rein-aharness/tests/test_messages_owner.py
tegwick 3e4c976090
Some checks failed
Governed runtime contract / contract (push) Failing after 23s
Bind the metered owner route to worker leases and sandbox lifecycle
Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a07ff8-19d0-7820-b4d0-1353833cb7fc
2026-09-09 22:24:37 +02:00

191 lines
10 KiB
Python

"""Owner/worker lifecycle; real namespace proof remains explicitly opt-in."""
from dataclasses import replace
from datetime import UTC, datetime, timedelta
import json
import os
from pathlib import Path
from types import SimpleNamespace
from unittest.mock import MagicMock
import pytest
from rein_aharness.execution_cancel import ExecutionCancel
from rein_aharness.messages_owner import MessagesOwner, accepted_lease
from rein_aharness.ops_run_client import ActivityCoreOpsClient, OpsRunConfig
from rein_aharness.request_admission import RequestLedger
from rein_aharness.spend_admission import SpendAdmissionError
from test_spend_admission import ledger as ledger, run, configured
from test_request_admission import policy as policy, fake_provider as fake_provider
def claimed():
return replace(run(), state="claimed", lease_until=(datetime.now(UTC) + timedelta(seconds=60)).isoformat())
@pytest.mark.parametrize("fields", [
{"id": "other"}, {"claim_owner": "other"}, {"attempt": 2},
{"state": "open"}, {"lease_until": None}, {"lease_until": "invalid"},
{"lease_until": "2020-01-01T00:00:00Z"},
])
def test_refuse_unaccepted_lease(fields):
item = claimed()
with pytest.raises(SpendAdmissionError):
accepted_lease(item, replace(item, **fields), "worker-1")
def test_worker_requires_owner_before_claim(tmp_path, monkeypatch):
from rein_aharness.claim_loop import process_one
from rein_aharness.close_outbox import CloseOutbox
client = MagicMock(spec=ActivityCoreOpsClient)
client.config = OpsRunConfig(require_request_admission=True)
result = process_one(client, outbox=CloseOutbox(state_dir=tmp_path / "close"))
assert not result.claimed and "not configured" in result.reason
client.claim.assert_not_called()
@pytest.mark.parametrize("cancel_reason", ["lease-loss", "signal", "timeout", None])
def test_owner_closes_and_never_rebinds(ledger, policy, fake_provider, cancel_reason, monkeypatch, tmp_path):
monkeypatch.setenv("XDG_DATA_HOME", str(tmp_path / "data"))
meter = RequestLedger(ledger)
meter.initialize()
item = claimed()
ledger.reserve(item)
cfg = configured(ledger)
provider, seen, _ = fake_provider
owner = MessagesOwner(policy, "dummy-provider-key", f"http://127.0.0.1:{provider.server_port}", True)
profile = SimpleNamespace(credential_route_refs=[], model=SimpleNamespace(model="fixture-model"),
sandbox_profile="profile.bwrap-local")
cancel = ExecutionCancel()
with owner.activate(item, cfg, ledger, profile, cancel) as manager:
binding = manager._messages_route
assert binding.socket_path.is_socket()
if cancel_reason:
cancel.cancel(cancel_reason)
with pytest.raises(SpendAdmissionError, match="revoked"):
meter.reserve_request(binding.token, policy.sha256, 1)
assert not binding.socket_path.exists() and not seen
with pytest.raises(SpendAdmissionError, match="revoked"):
meter.reserve_request(binding.token, policy.sha256, 1)
assert ledger.status()["reservations"][0]["state"] == "held"
@pytest.mark.skipif(os.environ.get("REIN_REAL_BWRAP") != "1", reason="opt-in kernel namespace proof")
def test_real_owner_route_confinement_and_revocation(ledger, policy, fake_provider, tmp_path, monkeypatch):
from sandboxer.models import SandboxCreateRequest, SandboxExecRequest, Consumer
monkeypatch.setenv("SANDBOXER_NO_STATE_HUB", "1")
monkeypatch.setenv("XDG_DATA_HOME", str(tmp_path / "data"))
meter = RequestLedger(ledger)
meter.initialize()
item = claimed()
ledger.reserve(item)
cfg = configured(ledger)
provider, seen, _ = fake_provider
owner = MessagesOwner(policy, "synthetic-provider-key-owner-only", f"http://127.0.0.1:{provider.server_port}", True)
profile = SimpleNamespace(credential_route_refs=[], model=SimpleNamespace(model="fixture-model"),
sandbox_profile="profile.bwrap-local")
consumer = Consumer(actor="agt", project=cfg.execution_project, run_id=item.id)
cancel = ExecutionCancel()
source = tmp_path / "source"
source.mkdir()
(source / "README.md").write_text("No owner state belongs in this tree.\n")
with owner.activate(item, cfg, ledger, profile, cancel) as manager:
binding = manager._messages_route
status = manager.create(SandboxCreateRequest(profile=profile.sandbox_profile,
inputs={"repo": str(source)}, consumer=consumer))
try:
assert status.state.value == "ready", status.error
def execute(code):
return manager.execute(status.sandbox_id, SandboxExecRequest(
command=["python3", "-c", code], consumer=consumer, timeout_seconds=10))
probe = execute("""import os, json, socket
from pathlib import Path
blocked = []
for address in [("127.0.0.1", PROVIDER_PORT), ("1.1.1.1", 443)]:
try:
s = socket.create_connection(address, timeout=0.2); s.close(); blocked.append(False)
except OSError: blocked.append(True)
print(json.dumps({"private_absent": not Path(PRIVATE).exists(),
"owner_state_through_proc_absent": not Path(OWNER_PROCESS).exists(),
"pid_namespace": os.readlink("/proc/self/ns/pid"),
"network_namespace": os.readlink("/proc/self/ns/net"),
"interfaces": sorted(p.name for p in Path("/sys/class/net").glob("*")) if Path("/sys/class/net").exists() else [line.split(':')[0].strip() for line in Path('/proc/net/dev').read_text().splitlines()[2:]],
"direct_blocked": blocked, "proxy_absent": not any("proxy" in k.lower() for k in os.environ),
"token_is_opaque": len(os.environ["ANTHROPIC_API_KEY"]) == 43}))
""".replace("PROVIDER_PORT", str(provider.server_port)).replace("PRIVATE", repr(str(ledger.path.parent))).replace("OWNER_PROCESS", repr(f"/proc/{os.getpid()}/root/{str(ledger.path.parent).lstrip(chr(47))}")))
assert probe.exit_code == 0, probe.stderr
evidence = json.loads(probe.stdout)
assert evidence["private_absent"] and evidence["owner_state_through_proc_absent"], evidence
assert evidence["direct_blocked"] == [True, True] and evidence["proxy_absent"]
assert evidence["token_is_opaque"] and evidence["interfaces"] == ["lo"]
assert evidence["network_namespace"] != os.readlink("/proc/self/ns/net")
assert evidence["pid_namespace"] != os.readlink("/proc/self/ns/pid")
request_code = """import os,json,http.client,urllib.parse
u=urllib.parse.urlsplit(os.environ['ANTHROPIC_BASE_URL'])
c=http.client.HTTPConnection(u.hostname,u.port,timeout=5)
c.request('POST','/v1/messages',json.dumps({'model':'fixture-model','max_tokens':1000,'stream':True,'messages':[{'role':'user','content':'synthetic request'}]}),{'Content-Type':'application/json','x-api-key':os.environ['ANTHROPIC_API_KEY']})
r=c.getresponse(); print(json.dumps({'status':r.status,'stopped':b'message_stop' in r.read()})); c.close()
"""
response = execute(request_code)
assert response.exit_code == 0, response.stderr
assert json.loads(response.stdout) == {"status": 200, "stopped": True}
assert len(seen) == 1 and seen[0]["key"] == "synthetic-provider-key-owner-only"
assert meter.status()[0]["state"] == "charged"
# This hook is the same callback used by the worker heartbeat monitor.
cancel.cancel("lease-loss")
response = execute(request_code)
assert json.loads(response.stdout)["status"] == 400
assert len(seen) == 1
assert binding.token not in json.dumps(status.model_dump(mode="json"))
assert "synthetic-provider-key-owner-only" not in probe.stdout + response.stdout
if directory := os.environ.get("REIN_OWNER_PROOF_OUTPUT"):
out = Path(directory); out.mkdir(parents=True, exist_ok=True)
(out / "owner-route.json").write_text(json.dumps({
"scope": "real local bwrap owner transport; deterministic provider, synthetic key and lease",
**evidence, "upstream_requests": len(seen), "revoked_request_status": 400,
"request_reservations": meter.status(), "factory_attempts": 0,
}, indent=2) + "\n")
finally:
manager.destroy(status.sandbox_id)
assert not Path(status.inputs["workspace_dir"]).exists()
assert not binding.socket_path.exists()
@pytest.mark.parametrize("valid", [False, True])
def test_claim_loop_uses_accepted_heartbeat_lease(ledger, policy, fake_provider, tmp_path, monkeypatch, valid):
from rein_aharness.claim_loop import process_one
from rein_aharness.close_outbox import CloseOutbox
client = MagicMock(spec=ActivityCoreOpsClient)
client.config = configured(ledger)
client.config.messages_owner = MessagesOwner(policy, "dummy")
item = claimed()
client.claim.return_value = [item]
expiry = (datetime.now(UTC) + timedelta(seconds=30)).isoformat() if valid else None
client.heartbeat.return_value = replace(item, lease_until=expiry)
process = MagicMock(return_value=SimpleNamespace(claimed=True))
monkeypatch.setattr("rein_aharness.claim_loop._process_profiled_run", process)
result = process_one(client, outbox=CloseOutbox(state_dir=tmp_path / "close"))
if valid:
assert item.lease_until == expiry
process.assert_called_once()
else:
assert "accepted queue lease" in result.reason
process.assert_not_called()
def test_lease_expiry_revokes_without_a_heartbeat(ledger, policy, tmp_path, monkeypatch):
monkeypatch.setenv("XDG_DATA_HOME", str(tmp_path / "data"))
meter = RequestLedger(ledger)
meter.initialize()
item = claimed()
item.lease_until = (datetime.now(UTC) + timedelta(seconds=0.5)).isoformat()
ledger.reserve(item)
profile = SimpleNamespace(credential_route_refs=[], model=SimpleNamespace(model="fixture-model"),
sandbox_profile="profile.bwrap-local")
cancel = ExecutionCancel()
with MessagesOwner(policy, "dummy").activate(item, configured(ledger), ledger, profile, cancel) as manager:
binding = manager._messages_route
assert cancel.wait(2), "accepted lease deadline was not enforced"
with pytest.raises(SpendAdmissionError):
meter.reserve_request(binding.token, policy.sha256, 1)