NK-WP-0056-T12 done: pilot operations; synthetic rotation and revert pass
Some checks are pending
CI Smoke / host-smoke (push) Waiting to run
CI Smoke / container-smoke (push) Waiting to run

operations.py: OpenBao KV v2 CAS, LLDAP self-rotation (forward and revert),
ExternalSecret force-sync and status, rollout restart (RolloutFailed is a
definite failure), pilot checks. synthetic_pilot.py on the T08 stack plus
OpenBao 2.5.4 with CCR-2026-0058's policy: rotation completed; a one-off wrong
delivery reverted in declared order with the earlier value restored.

Runner: revert steps run in declared order (BEA-10), definite failures revert,
unknown outcomes stop, receipts carry error types. Found and corrected (in
railiance-platform) CCR-2026-0058's required_parameters refusing reads.
Packaging moved to new T13. 29 executor tests.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

Assistant: claude-code
Assistant-Model: opus
Assistant-Process: 994874@bnt-lap001
Assistant-Session: 6017c416-d619-47eb-bd1a-f670a02d7d87
This commit is contained in:
tegwick 2026-10-31 16:24:17 +01:00
parent 9b7701a32a
commit db56d8468e
11 changed files with 1088 additions and 33 deletions

View file

@ -299,11 +299,12 @@ class FailureTests(Base):
self.w.fail_check["eso-synced"] = 1
result = self.run_it()
self.assertEqual(result["outcome"], "reverted", result)
self.assertEqual(self.ops(), ["generate", "set-directory", "deliver", "redeliver", "restore-directory", "restore-kv"])
# declared recovery order, only for steps that ran (restart did not run, so no restart-again)
self.assertEqual(self.ops(), ["generate", "set-directory", "deliver", "restore-kv", "restore-directory", "redeliver"])
data = result["receipt"]["data"]
self.assertTrue(data["reverted"])
reverts = [x for x in data["steps"] if x["kind"] == "revert"]
self.assertEqual([x["checks"][0]["id"] for x in reverts], ["eso-synced", "bind-signs-in", "kv-advanced"])
self.assertEqual([x["checks"][0]["id"] for x in reverts], ["kv-advanced", "bind-signs-in", "eso-synced"])
self.assertTrue(all(x["outcome"] == "done" for x in reverts))
self.assertEqual(data["attempts"], 1)
@ -319,10 +320,21 @@ class FailureTests(Base):
def test_revert_whose_check_fails_counts_as_failed(self):
self.doc = synthetic_admission(self.root, lambda s: s["budget"].update(attempts=1))
self.w = World(self.doc, self.clock)
self.w.fail_check["eso-synced"] = 2 # the forward check and the revert's own check
self.w.fail_check["eso-synced"] = 1
self.w.fail_check["kv-advanced"] = 0
original = self.w.check
calls = {"kv": 0}
def check(c, ctx): # kv-advanced passes forward, fails on the revert
if c["id"] == "kv-advanced":
calls["kv"] += 1
if calls["kv"] == 2:
self.w.calls.append("check:kv-advanced")
return False
return original(c, ctx)
self.w.check = check
result = self.run_it()
self.assertEqual(result["outcome"], "revert_failed")
self.assertNotIn("restore-directory", self.ops())
self.assertNotIn("restore-directory", self.ops()) # stop at the failed revert
def test_failed_revert_stops_and_alerts(self):
self.w.fail_check["eso-synced"] = 1
@ -330,7 +342,7 @@ class FailureTests(Base):
result = self.run_it()
self.assertEqual(result["outcome"], "revert_failed")
self.assertIn("revert_failed", self.w.alerts)
self.assertNotIn("restore-kv", self.ops()) # stop at the failed revert, do not continue blindly
self.assertNotIn("redeliver", self.ops()) # stop at the failed revert, do not continue blindly
def test_unknown_outcome_stops_without_revert(self):
self.w.unknown_op = {"eso.force-sync"}
@ -340,6 +352,23 @@ class FailureTests(Base):
self.assertFalse(result["receipt"]["data"]["reverted"])
self.assertIn("unknown", self.w.alerts)
def test_definite_failure_reverts_like_a_failed_check(self):
self.doc = synthetic_admission(self.root, lambda s: s["budget"].update(attempts=1))
self.w = World(self.doc, self.clock)
original = self.w.op
def op(step, ctx):
if step["id"] == "restart":
self.w.calls.append("restart")
raise X.StepFailed("never became ready")
return original(step, ctx)
self.w.op = op
result = self.run_it()
self.assertEqual(result["outcome"], "reverted")
self.assertEqual(self.ops(), ["generate", "set-directory", "deliver", "restart",
"restore-kv", "restore-directory", "redeliver", "restart-again"])
restart = next(s for s in result["receipt"]["data"]["steps"] if s["id"] == "restart")
self.assertEqual((restart["outcome"], restart["error_type"]), ("failed", "StepFailed"))
def test_budget_exhausted_reverts(self):
self.w.slow_op = 700.0 # wall_time_seconds is 1200
result = self.run_it()

View file

@ -0,0 +1,133 @@
"""Kubernetes adapters of the pilot operations against a fake API server (NK-WP-0056-T12). No cluster."""
from __future__ import annotations
import datetime as dt
import importlib.util
import json
import pathlib
import sys
import tempfile
import threading
import unittest
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
HERE = pathlib.Path(__file__).resolve().parent
spec = importlib.util.spec_from_file_location("operations", HERE.parent / "operations.py")
OPS = importlib.util.module_from_spec(spec)
sys.modules["operations"] = OPS
spec.loader.exec_module(OPS)
ES = "/apis/external-secrets.io/v1/namespaces/sso/externalsecrets/authelia-secrets"
DEP = "/apis/apps/v1/namespaces/sso/deployments/authelia"
T0 = dt.datetime(2026, 11, 3, 9, 30, tzinfo=dt.UTC)
class Api:
def __init__(self):
self.patches = []
self.auth = []
self.es_status = {"conditions": [{"type": "Ready", "status": "True"}], "refreshTime": "2026-11-03T09:29:00Z"}
self.dep = {"metadata": {"generation": 5}, "spec": {"replicas": 1},
"status": {"observedGeneration": 5, "replicas": 1, "updatedReplicas": 1, "availableReplicas": 1}}
self.gets_until_ready = 0
self.forbidden = False
def serve(api: Api):
class Handler(BaseHTTPRequestHandler):
def _send(self, code, body):
raw = json.dumps(body).encode()
self.send_response(code)
self.send_header("Content-Type", "application/json")
self.send_header("Content-Length", str(len(raw)))
self.end_headers()
self.wfile.write(raw)
def do_GET(self):
api.auth.append(self.headers.get("Authorization"))
if api.forbidden:
return self._send(403, {"kind": "Status"})
if self.path == ES:
return self._send(200, {"status": api.es_status})
if self.path == DEP:
if api.gets_until_ready > 0:
api.gets_until_ready -= 1
return self._send(200, {**api.dep, "status": {**api.dep["status"], "updatedReplicas": 0,
"unavailableReplicas": 1}})
return self._send(200, api.dep)
self._send(404, {})
def do_PATCH(self):
api.patches.append((self.path, self.headers.get("Content-Type"),
json.loads(self.rfile.read(int(self.headers["Content-Length"])))))
if api.forbidden:
return self._send(403, {"kind": "Status"})
if self.path == DEP:
api.dep["metadata"]["generation"] += 1
api.dep["status"]["observedGeneration"] = api.dep["metadata"]["generation"]
self._send(200, {})
def log_message(self, *a):
return
server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
threading.Thread(target=server.serve_forever, kwargs={"poll_interval": 0.02}, daemon=True).start()
return server
class KubeTests(unittest.TestCase):
def setUp(self):
self.api = Api()
self.server = serve(self.api)
self.addCleanup(self.server.shutdown)
tmp = tempfile.TemporaryDirectory()
self.addCleanup(tmp.cleanup)
token = pathlib.Path(tmp.name) / "token"
token.write_text("synthetic-sa-token\n")
self.kube = OPS.Kube(api=f"http://127.0.0.1:{self.server.server_port}", token_file=str(token), ca_file=None)
def test_force_sync_patches_only_the_annotation(self):
delivery = OPS.KubeDelivery(self.kube, "sso", "authelia-secrets", clock=lambda: T0)
self.assertEqual(delivery.force_sync(), T0)
((path, ctype, body),) = self.api.patches
self.assertEqual((path, ctype), (ES, "application/merge-patch+json"))
self.assertEqual(body, {"metadata": {"annotations": {"force-sync": str(int(T0.timestamp()))}}})
self.assertEqual(self.api.auth, []) # no read before the patch
def test_synced_needs_ready_and_a_refresh_after_the_sync(self):
delivery = OPS.KubeDelivery(self.kube, "sso", "authelia-secrets")
self.assertFalse(delivery.synced(T0)) # refreshed before T0
self.api.es_status["refreshTime"] = "2026-11-03T09:30:05Z"
self.assertTrue(delivery.synced(T0))
self.api.es_status["conditions"][0]["status"] = "False"
self.assertFalse(delivery.synced(T0))
def test_restart_patches_restarted_at_and_waits_for_the_rollout(self):
self.api.gets_until_ready = 2
restart = OPS.KubeRestart(self.kube, "sso", "authelia", timeout=10, poll=0.01, clock=lambda: T0)
restart.restart()
((path, _, body),) = self.api.patches
self.assertEqual(path, DEP)
self.assertEqual(body["spec"]["template"]["metadata"]["annotations"]["kubectl.kubernetes.io/restartedAt"],
"2026-11-03T09:30:00Z")
self.assertEqual(self.api.gets_until_ready, 0)
def test_rollout_that_never_becomes_ready_is_a_definite_failure(self):
self.api.gets_until_ready = 10 ** 6
ticks = iter(range(10 ** 6))
restart = OPS.KubeRestart(self.kube, "sso", "authelia", timeout=5, poll=0, monotonic=lambda: next(ticks),
sleep=lambda s: None)
with self.assertRaises(OPS.RolloutFailed) as caught:
restart.restart()
self.assertTrue(caught.exception.definite_failure)
def test_forbidden_is_an_operation_error_and_sends_the_bearer(self):
self.api.forbidden = True
with self.assertRaises(OPS.OperationError):
OPS.KubeDelivery(self.kube, "sso", "authelia-secrets").synced(T0)
self.assertEqual(self.api.auth, ["Bearer synthetic-sa-token"])
if __name__ == "__main__":
unittest.main()