Files
aios/active-runtime/app/silent_release_execution.py
T

565 lines
18 KiB
Python

#!/usr/bin/env python3
"""Execution-readiness adapters and the fail-closed Shadow controller service."""
from __future__ import annotations
import argparse
import base64
import dataclasses
import hashlib
import json
import os
import subprocess
import threading
import time
from http import HTTPStatus
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import Any, Callable, Mapping, Protocol
from urllib.parse import parse_qs, urlparse
from cryptography.hazmat.primitives.asymmetric.ed25519 import (
Ed25519PrivateKey,
)
from silent_release_controller import _sanitize, utc_now
from silent_release_hardening import (
BuilderAttestation,
CapabilityAuthorizationError,
ReleaseRecoveryWorker,
SignedApprovalVerifier,
SignedReleasePlanApproval,
SilentReleaseActionService,
TrustedCandidateBundle,
_canonical_json,
_durable_json,
_safe_child,
)
class BuilderSigner(Protocol):
@property
def key_id(self) -> str:
...
def sign(self, payload: bytes) -> bytes:
...
class LocalTestBuilderSigner:
"""Ephemeral in-memory signer. It is forbidden for production execution."""
test_only = True
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
self._key_id = str(key_id)
self._private_key = private_key
@property
def key_id(self) -> str:
return self._key_id
@classmethod
def generate(
cls, key_id: str = "shadow-builder-test-key"
) -> "LocalTestBuilderSigner":
return cls(key_id, Ed25519PrivateKey.generate())
@property
def public_key(self):
return self._private_key.public_key()
def sign(self, payload: bytes) -> bytes:
return self._private_key.sign(payload)
class ExternalKmsBuilderSigner:
"""Signer facade whose private operation remains in KMS/HSM."""
def __init__(
self,
key_id: str,
credential_reference: str,
sign_callback: Callable[[str, bytes], bytes],
):
if not str(credential_reference).startswith(
("kms://", "hsm://", "secret-manager://")
):
raise ValueError("production builder requires a KMS/HSM reference")
self._key_id = str(key_id)
self.credential_reference = str(credential_reference)
self._sign_callback = sign_callback
@property
def key_id(self) -> str:
return self._key_id
def sign(self, payload: bytes) -> bytes:
return bytes(self._sign_callback(self.credential_reference, payload))
class SignedTrustedBuilderAdapter:
"""Signs evidence produced by a trusted collector, never caller evidence."""
def __init__(
self,
collector: Callable[[Mapping[str, Any]], TrustedCandidateBundle],
signer: BuilderSigner,
):
self.collector = collector
self.signer = signer
def build(self, intent: Mapping[str, Any]) -> TrustedCandidateBundle:
forbidden = {
"artifact_sha256",
"canary",
"checks",
"manifest_sha256",
"tests",
"tree_oid",
}
if forbidden.intersection(intent):
raise CapabilityAuthorizationError(
"trusted builder rejects caller-supplied evidence"
)
unsigned = self.collector(dict(intent))
if unsigned.attestation is not None:
raise CapabilityAuthorizationError(
"collector cannot self-attest its evidence"
)
candidate = unsigned.candidate
test_sha = hashlib.sha256(
_canonical_json(_sanitize(candidate.tests))
).hexdigest()
canary_sha = hashlib.sha256(
_canonical_json(_sanitize(candidate.canary))
).hexdigest()
attestation_id = "builder-attestation-" + hashlib.sha256(
(
candidate.candidate_id
+ "\0"
+ candidate.source_commit
+ "\0"
+ candidate.artifact_sha256
).encode("utf-8")
).hexdigest()[:24]
attestation = BuilderAttestation(
builder_attestation_id=attestation_id,
builder_key_id=self.signer.key_id,
source_commit=candidate.source_commit,
tree_oid=candidate.tree_oid,
artifact_sha256=candidate.artifact_sha256,
manifest_sha256=candidate.manifest_sha256,
package_closure_sha256=(
unsigned.release_plan.deployment.package_closure_sha256
),
test_evidence_sha256=test_sha,
canary_evidence_sha256=canary_sha,
issued_at=utc_now(),
signature="",
)
attestation = dataclasses.replace(
attestation,
signature=base64.b64encode(
self.signer.sign(attestation.canonical_bytes())
).decode("ascii"),
)
return dataclasses.replace(unsigned, attestation=attestation)
class ApprovalBackendAdapter(Protocol):
@property
def available(self) -> bool:
...
def verify(
self,
approval: SignedReleasePlanApproval,
*,
candidate,
release_plan,
policy_sha256: str,
) -> SignedReleasePlanApproval:
...
class LocalTestApprovalSigner:
"""Test-only approval signer used solely for Shadow acceptance."""
test_only = True
def __init__(self, key_id: str, private_key: Ed25519PrivateKey):
self.key_id = str(key_id)
self.private_key = private_key
@classmethod
def generate(
cls, key_id: str = "shadow-owner-test-key"
) -> "LocalTestApprovalSigner":
return cls(key_id, Ed25519PrivateKey.generate())
def sign(
self, approval: SignedReleasePlanApproval
) -> SignedReleasePlanApproval:
unsigned = dataclasses.replace(
approval, key_id=self.key_id, signature=""
)
return dataclasses.replace(
unsigned,
signature=base64.b64encode(
self.private_key.sign(unsigned.canonical_bytes())
).decode("ascii"),
)
class ProductionApprovalBackendAdapter:
"""Verification-only production adapter configured by a secret/KMS ref."""
def __init__(
self,
verifier: SignedApprovalVerifier,
credential_reference: str,
):
if not str(credential_reference).startswith(
("kms://", "hsm://", "secret-manager://")
):
raise ValueError(
"production approval backend requires a KMS/secret reference"
)
self.verifier = verifier
self.credential_reference = str(credential_reference)
@property
def available(self) -> bool:
return True
def verify(
self,
approval: SignedReleasePlanApproval,
*,
candidate,
release_plan,
policy_sha256: str,
) -> SignedReleasePlanApproval:
return self.verifier.verify_release_plan(
approval, candidate, release_plan, policy_sha256
)
class UnavailableProductionApprovalBackend:
credential_reference = None
@property
def available(self) -> bool:
return False
def verify(self, *args, **kwargs):
raise CapabilityAuthorizationError(
"production approval backend is not configured"
)
class LeaderLock:
def __init__(self, path: Path):
self.path = Path(path)
self.handle = None
def __enter__(self):
self.path.parent.mkdir(parents=True, exist_ok=True)
os.chmod(self.path.parent, 0o700)
self.handle = self.path.open("a+", encoding="utf-8")
os.chmod(self.path, 0o600)
try:
import fcntl
fcntl.flock(
self.handle.fileno(), fcntl.LOCK_EX | fcntl.LOCK_NB
)
except BlockingIOError as exc:
self.handle.close()
self.handle = None
raise RuntimeError("silent release leader is already active") from exc
return self
def __exit__(self, exc_type, exc, tb):
if self.handle is not None:
try:
import fcntl
fcntl.flock(self.handle.fileno(), fcntl.LOCK_UN)
finally:
self.handle.close()
self.handle = None
class PersistentSilentReleaseController:
"""Idempotent main-event controller with durable startup/recovery reports."""
def __init__(
self,
root: Path,
service: SilentReleaseActionService,
*,
main_probe: Callable[[], str],
recovery_worker: ReleaseRecoveryWorker | None = None,
):
self.root = Path(root)
self.service = service
self.main_probe = main_probe
self.recovery_worker = recovery_worker
self.leader_path = self.root / "controller.leader.lock"
self.status_path = self.root / "controller-status.json"
def startup_verify(self) -> dict[str, Any]:
checked = 0
failed = 0
for journal in sorted(self.service.sagas.root.glob("*.events.jsonl")):
candidate_id = journal.name[: -len(".events.jsonl")]
saga = self.service.sagas.load(candidate_id)
checked += 1
if not saga.journal_integrity:
failed += 1
status = {
"checked_sagas": checked,
"execution_enabled": self.service.execution_enabled,
"failed_closed": failed,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"status": "READY" if failed == 0 else "FAIL_CLOSED",
}
_durable_json(self.status_path, status)
return status
def run_once(self) -> dict[str, Any]:
with LeaderLock(self.leader_path):
startup = self.startup_verify()
if startup["status"] != "READY":
result = {
"execution_enabled": self.service.execution_enabled,
"intent": None,
"notification": None,
"recovery": None,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"startup": startup,
"status": "FAIL_CLOSED",
}
_durable_json(self.status_path, result)
return _sanitize(result)
source_commit = str(self.main_probe())
event_id = f"main-{source_commit}"
intent = self.service.create_release_intent(
{"event_id": event_id, "source_commit": source_commit}
)
notification = None
if intent.get("candidate_id"):
notification = self.service.ensure_owner_notification(
str(intent["candidate_id"])
)
recovery = (
self.recovery_worker.run_once()
if self.recovery_worker is not None
else self.service.get_recovery_status()
)
result = {
"execution_enabled": self.service.execution_enabled,
"intent": intent,
"notification": notification,
"recovery": recovery,
"shadow_mode": not self.service.execution_enabled,
"side_effects_executed": False,
"startup": startup,
}
_durable_json(self.status_path, result)
return _sanitize(result)
class ShadowActionHandler(BaseHTTPRequestHandler):
service: SilentReleaseActionService
controller: PersistentSilentReleaseController
def log_message(self, fmt, *args):
return
def _json(self, payload: Mapping[str, Any], status=HTTPStatus.OK):
body = json.dumps(_sanitize(dict(payload)), sort_keys=True).encode()
self.send_response(int(status))
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(body)))
self.end_headers()
self.wfile.write(body)
def _body(self) -> dict[str, Any]:
size = int(self.headers.get("Content-Length", "0"))
if size > 1024 * 1024:
raise ValueError("request body is too large")
return json.loads(self.rfile.read(size) or b"{}")
def do_GET(self):
parsed = urlparse(self.path)
query = parse_qs(parsed.query)
candidate_id = str((query.get("candidate_id") or [""])[0])
try:
if parsed.path == "/healthz":
return self._json(
{
"execution_enabled": False,
"shadow_mode": True,
"side_effects_executed": False,
"status": "ok",
}
)
routes = {
"/getReleaseCandidate": self.service.get_release_candidate,
"/getReleasePlan": self.service.get_release_plan,
"/getReleaseAcceptance": self.service.get_acceptance,
"/getReleaseSaga": self.service.get_release_saga,
"/getCapabilityStatus": self.service.get_capability_status,
}
if parsed.path in routes:
return self._json(routes[parsed.path](candidate_id))
if parsed.path == "/getRecoveryStatus":
return self._json(self.service.get_recovery_status())
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
except (ValueError, FileNotFoundError) as exc:
self._json(
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
)
def do_POST(self):
parsed = urlparse(self.path)
try:
body = self._body()
if parsed.path == "/createReleaseIntent":
return self._json(self.service.create_release_intent(body))
if parsed.path in {
"/submitSignedApproval",
"/submitOwnerApproval",
}:
return self._json(self.service.submit_owner_approval(body))
if parsed.path == "/startDeployment":
return self._json(
self.service.start_deployment(
str(body.get("candidate_id") or "")
)
)
self._json({"error": "not_found"}, HTTPStatus.NOT_FOUND)
except (ValueError, FileNotFoundError, CapabilityAuthorizationError) as exc:
self._json(
{"error": type(exc).__name__}, HTTPStatus.BAD_REQUEST
)
def git_main_probe(repository: Path) -> Callable[[], str]:
repository = Path(repository)
def probe() -> str:
completed = subprocess.run(
[
"git",
f"--git-dir={repository}",
"rev-parse",
"refs/heads/main",
],
check=True,
capture_output=True,
text=True,
timeout=15,
env={"PATH": os.environ.get("PATH", "")},
)
return completed.stdout.strip()
return probe
def serve_shadow(
*,
state_root: Path,
repository: Path,
host: str,
port: int,
poll_seconds: float,
) -> None:
service = SilentReleaseActionService.shadow(state_root)
controller = PersistentSilentReleaseController(
state_root,
service,
main_probe=git_main_probe(repository),
)
controller.run_once()
stop = threading.Event()
def controller_loop() -> None:
while not stop.wait(poll_seconds):
try:
controller.run_once()
except Exception as exc: # fail closed and keep the API available
_durable_json(
controller.status_path,
{
"error": type(exc).__name__,
"execution_enabled": False,
"shadow_mode": True,
"side_effects_executed": False,
"status": "FAIL_CLOSED",
},
)
handler = type(
"ConfiguredShadowActionHandler",
(ShadowActionHandler,),
{"service": service, "controller": controller},
)
server = ThreadingHTTPServer((host, port), handler)
api_thread = threading.Thread(
target=server.serve_forever,
name="silent-release-shadow-api",
daemon=False,
)
controller_thread = threading.Thread(
target=controller_loop,
name="silent-release-shadow-controller",
daemon=True,
)
api_thread.start()
controller_thread.start()
try:
while api_thread.is_alive():
api_thread.join(timeout=1)
finally:
stop.set()
server.shutdown()
server.server_close()
controller_thread.join(timeout=max(1.0, poll_seconds + 1.0))
def main() -> None:
parser = argparse.ArgumentParser()
parser.add_argument("--state-root", required=True, type=Path)
parser.add_argument("--repository", required=True, type=Path)
parser.add_argument("--host", default="127.0.0.1")
parser.add_argument("--port", default=18891, type=int)
parser.add_argument("--poll-seconds", default=30.0, type=float)
arguments = parser.parse_args()
if arguments.poll_seconds <= 0:
raise SystemExit("poll seconds must be positive")
if os.environ.get("AIOS_GITOPS_WRITES_ENABLED", "false").lower() != "false":
raise SystemExit("GitOps writes must remain disabled")
if (
os.environ.get(
"AIOS_SILENT_RELEASE_EXECUTION_ENABLED", "false"
).lower()
!= "false"
):
raise SystemExit("Silent Release execution must remain disabled")
serve_shadow(
state_root=arguments.state_root,
repository=arguments.repository,
host=arguments.host,
port=arguments.port,
poll_seconds=arguments.poll_seconds,
)
if __name__ == "__main__":
main()