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

428 lines
18 KiB
Python

"""Owner-controlled, CAS-bound retry extension for exhausted Online Agent Tasks."""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timezone
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import os
from pathlib import Path
import re
import sqlite3
from typing import Any, Mapping
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
MAX_BODY = 64 * 1024
AUTHORIZE_EXTENSION_ID_ENV = "AIOS_AGENT_TASK_AUTHORIZATION_ID"
class RetryExtensionError(RuntimeError):
def __init__(self, code: str, status: int = 409) -> None:
super().__init__(code)
self.code = code
self.status = status
def _canonical(value: object) -> bytes:
return json.dumps(value, sort_keys=True, separators=(",", ":"), ensure_ascii=False).encode("utf-8")
def _sha(value: object) -> str:
return hashlib.sha256(_canonical(value)).hexdigest()
def _required_authorization_id() -> str:
value = os.environ.get(AUTHORIZE_EXTENSION_ID_ENV, "").strip()
if not value:
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_MISSING")
if KEY_RE.fullmatch(value) is None:
raise RuntimeError("TASK_RETRY_AUTHORIZATION_ID_INVALID")
return value
def _now() -> str:
return datetime.now(timezone.utc).isoformat()
def _require_string(value: object, code: str, pattern: re.Pattern[str] | None = None) -> str:
if not isinstance(value, str) or not value.strip():
raise RetryExtensionError(code, 400)
value = value.strip()
if pattern is not None and pattern.fullmatch(value) is None:
raise RetryExtensionError(code, 400)
return value
@dataclass(frozen=True)
class RetryExtensionRequest:
expected_status: str
expected_revision: int
expected_attempt: int
expected_max_attempts: int
next_max_attempts: int
previous_verification_sha256: str
authorization_id: str
idempotency_key: str
@classmethod
def from_mapping(cls, value: Mapping[str, Any]) -> "RetryExtensionRequest":
allowed = {
"expected_status", "expected_revision", "expected_attempt", "expected_max_attempts",
"next_max_attempts", "previous_verification_sha256", "authorization_id", "idempotency_key",
}
if set(value) != allowed:
raise RetryExtensionError("RETRY_EXTENSION_FIELDS_INVALID", 400)
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
if status != "FAILED":
raise RetryExtensionError("EXPECTED_STATUS_INVALID", 400)
ints: dict[str, int] = {}
for field in ("expected_revision", "expected_attempt", "expected_max_attempts", "next_max_attempts"):
item = value[field]
if not isinstance(item, int) or isinstance(item, bool) or item < 0:
raise RetryExtensionError("RETRY_EXTENSION_INTEGER_INVALID", 400)
ints[field] = item
if ints["expected_attempt"] != ints["expected_max_attempts"]:
raise RetryExtensionError("RETRY_EXTENSION_NOT_EXHAUSTED", 409)
if ints["next_max_attempts"] != ints["expected_max_attempts"] + 1:
raise RetryExtensionError("RETRY_EXTENSION_MUST_BE_BOUNDED_ONE_STEP", 400)
if ints["next_max_attempts"] > 50:
raise RetryExtensionError("RETRY_EXTENSION_LIMIT_EXCEEDED", 400)
verification = _require_string(value["previous_verification_sha256"], "VERIFICATION_SHA256_INVALID")
if re.fullmatch(r"[0-9a-f]{64}", verification) is None:
raise RetryExtensionError("VERIFICATION_SHA256_INVALID", 400)
authorization = _require_string(value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE)
key = _require_string(value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE)
return cls(
status,
ints["expected_revision"],
ints["expected_attempt"],
ints["expected_max_attempts"],
ints["next_max_attempts"],
verification,
authorization,
key,
)
def public(self) -> dict[str, Any]:
return {
"expected_status": self.expected_status,
"expected_revision": self.expected_revision,
"expected_attempt": self.expected_attempt,
"expected_max_attempts": self.expected_max_attempts,
"next_max_attempts": self.next_max_attempts,
"previous_verification_sha256": self.previous_verification_sha256,
"authorization_id": self.authorization_id,
"idempotency_key": self.idempotency_key,
}
class RetryExtensionStore:
"""Owns the official mutation. Direct/manual DB edits remain forbidden."""
def __init__(self, db_path: Path) -> None:
self.db_path = Path(db_path)
def _connect(self) -> sqlite3.Connection:
connection = sqlite3.connect(self.db_path, timeout=30.0)
connection.row_factory = sqlite3.Row
connection.execute("PRAGMA foreign_keys=ON")
connection.execute("PRAGMA busy_timeout=30000")
return connection
@staticmethod
def _columns(connection: sqlite3.Connection, table: str) -> dict[str, sqlite3.Row]:
return {str(row["name"]): row for row in connection.execute(f'PRAGMA table_info("{table}")')}
@staticmethod
def _event_table(connection: sqlite3.Connection) -> tuple[str, dict[str, sqlite3.Row]]:
tables = {
row["name"]
for row in connection.execute("SELECT name FROM sqlite_master WHERE type='table'")
}
for name in ("task_events", "events"):
if name not in tables:
continue
columns = RetryExtensionStore._columns(connection, name)
if "task_id" in columns and ("event_type" in columns or "type" in columns):
return name, columns
raise RetryExtensionError("TASK_EVENT_TABLE_UNSUPPORTED", 503)
@staticmethod
def _verification_hash(raw: object) -> str:
if raw in (None, ""):
value: object = {}
elif isinstance(raw, str):
try:
value = json.loads(raw)
except json.JSONDecodeError as exc:
raise RetryExtensionError("TASK_VERIFICATION_INVALID", 409) from exc
else:
value = raw
return _sha(value)
@staticmethod
def _ensure_extension_table(connection: sqlite3.Connection) -> None:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS task_retry_extensions (
task_id TEXT NOT NULL,
idempotency_key TEXT NOT NULL,
request_sha256 TEXT NOT NULL,
authorization_id TEXT NOT NULL,
previous_verification_sha256 TEXT NOT NULL,
previous_max_attempts INTEGER NOT NULL,
next_max_attempts INTEGER NOT NULL,
expected_revision INTEGER NOT NULL,
applied_revision INTEGER NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(task_id, idempotency_key)
)
"""
)
@staticmethod
def _insert_event(
connection: sqlite3.Connection,
task_id: str,
payload: Mapping[str, Any],
) -> None:
table, columns = RetryExtensionStore._event_table(connection)
values: dict[str, Any] = {"task_id": task_id}
if "event_type" in columns:
values["event_type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
else:
values["type"] = "TASK_RETRY_EXTENSION_AUTHORIZED"
payload_text = json.dumps(payload, sort_keys=True, separators=(",", ":"))
if "payload_json" in columns:
values["payload_json"] = payload_text
elif "payload" in columns:
values["payload"] = payload_text
else:
raise RetryExtensionError("TASK_EVENT_PAYLOAD_UNSUPPORTED", 503)
if "created_at" in columns:
values["created_at"] = _now()
if "agent_id" in columns:
values["agent_id"] = "owner-control"
if "actor_id" in columns:
values["actor_id"] = "owner-control"
names = list(values)
sql = f'INSERT INTO "{table}" ({",".join(f"""\"{name}\"""" for name in names)}) VALUES ({",".join("?" for _ in names)})'
connection.execute(sql, tuple(values[name] for name in names))
def extend(self, task_id: str, request: RetryExtensionRequest) -> dict[str, Any]:
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
required_authorization_id = _required_authorization_id()
if request.authorization_id != required_authorization_id:
raise RetryExtensionError("RETRY_EXTENSION_AUTHORIZATION_ID_MISMATCH", 403)
request_payload = request.public()
request_sha = _sha(request_payload)
with self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
self._ensure_extension_table(connection)
replay = connection.execute(
"SELECT * FROM task_retry_extensions WHERE task_id=? AND idempotency_key=?",
(task_id, request.idempotency_key),
).fetchone()
if replay is not None:
if replay["request_sha256"] != request_sha:
raise RetryExtensionError("RETRY_EXTENSION_IDEMPOTENCY_CONFLICT", 409)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": request.expected_attempt,
"max_attempts": int(replay["next_max_attempts"]),
"revision": int(replay["applied_revision"]),
"idempotent": True,
"authorization_id": replay["authorization_id"],
"previous_verification_sha256": replay["previous_verification_sha256"],
}
columns = self._columns(connection, "tasks")
required = {
"task_id", "status", "attempt", "max_attempts", "revision", "claimed_by",
"lease_token_hash", "lease_expires_at", "verification_json",
}
if not required.issubset(columns):
raise RetryExtensionError("TASK_SCHEMA_RETRY_EXTENSION_UNSUPPORTED", 503)
task = connection.execute("SELECT * FROM tasks WHERE task_id=?", (task_id,)).fetchone()
if task is None:
raise RetryExtensionError("TASK_NOT_FOUND", 404)
actual_verification_sha = self._verification_hash(task["verification_json"])
if actual_verification_sha != request.previous_verification_sha256:
raise RetryExtensionError("RETRY_EXTENSION_VERIFICATION_DRIFT", 409)
if (
task["status"] != request.expected_status
or int(task["revision"]) != request.expected_revision
or int(task["attempt"]) != request.expected_attempt
or int(task["max_attempts"]) != request.expected_max_attempts
):
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
for lease_field in ("lease_token_hash", "lease_expires_at"):
if lease_field in columns and task[lease_field] not in (None, ""):
raise RetryExtensionError("RETRY_EXTENSION_ACTIVE_LEASE_DENY", 409)
previous_claimed_by = task["claimed_by"]
applied_revision = request.expected_revision + 1
cursor = connection.execute(
"""
UPDATE tasks
SET status='QUEUED', max_attempts=?, revision=?, claimed_by=NULL,
lease_token_hash=NULL, lease_expires_at=NULL
WHERE task_id=? AND status=? AND revision=? AND attempt=? AND max_attempts=?
AND claimed_by IS ?
AND lease_token_hash IS NULL AND lease_expires_at IS NULL
""",
(
request.next_max_attempts,
applied_revision,
task_id,
request.expected_status,
request.expected_revision,
request.expected_attempt,
request.expected_max_attempts,
previous_claimed_by,
),
)
if cursor.rowcount != 1:
raise RetryExtensionError("RETRY_EXTENSION_CAS_MISMATCH", 409)
event_payload = {
"schema": "aios.task-retry-extension.event.v1",
"task_id": task_id,
"authorization_id": request.authorization_id,
"idempotency_key": request.idempotency_key,
"previous_verification_sha256": request.previous_verification_sha256,
"previous_max_attempts": request.expected_max_attempts,
"next_max_attempts": request.next_max_attempts,
"previous_revision": request.expected_revision,
"applied_revision": applied_revision,
"request_sha256": request_sha,
"previous_claimed_by": previous_claimed_by,
"stale_terminal_claim_normalized": previous_claimed_by not in (None, ""),
}
self._insert_event(connection, task_id, event_payload)
connection.execute(
"""
INSERT INTO task_retry_extensions(
task_id,idempotency_key,request_sha256,authorization_id,previous_verification_sha256,
previous_max_attempts,next_max_attempts,expected_revision,applied_revision,created_at
) VALUES (?,?,?,?,?,?,?,?,?,?)
""",
(
task_id,
request.idempotency_key,
request_sha,
request.authorization_id,
request.previous_verification_sha256,
request.expected_max_attempts,
request.next_max_attempts,
request.expected_revision,
applied_revision,
_now(),
),
)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": request.expected_attempt,
"max_attempts": request.next_max_attempts,
"revision": applied_revision,
"idempotent": False,
"authorization_id": request.authorization_id,
"previous_verification_sha256": request.previous_verification_sha256,
}
class RetryExtensionHandler(BaseHTTPRequestHandler):
store: RetryExtensionStore | None = None
control_token: str = ""
def log_message(self, *_args: Any) -> None:
return
def _json(self, value: Mapping[str, Any], status: int) -> None:
data = json.dumps(dict(value), sort_keys=True, separators=(",", ":")).encode("utf-8")
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(data)))
self.end_headers()
self.wfile.write(data)
def _authorized(self) -> bool:
header = self.headers.get("Authorization", "")
return (
header.startswith("Bearer ")
and bool(self.control_token)
and hmac.compare_digest(header[7:], self.control_token)
)
def do_GET(self) -> None:
if self.path == "/health":
self._json({"status": "ok", "service": "aios-agent-task-retry-extension"}, 200)
else:
self._json({"error": "NOT_FOUND"}, 404)
def do_POST(self) -> None:
match = re.fullmatch(r"/v1/tasks/([^/]+)/retry-extension", self.path)
if match is None:
self._json({"error": "NOT_FOUND"}, 404)
return
if not self._authorized():
self._json({"error": "UNAUTHORIZED"}, 401)
return
try:
length = int(self.headers.get("Content-Length", "0"))
except ValueError:
self._json({"error": "CONTENT_LENGTH_INVALID"}, 400)
return
if length < 1 or length > MAX_BODY:
self._json({"error": "REQUEST_SIZE_INVALID"}, 413)
return
try:
value = json.loads(self.rfile.read(length).decode("utf-8"))
if not isinstance(value, Mapping):
raise ValueError
request = RetryExtensionRequest.from_mapping(value)
if self.store is None:
raise RetryExtensionError("RUNTIME_UNAVAILABLE", 503)
result = self.store.extend(match.group(1), request)
self._json(result, 200 if result["idempotent"] else 201)
except RetryExtensionError as exc:
self._json({"error": exc.code}, exc.status)
except (UnicodeDecodeError, json.JSONDecodeError, ValueError):
self._json({"error": "REQUEST_INVALID"}, 400)
def load_control_token(path: Path) -> str:
if path.is_symlink() or not path.is_file():
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_UNAVAILABLE")
value = path.read_text(encoding="utf-8").strip()
if len(value) < 32:
raise RuntimeError("TASK_RETRY_CONTROL_CREDENTIAL_INVALID")
return value
def serve() -> None:
db = Path(os.environ.get("AIOS_AGENT_TASK_DB", "/var/lib/aios-agent-task/state.sqlite3"))
_required_authorization_id()
token_path = Path(
os.environ.get(
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
str(Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials")) / "agent_task_control_token"),
)
)
host = os.environ.get("AIOS_TASK_RETRY_HOST", "127.0.0.1")
port = int(os.environ.get("AIOS_TASK_RETRY_PORT", "18941"))
RetryExtensionHandler.store = RetryExtensionStore(db)
RetryExtensionHandler.control_token = load_control_token(token_path)
ThreadingHTTPServer((host, port), RetryExtensionHandler).serve_forever()
if __name__ == "__main__":
serve()