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

723 lines
28 KiB
Python

"""Owner-controlled CAS-bound execution-envelope rebind for Online Agent Tasks.
This service exists for a narrow recovery case: a Task was projected/claimed with a read-only
source_capture envelope before its already-registered deterministic plan became authoritative.
It never creates Tasks/Jobs/branches and never accepts arbitrary metadata patches. It only replaces
metadata.execution + the derived execution_projection for the same governed binding, after an
official NEEDS_REWORK transition has returned the Task to QUEUED with no active lease.
"""
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, Callable, Mapping, Sequence
import urllib.error
import urllib.request
from aios_online_agent_execution import (
GovernedExecutionBinding,
validate_execution_envelope,
)
TASK_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
KEY_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,159}$")
SHA_RE = re.compile(r"^[0-9a-f]{64}$")
MAX_BODY = 64 * 1024
AUTHORIZATION_ID_ENV = "AIOS_AGENT_TASK_EXECUTION_REBIND_AUTHORIZATION_ID"
class ExecutionRebindError(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 _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 ExecutionRebindError(code, 400)
value = value.strip()
if pattern is not None and pattern.fullmatch(value) is None:
raise ExecutionRebindError(code, 400)
return value
def _required_authorization_id() -> str:
value = os.environ.get(AUTHORIZATION_ID_ENV, "").strip()
if not value:
raise RuntimeError("TASK_EXECUTION_REBIND_AUTHORIZATION_ID_MISSING")
if KEY_RE.fullmatch(value) is None:
raise RuntimeError("TASK_EXECUTION_REBIND_AUTHORIZATION_ID_INVALID")
return value
@dataclass(frozen=True)
class ExecutionRebindRequest:
expected_status: str
expected_revision: int
expected_attempt: int
previous_verification_sha256: str
expected_old_execution_digest: str
expected_new_execution_digest: str
authorization_id: str
idempotency_key: str
reason: str
@classmethod
def from_mapping(cls, value: Mapping[str, Any]) -> "ExecutionRebindRequest":
allowed = {
"expected_status",
"expected_revision",
"expected_attempt",
"previous_verification_sha256",
"expected_old_execution_digest",
"expected_new_execution_digest",
"authorization_id",
"idempotency_key",
"reason",
}
if set(value) != allowed:
raise ExecutionRebindError("EXECUTION_REBIND_FIELDS_INVALID", 400)
status = _require_string(value["expected_status"], "EXPECTED_STATUS_INVALID")
if status != "QUEUED":
raise ExecutionRebindError("EXPECTED_STATUS_INVALID", 400)
revision = value["expected_revision"]
attempt = value["expected_attempt"]
if (
not isinstance(revision, int)
or isinstance(revision, bool)
or revision < 0
or not isinstance(attempt, int)
or isinstance(attempt, bool)
or attempt < 1
):
raise ExecutionRebindError("EXECUTION_REBIND_INTEGER_INVALID", 400)
verification = _require_string(
value["previous_verification_sha256"], "VERIFICATION_SHA256_INVALID"
)
old_digest = _require_string(
value["expected_old_execution_digest"], "OLD_EXECUTION_DIGEST_INVALID"
)
new_digest = _require_string(
value["expected_new_execution_digest"], "NEW_EXECUTION_DIGEST_INVALID"
)
for digest, code in (
(verification, "VERIFICATION_SHA256_INVALID"),
(old_digest, "OLD_EXECUTION_DIGEST_INVALID"),
(new_digest, "NEW_EXECUTION_DIGEST_INVALID"),
):
if SHA_RE.fullmatch(digest) is None:
raise ExecutionRebindError(code, 400)
if old_digest == new_digest:
raise ExecutionRebindError("EXECUTION_REBIND_DIGEST_UNCHANGED", 400)
authorization = _require_string(
value["authorization_id"], "AUTHORIZATION_ID_INVALID", KEY_RE
)
key = _require_string(value["idempotency_key"], "IDEMPOTENCY_KEY_INVALID", KEY_RE)
reason = _require_string(value["reason"], "EXECUTION_REBIND_REASON_INVALID")
if len(reason) > 512:
raise ExecutionRebindError("EXECUTION_REBIND_REASON_INVALID", 400)
return cls(
status,
revision,
attempt,
verification,
old_digest,
new_digest,
authorization,
key,
reason,
)
def public(self) -> dict[str, Any]:
return {
"expected_status": self.expected_status,
"expected_revision": self.expected_revision,
"expected_attempt": self.expected_attempt,
"previous_verification_sha256": self.previous_verification_sha256,
"expected_old_execution_digest": self.expected_old_execution_digest,
"expected_new_execution_digest": self.expected_new_execution_digest,
"authorization_id": self.authorization_id,
"idempotency_key": self.idempotency_key,
"reason": self.reason,
}
class CanonicalBridgeExecutionResolver:
"""Resolve the already-registered plan from the canonical governed Bridge."""
def __init__(self, base_url: str, control_token: str) -> None:
self.base_url = base_url.rstrip("/")
self.control_token = control_token
def __call__(
self,
task_id: str,
required_capabilities: Sequence[str],
) -> dict[str, Any]:
body = json.dumps(
{
"task_id": task_id,
"required_capabilities": list(required_capabilities),
},
sort_keys=True,
separators=(",", ":"),
).encode("utf-8")
request = urllib.request.Request(
self.base_url + "/v2/execution-envelope",
method="POST",
data=body,
headers={
"Authorization": "Bearer " + self.control_token,
"Content-Type": "application/json",
"Accept": "application/json",
},
)
try:
with urllib.request.urlopen(request, timeout=15) as response:
raw = response.read()
status = response.status
except urllib.error.HTTPError as exc:
raw = exc.read()
status = exc.code
try:
value = json.loads(raw.decode("utf-8"))
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
raise ExecutionRebindError("CANONICAL_EXECUTION_RESPONSE_INVALID", 502) from exc
if not isinstance(value, Mapping):
raise ExecutionRebindError("CANONICAL_EXECUTION_RESPONSE_INVALID", 502)
if status != 200:
raise ExecutionRebindError(
str(value.get("error") or "CANONICAL_EXECUTION_RESOLUTION_FAILED"),
502 if status >= 500 else 409,
)
return dict(value)
class ExecutionRebindStore:
"""Official owner-controlled mutation with CAS, plan resolution and durable audit."""
def __init__(
self,
db_path: Path,
resolver: Callable[[str, Sequence[str]], Mapping[str, Any]],
) -> None:
self.db_path = Path(db_path)
self.resolver = resolver
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 _json_value(raw: object, code: str) -> dict[str, Any]:
if isinstance(raw, Mapping):
return dict(raw)
if not isinstance(raw, str):
raise ExecutionRebindError(code, 409)
try:
value = json.loads(raw)
except json.JSONDecodeError as exc:
raise ExecutionRebindError(code, 409) from exc
if not isinstance(value, Mapping):
raise ExecutionRebindError(code, 409)
return dict(value)
@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 ExecutionRebindError("TASK_VERIFICATION_INVALID", 409) from exc
else:
value = raw
return _sha(value)
@staticmethod
def _metadata_column(columns: Mapping[str, sqlite3.Row]) -> str:
for name in ("metadata_json", "metadata"):
if name in columns:
return name
raise ExecutionRebindError("TASK_METADATA_SCHEMA_UNSUPPORTED", 503)
@staticmethod
def _required_capabilities(
task: sqlite3.Row,
columns: Mapping[str, sqlite3.Row],
old_execution: Mapping[str, Any],
) -> list[str]:
for field in ("required_capabilities_json", "required_capabilities"):
if field not in columns:
continue
raw = task[field]
if raw in (None, ""):
continue
if isinstance(raw, str):
try:
value = json.loads(raw)
except json.JSONDecodeError:
value = [item for item in raw.split(",") if item.strip()]
else:
value = raw
if isinstance(value, list) and all(isinstance(item, str) for item in value):
return [item.strip() for item in value if item.strip()]
value = old_execution.get("capability_scope")
if isinstance(value, list) and all(isinstance(item, str) for item in value):
return [item for item in value if item]
raise ExecutionRebindError("TASK_CAPABILITIES_UNAVAILABLE", 503)
@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 = ExecutionRebindStore._columns(connection, name)
if "task_id" in columns and ("event_type" in columns or "type" in columns):
return name, columns
raise ExecutionRebindError("TASK_EVENT_TABLE_UNSUPPORTED", 503)
@staticmethod
def _insert_event(
connection: sqlite3.Connection,
task_id: str,
payload: Mapping[str, Any],
) -> None:
table, columns = ExecutionRebindStore._event_table(connection)
values: dict[str, Any] = {"task_id": task_id}
if "event_type" in columns:
values["event_type"] = "TASK_EXECUTION_REBIND_AUTHORIZED"
else:
values["type"] = "TASK_EXECUTION_REBIND_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 ExecutionRebindError("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)
quoted = ",".join('"' + name + '"' for name in names)
placeholders = ",".join("?" for _ in names)
connection.execute(
f'INSERT INTO "{table}" ({quoted}) VALUES ({placeholders})',
tuple(values[name] for name in names),
)
@staticmethod
def _ensure_rebind_table(connection: sqlite3.Connection) -> None:
connection.execute(
"""
CREATE TABLE IF NOT EXISTS task_execution_rebinds (
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,
old_execution_digest TEXT NOT NULL,
new_execution_digest TEXT NOT NULL,
expected_revision INTEGER NOT NULL,
applied_revision INTEGER NOT NULL,
attempt INTEGER NOT NULL,
reason TEXT NOT NULL,
created_at TEXT NOT NULL,
PRIMARY KEY(task_id,idempotency_key)
)
"""
)
def _load_and_validate(
self,
connection: sqlite3.Connection,
task_id: str,
request: ExecutionRebindRequest,
) -> tuple[sqlite3.Row, dict[str, sqlite3.Row], str, dict[str, Any], dict[str, Any]]:
columns = self._columns(connection, "tasks")
required = {
"task_id",
"status",
"attempt",
"revision",
"claimed_by",
"lease_token_hash",
"lease_expires_at",
"verification_json",
}
if not required.issubset(columns):
raise ExecutionRebindError("TASK_SCHEMA_EXECUTION_REBIND_UNSUPPORTED", 503)
metadata_column = self._metadata_column(columns)
task = connection.execute(
"SELECT * FROM tasks WHERE task_id=?",
(task_id,),
).fetchone()
if task is None:
raise ExecutionRebindError("TASK_NOT_FOUND", 404)
if (
str(task["status"]) != request.expected_status
or int(task["revision"]) != request.expected_revision
or int(task["attempt"]) != request.expected_attempt
):
raise ExecutionRebindError("EXECUTION_REBIND_CAS_MISMATCH", 409)
if task["lease_token_hash"] not in (None, "") or task["lease_expires_at"] not in (None, ""):
raise ExecutionRebindError("EXECUTION_REBIND_ACTIVE_LEASE_DENY", 409)
verification_sha = self._verification_hash(task["verification_json"])
if verification_sha != request.previous_verification_sha256:
raise ExecutionRebindError("EXECUTION_REBIND_VERIFICATION_DRIFT", 409)
metadata = self._json_value(
task[metadata_column],
"TASK_METADATA_INVALID",
)
execution = metadata.get("execution")
if not isinstance(execution, Mapping):
raise ExecutionRebindError("TASK_EXECUTION_METADATA_MISSING", 409)
old_execution = validate_execution_envelope(dict(execution))
if old_execution["execution_digest"] != request.expected_old_execution_digest:
raise ExecutionRebindError("EXECUTION_REBIND_OLD_DIGEST_DRIFT", 409)
if old_execution.get("action") != "source_capture":
raise ExecutionRebindError("EXECUTION_REBIND_SOURCE_CAPTURE_REQUIRED", 409)
projection = metadata.get("execution_projection")
if isinstance(projection, Mapping):
projected_digest = str(projection.get("execution_digest") or "")
if projected_digest and projected_digest != request.expected_old_execution_digest:
raise ExecutionRebindError("EXECUTION_REBIND_PROJECTION_DRIFT", 409)
return task, columns, metadata_column, metadata, old_execution
def rebind(
self,
task_id: str,
request: ExecutionRebindRequest,
) -> dict[str, Any]:
task_id = _require_string(task_id, "TASK_ID_INVALID", TASK_RE)
required_authorization = _required_authorization_id()
if request.authorization_id != required_authorization:
raise ExecutionRebindError("EXECUTION_REBIND_AUTHORIZATION_ID_MISMATCH", 403)
request_sha = _sha(request.public())
# Idempotent replay must win before CAS validation because a successful
# rebind necessarily increments the Task revision and changes the persisted envelope.
with self._connect() as connection:
self._ensure_rebind_table(connection)
replay = connection.execute(
"SELECT * FROM task_execution_rebinds WHERE task_id=? AND idempotency_key=?",
(task_id, request.idempotency_key),
).fetchone()
if replay is not None:
if replay["request_sha256"] != request_sha:
raise ExecutionRebindError("EXECUTION_REBIND_IDEMPOTENCY_CONFLICT", 409)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": int(replay["attempt"]),
"revision": int(replay["applied_revision"]),
"old_execution_digest": replay["old_execution_digest"],
"new_execution_digest": replay["new_execution_digest"],
"authorization_id": replay["authorization_id"],
"idempotent": True,
}
# Read/CAS snapshot first. Canonical Bridge resolution happens outside the DB write lock.
with self._connect() as connection:
task, columns, _, _, old_execution = self._load_and_validate(
connection, task_id, request
)
capabilities = self._required_capabilities(task, columns, old_execution)
binding = GovernedExecutionBinding.from_mapping(old_execution)
resolved = dict(self.resolver(task_id, capabilities))
new_execution = validate_execution_envelope(resolved, binding=binding)
if new_execution.get("action") != "deterministic":
raise ExecutionRebindError("EXECUTION_REBIND_DETERMINISTIC_PLAN_REQUIRED", 409)
if new_execution["execution_digest"] != request.expected_new_execution_digest:
raise ExecutionRebindError("EXECUTION_REBIND_NEW_DIGEST_DRIFT", 409)
if new_execution["execution_digest"] == old_execution["execution_digest"]:
raise ExecutionRebindError("EXECUTION_REBIND_DIGEST_UNCHANGED", 409)
# Re-read under BEGIN IMMEDIATE and apply only if the exact snapshot is unchanged.
with self._connect() as connection:
connection.execute("BEGIN IMMEDIATE")
self._ensure_rebind_table(connection)
replay = connection.execute(
"SELECT * FROM task_execution_rebinds WHERE task_id=? AND idempotency_key=?",
(task_id, request.idempotency_key),
).fetchone()
if replay is not None:
if replay["request_sha256"] != request_sha:
raise ExecutionRebindError("EXECUTION_REBIND_IDEMPOTENCY_CONFLICT", 409)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": int(replay["attempt"]),
"revision": int(replay["applied_revision"]),
"old_execution_digest": replay["old_execution_digest"],
"new_execution_digest": replay["new_execution_digest"],
"authorization_id": replay["authorization_id"],
"idempotent": True,
}
task, columns, metadata_column, metadata, current_old = self._load_and_validate(
connection, task_id, request
)
if current_old["execution_digest"] != old_execution["execution_digest"]:
raise ExecutionRebindError("EXECUTION_REBIND_OLD_DIGEST_DRIFT", 409)
new_metadata = dict(metadata)
new_metadata["execution"] = new_execution
new_metadata["execution_projection"] = {
"schema": "aios.online-agent.task-projection.v1",
"task_id": binding.task_id,
"job_id": binding.job_id,
"execution_digest": new_execution["execution_digest"],
}
applied_revision = request.expected_revision + 1
previous_claimed_by = task["claimed_by"]
cursor = connection.execute(
f"""
UPDATE tasks
SET "{metadata_column}"=?, revision=?, claimed_by=NULL,
lease_token_hash=NULL, lease_expires_at=NULL
WHERE task_id=? AND status=? AND revision=? AND attempt=?
AND claimed_by IS ? AND lease_token_hash IS NULL AND lease_expires_at IS NULL
""",
(
json.dumps(new_metadata, sort_keys=True, separators=(",", ":")),
applied_revision,
task_id,
request.expected_status,
request.expected_revision,
request.expected_attempt,
previous_claimed_by,
),
)
if cursor.rowcount != 1:
raise ExecutionRebindError("EXECUTION_REBIND_CAS_MISMATCH", 409)
event_payload = {
"schema": "aios.task-execution-rebind.event.v1",
"task_id": task_id,
"job_id": binding.job_id,
"authorization_id": request.authorization_id,
"idempotency_key": request.idempotency_key,
"reason": request.reason,
"previous_verification_sha256": request.previous_verification_sha256,
"old_execution_digest": old_execution["execution_digest"],
"new_execution_digest": new_execution["execution_digest"],
"old_action": old_execution.get("action"),
"new_action": new_execution.get("action"),
"previous_revision": request.expected_revision,
"applied_revision": applied_revision,
"attempt": request.expected_attempt,
"request_sha256": request_sha,
"previous_claimed_by": previous_claimed_by,
"stale_claim_normalized": previous_claimed_by not in (None, ""),
}
self._insert_event(connection, task_id, event_payload)
connection.execute(
"""
INSERT INTO task_execution_rebinds(
task_id,idempotency_key,request_sha256,authorization_id,
previous_verification_sha256,old_execution_digest,new_execution_digest,
expected_revision,applied_revision,attempt,reason,created_at
) VALUES (?,?,?,?,?,?,?,?,?,?,?,?)
""",
(
task_id,
request.idempotency_key,
request_sha,
request.authorization_id,
request.previous_verification_sha256,
old_execution["execution_digest"],
new_execution["execution_digest"],
request.expected_revision,
applied_revision,
request.expected_attempt,
request.reason,
_now(),
),
)
connection.commit()
return {
"task_id": task_id,
"status": "QUEUED",
"attempt": request.expected_attempt,
"revision": applied_revision,
"old_execution_digest": old_execution["execution_digest"],
"new_execution_digest": new_execution["execution_digest"],
"authorization_id": request.authorization_id,
"idempotent": False,
}
class ExecutionRebindHandler(BaseHTTPRequestHandler):
store: ExecutionRebindStore | 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-execution-rebind"},
200,
)
else:
self._json({"error": "NOT_FOUND"}, 404)
def do_POST(self) -> None:
match = re.fullmatch(r"/v1/tasks/([^/]+)/execution-rebind", 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 = ExecutionRebindRequest.from_mapping(value)
if self.store is None:
raise ExecutionRebindError("RUNTIME_UNAVAILABLE", 503)
result = self.store.rebind(match.group(1), request)
self._json(result, 200 if result["idempotent"] else 201)
except ExecutionRebindError 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_EXECUTION_REBIND_CONTROL_CREDENTIAL_UNAVAILABLE")
value = path.read_text(encoding="utf-8").strip()
if len(value) < 32:
raise RuntimeError("TASK_EXECUTION_REBIND_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"
),
)
)
token = load_control_token(token_path)
bridge = os.environ.get(
"AIOS_GOVERNED_WRITE_API_URL",
"http://127.0.0.1:18892",
)
host = os.environ.get("AIOS_TASK_EXECUTION_REBIND_HOST", "127.0.0.1")
port = int(os.environ.get("AIOS_TASK_EXECUTION_REBIND_PORT", "18942"))
ExecutionRebindHandler.store = ExecutionRebindStore(
db,
CanonicalBridgeExecutionResolver(bridge, token),
)
ExecutionRebindHandler.control_token = token
ThreadingHTTPServer((host, port), ExecutionRebindHandler).serve_forever()
if __name__ == "__main__":
serve()