Research-Stack/5-Applications/hutter_prize/scripts/verify_builder_determinism.py
Devin AI 0c9efac330 chore(consolidation): integrate E8Sidon stack (PRs #79 #80 #81 #89) into one PR
Squash the four overlapping feature branches into a single change set against
main, eliminating cross-PR merge conflicts and the duplicated CI-fix scripts.

What this brings in (merge order #79 -> #80 -> #81 -> #89):
- #79 refactor(infra): shared utilities (4-Infrastructure/lib/*: q16, hashing,
  jsonl, fraction_utils) + the scripts/math-first/* validators that the
  math-check CI requires.
- #80 feat(lean): Semantics.E8Sidon (1025 lines) -- Eisenstein coefficient
  identity E4^2 = E8 and the Sidon framework. E4_sq_eq_E8_coeff is fully proved
  (all Fourier-coefficient extraction machine-checked); the single residual gap
  is pinned to E4_sq_eq_E8_qExpansion (Mathlib lacks the valence formula /
  dim M8 = 1). 4 sorries + 1 axiom (e8_additive_completeness), all TODO(lean-port).
- #81 refactor(lean): Float-free FixedPoint core (integer-only sqrt/log2/expNeg).
  E8Sidon.lean kept at #80's final 1025-line version (the #81 intermediate
  438-line copy was overridden by merge order).
- #89 feat(lean): Semantics.RRC.PolyFactorIdentity -- short-sleeve polynomial
  detection at the zerocopy limb boundary; now imports Semantics.E8Sidon for
  sigma3/sigma7/convolutionLHS (single source of truth) instead of inlining them.

Conflict resolution:
- flake.nix -> canonical rs-surface removal (Garnix shutdown).
- scripts/math-first/* -> byte-identical across branches, clean.
- .cursorrules / AGENTS.md -> unified; baselines + sorry inventory refreshed.

Verification:
- lake build (default aggregator): 3573 jobs, 0 errors.
- lake build Semantics.RRC.PolyFactorIdentity (E8Sidon + FixedPoint + PolyFactor):
  3655 jobs, 0 errors. Witnesses verified (sigma7 4 = 16513, convolutionLHS 6 = 2350).
- Python tests: 68/68 pass.

Note: the "Workers Builds: researchstack" check is a preexisting external
Cloudflare build unrelated to this change (no branch touches 4-Infrastructure/cloudflare/).

Build: 3573 jobs (default), 3655 jobs (narrow), 0 errors
Co-Authored-By: Allaun Silverfox <bigdataiscoming+9i37y6j2@protonmail.com>
2026-06-16 02:01:31 +00:00

118 lines
3.4 KiB
Python

#!/usr/bin/env python3
"""Verify that public-facing builders produce byte-stable output across reruns."""
from __future__ import annotations
import argparse
import json
import subprocess
import sys
import tempfile
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parents[3] / "4-Infrastructure"))
from lib.hashing import sha256_file
def file_map(root: Path) -> dict[str, str]:
files: dict[str, str] = {}
for path in sorted(p for p in root.rglob("*") if p.is_file()):
files[str(path.relative_to(root))] = sha256_file(path)
return files
def run_builder(command: list[str], out_dir: Path) -> dict[str, str]:
cmd = command + ["--out-dir", str(out_dir)]
subprocess.run(
cmd,
check=True,
text=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
return file_map(out_dir)
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument(
"--builder",
choices=("review-packet", "public-artifact"),
required=True,
help="Which builder to verify.",
)
parser.add_argument(
"--root",
default=".",
help="Repo root for the review-packet builder. Defaults to the current directory.",
)
parser.add_argument(
"--input",
help="Input artifact for the public-artifact builder.",
)
parser.add_argument(
"--label",
help="Optional label passed through to the builder.",
)
parser.add_argument(
"--include",
action="append",
default=[],
help="Extra file to include for the review-packet builder.",
)
parser.add_argument(
"--mode",
choices=("auto", "text", "json"),
default="auto",
help="Mode passed through to the public-artifact builder.",
)
return parser.parse_args()
def main() -> int:
args = parse_args()
scripts_dir = Path(__file__).resolve().parent
if args.builder == "review-packet":
command = [
sys.executable,
str(scripts_dir / "build_review_packet.py"),
"--root",
str(Path(args.root).resolve()),
]
if args.label:
command.extend(["--label", args.label])
for extra in args.include:
command.extend(["--include", extra])
else:
if not args.input:
print("--input is required for the public-artifact builder.", file=sys.stderr)
return 2
command = [
sys.executable,
str(scripts_dir / "prepare_public_artifact.py"),
"--input",
str(Path(args.input).resolve()),
"--mode",
args.mode,
]
if args.label:
command.extend(["--label", args.label])
with tempfile.TemporaryDirectory(prefix="hutter_verify_a_") as first_tmp:
with tempfile.TemporaryDirectory(prefix="hutter_verify_b_") as second_tmp:
first = run_builder(command, Path(first_tmp))
second = run_builder(command, Path(second_tmp))
report = {
"schema": "hutter_builder_determinism_report_v1",
"builder": args.builder,
"stable": first == second,
"first": first,
"second": second,
}
print(json.dumps(report, indent=2))
return 0 if report["stable"] else 1
if __name__ == "__main__":
raise SystemExit(main())