Files
stack/packages/mosaic/framework/tools/lease-broker/promote-complete.py
T

362 lines
12 KiB
Python

#!/usr/bin/env python3
"""Claude Stop hook that completes a pending operator-triggered promotion."""
from __future__ import annotations
import fcntl
import json
import os
import secrets
import stat
import subprocess
import sys
import time
from collections.abc import Callable, Mapping
from pathlib import Path
from typing import Final, NamedTuple, TextIO
MAX_FRAME: Final = 64 * 1024
PROMOTER_TIMEOUT_SECONDS: Final = 10.0
LEASE_TTL_SECONDS: Final = 60 * 60
PROMOTER: Final = Path(__file__).resolve().with_name("lease_promote.py")
PENDING_DIRECTORY: Final = "mosaic-lease"
LOCK_FILE: Final = "promotion.lock"
RESULT_FILE: Final = "last-result.json"
TERMINAL_FAILURE_CODES: Final = frozenset(
{
"RECEIPT_REPLAY",
"RECEIPT_MISMATCH",
"INVALID_LEASE_TRANSITION",
"PROMOTION_TOKEN_INVALID",
}
)
class PendingChallenge(NamedTuple):
value: str
device: int
inode: int
def reject_duplicate_json_keys(pairs: list[tuple[str, object]]) -> dict[str, object]:
value: dict[str, object] = {}
for key, item in pairs:
if key in value:
raise ValueError("duplicate promoter JSON key")
value[key] = item
return value
def session_pending_name(environ: Mapping[str, str]) -> tuple[Path, str]:
runtime_dir = Path(environ["XDG_RUNTIME_DIR"])
session_id = environ["MOSAIC_LEASE_SESSION_ID"]
if not runtime_dir.is_absolute():
raise ValueError("XDG_RUNTIME_DIR must be absolute")
if len(session_id) != 64 or any(character not in "0123456789abcdef" for character in session_id):
raise ValueError("invalid lease session id")
return runtime_dir, f"pending-{session_id}"
def open_pending_directory(runtime_dir: Path) -> int | None:
directory_flags = (
os.O_RDONLY
| getattr(os, "O_CLOEXEC", 0)
| getattr(os, "O_DIRECTORY", 0)
| getattr(os, "O_NOFOLLOW", 0)
)
try:
runtime_descriptor = os.open(runtime_dir, directory_flags)
except FileNotFoundError:
return None
try:
runtime_metadata = os.fstat(runtime_descriptor)
if (
not stat.S_ISDIR(runtime_metadata.st_mode)
or runtime_metadata.st_uid != os.getuid()
or stat.S_IMODE(runtime_metadata.st_mode) != 0o700
):
raise ValueError("unsafe XDG runtime directory")
try:
descriptor = os.open(PENDING_DIRECTORY, directory_flags, dir_fd=runtime_descriptor)
except FileNotFoundError:
return None
finally:
os.close(runtime_descriptor)
metadata = os.fstat(descriptor)
if (
not stat.S_ISDIR(metadata.st_mode)
or metadata.st_uid != os.getuid()
or stat.S_IMODE(metadata.st_mode) != 0o700
):
os.close(descriptor)
raise ValueError("unsafe promotion pending directory")
return descriptor
def acquire_lock(directory_descriptor: int) -> int:
flags = (
os.O_RDWR
| os.O_CREAT
| getattr(os, "O_CLOEXEC", 0)
| getattr(os, "O_NOFOLLOW", 0)
)
descriptor = os.open(LOCK_FILE, flags, 0o600, dir_fd=directory_descriptor)
metadata = os.fstat(descriptor)
if (
not stat.S_ISREG(metadata.st_mode)
or metadata.st_uid != os.getuid()
or stat.S_IMODE(metadata.st_mode) != 0o600
):
os.close(descriptor)
raise ValueError("unsafe promotion lock file")
try:
fcntl.flock(descriptor, fcntl.LOCK_EX | fcntl.LOCK_NB)
except BlockingIOError:
os.close(descriptor)
raise
return descriptor
def read_pending(directory_descriptor: int, name: str) -> PendingChallenge | None:
flags = os.O_RDONLY | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_NOFOLLOW", 0)
try:
descriptor = os.open(name, flags, dir_fd=directory_descriptor)
except FileNotFoundError:
return None
try:
metadata = os.fstat(descriptor)
if (
not stat.S_ISREG(metadata.st_mode)
or metadata.st_uid != os.getuid()
or stat.S_IMODE(metadata.st_mode) != 0o600
or metadata.st_size <= 0
or metadata.st_size > MAX_FRAME
):
raise ValueError("unsafe promotion pending file")
raw = os.read(descriptor, MAX_FRAME + 1)
finally:
os.close(descriptor)
if len(raw) > MAX_FRAME:
raise ValueError("oversized promotion challenge")
challenge = raw.decode("utf-8")
if (
len(challenge) != 64
or any(character not in "0123456789abcdef" for character in challenge)
):
raise ValueError("invalid promotion challenge")
return PendingChallenge(challenge, metadata.st_dev, metadata.st_ino)
def write_result(
directory_descriptor: int,
attempt_id: str,
verified: bool,
reason: str | None,
session_id: str,
wall_clock: float,
) -> None:
result = {
"attempt_id": attempt_id,
"expires_at_wallclock": wall_clock + LEASE_TTL_SECONDS if verified else None,
"reason": reason,
"session_id": session_id,
"ts": wall_clock,
"verified": verified,
}
temporary = f".{RESULT_FILE}.tmp-{secrets.token_hex(8)}"
flags = (
os.O_WRONLY
| os.O_CREAT
| os.O_EXCL
| getattr(os, "O_CLOEXEC", 0)
| getattr(os, "O_NOFOLLOW", 0)
)
descriptor = os.open(temporary, flags, 0o600, dir_fd=directory_descriptor)
try:
os.fchmod(descriptor, 0o600)
with os.fdopen(descriptor, "w", encoding="utf-8", closefd=False) as stream:
json.dump(result, stream, separators=(",", ":"), sort_keys=True)
stream.flush()
os.fsync(stream.fileno())
os.replace(
temporary,
RESULT_FILE,
src_dir_fd=directory_descriptor,
dst_dir_fd=directory_descriptor,
)
os.fsync(directory_descriptor)
except Exception:
try:
os.unlink(temporary, dir_fd=directory_descriptor)
except FileNotFoundError:
pass
raise
finally:
os.close(descriptor)
def delete_pending_if_unchanged(
directory_descriptor: int,
name: str,
pending: PendingChallenge,
error_stream: TextIO,
) -> None:
quarantine = f".{name}.delete-{secrets.token_hex(8)}"
try:
os.rename(
name,
quarantine,
src_dir_fd=directory_descriptor,
dst_dir_fd=directory_descriptor,
)
except FileNotFoundError:
return
except OSError as error:
print(f"Mosaic promotion could not quarantine pending file: {error}", file=error_stream)
return
try:
moved = os.stat(
quarantine,
dir_fd=directory_descriptor,
follow_symlinks=False,
)
if (moved.st_dev, moved.st_ino) == (pending.device, pending.inode):
os.unlink(quarantine, dir_fd=directory_descriptor)
os.fsync(directory_descriptor)
return
print("Mosaic promotion pending file changed; preserving replacement.", file=error_stream)
try:
os.link(
quarantine,
name,
src_dir_fd=directory_descriptor,
dst_dir_fd=directory_descriptor,
follow_symlinks=False,
)
except FileExistsError:
print(
f"Mosaic promotion preserved replacement as {quarantine}.",
file=error_stream,
)
else:
os.unlink(quarantine, dir_fd=directory_descriptor)
os.fsync(directory_descriptor)
except OSError as error:
print(f"Mosaic promotion could not resolve pending file: {error}", file=error_stream)
def parse_reply(completed: subprocess.CompletedProcess[str]) -> dict[str, object] | None:
if completed.returncode != 0:
return None
try:
value = json.loads(
completed.stdout,
object_pairs_hook=reject_duplicate_json_keys,
)
except (json.JSONDecodeError, RecursionError, TypeError, ValueError):
return None
if not isinstance(value, dict):
return None
if set(value) == {"stage", "ok", "state"}:
if (
value.get("stage") == "promote_lease"
and value.get("ok") is True
and value.get("state") == "VERIFIED"
):
return value
return None
if set(value) == {"stage", "ok", "code"}:
if (
value.get("stage") in {"observe_receipt", "promote_lease"}
and value.get("ok") is False
and isinstance(value.get("code"), str)
and value.get("code")
):
return value
return None
def main(
*,
environ: Mapping[str, str] | None = None,
stderr: TextIO | None = None,
run: Callable[..., subprocess.CompletedProcess[str]] = subprocess.run,
now: Callable[[], float] = time.time,
) -> int:
source_environment = os.environ if environ is None else environ
error_stream = sys.stderr if stderr is None else stderr
directory_descriptor: int | None = None
lock_descriptor: int | None = None
try:
runtime_dir, pending_name = session_pending_name(source_environment)
session_id = source_environment["MOSAIC_LEASE_SESSION_ID"]
directory_descriptor = open_pending_directory(runtime_dir)
if directory_descriptor is None:
return 0
try:
lock_descriptor = acquire_lock(directory_descriptor)
except (BlockingIOError, FileNotFoundError):
print("Mosaic promotion completion deferred: promotion is in progress.", file=error_stream)
return 0
pending = read_pending(directory_descriptor, pending_name)
if pending is None:
return 0
completed = run(
[
sys.executable,
"-I",
"-S",
"-B",
str(PROMOTER),
"--complete",
pending.value,
],
check=False,
capture_output=True,
text=True,
env=dict(source_environment),
timeout=PROMOTER_TIMEOUT_SECONDS,
)
reply = parse_reply(completed)
if reply is not None and reply.get("ok") is True:
write_result(directory_descriptor, pending.value, True, None, session_id, now())
delete_pending_if_unchanged(
directory_descriptor,
pending_name,
pending,
error_stream,
)
print("Mosaic lease promotion completed.", file=error_stream)
return 0
if reply is not None:
code = str(reply["code"])
print(f"Mosaic promotion incomplete: {code}.", file=error_stream)
if code in TERMINAL_FAILURE_CODES:
write_result(directory_descriptor, pending.value, False, code, session_id, now())
delete_pending_if_unchanged(
directory_descriptor,
pending_name,
pending,
error_stream,
)
else:
diagnostic = completed.stderr.strip() or f"promoter exit {completed.returncode}"
print(f"Mosaic promotion retryable failure: {diagnostic}.", file=error_stream)
except (KeyError, OSError, RecursionError, UnicodeError, ValueError, subprocess.SubprocessError) as error:
print(f"Mosaic promotion completion deferred: {type(error).__name__}: {error}", file=error_stream)
finally:
if lock_descriptor is not None:
os.close(lock_descriptor)
if directory_descriptor is not None:
os.close(directory_descriptor)
return 0
if __name__ == "__main__":
raise SystemExit(main())