslandWorldAssembly]" in text
                surface_plan = "[WorldAssemblerPrototype]" in text
                plan_matches = ((actual_recipe == "floating-islands" and floating_plan)
                                or (actual_recipe == "surface-world" and not floating_plan
                                    and surface_plan))
                marker = (f"[L31BaselineRecipeAudit] requested={recipe} actual={actual_recipe} "
                          f"headless_recipe={configured[0] if len(configured) == 1 else 'missing'} "
                          f"floating_island_plan={'present' if floating_plan else 'absent'} "
                          f"surface_world_plan={'present' if surface_plan else 'absent'} "
                          f"status={'PASS' if actual_recipe == recipe and plan_matches else 'FAIL'}\n")
                with logfile.open("a", encoding="utf-8") as stream:
                    stream.write(marker)
                text += marker
                stamp_ok = (actual_recipe == recipe and plan_matches
                            and len(configured) == 1)
            valid = (result is not None and result.returncode == 0 and len(matches) == 1
                     and "hash=off" in text and "cache_hits=0" in text)
            if build == "l31":
                valid = valid and stamp_ok and actual_recipe == recipe
            else:
                valid = valid and stamp_ok and "status=PASS" in marker
            ready = float(matches[0]) if len(matches) == 1 else float("nan")
            rows.append((recipe, pair, build, ready, elapsed,
                         result.returncode if result else "TIMEOUT", valid))
            print(f"{recipe} pair={pair} build={build} whole_view_ready={ready:.3f}s "
                  f"process_elapsed={elapsed:.1f}s {'PASS' if valid else 'FAIL'}", flush=True)
            failed |= not valid

summary = OUT / "cost-runs.csv"
summary.write_text(
    "recipe,pair,build,whole_view_ready_seconds,process_elapsed_seconds,exit_code,status\n" +
    "".join(f"{recipe},{pair},{build},{ready:.6f},{elapsed:.3f},{code},"
            f"{'PASS' if ok else 'FAIL'}\n"
            for recipe, pair, build, ready, elapsed, code, ok in rows), encoding="utf-8")

for recipe in ("surface-world", "floating-islands"):
    by_build = {build: [row[3] for row in rows if row[0] == recipe and row[2] == build]
                for build in BINARIES}
    l30 = statistics.median(by_build["l30"])
    l31 = statistics.median(by_build["l31"])
    paired = []
    for pair in range(1, 6):
        values = {row[2]: row[3] for row in rows if row[0] == recipe and row[1] == pair}
        paired.append((values["l31"] - values["l30"]) / values["l30"] * 100.0)
    print(f"[L31CostSummary] recipe={recipe} pairs=5 median_l30_s={l30:.3f} "
          f"median_l31_s={l31:.3f} median_change_pct={(l31/l30-1)*100.0:+.2f} "
          f"paired_change_pct={','.join(f'{value:+.2f}' for value in paired)}", flush=True)

print(f"[L31Cost] runs={len(rows)} status={'FAIL' if failed else 'PASS'} summary={summary}", flush=True)
raise SystemExit(1 if failed or len(rows) != 20 else 0)