tools(verify): fast/medium/full verification tiers with a compiled-in source stamp (L39); research R6
BuildLinux.sh hashes a sorted manifest of compiled inputs into VOXELFORGE_SOURCE_STAMP, printed first by every executable; Standalone/Tools/verify/verify.py checks it before and after each tier and records binary/input hashes and the resolved recipe, style map and layout. Fast (163 s) runs on the canonical owner world only and asserts FI Style 2 / SW Style 1; medium (8 min) and full (26 min) add the style matrix, GCC, determinism and cost. Controls: stale source, mislabelled style-0 owner, all-black capture, L30/L31, L35/L36 and the L38 step are all rejected. No geometry change; owner hashes identical to L37. Research R6: leak table, generator contract and a 10-step metre-native migration plan. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016dhxM43dnWvUu2B5Ph1iG1
This commit is contained in:
Fr0zkaandClaude Opus 5.5 committed
1 parent
88c54eab44
commit
753cc9c259
22 files changed
+1831
-163
No files matched your search
@@ -0,0 +1,640 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Run the reusable VoxelForge verification tiers: fast, medium, or full."""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import shutil
|
||||
import statistics
|
||||
import struct
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import zlib
|
||||
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[3]
|
||||
VERIFY_DIR = ROOT / "Standalone/Tools/verify"
|
||||
LINUX37 = ROOT / "Standalone/Research/WorldAssemblerM3/Linux37"
|
||||
OWNER = ROOT / "Standalone/data/owner_world.json"
|
||||
OUT_DEFAULT = ROOT / "Saved/Linux/l39"
|
||||
|
||||
PARSER = argparse.ArgumentParser(description=__doc__)
|
||||
PARSER.add_argument("tier", choices=("fast", "medium", "full"))
|
||||
PARSER.add_argument("--out", type=Path, default=OUT_DEFAULT,
|
||||
help="artifact directory (default: Saved/Linux/l39)")
|
||||
ARGS = PARSER.parse_args()
|
||||
OUT = ARGS.out.resolve()
|
||||
os.environ["VOXELFORGE_VERIFY_OUT"] = str(OUT)
|
||||
os.environ["PYTHONDONTWRITEBYTECODE"] = "1"
|
||||
sys.dont_write_bytecode = True
|
||||
|
||||
sys.path.insert(0, str(VERIFY_DIR))
|
||||
from owner_step import measure as measure_owner_step
|
||||
from runner import VerificationFailure, VerificationRunner, bounded_run
|
||||
from source_stamp import source_stamp
|
||||
|
||||
|
||||
CLANG = OUT / "bin/VoxelForgeCoreHeadless-l39-clang"
|
||||
GCC = OUT / "bin/VoxelForgeCoreHeadless-l39-gcc"
|
||||
RENDERER = OUT / "bin/VoxelForgeOffscreenCapture-l39-clang"
|
||||
HASH_RE = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
|
||||
RECIPE_RE = re.compile(
|
||||
r"^\[WorldAssemblerRecipeAudit\] requested=([^ ]+) actual=([^ ]+).*status=([^ ]+)$", re.M)
|
||||
|
||||
|
||||
def compiler_name(binary: Path) -> str:
|
||||
return "gcc" if "gcc" in binary.name else "clang"
|
||||
|
||||
|
||||
def env_for(*, capture: bool = False) -> dict[str, str]:
|
||||
result = os.environ.copy()
|
||||
result["VOXELFORGE_VERIFY_OUT"] = str(OUT)
|
||||
result["VOXELFORGE_L37_OUT"] = str(OUT)
|
||||
result["VOXELFORGE_L37_CAPTURE_DIR"] = str(OUT / "captures")
|
||||
result["VOXELFORGE_L37_HEADLESS"] = str(CLANG)
|
||||
result["VOXELFORGE_L37_RENDERER"] = str(RENDERER)
|
||||
result["VOXELFORGE_VERIFY_HEADLESS"] = str(CLANG)
|
||||
if capture:
|
||||
result["LP_NUM_THREADS"] = "12"
|
||||
result["XDG_CACHE_HOME"] = str(OUT / "xdg-cache")
|
||||
return result
|
||||
|
||||
|
||||
def all_match(text: str, pattern: str) -> bool:
|
||||
return re.search(pattern, text, re.M) is not None
|
||||
|
||||
|
||||
def parse_ratio(text: str, name: str) -> float | None:
|
||||
match = re.search(rf"(?:^| ){re.escape(name)}=(\d+)/(\d+)", text)
|
||||
return int(match.group(1)) / max(1, int(match.group(2))) if match else None
|
||||
|
||||
|
||||
def validate_passage(runner: VerificationRunner, name: str, output: str) -> None:
|
||||
required = (
|
||||
("strict-layout", r"^\[ResolvedLayoutStrict\] accepted=true issues=0 error=$"),
|
||||
("layout-controls", r"^\[ResolvedLayoutValidatorControls\].*status=PASS$"),
|
||||
("walkability", r"^\[Walkability\] PASS"),
|
||||
("floor-profile", r"^\[FloorProfileBlend\].*negative_controls=step_detected/slope_detected status=PASS$"),
|
||||
("mouth-profile", r"^\[PassageMouthProfileAudit\].*status=PASS$"),
|
||||
("route-binding", r"^\[ResolvedStrateRouteAudit\].*mouth_binding=PASS status=PASS$"),
|
||||
("naturalness", r"^\[PassageNaturalnessSummary\].*status=PASS$"),
|
||||
("open-air", r"^\[PassageOpenAirAuditSummary\].*status=PASS$"),
|
||||
("no-long-bridge", r"^\[PassageNoLongBridgeAudit\].*status=PASS$"),
|
||||
("rock-columns", r"^\[PassageRockColumnAuditSummary\].*status=PASS$"),
|
||||
("ripple-controls", r"^\[PassageRippleAuditSummary\].*status=PASS$"),
|
||||
("passage-summary", r"^\[ResolvedPassageAuditSummary\].*route_binding_failures=0 .*status=PASS$"),
|
||||
)
|
||||
for gate, pattern in required:
|
||||
runner.require(f"{name}:{gate}", all_match(output, pattern),
|
||||
"required resolved-passage gate")
|
||||
|
||||
rows = re.findall(r"^\[PassageRippleAudit\].*$", output, re.M)
|
||||
ripple_ok = bool(rows)
|
||||
for line in rows:
|
||||
wall = re.search(r"local_peak_amplitude_m=([-0-9.]+)", line)
|
||||
if wall is None:
|
||||
wall = re.search(r"amplitude_m=([-0-9.]+)", line)
|
||||
wall_threshold = re.search(r"threshold_m=([-0-9.]+)", line)
|
||||
floor = re.search(r"floor_amplitude_m=([-0-9.]+)", line)
|
||||
floor_threshold = re.search(r"floor_threshold_m=([-0-9.]+)", line)
|
||||
wall_coverage = parse_ratio(line, "coverage")
|
||||
floor_coverage = parse_ratio(line, "floor_coverage")
|
||||
ripple_ok &= bool(
|
||||
"status=PASS" in line and wall and wall_threshold and floor and floor_threshold
|
||||
and wall_coverage is not None and floor_coverage is not None
|
||||
and float(wall.group(1)) <= float(wall_threshold.group(1))
|
||||
and float(floor.group(1)) <= float(floor_threshold.group(1))
|
||||
and wall_coverage >= 0.75 and floor_coverage >= 0.75)
|
||||
runner.require(f"{name}:wall-floor-ripple-and-coverage", ripple_ok,
|
||||
f"profiles={len(rows)} wall/floor amplitudes under their thresholds; coverage>=0.75")
|
||||
|
||||
|
||||
def run_passage(runner: VerificationRunner, binary: Path, name: str,
|
||||
data: Path, recipe: str, style: int, *, workers: int = 12,
|
||||
flags: list[str] | None = None, max_level: int = -1,
|
||||
layout_path: Path | None = None, passage_style: int | None = None,
|
||||
expected_strate_styles: dict[str, int] | None = None) -> tuple[dict, str]:
|
||||
layout_path = layout_path or OUT / "layouts" / f"{name}.json"
|
||||
row, output = runner.run_cpp(name, binary, data, recipe,
|
||||
["--audit-resolved-layout-passages", *(flags or [])],
|
||||
expected_style=style if passage_style is None else passage_style,
|
||||
expected_strate_styles=expected_strate_styles,
|
||||
workers=workers, max_level=max_level,
|
||||
layout_path=layout_path)
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = style if passage_style is None else passage_style
|
||||
row["requested_strate_styles"] = expected_strate_styles
|
||||
validate_passage(runner, name, output)
|
||||
return row, output
|
||||
|
||||
|
||||
def run_owner_passages(runner: VerificationRunner, binaries: tuple[Path, ...]) -> dict[str, tuple[dict, str]]:
|
||||
result: dict[str, tuple[dict, str]] = {}
|
||||
expected_strate_styles = {"0": 2, "1": 1}
|
||||
for binary in binaries:
|
||||
compiler = compiler_name(binary)
|
||||
for recipe, style in (("floating-islands", 2), ("surface-world", 1)):
|
||||
name = f"owner-{recipe}-style{style}-{compiler}"
|
||||
row, output = run_passage(runner, binary, name, OWNER, recipe, style,
|
||||
passage_style=2, expected_strate_styles=expected_strate_styles)
|
||||
result[f"{compiler}:{recipe}"] = (row, output)
|
||||
actual_styles = row.get("resolved_strate_styles", {})
|
||||
runner.require(f"{name}:owner-style-map",
|
||||
actual_styles == expected_strate_styles,
|
||||
f"resolved_strate_styles={actual_styles} expected={expected_strate_styles}")
|
||||
if compiler == "clang":
|
||||
measured = measure_owner_step(output)
|
||||
worst = measured.get("worst")
|
||||
runner.require(f"{name}:adjacent-owner-step",
|
||||
bool(measured["passed"]),
|
||||
f"max_step_m={measured['maximum_adjacent_step_m']:.6f} "
|
||||
f"limit_m=0.100 pairs={measured['adjacent_pairs']} "
|
||||
f"fitted_periods_m={measured['fitted_periods_m']} "
|
||||
f"period_role=diagnostic worst={worst}")
|
||||
return result
|
||||
|
||||
|
||||
def expected_control_row(runner: VerificationRunner, name: str) -> None:
|
||||
if runner.runs:
|
||||
row = runner.runs[-1]
|
||||
row["observed_status"] = row["status"]
|
||||
row["status"] = "EXPECTED_FAIL"
|
||||
row["negative_control"] = name
|
||||
|
||||
|
||||
def run_stamp_and_input_controls(runner: VerificationRunner) -> None:
|
||||
# Mutate one compiled Core input only while checking that the runner refuses it.
|
||||
core_file = ROOT / "Standalone/Core/src/VoxelForgeCore.cpp"
|
||||
original = core_file.read_bytes()
|
||||
rejected = False
|
||||
try:
|
||||
core_file.write_bytes(original + b"\n// temporary L39 stale-build negative control\n")
|
||||
try:
|
||||
runner.probe_binary(CLANG)
|
||||
except RuntimeError as error:
|
||||
rejected = "source changed" in str(error)
|
||||
finally:
|
||||
core_file.write_bytes(original)
|
||||
runner.assert_current_tree("after restoring stale-build control")
|
||||
runner.require("stale-build-source-edit-control", rejected,
|
||||
"runner refused the binary after a Core source edit; original bytes restored")
|
||||
|
||||
fixture = ROOT / "Saved/Linux/l33/fixtures/sw-upper-tunnel-network-style0.json"
|
||||
mislabelled = OUT / "controls/mislabelled-owner/owner_world.json"
|
||||
mislabelled.parent.mkdir(parents=True, exist_ok=True)
|
||||
shutil.copyfile(fixture, mislabelled)
|
||||
try:
|
||||
runner.run_cpp("control-mislabelled-owner-style0", CLANG, mislabelled,
|
||||
"floating-islands", ["--resolved-layout-only"], expected_style=2,
|
||||
layout_path=OUT / "controls/mislabelled-owner/layout-owner.json")
|
||||
detected = False
|
||||
except VerificationFailure:
|
||||
detected = bool(runner.runs and 0 in runner.runs[-1]["resolved_style"]
|
||||
and runner.runs[-1]["status"] == "FAIL")
|
||||
if detected:
|
||||
expected_control_row(runner, "mislabelled-style0-input")
|
||||
runner.require("mislabelled-owner-style-control", detected,
|
||||
"style-0 fixture named owner_world.json rejected for expected FI Style 2")
|
||||
|
||||
black = OUT / "controls/all-black.png"
|
||||
black.parent.mkdir(parents=True, exist_ok=True)
|
||||
write_black_png(black)
|
||||
script = VERIFY_DIR / "capture_quality.py"
|
||||
try:
|
||||
runner.run_stage("control-all-black-capture", script, [str(black)],
|
||||
binary=CLANG, data=None, recipe=None, style=None,
|
||||
env=env_for(), script_inputs=[black])
|
||||
black_rejected = False
|
||||
except VerificationFailure:
|
||||
black_rejected = "status=FAIL" in (OUT / "control-all-black-capture.log").read_text(
|
||||
encoding="utf-8", errors="replace")
|
||||
if black_rejected:
|
||||
expected_control_row(runner, "all-black-capture")
|
||||
runner.require("all-black-capture-control", black_rejected,
|
||||
"pixel variance and coverage floor reject a valid all-black PNG")
|
||||
|
||||
|
||||
def write_black_png(path: Path) -> None:
|
||||
def chunk(tag: bytes, payload: bytes) -> bytes:
|
||||
return (struct.pack(">I", len(payload)) + tag + payload
|
||||
+ struct.pack(">I", zlib.crc32(tag + payload) & 0xffffffff))
|
||||
pixels = b"".join(b"\0" + b"\0\0\0" * 2 for _ in range(2))
|
||||
body = (b"\x89PNG\r\n\x1a\n"
|
||||
+ chunk(b"IHDR", struct.pack(">IIBBBBB", 2, 2, 8, 2, 0, 0, 0))
|
||||
+ chunk(b"IDAT", zlib.compress(pixels)) + chunk(b"IEND", b""))
|
||||
path.write_bytes(body)
|
||||
|
||||
|
||||
def run_regression_controls(runner: VerificationRunner) -> None:
|
||||
run_stamp_and_input_controls(runner)
|
||||
controls = (
|
||||
("l35-wall-ribs", "wall-ribs",
|
||||
ROOT / "Saved/Linux/l35/failed/passage-audit-cascade-cosine-owner-fi-style3-clang.log"),
|
||||
("l36-floor-washboard", "floor-washboard",
|
||||
ROOT / "Saved/Linux/l36/audit-nearest-fi-style0.log"),
|
||||
)
|
||||
script = VERIFY_DIR / "historical_controls.py"
|
||||
for name, kind, log in controls:
|
||||
runner.run_stage(f"control-{name}", script, [kind, str(log)],
|
||||
binary=CLANG, data=None, recipe=None, style=None,
|
||||
env=env_for(), script_inputs=[log])
|
||||
|
||||
l38 = ROOT / "Saved/Linux/l38/owner-fi-real-final.log"
|
||||
step_script = VERIFY_DIR / "owner_step.py"
|
||||
runner.run_stage("control-l38-owner-step", step_script,
|
||||
[str(l38), "--expect-fail"], binary=CLANG, data=None,
|
||||
recipe=None, style=None, env=env_for(), script_inputs=[l38])
|
||||
|
||||
|
||||
def run_hash_pairs(runner: VerificationRunner,
|
||||
owner_results: dict[str, tuple[dict, str]]) -> None:
|
||||
for recipe, style in (("floating-islands", 2), ("surface-world", 1)):
|
||||
hashes: dict[int, tuple[str, ...]] = {}
|
||||
for workers in (1, 12):
|
||||
name = f"owner-hash-{recipe}-style{style}-w{workers}"
|
||||
row, output = runner.run_cpp(name, CLANG, OWNER, recipe,
|
||||
["--stream-hash"], expected_style=2,
|
||||
expected_strate_styles={"0": 2, "1": 1}, workers=workers,
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = 2
|
||||
values = tuple(HASH_RE.findall(output))
|
||||
hashes[workers] = values
|
||||
runner.require(f"{name}:hash-count", len(values) == 12,
|
||||
f"hashes={len(values)}/12")
|
||||
same = hashes[1] == hashes[12]
|
||||
baseline = ROOT / "Saved/Linux/l37" / f"determinism-l25-clang-{recipe}-w12.log"
|
||||
old_hashes = tuple(HASH_RE.findall(baseline.read_text(encoding="utf-8", errors="replace")))
|
||||
same_l37 = hashes[12] == old_hashes and len(old_hashes) == 12
|
||||
runner.require(f"owner-hash-{recipe}-w1-w12", same,
|
||||
"W1 and W12 each produced identical 12-hash signatures")
|
||||
runner.require(f"owner-hash-{recipe}-matches-l37", same_l37,
|
||||
f"current owner hashes match {baseline.name}; hashes={len(old_hashes)}")
|
||||
|
||||
|
||||
def run_ring(runner: VerificationRunner, *, full: bool) -> None:
|
||||
script = LINUX37 / "RunRingAuditsL37.py"
|
||||
audit_inputs = [script,
|
||||
ROOT / "Standalone/Research/WorldAssemblerM3/Linux32/AuditRingTerraceL32.py",
|
||||
ROOT / "Standalone/Research/WorldAssemblerM3/Linux32/AuditRingSetL32.py"]
|
||||
for label, recipe, style in (("fi-floor", "floating-islands", 2),
|
||||
("sw-ceiling", "surface-world", 1)):
|
||||
args = ["--scene", label]
|
||||
layout = OUT / "layouts" / f"ring-layout-{label}-lod0.json"
|
||||
if not full:
|
||||
args.append("--lod0-only")
|
||||
if label == "sw-ceiling":
|
||||
args.append("--skip-controls")
|
||||
runner.run_stage(f"ring-{label}-{'lod0-8' if full else 'lod0'}", script, args,
|
||||
binary=CLANG, data=OWNER, recipe=recipe, style=style,
|
||||
layout_path=layout, env=env_for(), script_inputs=audit_inputs)
|
||||
|
||||
|
||||
def style_override_matrix(runner: VerificationRunner, binary: Path) -> None:
|
||||
sources: list[tuple[str, Path, str]] = []
|
||||
for recipe in ("floating-islands", "surface-world"):
|
||||
for style in range(4):
|
||||
source = ROOT / f"Saved/Linux/linux25-owner-{recipe}-style{style}.json"
|
||||
sources.append((f"{recipe}-style{style}", source, recipe))
|
||||
for style in range(4):
|
||||
source = ROOT / f"Saved/Linux/l33/fixtures/sw-upper-tunnel-network-style{style}.json"
|
||||
sources.append((f"upper-sw-fixture-style{style}", source, "floating-islands"))
|
||||
|
||||
for fixture_name, source, recipe in sources:
|
||||
label = f"style-override-{fixture_name}"
|
||||
destination = OUT / "fixtures" / f"{label}.json"
|
||||
destination.parent.mkdir(parents=True, exist_ok=True)
|
||||
shutil.copyfile(source, destination)
|
||||
style = int(re.search(r"style([0-3])$", fixture_name).group(1))
|
||||
name = f"{label}-{compiler_name(binary)}"
|
||||
if fixture_name.startswith("upper-sw-fixture-"):
|
||||
expected_strate_styles = {"1": style}
|
||||
else:
|
||||
expected_strate_styles = {"0": style, "1": 1}
|
||||
row, output = runner.run_cpp(name, binary, destination, recipe,
|
||||
["--audit-resolved-layout-passages"], expected_style=None,
|
||||
expected_strate_styles=expected_strate_styles,
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = style
|
||||
row["requested_strate_styles"] = expected_strate_styles
|
||||
validate_passage(runner, name, output)
|
||||
|
||||
|
||||
def run_transitions_and_invariants(runner: VerificationRunner,
|
||||
binaries: tuple[Path, ...]) -> None:
|
||||
for binary in binaries:
|
||||
compiler = compiler_name(binary)
|
||||
for recipe, style in (("floating-islands", 2), ("surface-world", 1)):
|
||||
for mode in ("hard", "gradient", "interleaved"):
|
||||
name = f"transition-{recipe}-{mode}-{compiler}"
|
||||
row, output = runner.run_cpp(name, binary, OWNER, recipe,
|
||||
[f"--transition-mode={mode}", "--audit-strate-transitions"],
|
||||
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = 2
|
||||
gates = (r"^\[StrateTransitionAuditSummary\].*hole_columns=0 air_samples=0 .*status=PASS$",
|
||||
r"^\[StrateTransitionNegativeControls\].*status=PASS$")
|
||||
for index, pattern in enumerate(gates):
|
||||
runner.require(f"{name}:gate-{index + 1}", all_match(output, pattern), pattern)
|
||||
|
||||
name = f"invariant-route-proof-{recipe}-{compiler}"
|
||||
row, output = runner.run_cpp(name, binary, OWNER, recipe,
|
||||
["--audit-uniform-block-proofs", "--audit-route-parity"],
|
||||
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = 2
|
||||
runner.require(f"{name}:route-parity",
|
||||
all_match(output, r"^\[RouteParityAudit\].*status=PASS$"),
|
||||
"route parity L13")
|
||||
runner.require(f"{name}:uniform-block-proof",
|
||||
all_match(output, r"^\[UniformBlockProofAudit\].*violations=0(?:\s|$)"),
|
||||
"uniform-block proof L9")
|
||||
|
||||
|
||||
def run_captures_and_mesh_audits(runner: VerificationRunner) -> None:
|
||||
capture_script = LINUX37 / "CapturePassageStandardSetL37.py"
|
||||
capture_inputs = [capture_script, VERIFY_DIR / "capture_quality.py",
|
||||
ROOT / "Standalone/Research/WorldAssemblerM3/Linux32/AuditRingTerraceL32.py"]
|
||||
capture_rows: dict[str, tuple[dict, str]] = {}
|
||||
for scene, recipe, style in (("owner-fi", "floating-islands", 2),
|
||||
("owner-sw", "surface-world", 1)):
|
||||
layout_path = OUT / f"layout-{scene}.json"
|
||||
name = f"capture-standard-{scene}-style{style}"
|
||||
row, output = runner.run_stage(name, capture_script,
|
||||
["--scene", scene], binary=CLANG, data=OWNER, recipe=recipe,
|
||||
style=style, layout_path=layout_path, env=env_for(capture=True),
|
||||
script_inputs=capture_inputs)
|
||||
resolved_strate_styles = row.get("resolved_strate_styles", {})
|
||||
target_strate = "0" if scene == "owner-fi" else "1"
|
||||
style_ok = (resolved_strate_styles == {"0": 2, "1": 1}
|
||||
and resolved_strate_styles.get(target_strate) == style)
|
||||
runner.require(f"{name}:resolved-style", style_ok,
|
||||
f"resolved_strate_styles={resolved_strate_styles} "
|
||||
f"target_strate={target_strate} expected_style={style}")
|
||||
capture_rows[scene] = (row, output)
|
||||
|
||||
shape_script = LINUX37 / "AuditMouthShapeL37.py"
|
||||
baseline = ROOT / "Saved/Linux/l37/no-tread-control"
|
||||
controls = [ROOT / "Saved/Linux/l36/owner-fi-ground-mouth.vfmesh"]
|
||||
for scene, recipe, style in (("owner-fi", "floating-islands", 2),
|
||||
("owner-sw", "surface-world", 1)):
|
||||
name = f"mouth-shape-{scene}-style{style}"
|
||||
runner.run_stage(name, shape_script,
|
||||
[f"--out={OUT}", f"--baseline-out={baseline}",
|
||||
"--control-out=Saved/Linux/l36", "--scene", scene],
|
||||
binary=CLANG, data=OWNER, recipe=recipe, style=style,
|
||||
layout_path=OUT / f"layout-{scene}.json", env=env_for(),
|
||||
script_inputs=[shape_script, *controls])
|
||||
|
||||
crease_script = LINUX37 / "RunMouthCreaseAuditL37.py"
|
||||
sw_capture_log = OUT / "capture-standard-owner-sw-style1.log"
|
||||
crease_args = [
|
||||
f"--candidate={OUT / 'owner-fi-ground-mouth.vfmesh'}",
|
||||
f"--candidate-sw={OUT / 'owner-sw-ground-mouth.vfmesh'}",
|
||||
f"--layout-sw={OUT / 'layout-owner-sw.json'}",
|
||||
f"--capture-log-sw={sw_capture_log}"]
|
||||
control_meshes = [ROOT / f"Saved/Linux/{round_name}/owner-fi-ground-mouth.vfmesh"
|
||||
for round_name in ("l35", "l36")]
|
||||
runner.run_stage("mouth-crease-fragments-owner-fi2-sw1", crease_script,
|
||||
crease_args, binary=CLANG, data=OWNER, recipe="floating-islands", style=2,
|
||||
layout_path=OUT / "layout-owner-fi.json", env=env_for(),
|
||||
script_inputs=[crease_script,
|
||||
LINUX37 / "RunMouthFragmentAuditL37.py", *control_meshes,
|
||||
OUT / "owner-fi-ground-mouth.vfmesh", OUT / "owner-sw-ground-mouth.vfmesh",
|
||||
OUT / "layout-owner-sw.json", sw_capture_log])
|
||||
|
||||
overview_script = LINUX37 / "CaptureMouthOverviewL37.py"
|
||||
runner.run_stage("capture-fi-overview-style2", overview_script, [],
|
||||
binary=CLANG, data=OWNER, recipe="floating-islands", style=2,
|
||||
layout_path=OUT / "layout-owner-fi.json", env=env_for(capture=True),
|
||||
script_inputs=[overview_script, VERIFY_DIR / "capture_quality.py",
|
||||
OUT / "owner-fi-ground-mouth.vfmesh"])
|
||||
|
||||
|
||||
def verify_determinism_cell(runner: VerificationRunner, binary: Path,
|
||||
kind: str, recipe: str, style: int, workers: int,
|
||||
reference: dict[tuple[str, str], tuple[str, ...]]) -> None:
|
||||
name = f"determinism-{kind}-{recipe}-{compiler_name(binary)}-w{workers}"
|
||||
flags = ["--stream-hash"]
|
||||
if kind == "crossing24":
|
||||
flags.extend(("--camera-step=24,0,0", "--region-crossing"))
|
||||
row, output = runner.run_cpp(name, binary, OWNER, recipe, flags,
|
||||
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
||||
workers=workers,
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = 2
|
||||
values = tuple(HASH_RE.findall(output))
|
||||
key = (kind, recipe)
|
||||
expected = reference.get(key)
|
||||
stable = expected is None or values == expected
|
||||
if expected is None and values:
|
||||
reference[key] = values
|
||||
runner.require(f"{name}:stable-hashes", len(values) == 12 and stable,
|
||||
f"hashes={len(values)}/12 stable={stable}")
|
||||
|
||||
|
||||
def run_30_cell_determinism(runner: VerificationRunner) -> None:
|
||||
references: dict[tuple[str, str], tuple[str, ...]] = {}
|
||||
count = 0
|
||||
for kind in ("l25", "crossing24"):
|
||||
for recipe, style in (("surface-world", 1), ("floating-islands", 2)):
|
||||
for binary in (CLANG, GCC):
|
||||
for workers in (1, 8, 12):
|
||||
verify_determinism_cell(runner, binary, kind, recipe, style,
|
||||
workers, references)
|
||||
count += 1
|
||||
|
||||
fixture_source = ROOT / "Saved/Linux/l33/fixtures/sw-upper-tunnel-network-style0.json"
|
||||
fixture = OUT / "fixtures/style-override-upper-sw-fixture-style0.json"
|
||||
fixture.parent.mkdir(parents=True, exist_ok=True)
|
||||
shutil.copyfile(fixture_source, fixture)
|
||||
signatures = None
|
||||
for binary in (CLANG, GCC):
|
||||
for workers in (1, 8, 12):
|
||||
name = f"determinism-style-override-upper-sw-fixture-style0-{compiler_name(binary)}-w{workers}"
|
||||
row, output = runner.run_cpp(name, binary, fixture, "floating-islands",
|
||||
["--audit-resolved-layout-passages"], expected_style=None,
|
||||
expected_strate_styles={"1": 0}, workers=workers,
|
||||
layout_path=OUT / "layouts" / f"{name}.json")
|
||||
row["requested_style"] = 0
|
||||
row["requested_strate_styles"] = {"1": 0}
|
||||
validate_passage(runner, name, output)
|
||||
current = tuple(re.findall(
|
||||
r"^\[ResolvedLayoutSnapshot\].*stable_identity=([^ ]+)", output, re.M)
|
||||
+ re.findall(r"^\[WorldAssemblyPlanSerialization\].*plan_hash=([0-9a-f]+)", output, re.M)
|
||||
+ re.findall(r"^\[WorldAssemblerRouteAccepted\].*$", output, re.M))
|
||||
stable = signatures is None or current == signatures
|
||||
if signatures is None and current:
|
||||
signatures = current
|
||||
runner.require(f"{name}:stable-plan-route", bool(current) and stable,
|
||||
f"snapshot-plan-route_records={len(current)} stable={stable}")
|
||||
count += 1
|
||||
runner.require("determinism-30-cell-count", count == 30, f"cells={count}/30")
|
||||
|
||||
|
||||
def prepare_l36_cost_baseline(runner: VerificationRunner) -> tuple[Path, str]:
|
||||
temp = Path("/tmp/voxelforge-l36-stamped")
|
||||
if temp.exists():
|
||||
shutil.rmtree(temp)
|
||||
temp.mkdir(parents=True)
|
||||
tarball = temp / "l36.tar"
|
||||
archive = bounded_run(["git", "archive", "-o", str(tarball),
|
||||
"8be1c4d", "Standalone"], timeout=120)
|
||||
if archive is None or archive.returncode != 0 or not tarball.is_file():
|
||||
raise VerificationFailure("could not export historical L36 source commit 8be1c4d")
|
||||
extract = bounded_run(["tar", "-xf", str(tarball), "-C", str(temp)], timeout=120)
|
||||
if extract is None or extract.returncode != 0:
|
||||
raise VerificationFailure("historical L36 source extraction failed")
|
||||
tarball.unlink(missing_ok=True)
|
||||
|
||||
base = temp / "Standalone"
|
||||
(base / "Tools/verify").mkdir(parents=True, exist_ok=True)
|
||||
shutil.copy2(ROOT / "Standalone/BuildLinux.sh", base / "BuildLinux.sh")
|
||||
shutil.copy2(VERIFY_DIR / "source_stamp.py", base / "Tools/verify/source_stamp.py")
|
||||
shutil.copy2(ROOT / "Standalone/Source/SourceStamp.h", base / "Source/SourceStamp.h")
|
||||
legacy_main = base / "Source/StreamBenchmarkHeadless.cpp"
|
||||
text = legacy_main.read_text(encoding="utf-8")
|
||||
if "VoxelForgePrintSourceStamp" not in text:
|
||||
text = text.replace("#include \"OwnerWorldLoader.h\"",
|
||||
"#include \"SourceStamp.h\"\n#include <cstring>\n#include \"OwnerWorldLoader.h\"", 1)
|
||||
anchor = re.search(r"int main\(int argc,\s*char\*\*\s*argv\)\s*\{", text)
|
||||
if anchor is None:
|
||||
raise VerificationFailure("cannot instrument historical L36 headless entry point")
|
||||
injected = ("\n VoxelForgePrintSourceStamp();\n"
|
||||
" if(argc==2&&std::strcmp(argv[1],\"--print-source-stamp\")==0)return 0;")
|
||||
text = text[:anchor.end()] + injected + text[anchor.end():]
|
||||
legacy_main.write_text(text, encoding="utf-8")
|
||||
|
||||
baseline_stamp = source_stamp(temp)
|
||||
binary = OUT / "historical-bin/VoxelForgeCoreHeadless-l36-stamped"
|
||||
env = os.environ.copy()
|
||||
env["VOXELFORGE_BUILD_ROOT"] = str(temp / "build")
|
||||
env["VOXELFORGE_BIN_DIR"] = str(binary.parent)
|
||||
command = ["bash", str(base / "BuildLinux.sh"), "--compiler=clang++-19",
|
||||
"--variant=l36-stamped", "--fp-contract=off", "--jobs=12"]
|
||||
log = OUT / "cost-baseline-build-l36.log"
|
||||
log.parent.mkdir(parents=True, exist_ok=True)
|
||||
started = time.monotonic()
|
||||
with log.open("w", encoding="utf-8") as stream:
|
||||
proc = bounded_run(command, timeout=1800, env=env, stdout=stream)
|
||||
elapsed = time.monotonic() - started
|
||||
runner.require("cost-baseline-l36-build",
|
||||
proc is not None and proc.returncode == 0 and binary.is_file(),
|
||||
f"source_stamp={baseline_stamp} elapsed_seconds={elapsed:.1f} log={log}")
|
||||
runner.binary_stamp_overrides[str(binary)] = baseline_stamp
|
||||
return binary, baseline_stamp
|
||||
|
||||
|
||||
def run_cost_pairs(runner: VerificationRunner) -> None:
|
||||
baseline, baseline_stamp = prepare_l36_cost_baseline(runner)
|
||||
candidate = CLANG
|
||||
orders = (("l36", "l39"), ("l39", "l36"), ("l36", "l39"),
|
||||
("l39", "l36"), ("l36", "l39"))
|
||||
by_recipe: dict[str, dict[str, list[float]]] = {
|
||||
"floating-islands": {"l36": [], "l39": []},
|
||||
"surface-world": {"l36": [], "l39": []}}
|
||||
by_pair: dict[tuple[str, int], dict[str, float]] = {}
|
||||
for recipe, style in (("floating-islands", 2), ("surface-world", 1)):
|
||||
for pair, order in enumerate(orders, 1):
|
||||
for build in order:
|
||||
binary = baseline if build == "l36" else candidate
|
||||
expected_style = None if build == "l36" else style
|
||||
name = f"cost-{recipe}-pair{pair}-{build}"
|
||||
expected_stamp = baseline_stamp if build == "l36" else None
|
||||
row, output = runner.run_cpp(name, binary, OWNER, recipe, [],
|
||||
expected_style=2 if build == "l39" else None,
|
||||
expected_strate_styles={"0": 2, "1": 1} if build == "l39" else None,
|
||||
layout_path=OUT / "layouts" / f"{name}.json",
|
||||
expected_stamp=expected_stamp)
|
||||
row["requested_style"] = style
|
||||
row["expected_passage_style"] = 2 if build == "l39" else None
|
||||
ready = re.findall(r"\bwhole_view_ready=([0-9.]+)s", output)
|
||||
ok = (len(ready) == 1 and "hash=off" in output
|
||||
and "cache_hits=0" in output
|
||||
and RECIPE_RE.findall(output) == [(recipe, recipe, "PASS")])
|
||||
runner.require(f"{name}:cost-record", ok,
|
||||
f"whole_view_ready={ready[0] if ready else 'MISSING'}s "
|
||||
f"source_stamp={row['source_stamp']}")
|
||||
by_recipe[recipe][build].append(float(ready[0]))
|
||||
by_pair.setdefault((recipe, pair), {})[build] = float(ready[0])
|
||||
for recipe, values in by_recipe.items():
|
||||
old = statistics.median(values["l36"])
|
||||
new = statistics.median(values["l39"])
|
||||
paired = [((by_pair[(recipe, pair)]["l39"] - by_pair[(recipe, pair)]["l36"])
|
||||
/ by_pair[(recipe, pair)]["l36"] * 100.0)
|
||||
for pair in range(1, 6)]
|
||||
runner.require(f"cost-{recipe}-five-pairs",
|
||||
len(values["l36"]) == len(values["l39"]) == 5,
|
||||
f"median_l36_s={old:.3f} median_l39_s={new:.3f} "
|
||||
f"median_change_pct={(new / old - 1.0) * 100.0:+.2f} "
|
||||
f"paired_change_pct={','.join(f'{value:+.2f}' for value in paired)}")
|
||||
|
||||
|
||||
def run_medium_suite(runner: VerificationRunner, *, both_compilers: bool = False) -> None:
|
||||
binaries = (CLANG, GCC) if both_compilers else (CLANG,)
|
||||
run_owner_passages(runner, binaries)
|
||||
run_regression_controls(runner)
|
||||
style_override_matrix(runner, CLANG)
|
||||
if both_compilers:
|
||||
style_override_matrix(runner, GCC)
|
||||
run_transitions_and_invariants(runner, binaries)
|
||||
run_ring(runner, full=True)
|
||||
run_captures_and_mesh_audits(runner)
|
||||
|
||||
|
||||
def run_gcc_supplement(runner: VerificationRunner) -> None:
|
||||
"""Add GCC evidence to a stamped, already-passed Clang medium tier."""
|
||||
run_owner_passages(runner, (GCC,))
|
||||
style_override_matrix(runner, GCC)
|
||||
run_transitions_and_invariants(runner, (GCC,))
|
||||
|
||||
|
||||
def main() -> int:
|
||||
runner = VerificationRunner(ARGS.tier)
|
||||
started = time.monotonic()
|
||||
try:
|
||||
if not OWNER.is_file():
|
||||
raise VerificationFailure(f"canonical owner input is missing: {OWNER}")
|
||||
for binary in (CLANG, GCC, RENDERER):
|
||||
if binary.is_file():
|
||||
runner.probe_binary(binary)
|
||||
if ARGS.tier == "fast":
|
||||
owners = run_owner_passages(runner, (CLANG,))
|
||||
run_regression_controls(runner)
|
||||
run_hash_pairs(runner, owners)
|
||||
run_ring(runner, full=False)
|
||||
elif ARGS.tier == "medium":
|
||||
run_medium_suite(runner, both_compilers=False)
|
||||
else:
|
||||
medium_summary = OUT / "medium-summary.json"
|
||||
if not runner.reuse_passed_tier(medium_summary, "medium"):
|
||||
run_medium_suite(runner, both_compilers=False)
|
||||
run_gcc_supplement(runner)
|
||||
run_30_cell_determinism(runner)
|
||||
run_cost_pairs(runner)
|
||||
# The validated medium summary carries the final canonical capture set.
|
||||
|
||||
runner.assert_binaries_current()
|
||||
runner.assert_current_tree("at tier completion")
|
||||
elapsed = time.monotonic() - started
|
||||
runner.save_summary("PASS")
|
||||
print(f"[{ARGS.tier}] DONE PASS elapsed={elapsed:.1f}s", flush=True)
|
||||
return 0
|
||||
except Exception as error:
|
||||
elapsed = time.monotonic() - started
|
||||
runner.save_summary("FAIL", str(error))
|
||||
print(f"[{ARGS.tier}] DONE FAIL elapsed={elapsed:.1f}s error={error}", flush=True)
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
Reference in new issue
Block a user