Fr0zkaandClaude Opus 5.5
28069f0d98
On the real FloatingIslands recipe, column caps sit inside anchor-island rock and native bedrock; the old check sampled the route foot. The audit now samples each planned cap against the native field (negative control: a cap moved into air is detected). The audit runner records requested vs actual recipe and exits on mismatch. All 16 passage rows (4 styles x 2 recipes x 2 compilers) pass. The readable shader uses a smooth tint. Interim: FI Gradient displacement capped at width/256 (flat floor, no contour rings); restoring real undulation is L32. Evaluator 19. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CSFYgsdW8ejZSyiMf4qRSX
82 lines
3.5 KiB
Python
82 lines
3.5 KiB
Python
#!/usr/bin/env python3
|
|
"""Run L31 route/proof and transition invariants with recipe-stamped logs."""
|
|
import re
|
|
import subprocess
|
|
import time
|
|
from pathlib import Path
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[4]
|
|
OUT = ROOT / "Saved/Linux/l31"
|
|
BINARIES = {
|
|
"clang": OUT / "bin/VoxelForgeCoreHeadless-linux31-clang",
|
|
"gcc": OUT / "bin/VoxelForgeCoreHeadless-linux31-gcc",
|
|
}
|
|
rows = []
|
|
failed = False
|
|
|
|
|
|
def run(name, binary, data, recipe, extra, checks):
|
|
global failed
|
|
logfile = OUT / f"{name}.log"
|
|
command = [
|
|
str(binary), str(data), "--workers=12", "--world-assembler-prototype",
|
|
"--stream-benchmark", "--stream-pipeline", "--force-generate",
|
|
"--clip-radius=3", "--max-clip-level=8", "--max-level=-1",
|
|
f"--recipe={recipe}", *extra,
|
|
]
|
|
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")
|
|
stamps = re.findall(
|
|
r"^\[WorldAssemblerRecipeAudit\] requested=([^ ]+) actual=([^ ]+).*status=([^ ]+)$",
|
|
text, re.M)
|
|
stamp_ok = stamps == [(recipe, recipe, "PASS")]
|
|
checks_ok = all(check(text) for check in checks)
|
|
ok = result is not None and result.returncode == 0 and stamp_ok and checks_ok
|
|
rows.append((name, recipe, elapsed, result.returncode if result else "TIMEOUT", ok))
|
|
print(f"{name} elapsed={elapsed:.1f}s recipe={stamps[0][1] if stamps else 'MISSING'} "
|
|
f"stamp={'PASS' if stamp_ok else 'FAIL'} checks={'PASS' if checks_ok else 'FAIL'} "
|
|
f"{'PASS' if ok else 'FAIL'}", flush=True)
|
|
failed |= not ok
|
|
|
|
|
|
owner = ROOT / "Standalone/data/owner_world.json"
|
|
for recipe in ("surface-world", "floating-islands"):
|
|
for compiler, binary in BINARIES.items():
|
|
name = f"invariant-route-proof-{recipe}-{compiler}"
|
|
run(name, binary, owner, recipe,
|
|
["--stream-hash", "--audit-uniform-block-proofs", "--audit-route-parity"],
|
|
[lambda text: bool(re.search(
|
|
r"^\[RouteParityAudit\].*status=PASS$", text, re.M)),
|
|
lambda text: bool(re.search(
|
|
r"^\[UniformBlockProofAudit\].*violations=0(?:\s|$)", text, re.M))])
|
|
|
|
for recipe in ("surface-world", "floating-islands"):
|
|
for compiler, binary in BINARIES.items():
|
|
for mode in ("hard", "gradient", "interleaved"):
|
|
name = f"invariant-transition-{recipe}-{mode}-{compiler}"
|
|
run(name, binary, owner, recipe,
|
|
[f"--transition-mode={mode}", "--audit-strate-transitions"],
|
|
[lambda text: bool(re.search(
|
|
r"^\[StrateTransitionAuditSummary\].*hole_columns=0 air_samples=0 .*status=PASS$",
|
|
text, re.M)),
|
|
lambda text: bool(re.search(
|
|
r"^\[StrateTransitionNegativeControls\].*status=PASS$", text, re.M))])
|
|
|
|
summary = OUT / "invariant-audits.csv"
|
|
summary.write_text(
|
|
"run,recipe,elapsed_seconds,exit_code,status\n" +
|
|
"".join(f"{name},{recipe},{elapsed:.3f},{code},{'PASS' if ok else 'FAIL'}\n"
|
|
for name, recipe, elapsed, code, ok in rows),
|
|
encoding="utf-8")
|
|
print(f"[L31InvariantAudits] runs={len(rows)} pass={sum(row[-1] for row in rows)} "
|
|
f"fail={sum(not row[-1] for row in rows)} summary={summary}", flush=True)
|
|
raise SystemExit(1 if failed or len(rows) != 16 else 0)
|