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

289 lines
10 KiB
Python

"""Unified autonomous control-plane primitives.
This is deliberately a library, not another daemon. Task API, workers and host
recovery code consume the same Admission -> Invariant -> Repair semantics.
"""
from __future__ import annotations
from dataclasses import asdict, dataclass
from enum import Enum
import re
from typing import Callable, Iterable, Mapping, Sequence
from aios_capability_contract import (
capability_contract,
has_capabilities,
normalize_required_capabilities,
normalize_worker_capabilities,
registered_capability,
validate_capability_contract_registry,
)
class FailureClass(str, Enum):
CAPABILITY_CONTRACT_ERROR = "CAPABILITY_CONTRACT_ERROR"
CREDENTIAL_PROJECTION_ERROR = "CREDENTIAL_PROJECTION_ERROR"
DEPENDENCY_UNAVAILABLE = "DEPENDENCY_UNAVAILABLE"
POLICY_DENIED = "POLICY_DENIED"
RESOURCE_UNAVAILABLE = "RESOURCE_UNAVAILABLE"
WORKER_CRASH = "WORKER_CRASH"
LEASE_LOST = "LEASE_LOST"
BUSINESS_PERMANENT = "BUSINESS_PERMANENT"
UNKNOWN = "UNKNOWN"
class RepairLevel(int, Enum):
AUTO_LOCAL = 0
AUTO_REPAIR_TASK = 1
OWNER_APPROVAL = 2
MANUAL = 3
@dataclass(frozen=True)
class InvariantResult:
name: str
passed: bool
detail: str = ""
def as_dict(self) -> dict[str, object]:
return asdict(self)
@dataclass(frozen=True)
class AdmissionDecision:
admitted: bool
state: str
invariants: tuple[InvariantResult, ...]
failure_class: FailureClass | None = None
repair_level: RepairLevel | None = None
repair_action: str | None = None
def as_dict(self) -> dict[str, object]:
return {
"schema": "aios.runtime-admission.decision.v1",
"admitted": self.admitted,
"state": self.state,
"invariants": [item.as_dict() for item in self.invariants],
"failure_class": None if self.failure_class is None else self.failure_class.value,
"repair_level": None if self.repair_level is None else int(self.repair_level),
"repair_action": self.repair_action,
}
@dataclass(frozen=True)
class RepairDecision:
failure_class: FailureClass
level: RepairLevel
action: str
consumes_business_attempt: bool
def as_dict(self) -> dict[str, object]:
return {
"failure_class": self.failure_class.value,
"level": int(self.level),
"action": self.action,
"consumes_business_attempt": self.consumes_business_attempt,
}
def classify_failure(error: object, *, phase: str = "") -> FailureClass:
text = (str(error) + " " + str(phase)).lower()
if any(token in text for token in (
"credential", "permission denied", "token registry", "secret", "unauthorized"
)):
return FailureClass.CREDENTIAL_PROJECTION_ERROR
if any(token in text for token in (
"transport", "unavailable", "timeout", "connection", "bad gateway", "http_5"
)):
return FailureClass.DEPENDENCY_UNAVAILABLE
if any(token in text for token in (
"capability", "eligible", "matcher", "contract"
)):
return FailureClass.CAPABILITY_CONTRACT_ERROR
if any(token in text for token in (
"policy", "forbidden", "approval required", "not authorized"
)):
return FailureClass.POLICY_DENIED
if any(token in text for token in ("lease lost", "lease_expired", "heartbeat_failed")):
return FailureClass.LEASE_LOST
if any(token in text for token in ("out of memory", "disk full", "resource")):
return FailureClass.RESOURCE_UNAVAILABLE
if any(token in text for token in ("worker crash", "process exited", "signal")):
return FailureClass.WORKER_CRASH
if any(token in text for token in ("invalid release", "business permanent")):
return FailureClass.BUSINESS_PERMANENT
return FailureClass.UNKNOWN
def repair_for_failure(failure: FailureClass) -> RepairDecision:
table = {
FailureClass.CAPABILITY_CONTRACT_ERROR: RepairDecision(
failure, RepairLevel.AUTO_REPAIR_TASK,
"create_same_lineage_capability_contract_repair", False,
),
FailureClass.CREDENTIAL_PROJECTION_ERROR: RepairDecision(
failure, RepairLevel.AUTO_REPAIR_TASK,
"restore_service_private_credential_projection", False,
),
FailureClass.DEPENDENCY_UNAVAILABLE: RepairDecision(
failure, RepairLevel.AUTO_LOCAL,
"retry_dependency_health_and_resume", False,
),
FailureClass.RESOURCE_UNAVAILABLE: RepairDecision(
failure, RepairLevel.AUTO_LOCAL,
"heal_runtime_resource_and_resume", False,
),
FailureClass.WORKER_CRASH: RepairDecision(
failure, RepairLevel.AUTO_LOCAL,
"restart_worker_and_resume_same_lineage", False,
),
FailureClass.LEASE_LOST: RepairDecision(
failure, RepairLevel.AUTO_LOCAL,
"recover_lease_and_resume_same_lineage", False,
),
FailureClass.POLICY_DENIED: RepairDecision(
failure, RepairLevel.OWNER_APPROVAL,
"request_bound_owner_authorization", False,
),
FailureClass.BUSINESS_PERMANENT: RepairDecision(
failure, RepairLevel.MANUAL,
"terminal_business_failure", True,
),
FailureClass.UNKNOWN: RepairDecision(
failure, RepairLevel.AUTO_REPAIR_TASK,
"create_diagnostic_repair_task", False,
),
}
return table[failure]
def _probe(
name: str,
probes: Mapping[str, Callable[[], bool]],
) -> InvariantResult:
fn = probes.get(name)
if fn is None:
return InvariantResult(name, False, "PROBE_MISSING")
try:
passed = bool(fn())
except Exception as exc:
return InvariantResult(name, False, "PROBE_ERROR:" + type(exc).__name__)
return InvariantResult(name, passed, "PASS" if passed else "NOT_READY")
def runtime_admission(
*,
worker_capabilities: Iterable[object],
required_capabilities: Iterable[object],
requested_operations: Sequence[str] = (),
probes: Mapping[str, Callable[[], bool]] | None = None,
) -> AdmissionDecision:
"""Admission is evaluated before claim; failures do not consume attempts."""
worker_values = tuple(worker_capabilities)
required_values = tuple(required_capabilities)
probe_map = probes or {}
invariants: list[InvariantResult] = []
registry = validate_capability_contract_registry()
invariants.append(InvariantResult(
"capability_contract_registry",
bool(registry.get("valid")),
"PASS" if registry.get("valid") else "REGISTRY_INVALID",
))
task_known = all(registered_capability(item) for item in required_values)
worker_known = all(registered_capability(item, worker=True) for item in worker_values)
invariants.extend((
InvariantResult("task_capabilities_registered", task_known, "PASS" if task_known else "UNKNOWN_TASK_CAPABILITY"),
InvariantResult("worker_capabilities_registered", worker_known, "PASS" if worker_known else "UNKNOWN_WORKER_CAPABILITY"),
))
capability_match = (
task_known
and worker_known
and has_capabilities(worker_values, required_values)
)
invariants.append(InvariantResult(
"capability_match",
capability_match,
"PASS" if capability_match else "WORKER_NOT_ELIGIBLE",
))
normalized = normalize_required_capabilities(required_values)
contracts = [
capability_contract(item)
for item in normalized
if not str(item).startswith("exact:")
]
contracts = [item for item in contracts if item is not None]
forbidden: set[str] = set()
dependencies: set[str] = set()
health: set[str] = set()
for contract in contracts:
forbidden.update(contract.forbidden)
dependencies.update(contract.dependencies)
health.update(contract.health_requirements)
requested = {str(item).strip().lower() for item in requested_operations if str(item).strip()}
forbidden_hit = sorted(requested & {item.lower() for item in forbidden})
invariants.append(InvariantResult(
"forbidden_operations_absent",
not forbidden_hit,
"PASS" if not forbidden_hit else "FORBIDDEN:" + ",".join(forbidden_hit),
))
for name in sorted(dependencies | health):
invariants.append(_probe(name, probe_map))
failed = [item for item in invariants if not item.passed]
if not failed:
return AdmissionDecision(
True,
"EXECUTION_READY",
tuple(invariants),
)
details = " ".join(item.name + ":" + item.detail for item in failed)
failure = classify_failure(details, phase="admission")
if any(item.name == "forbidden_operations_absent" and not item.passed for item in failed):
failure = FailureClass.POLICY_DENIED
elif any("credential" in item.name for item in failed):
failure = FailureClass.CREDENTIAL_PROJECTION_ERROR
elif any(item.name in {"capability_contract_registry", "task_capabilities_registered", "worker_capabilities_registered", "capability_match"} for item in failed):
failure = FailureClass.CAPABILITY_CONTRACT_ERROR
elif any(item.name in dependencies or item.name in health for item in failed):
failure = FailureClass.DEPENDENCY_UNAVAILABLE
repair = repair_for_failure(failure)
return AdmissionDecision(
False,
"EXECUTION_READY_FAILED",
tuple(invariants),
failure,
repair.level,
repair.action,
)
def system_invariant_snapshot(
*,
worker_capabilities: Iterable[object],
required_capabilities: Iterable[object],
requested_operations: Sequence[str] = (),
probes: Mapping[str, Callable[[], bool]] | None = None,
) -> dict[str, object]:
decision = runtime_admission(
worker_capabilities=worker_capabilities,
required_capabilities=required_capabilities,
requested_operations=requested_operations,
probes=probes,
)
return {
"schema": "aios.system-invariants.v1",
"status": "HEALTHY" if decision.admitted else "DEGRADED",
"execution_ready": decision.admitted,
"admission": decision.as_dict(),
}