better-claude-config/scripts/sign_checksums.py

#!/usr/bin/env python3
"""
Generate a SHA256SUMS file for release artifacts and sign it with Ed25519.

BCC ships PyInstaller binaries that are not code-signed (no budget for a
macOS Developer ID / Windows Authenticode certificate). This script provides
the free half of supply-chain integrity: a checksum manifest, detached-signed
so downloaders can verify the file they got is the file we published.

This does NOT remove Gatekeeper/SmartScreen warnings and does NOT prove the
binary is safe to run -- only that it matches what the release signing key
attested to.

Usage:
    # Hash every file in a directory into a SHA256SUMS-format manifest.
    python scripts/sign_checksums.py generate <dir> --out SHA256SUMS

    # Sign a manifest, producing a detached signature.
    # Private key comes from $RELEASE_SIGNING_KEY (base64 raw Ed25519 seed)
    # unless --key-b64 is given explicitly (mostly for tests).
    python scripts/sign_checksums.py sign --sums SHA256SUMS --out SHA256SUMS.sig

    # Verify a manifest against a detached signature and a public key.
    python scripts/sign_checksums.py verify --sums SHA256SUMS --sig SHA256SUMS.sig \
        --pubkey-b64 <base64 raw Ed25519 public key>

The private key is generated and rotated via the Catalog Console (#62) --
this script never generates or stores a key itself.
"""

from __future__ import annotations

import argparse
import base64
import hashlib
import os
import sys
from pathlib import Path

# Domain separation prefix: ties every signature to "a BCC release checksum
# manifest" so a signature can never be replayed against an unrelated
# message signed by the same key.
DOMAIN_PREFIX = b"bcc-release-v1|"

# Public half of the RELEASE signing key(s) -- a SEPARATE keypair from
# bcc_core.CATALOG_PUBKEYS (issue #68 finding 5). The catalog key is the
# offline, Console-only root of trust for what BCC executes; this key is
# CI-resident and signs ONLY the release SHA256SUMS manifest, never the
# catalog. Keeping them apart means a CI/repo-secret compromise burns the
# release key -- annoying, but it never lets an attacker sign a catalog a
# user's binary would trust. A LIST (not a single key), mirroring
# CATALOG_PUBKEYS, so the release key can be rotated without invalidating
# the signature on every past release: verification accepts a match against
# ANY key here.
#
# Empty until the maintainer generates the release keypair (separately from
# the catalog keypair) and pastes the public half in:
#     python catalog_console.py keygen --release
# This is intentionally NOT pre-populated with a placeholder that looks
# like a real key -- release.yml's signing-smoke-test fails closed (loudly)
# on an empty list rather than silently verifying against nothing.
RELEASE_PUBKEYS: list[bytes] = []

CHUNK_SIZE = 1024 * 1024


def sha256_file(path: Path) -> str:
    """Return the lowercase hex SHA-256 digest of a file's contents."""
    digest = hashlib.sha256()
    with open(path, "rb") as fh:
        while chunk := fh.read(CHUNK_SIZE):
            digest.update(chunk)
    return digest.hexdigest()


def build_checksums_text(files: dict[str, str]) -> str:
    """Build a sha256sum(1)-compatible manifest body.

    `files` maps filename -> hex digest. Entries are sorted by filename for
    a deterministic, diffable output. Format matches `sha256sum` exactly:
    "<hash>  <filename>\n" (two spaces, no path components).
    """
    lines = [f"{digest}  {name}" for name, digest in sorted(files.items())]
    body = "\n".join(lines)
    return body + "\n" if body else ""


def generate_checksums(directory: Path, *, exclude: set[str] | None = None) -> str:
    """Hash every regular file directly inside `directory` (non-recursive)
    and return the SHA256SUMS text. Filenames are recorded without any
    directory prefix so the manifest can be verified from inside the
    directory it describes.
    """
    exclude = exclude or set()
    files: dict[str, str] = {}
    for entry in sorted(directory.iterdir()):
        if not entry.is_file():
            continue
        if entry.name in exclude:
            continue
        files[entry.name] = sha256_file(entry)
    return build_checksums_text(files)


def _signing_message(sums_text: str) -> bytes:
    """The exact bytes that get signed: the domain prefix followed by the
    raw bytes of the SHA256SUMS file content."""
    return DOMAIN_PREFIX + sums_text.encode("utf-8")


def sign_checksums(seed_b64: str, sums_text: str) -> bytes:
    """Sign `sums_text` with the Ed25519 private key encoded (base64, raw
    32-byte seed) in `seed_b64`. Returns the raw 64-byte signature."""
    # Imported lazily so `generate` mode (used on every CI run) never
    # requires the `cryptography` package to be installed.
    from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey

    seed = base64.b64decode(seed_b64)
    if len(seed) != 32:
        raise ValueError(f"expected a 32-byte raw Ed25519 seed, got {len(seed)} bytes")
    private_key = Ed25519PrivateKey.from_private_bytes(seed)
    return private_key.sign(_signing_message(sums_text))


def verify_checksums(pubkey_b64: str, sums_text: str, signature: bytes) -> bool:
    """Verify `signature` over `sums_text` against the base64-encoded raw
    32-byte Ed25519 public key. Returns True/False; never raises for a bad
    signature (only for malformed inputs)."""
    from cryptography.exceptions import InvalidSignature
    from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PublicKey

    pubkey_bytes = base64.b64decode(pubkey_b64)
    if len(pubkey_bytes) != 32:
        raise ValueError(
            f"expected a 32-byte raw Ed25519 public key, got {len(pubkey_bytes)} bytes"
        )
    public_key = Ed25519PublicKey.from_public_bytes(pubkey_bytes)
    try:
        public_key.verify(signature, _signing_message(sums_text))
        return True
    except InvalidSignature:
        return False


def public_key_b64_from_seed(seed_b64: str) -> str:
    """Derive the base64 raw public key from a base64 raw seed. Handy for
    local key-pair sanity checks; not used by the release workflow."""
    from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
    from cryptography.hazmat.primitives.serialization import Encoding, PublicFormat

    seed = base64.b64decode(seed_b64)
    private_key = Ed25519PrivateKey.from_private_bytes(seed)
    raw = private_key.public_key().public_bytes(Encoding.Raw, PublicFormat.Raw)
    return base64.b64encode(raw).decode("ascii")


def verify_checksums_against_any(pubkeys: list[bytes], sums_text: str, signature: bytes) -> bool:
    """Verify `signature` against ANY key in `pubkeys` (each a raw 32-byte
    Ed25519 public key). Mirrors bcc_core.verify_catalog_signature's
    rotation-friendly "any currently-trusted key" semantics, applied to
    RELEASE_PUBKEYS instead of the catalog's key list. Returns False (never
    raises) for an empty `pubkeys` list -- fails closed rather than
    vacuously verifying against nothing."""
    return any(
        verify_checksums(base64.b64encode(pk).decode("ascii"), sums_text, signature)
        for pk in pubkeys
    )


# --------------------------------------------------------------------------- #
# CLI
# --------------------------------------------------------------------------- #
def _cmd_generate(args: argparse.Namespace) -> int:
    directory = Path(args.directory)
    exclude = {"SHA256SUMS", "SHA256SUMS.sig"}
    text = generate_checksums(directory, exclude=exclude)
    out_path = Path(args.out)
    out_path.write_text(text, encoding="utf-8")
    print(f"Wrote {out_path} ({len(text.splitlines())} entries)")
    return 0


def _cmd_sign(args: argparse.Namespace) -> int:
    seed_b64 = args.key_b64 or os.environ.get(args.key_env, "")
    if not seed_b64:
        print(
            f"error: no signing key provided (checked --key-b64 and ${args.key_env})",
            file=sys.stderr,
        )
        return 1
    sums_text = Path(args.sums).read_text(encoding="utf-8")
    signature = sign_checksums(seed_b64, sums_text)
    Path(args.out).write_bytes(signature)
    print(f"Wrote {args.out} ({len(signature)} bytes)")
    return 0


def _cmd_verify(args: argparse.Namespace) -> int:
    pubkey_b64 = args.pubkey_b64 or os.environ.get(args.pubkey_env, "")
    if not pubkey_b64:
        print(
            f"error: no public key provided (checked --pubkey-b64 and ${args.pubkey_env})",
            file=sys.stderr,
        )
        return 1
    sums_text = Path(args.sums).read_text(encoding="utf-8")
    signature = Path(args.sig).read_bytes()
    ok = verify_checksums(pubkey_b64, sums_text, signature)
    if ok:
        print("OK: signature is valid")
        return 0
    print("FAILED: signature is invalid", file=sys.stderr)
    return 1


def build_parser() -> argparse.ArgumentParser:
    parser = argparse.ArgumentParser(
        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
    )
    sub = parser.add_subparsers(dest="mode", required=True)

    p_gen = sub.add_parser(
        "generate", help="hash every file in a directory into a SHA256SUMS manifest"
    )
    p_gen.add_argument("directory", help="directory whose files should be hashed (non-recursive)")
    p_gen.add_argument("--out", required=True, help="path to write the SHA256SUMS manifest to")
    p_gen.set_defaults(func=_cmd_generate)

    p_sign = sub.add_parser("sign", help="detached-sign a SHA256SUMS manifest with Ed25519")
    p_sign.add_argument("--sums", required=True, help="path to the SHA256SUMS manifest to sign")
    p_sign.add_argument("--out", required=True, help="path to write the detached signature to")
    p_sign.add_argument(
        "--key-b64", default=None, help="base64 raw Ed25519 seed (overrides --key-env)"
    )
    p_sign.add_argument(
        "--key-env",
        default="RELEASE_SIGNING_KEY",
        help="environment variable holding the base64 seed (default: RELEASE_SIGNING_KEY)",
    )
    p_sign.set_defaults(func=_cmd_sign)

    p_verify = sub.add_parser(
        "verify", help="verify a SHA256SUMS manifest against a detached signature"
    )
    p_verify.add_argument("--sums", required=True, help="path to the SHA256SUMS manifest")
    p_verify.add_argument("--sig", required=True, help="path to the detached signature")
    p_verify.add_argument(
        "--pubkey-b64", default=None, help="base64 raw Ed25519 public key (overrides --pubkey-env)"
    )
    p_verify.add_argument(
        "--pubkey-env",
        default="RELEASE_SIGNING_PUBKEY",
        help="environment variable holding the base64 public key (default: RELEASE_SIGNING_PUBKEY)",
    )
    p_verify.set_defaults(func=_cmd_verify)

    return parser


def main(argv: list[str] | None = None) -> int:
    parser = build_parser()
    args = parser.parse_args(argv)
    return args.func(args)


if __name__ == "__main__":
    raise SystemExit(main())