feat(869-c4): activation version-coupling assertion (Part of #869)
Part of #869 Mos (id-11) Gate-16 merge: independent APPROVE @90eb48fa (fail-closed identity locks byte-unchanged verified), author id2 != approver id11, clean mosaic-coder author, CI green wp1992. #869 Point-1 CODE COMPLETE (C1/C3/C5/C2/C4). Co-authored-by: jason.woltje <jason@diversecanvas.com> Co-committed-by: jason.woltje <jason@diversecanvas.com>
This commit was merged in pull request #881.
This commit is contained in:
@@ -47,6 +47,22 @@ const piLifecyclePath = join(frameworkRoot, 'runtime/pi/lease-lifecycle.ts');
|
||||
const prdyInitPath = join(frameworkRoot, 'tools/prdy/prdy-init.sh');
|
||||
const prdyUpdatePath = join(frameworkRoot, 'tools/prdy/prdy-update.sh');
|
||||
const remediationHandlerPath = join(frameworkRoot, 'tools/qa/remediation-hook-handler.sh');
|
||||
|
||||
// C4 (#869 Point-1): launch-runtime.py now asserts, before anything else,
|
||||
// that the CLI's advertised lease-activation capability (normally read via
|
||||
// the hidden `mosaic __lease-capability` subcommand) matches what
|
||||
// enforcement expects — see framework/tools/lease-broker/
|
||||
// activation_version_gate.py. This suite drives launch-runtime.py directly
|
||||
// as a subprocess (never through the real `mosaic` CLI), so — exactly like
|
||||
// the fake broker (daemon.py) and fake `claude` binaries already used
|
||||
// below — it must supply a fake activation-capability probe rather than
|
||||
// depend on a real `mosaic` binary being on PATH. `MOSAIC_LEASE_VERSION_PROBE_COMMAND`
|
||||
// is launch-runtime.py's injection point for that fake; this literal
|
||||
// {name, version} pair must be kept in sync with
|
||||
// `EXPECTED_ACTIVATION_CAPABILITY` (activation_version_gate.py) and
|
||||
// `LEASE_ACTIVATION_CAPABILITY` (lease-activation-probe.ts) — all three
|
||||
// currently agree on v1.
|
||||
const leaseCapabilityProbeStub = `python3 -c "import json; print(json.dumps({'name': 'lease-runtime-activation', 'version': 1}))"`;
|
||||
const children: ChildProcess[] = [];
|
||||
const temporaryRoots: string[] = [];
|
||||
|
||||
@@ -184,6 +200,7 @@ raise SystemExit(0 if len(session_id) == 64 and denied else 1)
|
||||
MOSAIC_PRDY_RUNTIME: 'claude',
|
||||
MOSAIC_LEASE_BROKER_SOCKET: socket,
|
||||
MOSAIC_RUNTIME_GENERATION: '1',
|
||||
MOSAIC_LEASE_VERSION_PROBE_COMMAND: leaseCapabilityProbeStub,
|
||||
},
|
||||
});
|
||||
}
|
||||
@@ -743,6 +760,7 @@ describe('whole mutator-class lease gate', () => {
|
||||
...process.env,
|
||||
MOSAIC_LEASE_BROKER_SOCKET: socket,
|
||||
MOSAIC_RUNTIME_GENERATION: '1',
|
||||
MOSAIC_LEASE_VERSION_PROBE_COMMAND: leaseCapabilityProbeStub,
|
||||
},
|
||||
},
|
||||
);
|
||||
@@ -761,6 +779,7 @@ describe('whole mutator-class lease gate', () => {
|
||||
...process.env,
|
||||
MOSAIC_LEASE_BROKER_SOCKET: join(tmpdir(), 'missing-mosaic-broker.sock'),
|
||||
MOSAIC_RUNTIME_GENERATION: '1',
|
||||
MOSAIC_LEASE_VERSION_PROBE_COMMAND: leaseCapabilityProbeStub,
|
||||
},
|
||||
},
|
||||
);
|
||||
@@ -878,6 +897,7 @@ raise SystemExit(0 if len(session_id) == 64 and hook_present and observers_prese
|
||||
PATH: `${binDir}:${process.env.PATH ?? ''}`,
|
||||
MOSAIC_LEASE_BROKER_SOCKET: socket,
|
||||
MOSAIC_RUNTIME_GENERATION: '1',
|
||||
MOSAIC_LEASE_VERSION_PROBE_COMMAND: leaseCapabilityProbeStub,
|
||||
},
|
||||
proxyGate: () =>
|
||||
Promise.resolve({
|
||||
|
||||
@@ -39,6 +39,18 @@ LAUNCHER = load_tool("lease_runtime_launcher", "launch-runtime.py")
|
||||
GATE = load_tool("lease_mutator_gate", "mutator-gate.py")
|
||||
|
||||
|
||||
def matching_activation_probe(*_args: object, **_kwargs: object) -> dict[str, object]:
|
||||
"""Fake activation-capability probe matching what enforcement expects
|
||||
(C4, #869 Point-1). Injected into `LAUNCHER.main()` calls below that are
|
||||
exercising OTHER branches (registration, exec, generation init, ...) so
|
||||
the new version-coupling gate — which runs before those — never blocks
|
||||
on host state (no real `mosaic` CLI on PATH in a test sandbox). The
|
||||
version-coupling gate's OWN behavior (match/mismatch/absent) is covered
|
||||
by its dedicated red-first tests in `version_coupling_unittest.py`."""
|
||||
|
||||
return dict(LAUNCHER.EXPECTED_ACTIVATION_CAPABILITY)
|
||||
|
||||
|
||||
class FakeSocket:
|
||||
def __init__(self, *chunks: bytes):
|
||||
self.chunks = list(chunks)
|
||||
@@ -95,6 +107,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
request=request,
|
||||
execute=execute,
|
||||
initialize_generation=initialize_generation,
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
)
|
||||
|
||||
self.assertEqual(result, 0)
|
||||
@@ -127,6 +140,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
request=lambda *_args: {"ok": True, "session_id": "e" * 64},
|
||||
execute=lambda *args: executed.append(args),
|
||||
initialize_generation=lambda *_args: None,
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
)
|
||||
self.assertEqual(result, 0)
|
||||
self.assertEqual(
|
||||
@@ -153,6 +167,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
request=lambda *_args: {"ok": True, "session_id": "f" * 64},
|
||||
execute=lambda *args: executed.append(args),
|
||||
initialize_generation=lambda *_args: None,
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
)
|
||||
self.assertEqual(result, 0)
|
||||
self.assertEqual(executed[0][0:2], ("pi", ["pi", "--print", "hello"]))
|
||||
@@ -188,6 +203,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
environ=environment,
|
||||
request=lambda *_args, value=reply: value,
|
||||
execute=lambda *args: executed.append(args),
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
)
|
||||
self.assertEqual(result, 1)
|
||||
self.assertEqual(executed, [])
|
||||
@@ -203,6 +219,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
initialize_generation=lambda *_args: (_ for _ in ()).throw(
|
||||
OSError("unsafe state")
|
||||
),
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
),
|
||||
1,
|
||||
)
|
||||
@@ -220,6 +237,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
environ={"MOSAIC_LEASE_BROKER_SOCKET": "/x"},
|
||||
request=request,
|
||||
execute=lambda *_args: self.fail("must not execute"),
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
),
|
||||
1,
|
||||
)
|
||||
@@ -233,6 +251,7 @@ class LaunchRuntimeTest(unittest.TestCase):
|
||||
request=lambda *_args: {"ok": True, "session_id": "c" * 64},
|
||||
execute=lambda *_args: (_ for _ in ()).throw(OSError("missing")),
|
||||
initialize_generation=lambda *_args: None,
|
||||
probe_activation_capability=matching_activation_probe,
|
||||
),
|
||||
1,
|
||||
)
|
||||
|
||||
287
packages/mosaic/src/mutator-gate/version_coupling_unittest.py
Normal file
287
packages/mosaic/src/mutator-gate/version_coupling_unittest.py
Normal file
@@ -0,0 +1,287 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Red-first tests for issue #869 Point-1 C4 — the enforcement/activation
|
||||
version-coupling assertion at the `launch-runtime.py` seam.
|
||||
|
||||
Root cause under test (#828 restated): the lease broker's ENFORCEMENT half
|
||||
(this toolkit) and its ACTIVATION half (`execLeaseGatedRuntime()` in
|
||||
`launch.ts`, chained through `launch-runtime.py`) shipped on different
|
||||
channels and drifted. C1 (`lease-activation-probe.ts`) gave the activation
|
||||
half a versioned, machine-checkable identity
|
||||
(`LEASE_ACTIVATION_CAPABILITY`, printed via the hidden CLI subcommand
|
||||
`mosaic __lease-capability`). C4 (this module + `activation_version_gate.py`)
|
||||
is the assertion that actually USES that identity: enforcement must refuse
|
||||
to proceed — loudly, with an actionable remediation message, never a
|
||||
silent pass — unless the activation capability it observes exactly matches
|
||||
what enforcement expects.
|
||||
|
||||
Every case here drives the seam with injected fakes/stubs (a fake
|
||||
`probe_activation_capability` callable at the `launch-runtime.py` level, or
|
||||
a fake `run` transport at the `activation_version_gate` level) — never a
|
||||
real broker, a real installed CLI, or a real `mosaic` binary on PATH.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib.util
|
||||
import io
|
||||
import subprocess
|
||||
import sys
|
||||
import unittest
|
||||
from contextlib import redirect_stderr
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
TOOLS_DIR = Path(__file__).parents[2] / "framework/tools/lease-broker"
|
||||
if str(TOOLS_DIR) not in sys.path:
|
||||
sys.path.insert(0, str(TOOLS_DIR))
|
||||
|
||||
|
||||
def load_tool(module_name: str, filename: str):
|
||||
spec = importlib.util.spec_from_file_location(module_name, TOOLS_DIR / filename)
|
||||
if spec is None or spec.loader is None:
|
||||
raise RuntimeError(f"unable to load {filename}")
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(module)
|
||||
return module
|
||||
|
||||
|
||||
# Loaded under distinct module names from runtime_tools_unittest.py's own
|
||||
# LAUNCHER/GATE loads — importlib.util.module_from_spec() gives each load a
|
||||
# fresh module object regardless of name collisions, but distinct names keep
|
||||
# tracebacks/debugging unambiguous when both files run in the same process.
|
||||
LAUNCHER = load_tool("lease_runtime_launcher_version_coupling", "launch-runtime.py")
|
||||
VERSION_GATE = load_tool("lease_activation_version_gate_test", "activation_version_gate.py")
|
||||
|
||||
|
||||
def matching_capability() -> dict[str, object]:
|
||||
return dict(VERSION_GATE.EXPECTED_ACTIVATION_CAPABILITY)
|
||||
|
||||
|
||||
class AssertActivationCapabilityMatchesTest(unittest.TestCase):
|
||||
"""Unit-level coverage of `activation_version_gate.py`'s own assertion,
|
||||
isolated from the launch-runtime.py seam it is wired into below."""
|
||||
|
||||
def test_matching_capability_passes_silently(self) -> None:
|
||||
VERSION_GATE.assert_activation_capability_matches(matching_capability())
|
||||
# No exception is the assertion; nothing further to check.
|
||||
|
||||
def test_absent_capability_fails_closed_not_silent_pass(self) -> None:
|
||||
with self.assertRaises(VERSION_GATE.VersionCouplingError) as raised:
|
||||
VERSION_GATE.assert_activation_capability_matches(None)
|
||||
message = str(raised.exception)
|
||||
self.assertIn("#869", message)
|
||||
self.assertIn("upgrade", message.lower())
|
||||
|
||||
def test_version_mismatch_message_is_actionable(self) -> None:
|
||||
expected = {"name": "lease-runtime-activation", "version": 1}
|
||||
mismatched = {"name": "lease-runtime-activation", "version": 2}
|
||||
with self.assertRaises(VERSION_GATE.VersionCouplingError) as raised:
|
||||
VERSION_GATE.assert_activation_capability_matches(mismatched, expected)
|
||||
message = str(raised.exception)
|
||||
self.assertIn("v2", message)
|
||||
self.assertIn("v1", message)
|
||||
self.assertIn("#869", message)
|
||||
self.assertIn("upgrade", message.lower())
|
||||
self.assertIn("version skew", message.lower())
|
||||
|
||||
def test_name_mismatch_fails_loud(self) -> None:
|
||||
expected = {"name": "lease-runtime-activation", "version": 1}
|
||||
mismatched = {"name": "some-other-capability", "version": 1}
|
||||
with self.assertRaises(VERSION_GATE.VersionCouplingError) as raised:
|
||||
VERSION_GATE.assert_activation_capability_matches(mismatched, expected)
|
||||
message = str(raised.exception)
|
||||
self.assertIn("some-other-capability", message)
|
||||
self.assertIn("lease-runtime-activation", message)
|
||||
self.assertIn("#869", message)
|
||||
|
||||
def test_reversed_drift_newer_activation_than_enforcement_expects_also_fails(self) -> None:
|
||||
# A build/deploy where ACTIVATION shipped ahead of ENFORCEMENT is
|
||||
# exactly as much version skew as the reverse (#828's actual shape
|
||||
# was enforcement ahead of activation) — the assertion must not special
|
||||
# case direction.
|
||||
expected = {"name": "lease-runtime-activation", "version": 1}
|
||||
newer_activation = {"name": "lease-runtime-activation", "version": 2}
|
||||
with self.assertRaises(VERSION_GATE.VersionCouplingError):
|
||||
VERSION_GATE.assert_activation_capability_matches(newer_activation, expected)
|
||||
|
||||
|
||||
class ProbeActivationCapabilityTest(unittest.TestCase):
|
||||
"""Coverage of the probe's command resolution and fail-closed transport
|
||||
handling — never spawns a real `mosaic` process."""
|
||||
|
||||
def test_returns_none_when_mosaic_is_not_resolvable_on_path(self) -> None:
|
||||
result = VERSION_GATE.default_probe_activation_capability(
|
||||
{"PATH": "/nonexistent-bin-dir-for-869-c4-test"}
|
||||
)
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_override_command_is_parsed_and_the_probe_subcommand_is_not_double_appended(
|
||||
self,
|
||||
) -> None:
|
||||
captured: list[list[str]] = []
|
||||
|
||||
class FakeCompleted:
|
||||
returncode = 0
|
||||
stdout = '{"name": "lease-runtime-activation", "version": 1}'
|
||||
|
||||
def fake_run(argv: list[str], **_kwargs: object) -> FakeCompleted:
|
||||
captured.append(argv)
|
||||
return FakeCompleted()
|
||||
|
||||
result = VERSION_GATE.default_probe_activation_capability(
|
||||
{VERSION_GATE.MOSAIC_COMMAND_OVERRIDE_VAR: "/fake/mosaic __lease-capability"},
|
||||
run=fake_run,
|
||||
)
|
||||
self.assertEqual(result, {"name": "lease-runtime-activation", "version": 1})
|
||||
self.assertEqual(captured, [["/fake/mosaic", "__lease-capability"]])
|
||||
|
||||
def test_fails_closed_on_nonzero_exit_malformed_json_and_missing_fields(self) -> None:
|
||||
class NonZeroExit:
|
||||
returncode = 1
|
||||
stdout = '{"name": "lease-runtime-activation", "version": 1}'
|
||||
|
||||
class MalformedOutput:
|
||||
returncode = 0
|
||||
stdout = "not-json"
|
||||
|
||||
class MissingVersion:
|
||||
returncode = 0
|
||||
stdout = '{"name": "lease-runtime-activation"}'
|
||||
|
||||
class WrongShapeVersion:
|
||||
returncode = 0
|
||||
stdout = '{"name": "lease-runtime-activation", "version": "1"}'
|
||||
|
||||
class BooleanVersion:
|
||||
# bool is a subclass of int in Python; must not be accepted as
|
||||
# a version number.
|
||||
returncode = 0
|
||||
stdout = '{"name": "lease-runtime-activation", "version": true}'
|
||||
|
||||
for fake in (
|
||||
NonZeroExit(),
|
||||
MalformedOutput(),
|
||||
MissingVersion(),
|
||||
WrongShapeVersion(),
|
||||
BooleanVersion(),
|
||||
):
|
||||
with self.subTest(stdout=fake.stdout, returncode=fake.returncode):
|
||||
result = VERSION_GATE.default_probe_activation_capability(
|
||||
{VERSION_GATE.MOSAIC_COMMAND_OVERRIDE_VAR: "/fake/mosaic"},
|
||||
run=lambda *_a, fake=fake, **_kw: fake,
|
||||
)
|
||||
self.assertIsNone(result)
|
||||
|
||||
def test_fails_closed_on_timeout_and_transport_error(self) -> None:
|
||||
def timeout_run(*_args: object, **_kwargs: object) -> None:
|
||||
raise subprocess.TimeoutExpired(cmd="mosaic", timeout=2.0)
|
||||
|
||||
def oserror_run(*_args: object, **_kwargs: object) -> None:
|
||||
raise OSError("no such file or directory")
|
||||
|
||||
for run_fake in (timeout_run, oserror_run):
|
||||
with self.subTest(run=run_fake.__name__):
|
||||
result = VERSION_GATE.default_probe_activation_capability(
|
||||
{VERSION_GATE.MOSAIC_COMMAND_OVERRIDE_VAR: "/fake/mosaic"},
|
||||
run=run_fake,
|
||||
)
|
||||
self.assertIsNone(result)
|
||||
|
||||
|
||||
class LaunchRuntimeVersionCouplingSeamTest(unittest.TestCase):
|
||||
"""End-to-end (still fully faked) coverage of the seam as wired into
|
||||
`launch-runtime.py`'s `main()` — the strongest natural enforcement point
|
||||
per the C4 card, run before any broker registration."""
|
||||
|
||||
def _run(self, *, probe):
|
||||
calls: dict[str, object] = {}
|
||||
|
||||
def request(_path: Path, payload: dict[str, object]) -> dict[str, object]:
|
||||
calls["registered"] = True
|
||||
calls["request"] = payload
|
||||
return {"ok": True, "session_id": "a" * 64}
|
||||
|
||||
def execute(command: str, argv: list[str], environment: dict[str, str]) -> None:
|
||||
calls["executed"] = (command, argv, environment)
|
||||
|
||||
def initialize_generation(_path: Path, _generation: int) -> None:
|
||||
calls["generation_initialized"] = True
|
||||
|
||||
stderr = io.StringIO()
|
||||
with redirect_stderr(stderr):
|
||||
result = LAUNCHER.main(
|
||||
["--runtime", "claude", "--", "claude", "--print", "hello"],
|
||||
environ={"MOSAIC_LEASE_BROKER_SOCKET": "/run/test/broker.sock"},
|
||||
request=request,
|
||||
execute=execute,
|
||||
initialize_generation=initialize_generation,
|
||||
probe_activation_capability=probe,
|
||||
)
|
||||
return result, stderr.getvalue(), calls
|
||||
|
||||
def test_matching_activation_version_passes_and_the_gate_proceeds(self) -> None:
|
||||
result, stderr_text, calls = self._run(probe=lambda *_a, **_kw: matching_capability())
|
||||
self.assertEqual(result, 0)
|
||||
self.assertEqual(stderr_text, "")
|
||||
self.assertTrue(calls.get("registered"))
|
||||
self.assertIn("executed", calls)
|
||||
|
||||
def test_version_mismatch_fails_loud_denies_and_never_registers_or_execs(self) -> None:
|
||||
expected = LAUNCHER.EXPECTED_ACTIVATION_CAPABILITY
|
||||
mismatched = {"name": expected["name"], "version": expected["version"] + 1}
|
||||
result, stderr_text, calls = self._run(probe=lambda *_a, **_kw: mismatched)
|
||||
|
||||
self.assertEqual(result, LAUNCHER.EXIT_VERSION_SKEW)
|
||||
self.assertNotEqual(result, 0)
|
||||
self.assertIn("#869", stderr_text)
|
||||
self.assertIn(f"v{mismatched['version']}", stderr_text)
|
||||
self.assertIn(f"v{expected['version']}", stderr_text)
|
||||
self.assertIn("upgrade", stderr_text.lower())
|
||||
# Never reaches broker registration or exec — the version gate is a
|
||||
# hard stop, not advisory.
|
||||
self.assertNotIn("registered", calls)
|
||||
self.assertNotIn("executed", calls)
|
||||
|
||||
def test_name_mismatch_fails_loud(self) -> None:
|
||||
expected = LAUNCHER.EXPECTED_ACTIVATION_CAPABILITY
|
||||
mismatched = {"name": "some-other-capability", "version": expected["version"]}
|
||||
result, stderr_text, calls = self._run(probe=lambda *_a, **_kw: mismatched)
|
||||
|
||||
self.assertEqual(result, LAUNCHER.EXIT_VERSION_SKEW)
|
||||
self.assertIn("#869", stderr_text)
|
||||
self.assertIn("some-other-capability", stderr_text)
|
||||
self.assertNotIn("registered", calls)
|
||||
self.assertNotIn("executed", calls)
|
||||
|
||||
def test_absent_activation_capability_fails_closed_not_a_silent_pass(self) -> None:
|
||||
result, stderr_text, calls = self._run(probe=lambda *_a, **_kw: None)
|
||||
|
||||
self.assertEqual(result, LAUNCHER.EXIT_VERSION_SKEW)
|
||||
self.assertNotEqual(result, 0)
|
||||
self.assertIn("#869", stderr_text)
|
||||
self.assertNotIn("registered", calls)
|
||||
self.assertNotIn("executed", calls)
|
||||
|
||||
def test_version_gate_runs_before_and_independently_of_broker_registration(self) -> None:
|
||||
def request_must_not_be_called(*_args: object, **_kwargs: object) -> dict[str, object]:
|
||||
self.fail("broker must not be contacted when activation version is mismatched")
|
||||
|
||||
stderr = io.StringIO()
|
||||
with redirect_stderr(stderr):
|
||||
result = LAUNCHER.main(
|
||||
["--runtime", "claude", "--", "claude"],
|
||||
environ={"MOSAIC_LEASE_BROKER_SOCKET": "/run/test/broker.sock"},
|
||||
request=request_must_not_be_called,
|
||||
probe_activation_capability=lambda *_a, **_kw: None,
|
||||
)
|
||||
self.assertEqual(result, LAUNCHER.EXIT_VERSION_SKEW)
|
||||
|
||||
def test_dedicated_exit_code_never_collides_with_usage_or_registration_codes(self) -> None:
|
||||
# Distinctness guard: a version-skew denial must never be mistaken
|
||||
# for the pre-existing usage error (64) or registration/exec
|
||||
# fail-closed code (1) this script already owns.
|
||||
self.assertNotIn(LAUNCHER.EXIT_VERSION_SKEW, (0, 1, 64))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user