Fr0zkaandClaude Opus 5.5
e016f6a20f
The flagged SW demo's ramp (57 carves + 107 support pillars, visibly ribbed) becomes one cubic-Bezier sweep: closest point by 17-point seed plus 5 Newton steps, a cubic floor profile, a rounded 2.6 m bore, and a hard floor cap applied after unions and relief that only adds support where the field is air. Optional resolved cavern-graph records (one room, one edge) enter canonical identity only when present; their bounds extend World::isTileShapeFree. Reachability passes (L43 control fails), headroom 2.8 m, floor ripple 1.8 mm (L45 ramp control fails at 17.9 mm), shape limits met; demo off: owner hashes identical to L45. fast/medium/full PASS. Research R13 (read-only): continuous SDF sweeps along curves. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016dhxM43dnWvUu2B5Ph1iG1
958 lines
50 KiB
Python
958 lines
50 KiB
Python
#!/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 signal
|
|
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/l42"
|
|
|
|
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/l41)")
|
|
PARSER.add_argument("--baseline", default="HEAD",
|
|
help="commit used for the full-tier cost baseline (default: HEAD)")
|
|
PARSER.add_argument("--overall-timeout", type=int, default=7200,
|
|
help="maximum tier wall time in seconds (default: 7200; each child is capped at 1800)")
|
|
ARGS = PARSER.parse_args()
|
|
OUT = ARGS.out.resolve()
|
|
ROUND_NAME = OUT.name
|
|
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" / f"VoxelForgeCoreHeadless-{ROUND_NAME}-clang"
|
|
GCC = OUT / "bin" / f"VoxelForgeCoreHeadless-{ROUND_NAME}-gcc"
|
|
RENDERER = OUT / "bin" / f"VoxelForgeOffscreenCapture-{ROUND_NAME}-clang"
|
|
HASH_RE = re.compile(r"^\[Pipeline(?:FullDetailHash|WholeViewHash|LODHash|ExactQueryHash)\].*$", re.M)
|
|
TILE_HASH_RE = re.compile(
|
|
r"^\[PipelineTileHash\] lod=(-?\d+) x=(-?\d+) y=(-?\d+) z=(-?\d+) "
|
|
r"density=(0x[0-9a-f]+) mesh=(0x[0-9a-f]+) "
|
|
r"payload=(0x[0-9a-f]+) topology=(0x[0-9a-f]+)$", re.M)
|
|
CAMERA_SWEEP_SEED = 0x4C3434
|
|
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}"
|
|
flags = ["--landmark-chamber-demo"] if recipe == "surface-world" else []
|
|
row, output = run_passage(runner, binary, name, OWNER, recipe, style,
|
|
flags=flags,
|
|
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 run_landmark_reachability(runner: VerificationRunner,
|
|
binaries: tuple[Path, ...]) -> None:
|
|
for binary in binaries:
|
|
compiler = compiler_name(binary)
|
|
name = f"landmark-reachability-{compiler}"
|
|
row, output = runner.run_cpp(name, binary, OWNER, "surface-world",
|
|
["--landmark-chamber-demo", "--audit-landmark-reachability",
|
|
"--max-clip-level=0", "--render-distance-chunks=0"],
|
|
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
|
max_level=0, layout_path=OUT / "layouts" / f"{name}.json")
|
|
row["requested_style"] = 1
|
|
row["expected_passage_style"] = 2
|
|
passage_name = f"landmark-demo-passages-{compiler}"
|
|
_, passage_output = runner.run_cpp(passage_name, binary, OWNER, "surface-world",
|
|
["--landmark-chamber-demo", "--audit-resolved-layout-passages",
|
|
"--max-clip-level=0", "--render-distance-chunks=0"],
|
|
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
|
max_level=0, layout_path=OUT / "layouts" / f"{passage_name}.json")
|
|
runner.require(f"{passage_name}:demo-enabled",
|
|
all_match(passage_output, r"^\[LandmarkCavernGraphDemo\] enabled=true .*rooms=1 edges=1 .*status=PASS$"),
|
|
"landmark demo flag resolved while running passage audits")
|
|
validate_passage(runner, passage_name, passage_output)
|
|
|
|
interface_name = f"landmark-demo-interfaces-{compiler}"
|
|
_, interface_output = runner.run_cpp(interface_name, binary, OWNER, "surface-world",
|
|
["--landmark-chamber-demo", "--audit-strate-transitions",
|
|
"--max-clip-level=0", "--render-distance-chunks=0"],
|
|
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
|
max_level=0, layout_path=OUT / "layouts" / f"{interface_name}.json")
|
|
runner.require(f"{interface_name}:demo-enabled",
|
|
all_match(interface_output, r"^\[LandmarkCavernGraphDemo\] enabled=true .*rooms=1 edges=1 .*status=PASS$"),
|
|
"landmark demo flag resolved while running interface audits")
|
|
runner.require(f"{interface_name}:hole-audit",
|
|
all_match(interface_output, r"^\[StrateTransitionAuditSummary\].*hole_columns=0 "
|
|
r"air_samples=0 .*status=PASS$"),
|
|
"demo-on stratum interfaces contain no holes or air columns")
|
|
runner.require(f"{interface_name}:negative-controls",
|
|
all_match(interface_output, r"^\[StrateTransitionNegativeControls\].*status=PASS$"),
|
|
"demo-on interface audit detects both thickness controls")
|
|
runner.require(f"{name}:candidate-walkability",
|
|
all_match(output, r"^\[LandmarkWalkability\] layout=L46 .*headroom_required_m=0\.300 status=PASS$"),
|
|
"demo capsule clearance, support, headroom and <=15 degree grade")
|
|
runner.require(f"{name}:headroom",
|
|
all_match(output, r"^\[LandmarkHeadroom\] minimum_m=(?:0\.[3-9][0-9][0-9]|[1-9][0-9]*\.[0-9]{3}) required_m=0\.300 status=PASS$"),
|
|
"at least 0.3 m above the capsule along the complete route")
|
|
runner.require(f"{name}:continuous-tunnel-ripple",
|
|
all_match(output, r"^\[CavernTunnelRipple\] layout=L46 .*floor_limit_m=0\.015 .*wall_limit_m=0\.035 status=PASS$"),
|
|
"floor and wall ripple remain below L36/L35 limits")
|
|
runner.require(f"{name}:buried-l43-control",
|
|
all_match(output, r"^\[LandmarkReachabilityControl\] layout=L43-buried .*"
|
|
r"result=FAIL expected=FAIL status=PASS$"),
|
|
"the exact buried L43 chamber fails the same route audit")
|
|
runner.require(f"{name}:surface-to-floor-route",
|
|
all_match(output, r"^\[LandmarkSurfaceRoute\] reachable=true .*"
|
|
r"surface_points=[1-9][0-9]* grade_limit_deg=15\.000$"),
|
|
"walkable surface path from ground near the arrival mouth joins the ramp")
|
|
runner.require(f"{name}:reachability-control-summary",
|
|
all_match(output, r"^\[LandmarkReachabilityAudit\] positive=PASS "
|
|
r"control=EXPECTED_FAIL status=PASS$"),
|
|
"candidate passes and buried control fails")
|
|
ripple_control = f"landmark-l45-ramp-ripple-control-{compiler}"
|
|
_, control_output = runner.run_cpp(ripple_control, binary, OWNER, "surface-world",
|
|
["--landmark-chamber-demo", "--landmark-l45-ramp-control",
|
|
"--audit-landmark-reachability", "--max-clip-level=0",
|
|
"--render-distance-chunks=0"],
|
|
expected_style=2, expected_strate_styles={"0": 2, "1": 1},
|
|
max_level=0, layout_path=OUT / "layouts" / f"{ripple_control}.json")
|
|
runner.require(f"{ripple_control}:negative-control",
|
|
all_match(control_output,
|
|
r"^\[CavernTunnelRippleControl\] layout=L45-ramp .*"
|
|
r"floor_limit_m=0\.015 .*observed=FAIL expected=FAIL status=PASS$"),
|
|
"the segmented L45 ramp exceeds the floor ripple threshold")
|
|
|
|
|
|
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)}")
|
|
|
|
|
|
class _SplitMix64:
|
|
"""Small fixed-seed generator whose camera sequence is independent of Python random."""
|
|
def __init__(self, seed: int):
|
|
self.state = seed & 0xffffffffffffffff
|
|
|
|
def unit(self) -> float:
|
|
self.state = (self.state + 0x9e3779b97f4a7c15) & 0xffffffffffffffff
|
|
value = self.state
|
|
value = ((value ^ (value >> 30)) * 0xbf58476d1ce4e5b9) & 0xffffffffffffffff
|
|
value = ((value ^ (value >> 27)) * 0x94d049bb133111eb) & 0xffffffffffffffff
|
|
value ^= value >> 31
|
|
return (value >> 11) / float(1 << 53)
|
|
|
|
def between(self, low: float, high: float) -> float:
|
|
return low + (high - low) * self.unit()
|
|
|
|
|
|
def seeded_camera_positions(count: int) -> list[tuple[float, float, float, float, float]]:
|
|
rng = _SplitMix64(CAMERA_SWEEP_SEED)
|
|
positions: list[tuple[float, float, float, float, float]] = []
|
|
for index in range(count):
|
|
if index == 0:
|
|
# Stay in the known failing 8 m tile neighbourhood while still deriving the
|
|
# camera from the fixed seed. The negative Y offset keeps it below the 32 m seam.
|
|
x = -8.918 + rng.between(-0.02, 0.02)
|
|
y = 31.95 - rng.between(0.005, 0.035)
|
|
z = -513.083 + rng.between(-0.02, 0.02)
|
|
else:
|
|
x = rng.between(-900.0, 900.0)
|
|
y = rng.between(-900.0, 900.0)
|
|
while math.hypot(x + 46.45, y + 472.88) < 320.0:
|
|
x = rng.between(-900.0, 900.0)
|
|
y = rng.between(-900.0, 900.0)
|
|
if index % 2:
|
|
z = -256.0 + rng.between(-12.0, 12.0) # SurfaceWorld strate 0.
|
|
else:
|
|
z = -1536.0 + rng.between(-120.0, 120.0) # FloatingIslands strate 1.
|
|
yaw = rng.between(-180.0, 180.0)
|
|
pitch = rng.between(-35.0, 35.0)
|
|
positions.append((x, y, z, yaw, pitch))
|
|
return positions
|
|
|
|
|
|
def parse_tile_hashes(output: str) -> dict[tuple[int, int, int, int], tuple[str, ...]]:
|
|
rows: dict[tuple[int, int, int, int], tuple[str, ...]] = {}
|
|
for match in TILE_HASH_RE.finditer(output):
|
|
key = tuple(int(match.group(i)) for i in range(1, 5))
|
|
rows[key] = tuple(match.group(i) for i in range(5, 9))
|
|
return rows
|
|
|
|
|
|
def cavern_audit_cameras(layout_path: Path) -> list[tuple[float, float, float, float, float]]:
|
|
layout = json.loads(layout_path.read_text(encoding="utf-8"))
|
|
edges = layout.get("cavern_edges", [])
|
|
if layout.get("cavern_graph_vocabulary_version") != 1 or len(edges) != 1:
|
|
raise VerificationFailure(f"missing one resolved cavern edge in {layout_path}")
|
|
points = [[value / 1_000_000.0 for value in point]
|
|
for point in edges[0]["control_points_um"]]
|
|
|
|
def value(t: float, axis: int) -> float:
|
|
one = 1.0 - t
|
|
return (one ** 3 * points[0][axis] + 3.0 * one ** 2 * t * points[1][axis]
|
|
+ 3.0 * one * t ** 2 * points[2][axis] + t ** 3 * points[3][axis])
|
|
|
|
def derivative(t: float, axis: int) -> float:
|
|
one = 1.0 - t
|
|
return (3.0 * one ** 2 * (points[1][axis] - points[0][axis])
|
|
+ 6.0 * one * t * (points[2][axis] - points[1][axis])
|
|
+ 3.0 * t ** 2 * (points[3][axis] - points[2][axis]))
|
|
|
|
cameras = []
|
|
for t, lateral in ((0.50, 0.0), (0.32, 3.3)):
|
|
x, y, floor = value(t, 0), value(t, 1), value(t, 2)
|
|
dx, dy = derivative(t, 0), derivative(t, 1)
|
|
length = math.hypot(dx, dy)
|
|
side_x, side_y = -dy / length, dx / length
|
|
cameras.append((x + side_x * lateral, y + side_y * lateral,
|
|
floor + 1.6, math.degrees(math.atan2(dx, dy)), 0.0))
|
|
return cameras
|
|
|
|
|
|
def run_random_camera_sweep(runner: VerificationRunner, binaries: tuple[Path, ...],
|
|
camera_count: int,
|
|
configurations: tuple[tuple[int, int, int], ...]) -> None:
|
|
positions = seeded_camera_positions(camera_count)
|
|
for binary in binaries:
|
|
compiler = compiler_name(binary)
|
|
for recipe in ("surface-world", "floating-islands"):
|
|
for camera_index, camera in enumerate(positions):
|
|
x, y, z, yaw, pitch = camera
|
|
camera_flag = f"--camera={x:.6f},{y:.6f},{z:.6f},{yaw:.3f},{pitch:.3f}"
|
|
for clip_radius, max_clip_level, max_level in configurations:
|
|
settings = (clip_radius, max_clip_level, max_level)
|
|
label = (f"random-camera-{compiler}-{recipe}-s{CAMERA_SWEEP_SEED:06x}"
|
|
f"-p{camera_index:02d}-r{clip_radius}-c{max_clip_level}-m{max_level}")
|
|
signatures: dict[int, dict[tuple[int, int, int, int], tuple[str, ...]]] = {}
|
|
for workers in (1, 8, 12):
|
|
name = f"{label}-w{workers}"
|
|
flags = ["--stream-hash-tiles", camera_flag,
|
|
f"--clip-radius={clip_radius}",
|
|
f"--max-clip-level={max_clip_level}",
|
|
f"--max-level={max_level}", "--render-distance-chunks=0"]
|
|
if recipe == "surface-world":
|
|
flags.append("--landmark-chamber-demo")
|
|
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["camera_sweep_seed"] = CAMERA_SWEEP_SEED
|
|
row["camera_position_m"] = [round(value, 6) for value in camera[:3]]
|
|
row["camera_rotation_degrees"] = [round(value, 3) for value in camera[3:]]
|
|
row["sweep_settings"] = {
|
|
"clip_radius": clip_radius,
|
|
"max_clip_level": max_clip_level,
|
|
"max_level": max_level,
|
|
}
|
|
current = parse_tile_hashes(output)
|
|
signatures[workers] = current
|
|
whole = re.search(r"^\[PipelineWholeViewHash\] tiles=(\d+)", output, re.M)
|
|
expected_rows = int(whole.group(1)) if whole else -1
|
|
runner.require(f"{name}:tile-hash-rows",
|
|
bool(current) and len(current) == expected_rows,
|
|
f"rows={len(current)} expected={expected_rows} settings={settings}")
|
|
camera_text = (f"seed=0x{CAMERA_SWEEP_SEED:06x} camera_m="
|
|
f"({x:.3f},{y:.3f},{z:.3f}) recipe={recipe} settings={settings}")
|
|
for left, right in ((1, 8), (1, 12), (8, 12)):
|
|
left_rows, right_rows = signatures[left], signatures[right]
|
|
keys = set(left_rows) | set(right_rows)
|
|
density_diff = [key for key in keys
|
|
if left_rows.get(key, (None,))[0] != right_rows.get(key, (None,))[0]]
|
|
mesh_diff = [key for key in keys
|
|
if left_rows.get(key, (None, None))[1]
|
|
!= right_rows.get(key, (None, None))[1]]
|
|
payload_diff = [key for key in keys
|
|
if left_rows.get(key, (None, None, None))[2]
|
|
!= right_rows.get(key, (None, None, None))[2]]
|
|
topology_diff = [key for key in keys
|
|
if left_rows.get(key, (None, None, None, None))[3]
|
|
!= right_rows.get(key, (None, None, None, None))[3]]
|
|
detail = (f"{camera_text} W{left}=W{right} "
|
|
f"density_tiles={len(density_diff)} mesh_tiles={len(mesh_diff)} "
|
|
f"payload_tiles={len(payload_diff)} topology_tiles={len(topology_diff)} "
|
|
f"sample_coords={sorted(density_diff or mesh_diff)[:6]}")
|
|
runner.require(f"{label}:W{left}-W{right}",
|
|
left_rows == right_rows, detail)
|
|
|
|
# Keep a pair of fixed cameras on the current owner graph: one in the bore and
|
|
# one beside its curved wall. Their tile hashes join the seeded W1/W8/W12 sweep.
|
|
layout_path = OUT / "layouts" / "landmark-reachability-clang.json"
|
|
if layout_path.is_file():
|
|
graph_cameras = cavern_audit_cameras(layout_path)
|
|
for binary in binaries:
|
|
compiler = compiler_name(binary)
|
|
for camera_index, camera in enumerate(graph_cameras):
|
|
x, y, z, yaw, pitch = camera
|
|
camera_flag = f"--camera={x:.6f},{y:.6f},{z:.6f},{yaw:.3f},{pitch:.3f}"
|
|
label = f"cavern-camera-{compiler}-s{CAMERA_SWEEP_SEED:06x}-p{camera_index:02d}"
|
|
signatures: dict[int, dict[tuple[int, int, int, int], tuple[str, ...]]] = {}
|
|
for workers in (1, 8, 12):
|
|
name = f"{label}-w{workers}"
|
|
row, output = runner.run_cpp(name, binary, OWNER, "surface-world",
|
|
["--stream-hash-tiles", camera_flag, "--landmark-chamber-demo",
|
|
"--clip-radius=3", "--max-clip-level=0", "--max-level=0",
|
|
"--render-distance-chunks=0"],
|
|
expected_style=2,
|
|
expected_strate_styles={"0": 2, "1": 1}, workers=workers,
|
|
max_level=0, layout_path=OUT / "layouts" / f"{name}.json")
|
|
row["camera_position_m"] = [round(value, 6) for value in camera[:3]]
|
|
row["camera_region"] = "inside-tunnel" if camera_index == 0 else "near-tunnel-wall"
|
|
signatures[workers] = parse_tile_hashes(output)
|
|
whole = re.search(r"^\[PipelineWholeViewHash\] tiles=(\d+)", output, re.M)
|
|
expected_rows = int(whole.group(1)) if whole else -1
|
|
runner.require(f"{name}:tile-hash-rows",
|
|
bool(signatures[workers]) and len(signatures[workers]) == expected_rows,
|
|
f"rows={len(signatures[workers])} expected={expected_rows} camera={camera[:3]}")
|
|
for left, right in ((1, 8), (1, 12), (8, 12)):
|
|
runner.require(f"{label}:W{left}-W{right}",
|
|
signatures[left] == signatures[right],
|
|
f"camera_m=({x:.3f},{y:.3f},{z:.3f}) "
|
|
f"region={'inside' if camera_index == 0 else 'near'}-tunnel "
|
|
f"W{left}=W{right} density/mesh/payload/topology tile hashes match")
|
|
|
|
|
|
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}"
|
|
flags = [f"--transition-mode={mode}", "--audit-strate-transitions"]
|
|
if recipe == "surface-world":
|
|
flags.append("--landmark-chamber-demo")
|
|
row, output = runner.run_cpp(name, binary, OWNER, recipe,
|
|
flags,
|
|
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}"
|
|
flags = ["--audit-uniform-block-proofs", "--audit-route-parity"]
|
|
if recipe == "surface-world":
|
|
flags.append("--landmark-chamber-demo")
|
|
row, output = runner.run_cpp(name, binary, OWNER, recipe,
|
|
flags,
|
|
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"])
|
|
|
|
landmark_script = ROOT / "Standalone/Research/WorldAssemblerM3/Linux46/CaptureLandmarkL46.py"
|
|
landmark_layout = OUT / "layouts" / "landmark-reachability-clang.json"
|
|
runner.run_stage("capture-landmark-l46", landmark_script,
|
|
["--layout", str(landmark_layout), "--artifact-dir", str(OUT),
|
|
"--capture-dir", str(ROOT / "Standalone/Research/WorldAssemblerM3/Linux46/captures"),
|
|
"--data", str(OWNER)],
|
|
binary=CLANG, data=OWNER, recipe="surface-world", style=1,
|
|
layout_path=landmark_layout, env=env_for(capture=True),
|
|
script_inputs=[landmark_script, VERIFY_DIR / "capture_quality.py",
|
|
LINUX37 / "AuditMouthShapeL37.py",
|
|
ROOT / "Standalone/Research/WorldAssemblerM3/Linux32/AuditRingTerraceL32.py"])
|
|
|
|
|
|
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_cost_baseline(runner: VerificationRunner) -> tuple[Path, str]:
|
|
resolved = bounded_run(["git", "rev-parse", "--verify", f"{ARGS.baseline}^{{commit}}"], timeout=120)
|
|
if resolved is None or resolved.returncode != 0:
|
|
raise VerificationFailure(f"could not resolve cost baseline commit {ARGS.baseline!r}")
|
|
baseline_commit = resolved.stdout.strip()
|
|
if not re.fullmatch(r"[0-9a-f]{40,64}", baseline_commit):
|
|
raise VerificationFailure(f"git returned an invalid baseline commit: {baseline_commit!r}")
|
|
temp = Path(f"/tmp/voxelforge-cost-baseline-{baseline_commit[:12]}")
|
|
if temp.exists():
|
|
shutil.rmtree(temp)
|
|
temp.mkdir(parents=True)
|
|
tarball = temp / "baseline.tar"
|
|
archive = bounded_run(["git", "archive", "-o", str(tarball),
|
|
baseline_commit, "Standalone"], timeout=120)
|
|
if archive is None or archive.returncode != 0 or not tarball.is_file():
|
|
raise VerificationFailure(
|
|
f"could not export Standalone from cost baseline commit {baseline_commit}")
|
|
extract = bounded_run(["tar", "-xf", str(tarball), "-C", str(temp)], timeout=120)
|
|
if extract is None or extract.returncode != 0:
|
|
raise VerificationFailure("cost baseline 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 cost-baseline 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)
|
|
baseline_variant = f"baseline-{baseline_commit[:12]}-stamped"
|
|
binary = OUT / "historical-bin" / f"VoxelForgeCoreHeadless-{baseline_variant}"
|
|
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",
|
|
f"--variant={baseline_variant}", "--fp-contract=off", "--jobs=12"]
|
|
log = OUT / "cost-baseline-build.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-build",
|
|
proc is not None and proc.returncode == 0 and binary.is_file(),
|
|
f"baseline={baseline_commit} source_stamp={baseline_stamp} "
|
|
f"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_cost_baseline(runner)
|
|
candidate = CLANG
|
|
orders = (("baseline", "candidate"), ("candidate", "baseline"),
|
|
("baseline", "candidate"), ("candidate", "baseline"),
|
|
("baseline", "candidate"))
|
|
by_recipe: dict[str, dict[str, list[float]]] = {
|
|
"floating-islands": {"baseline": [], "candidate": []},
|
|
"surface-world": {"baseline": [], "candidate": []}}
|
|
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 == "baseline" else candidate
|
|
name = f"cost-{recipe}-pair{pair}-{build}"
|
|
expected_stamp = baseline_stamp if build == "baseline" else None
|
|
row, output = runner.run_cpp(name, binary, OWNER, recipe, [],
|
|
expected_style=2 if build == "candidate" else None,
|
|
expected_strate_styles={"0": 2, "1": 1} if build == "candidate" else None,
|
|
layout_path=OUT / "layouts" / f"{name}.json",
|
|
expected_stamp=expected_stamp)
|
|
row["requested_style"] = style
|
|
row["expected_passage_style"] = 2 if build == "candidate" 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["baseline"])
|
|
new = statistics.median(values["candidate"])
|
|
paired = [((by_pair[(recipe, pair)]["candidate"] - by_pair[(recipe, pair)]["baseline"])
|
|
/ by_pair[(recipe, pair)]["baseline"] * 100.0)
|
|
for pair in range(1, 6)]
|
|
runner.require(f"cost-{recipe}-five-pairs",
|
|
len(values["baseline"]) == len(values["candidate"]) == 5,
|
|
f"median_baseline_s={old:.3f} median_candidate_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_landmark_reachability(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)
|
|
run_random_camera_sweep(runner, (CLANG,), 5,
|
|
((3, 0, 0), (2, 1, 1), (3, 2, 1)))
|
|
|
|
|
|
def run_gcc_supplement(runner: VerificationRunner) -> None:
|
|
"""Add GCC evidence to a stamped, already-passed Clang medium tier."""
|
|
run_owner_passages(runner, (GCC,))
|
|
run_landmark_reachability(runner, (GCC,))
|
|
style_override_matrix(runner, GCC)
|
|
run_transitions_and_invariants(runner, (GCC,))
|
|
|
|
|
|
def _tier_deadline(_signum: int, _frame: object) -> None:
|
|
raise VerificationFailure(
|
|
f"{ARGS.tier} tier exceeded its {ARGS.overall_timeout}s overall timeout")
|
|
|
|
|
|
def main() -> int:
|
|
runner = VerificationRunner(ARGS.tier)
|
|
started = time.monotonic()
|
|
if ARGS.overall_timeout <= 0:
|
|
raise VerificationFailure("--overall-timeout must be a positive number of seconds")
|
|
signal.signal(signal.SIGALRM, _tier_deadline)
|
|
signal.setitimer(signal.ITIMER_REAL, ARGS.overall_timeout)
|
|
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_landmark_reachability(runner, (CLANG,))
|
|
run_regression_controls(runner)
|
|
run_hash_pairs(runner, owners)
|
|
run_random_camera_sweep(runner, (CLANG,), 3, ((3, 0, 0),))
|
|
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_random_camera_sweep(runner, (GCC,), 5,
|
|
((3, 0, 0), (2, 1, 1), (3, 2, 1)))
|
|
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
|
|
finally:
|
|
signal.setitimer(signal.ITIMER_REAL, 0)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
raise SystemExit(main())
|