feat(control-plane): add admission invariant repair core

This commit is contained in:
AIOS Governed Continuation
2026-08-19 22:28:38 +08:00
parent 17deb91ca7
commit b4b4416c93
6 changed files with 915 additions and 3 deletions
@@ -0,0 +1,288 @@
"""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(),
}
+171 -2
View File
@@ -3,6 +3,8 @@
from __future__ import annotations
from collections.abc import Iterable
from dataclasses import asdict, dataclass
from typing import Any
_TASK_ALIASES: dict[str, frozenset[str]] = {
@@ -75,6 +77,169 @@ _WORKER_ALIASES: dict[str, frozenset[str]] = {
"release:candidate": frozenset({"release:candidate"}),
}
@dataclass(frozen=True)
class CapabilityContract:
"""Versioned runtime contract attached to one canonical semantic capability."""
name: str
min_version: int = 1
max_version: int = 1
permissions: tuple[str, ...] = ()
forbidden: tuple[str, ...] = ()
dependencies: tuple[str, ...] = ()
health_requirements: tuple[str, ...] = ()
def as_dict(self) -> dict[str, Any]:
return asdict(self)
# This registry is the semantic source of truth. Alias tables below are retained
# as compatibility adapters; startup/tests validate every alias target against
# this registry so a name cannot be accepted in one layer and be unknown in
# another.
_CAPABILITY_CONTRACTS: dict[str, CapabilityContract] = {
"repo.read": CapabilityContract("repo.read", permissions=("repository_read",)),
"test.execute": CapabilityContract("test.execute", permissions=("test_execution",)),
"governed.git.write.branch": CapabilityContract(
"governed.git.write.branch",
permissions=("governed_branch_write",),
dependencies=("writer_lease", "governed_gitops"),
),
"governed.git.write.file": CapabilityContract(
"governed.git.write.file",
permissions=("governed_file_write",),
dependencies=("writer_lease", "governed_gitops"),
),
"governed.git.write": CapabilityContract(
"governed.git.write",
permissions=("governed_git_write",),
dependencies=("writer_lease", "governed_gitops"),
),
"runtime.shell": CapabilityContract("runtime.shell", permissions=("runtime_shell",)),
"runtime.git": CapabilityContract("runtime.git", permissions=("runtime_git",)),
"runtime.python": CapabilityContract("runtime.python", permissions=("runtime_python",)),
"legacy.code.read": CapabilityContract("legacy.code.read"),
"legacy.code.review": CapabilityContract("legacy.code.review"),
"legacy.code.write": CapabilityContract("legacy.code.write"),
"legacy.code.write.patch": CapabilityContract("legacy.code.write.patch"),
"legacy.test.python": CapabilityContract("legacy.test.python"),
"legacy.test.shell.allowlisted": CapabilityContract("legacy.test.shell.allowlisted"),
"legacy.git.commit": CapabilityContract("legacy.git.commit"),
"legacy.git.diff.read": CapabilityContract("legacy.git.diff.read"),
"legacy.git.force_push": CapabilityContract(
"legacy.git.force_push",
forbidden=("protected_ref_bypass",),
),
"legacy.deploy.production": CapabilityContract(
"legacy.deploy.production",
permissions=("production_deploy",),
dependencies=("owner_approval", "deployment_controller"),
health_requirements=("approval_envelope_verified", "runtime_acceptance_available"),
),
"legacy.secret.transform": CapabilityContract("legacy.secret.transform"),
"legacy.secure_file_transformer": CapabilityContract("legacy.secure_file_transformer"),
"legacy.runtime.shadow": CapabilityContract("legacy.runtime.shadow"),
"legacy.review.security": CapabilityContract("legacy.review.security"),
"legacy.review.api-contract": CapabilityContract("legacy.review.api-contract"),
"legacy.gpu.train": CapabilityContract("legacy.gpu.train"),
"agent.runtime.hermes": CapabilityContract(
"agent.runtime.hermes",
dependencies=("hermes_runtime",),
health_requirements=("worker_liveness",),
),
"agent.runtime.openclaw": CapabilityContract(
"agent.runtime.openclaw",
dependencies=("openclaw_runtime",),
health_requirements=("worker_liveness",),
),
"release:candidate": CapabilityContract(
"release:candidate",
min_version=1,
max_version=1,
permissions=("prepare_release",),
forbidden=(
"production_deploy",
"submit_owner_approval",
"tag_publish",
"baseline_registry_finalize",
"runtime_switch",
),
dependencies=(
"credential_projection",
"trusted_builder",
),
health_requirements=(
"authenticated_probe",
"release_api_health",
"worker_liveness",
),
),
}
def capability_contract(name: object) -> CapabilityContract | None:
"""Return the contract for one canonical or registered capability name."""
text = _clean(name)
direct = _CAPABILITY_CONTRACTS.get(text)
if direct is not None:
return direct
mapped = _TASK_ALIASES.get(text) or _WORKER_ALIASES.get(text)
if mapped is None or len(mapped) != 1:
return None
return _CAPABILITY_CONTRACTS.get(next(iter(mapped)))
def registered_capability(name: object, *, worker: bool = False) -> bool:
"""Fail-closed validation used by registration/task admission."""
text = _clean(name)
if "*" in text:
return False
aliases = _WORKER_ALIASES if worker else _TASK_ALIASES
mapped = aliases.get(text)
if mapped is None:
return text in _CAPABILITY_CONTRACTS
return all(item in _CAPABILITY_CONTRACTS for item in mapped)
def validate_capability_contract_registry() -> dict[str, object]:
"""Prove alias/contract closure and contract safety invariants."""
alias_targets: set[str] = set()
for mapping in (_TASK_ALIASES, _WORKER_ALIASES):
for values in mapping.values():
alias_targets.update(values)
missing = sorted(alias_targets - set(_CAPABILITY_CONTRACTS))
invalid_versions = sorted(
name
for name, contract in _CAPABILITY_CONTRACTS.items()
if contract.min_version < 1 or contract.max_version < contract.min_version
)
permission_forbidden_overlap = sorted(
name
for name, contract in _CAPABILITY_CONTRACTS.items()
if set(contract.permissions) & set(contract.forbidden)
)
return {
"schema": "aios.capability-contract-registry.v1",
"contract_count": len(_CAPABILITY_CONTRACTS),
"missing_alias_targets": missing,
"invalid_versions": invalid_versions,
"permission_forbidden_overlap": permission_forbidden_overlap,
"valid": not missing and not invalid_versions and not permission_forbidden_overlap,
}
def capability_contract_snapshot() -> dict[str, dict[str, Any]]:
return {
name: contract.as_dict()
for name, contract in sorted(_CAPABILITY_CONTRACTS.items())
}
_UNKNOWN_PREFIX = "exact:"
@@ -100,7 +265,11 @@ def normalize_required_capabilities(values: Iterable[object]) -> frozenset[str]:
if "*" in text:
result.add(_UNKNOWN_PREFIX + text)
else:
result.update(_TASK_ALIASES.get(text, frozenset({_UNKNOWN_PREFIX + text})))
mapped = _TASK_ALIASES.get(text)
if mapped is None or any(item not in _CAPABILITY_CONTRACTS for item in mapped):
result.add(_UNKNOWN_PREFIX + text)
else:
result.update(mapped)
return frozenset(result)
@@ -113,7 +282,7 @@ def normalize_worker_capabilities(values: Iterable[object]) -> frozenset[str]:
if "*" in text:
continue
mapped = _WORKER_ALIASES.get(text)
if mapped is not None:
if mapped is not None and all(item in _CAPABILITY_CONTRACTS for item in mapped):
result.update(mapped)
if {
"governed.git.write.branch",
@@ -23,6 +23,11 @@ import time
import urllib.error
import urllib.request
from typing import Any, Mapping
from aios_autonomous_control_plane import (
classify_failure,
repair_for_failure,
runtime_admission,
)
AGENT_ID = os.environ.get(
"AIOS_RELEASE_WORKER_AGENT_ID",
@@ -431,6 +436,53 @@ class Heartbeat:
self.thread.join(timeout=2)
def release_admission(
task: Mapping[str, Any],
*,
release_token: str,
):
required = task.get("required_capabilities")
if not isinstance(required, list):
required = []
def release_api_health() -> bool:
status, value = http_json(
RELEASE_API,
"GET",
"/health",
"",
timeout=10,
)
return status == 200 and str(value.get("status") or "").lower() in {"ok", "healthy"}
def authenticated_probe() -> bool:
status, _ = http_json(
RELEASE_API,
"POST",
"/createReleaseCandidate",
release_token,
{},
timeout=10,
)
# Authentication + credential projection succeeded; the empty release
# request is intentionally rejected by request validation.
return status == 400
probes = {
"credential_projection": authenticated_probe,
"trusted_builder": release_api_health,
"authenticated_probe": authenticated_probe,
"release_api_health": release_api_health,
"worker_liveness": lambda: True,
}
return runtime_admission(
worker_capabilities=EXPECTED_CAPABILITIES,
required_capabilities=required,
requested_operations=("prepare_release",),
probes=probes,
)
def result_payload(
task_id: str,
release: ReleaseRequest,
@@ -478,6 +530,28 @@ def execute_task(
) -> bool:
task_id = str(task.get("task_id") or "")
release = ReleaseRequest.from_task(task)
admission = release_admission(
task,
release_token=release_token,
)
if not admission.admitted:
audit(
"TASK_ADMISSION_BLOCKED",
task_id=task_id,
admission=admission.as_dict(),
)
write_liveness(
"BLOCKED",
task_id=task_id,
stage="execution_ready",
error=admission.failure_class.value if admission.failure_class else "ADMISSION_FAILED",
)
return False
audit(
"TASK_ADMISSION_PASSED",
task_id=task_id,
admission=admission.as_dict(),
)
status, claimed = http_json(
TASK_API,
"POST",
@@ -610,11 +684,15 @@ def main() -> int:
release_token=release_token,
) or handled
except ReleaseWorkerError as exc:
failure = classify_failure(exc.code, phase=exc.phase)
repair = repair_for_failure(failure)
audit(
"TASK_EXECUTION_FAILED",
task_id=raw.get("task_id"),
phase=exc.phase,
error=exc.code,
failure_class=failure.value,
repair=repair.as_dict(),
)
time.sleep(0 if handled else POLL_SECONDS)
except KeyboardInterrupt:
@@ -0,0 +1,210 @@
# AIOS Autonomous Control Plane — Admission + Invariant + Repair
## Why this exists
Recent Agent registration, Task claim, release-worker, credential and retry failures shared one
failure mode:
> The control plane accepted an intent before the runtime had proved it could execute the intent.
This design does not add another fleet of daemons. It adds one shared library contract that Task API,
workers and governed host recovery consume.
## Three layers
```text
Intent
↓
Runtime Admission
↓
System Invariants
↓
Repair Policy
↓
Execution
```
### Runtime Admission
Admission occurs before Task claim.
A capability such as `release:candidate` is not considered executable merely because its name
matches. The capability contract also binds:
- supported contract version;
- allowed permission;
- forbidden operations;
- runtime dependencies;
- health requirements.
For `release:candidate`:
```text
permission:
prepare_release
forbidden:
production_deploy
submit_owner_approval
tag_publish
baseline_registry_finalize
runtime_switch
dependencies:
credential_projection
trusted_builder
health:
authenticated_probe
release_api_health
worker_liveness
```
Only a fully passing decision reaches:
```text
EXECUTION_READY
```
A failed decision remains:
```text
EXECUTION_READY_FAILED
```
and the worker does not call `/claim`.
Therefore an infrastructure defect discovered by admission does not consume a business attempt.
### System Invariants
The same admission checks are exposed as a machine-readable invariant snapshot.
Examples:
```text
capability_contract_registry
task_capabilities_registered
worker_capabilities_registered
capability_match
forbidden_operations_absent
credential_projection
trusted_builder
authenticated_probe
release_api_health
worker_liveness
```
A runtime can expose:
```text
HEALTHY
DEGRADED
```
without relying on a human reconstructing state from logs.
### Repair Policy
Failure classification maps to bounded recovery:
```text
DEPENDENCY_UNAVAILABLE → level 0 / auto local
RESOURCE_UNAVAILABLE → level 0 / auto local
WORKER_CRASH → level 0 / auto local
LEASE_LOST → level 0 / auto local
CAPABILITY_CONTRACT_ERROR → level 1 / same-lineage repair task
CREDENTIAL_PROJECTION_ERROR → level 1 / same-lineage repair task
UNKNOWN → level 1 / diagnostic repair task
POLICY_DENIED → level 2 / Owner authorization
BUSINESS_PERMANENT → level 3 / terminal/manual decision
```
Only business-permanent failure consumes the business retry budget in this first contract.
The current Task API does not yet have a first-class `EXECUTION_READY_FAILED` durable state. Until it
does, the Release Worker enforces the most important invariant by refusing to claim a Task whose
admission fails.
## Capability Contract Registry
`aios_capability_contract.py` remains backward-compatible with existing aliases but now validates
every alias target against a versioned semantic contract registry.
Unknown capabilities and wildcard capabilities remain fail-closed.
Agent registration and Task creation should next be changed to call `registered_capability()` so a
capability cannot be accepted at registration and rejected only later by the matcher.
## Credential rule
Admission probes credential usability, not merely credential existence.
For release candidate creation the authenticated probe intentionally sends an invalid empty
`/createReleaseCandidate` request.
Expected:
```text
HTTP 400
```
This proves:
```text
credential readable
→ authentication succeeded
→ scope accepted
→ request validation rejected empty business input
```
A permission failure/401/403/5xx is `EXECUTION_READY_FAILED`.
## Lineage
Repair actions are descriptive, not permission grants. Any repair Task must retain the existing
root/parent/attempt/authority chain and use governed same-lineage recovery.
No repair action may silently create a replacement business Task.
## Authority separation
Capability answers:
```text
can this runtime perform the operation?
```
Authority answers:
```text
is this operation currently authorized?
```
`release:candidate` never implies Owner approval, deployment, tag publication, baseline finalization
or runtime switch.
## Deployment sequence
Phase 1 (this candidate):
- Capability Contract Registry;
- shared Autonomous Control Plane library;
- Release Worker pre-claim admission;
- failure classification + repair evidence.
Phase 2:
- Task API uses the same library before returning Tasks from poll and again during claim CAS;
- Task schema gains durable `ADMITTED/EXECUTION_READY/EXECUTION_READY_FAILED` evidence without
counting pre-side-effect infrastructure failures against business attempts.
Phase 3:
- Agent registration validates against the same Capability Contract Registry;
- external connector writes only durable Intent/Command Inbox records and leaves execution to the
local control plane.
This sequencing avoids a second controller stack while converging every decision onto one contract.
+157
View File
@@ -0,0 +1,157 @@
from __future__ import annotations
import sys
from pathlib import Path
import pytest
ROOT=Path(__file__).resolve().parents[1]
APP=ROOT/"active-runtime/app"
sys.path.insert(0,str(APP))
import aios_autonomous_control_plane as acp
import aios_capability_contract as contract
import aios_release_online_agent_worker as worker
def _ready_probes():
return {
"credential_projection": lambda: True,
"trusted_builder": lambda: True,
"authenticated_probe": lambda: True,
"release_api_health": lambda: True,
"worker_liveness": lambda: True,
}
def _task():
return {
"task_id":"r42-autonomous-release-admission-test",
"required_capabilities":["release:candidate"],
"constraints":{
"release_candidate":{
"candidate_id":"r42-release-candidate-v2r2c9-test",
"source_commit":"1"*40,
"version":"V2R2C9",
"projection_id":"projection-"+"a"*32,
}
},
}
def test_capability_contract_registry_is_closed_and_release_is_versioned():
status=contract.validate_capability_contract_registry()
assert status["valid"] is True
release=contract.capability_contract("release:candidate")
assert release is not None
assert release.min_version==1
assert release.max_version==1
assert release.permissions==("prepare_release",)
assert "credential_projection" in release.dependencies
assert "trusted_builder" in release.dependencies
assert "authenticated_probe" in release.health_requirements
assert "production_deploy" in release.forbidden
assert "runtime_switch" in release.forbidden
def test_unknown_agent_capability_cannot_register_or_match():
assert contract.registered_capability("release:future",worker=True) is False
assert contract.registered_capability("release:*",worker=True) is False
assert contract.has_capabilities(["release:future"],["release:future"]) is False
def test_runtime_admission_requires_all_release_execution_readiness():
decision=acp.runtime_admission(
worker_capabilities=["release:candidate"],
required_capabilities=["release:candidate"],
requested_operations=["prepare_release"],
probes=_ready_probes(),
)
assert decision.admitted is True
assert decision.state=="EXECUTION_READY"
def test_runtime_admission_blocks_credential_failure_before_execution():
probes=_ready_probes()
probes["credential_projection"]=lambda:False
probes["authenticated_probe"]=lambda:False
decision=acp.runtime_admission(
worker_capabilities=["release:candidate"],
required_capabilities=["release:candidate"],
requested_operations=["prepare_release"],
probes=probes,
)
assert decision.admitted is False
assert decision.state=="EXECUTION_READY_FAILED"
assert decision.failure_class==acp.FailureClass.CREDENTIAL_PROJECTION_ERROR
assert decision.repair_level==acp.RepairLevel.AUTO_REPAIR_TASK
def test_forbidden_release_operation_requires_owner_boundary():
decision=acp.runtime_admission(
worker_capabilities=["release:candidate"],
required_capabilities=["release:candidate"],
requested_operations=["production_deploy"],
probes=_ready_probes(),
)
assert decision.admitted is False
assert decision.failure_class==acp.FailureClass.POLICY_DENIED
assert decision.repair_level==acp.RepairLevel.OWNER_APPROVAL
@pytest.mark.parametrize(
"error,phase,expected,level,consumes",
[
("Permission denied: gitops.tokens","release",acp.FailureClass.CREDENTIAL_PROJECTION_ERROR,acp.RepairLevel.AUTO_REPAIR_TASK,False),
("HTTP_TRANSPORT_UNAVAILABLE","network",acp.FailureClass.DEPENDENCY_UNAVAILABLE,acp.RepairLevel.AUTO_LOCAL,False),
("TASK_CAPABILITY_SCOPE_INVALID","validation",acp.FailureClass.CAPABILITY_CONTRACT_ERROR,acp.RepairLevel.AUTO_REPAIR_TASK,False),
("lease lost","heartbeat",acp.FailureClass.LEASE_LOST,acp.RepairLevel.AUTO_LOCAL,False),
("business permanent invalid release","release",acp.FailureClass.BUSINESS_PERMANENT,acp.RepairLevel.MANUAL,True),
],
)
def test_failure_classification_drives_repair_policy(error,phase,expected,level,consumes):
failure=acp.classify_failure(error,phase=phase)
assert failure==expected
repair=acp.repair_for_failure(failure)
assert repair.level==level
assert repair.consumes_business_attempt is consumes
def test_release_worker_does_not_claim_when_admission_is_not_ready(monkeypatch):
calls=[]
def fake_http(base,method,route,token,body=None,timeout=30):
calls.append((base,method,route,body))
if route=="/health":
return 200,{"status":"ok"}
if route=="/createReleaseCandidate" and body=={}:
return 500,{"error":"Permission denied: gitops.tokens"}
if route.endswith("/claim"):
raise AssertionError("claim must not happen before EXECUTION_READY")
raise AssertionError(route)
events=[]
monkeypatch.setattr(worker,"http_json",fake_http)
monkeypatch.setattr(worker,"audit",lambda event,**fields:events.append((event,fields)))
monkeypatch.setattr(worker,"write_liveness",lambda *args,**kwargs:None)
assert worker.execute_task(
_task(),
agent_token="a"*32,
release_token="r"*32,
) is False
assert not any(route.endswith("/claim") for _,_,route,_ in calls)
blocked=[item for item in events if item[0]=="TASK_ADMISSION_BLOCKED"]
assert len(blocked)==1
assert blocked[0][1]["admission"]["state"]=="EXECUTION_READY_FAILED"
def test_system_invariant_snapshot_is_degraded_when_dependency_is_missing():
probes=_ready_probes()
probes["trusted_builder"]=lambda:False
snapshot=acp.system_invariant_snapshot(
worker_capabilities=["release:candidate"],
required_capabilities=["release:candidate"],
probes=probes,
)
assert snapshot["status"]=="DEGRADED"
assert snapshot["execution_ready"] is False
+11 -1
View File
@@ -120,6 +120,10 @@ def test_worker_calls_only_fixed_release_candidate_route(monkeypatch):
def fake_http(base,method,route,token,body=None,timeout=30):
calls.append((base,method,route,token,body))
if route=="/health":
return 200,{"status":"ok"}
if route=="/createReleaseCandidate" and body=={}:
return 400,{"error":"request_invalid"}
if route.endswith("/claim"):
return 200,{"lease_token":"l"*32,"attempt":1}
if route.endswith("/heartbeat"):
@@ -135,6 +139,7 @@ def test_worker_calls_only_fixed_release_candidate_route(monkeypatch):
monkeypatch.setattr(worker,"http_json",fake_http)
monkeypatch.setattr(worker,"audit",lambda *args,**kwargs:None)
monkeypatch.setattr(worker,"write_liveness",lambda *args,**kwargs:None)
monkeypatch.setattr(worker.Heartbeat,"first",lambda self:None)
monkeypatch.setattr(worker.Heartbeat,"close",lambda self:None)
monkeypatch.setattr(worker.Heartbeat,"ensure",lambda self:None)
@@ -146,7 +151,12 @@ def test_worker_calls_only_fixed_release_candidate_route(monkeypatch):
release_token="r"*32,
) is True
release_calls=[item for item in calls if item[0]==worker.RELEASE_API]
release_calls=[
item for item in calls
if item[0]==worker.RELEASE_API
and item[2]=="/createReleaseCandidate"
and item[4]!={}
]
assert len(release_calls)==1
assert release_calls[0][1]=="POST"
assert release_calls[0][2]=="/createReleaseCandidate"