Add documented KoKonna failure policy, bounded retries and durable recovery escalation [skip ci]

This commit is contained in:
渡口浪人
2026-10-16 12:25:16 +08:00
parent d2f02d8054
commit a843d4de9b
17 changed files with 873 additions and 70 deletions
+53
View File
@@ -613,6 +613,16 @@
},
"Operation": {
"properties": {
"recovery": {
"anyOf": [
{
"$ref": "#/components/schemas/RecoveryState"
},
{
"type": "null"
}
]
},
"operation_id": {
"type": "string",
"title": "Operation Id"
@@ -1422,5 +1432,48 @@
"type"
],
"title": "AutoCollageContent"
},
"RecoveryState": {
"properties": {
"state": {
"type": "string",
"enum": [
"checking",
"manual_review",
"resolved"
],
"title": "State"
},
"reason": {
"type": "string",
"title": "Reason"
},
"first_checked_at": {
"type": "string",
"title": "First Checked At"
},
"last_checked_at": {
"type": "string",
"title": "Last Checked At"
},
"checks": {
"type": "integer",
"title": "Checks"
},
"requires_manual_review": {
"type": "boolean",
"title": "Requires Manual Review"
}
},
"type": "object",
"required": [
"state",
"reason",
"first_checked_at",
"last_checked_at",
"checks",
"requires_manual_review"
],
"title": "RecoveryState"
}
}
+178 -8
View File
@@ -1,3 +1,4 @@
from types import SimpleNamespace
from unittest.mock import Mock
import pytest
@@ -7,11 +8,28 @@ from pigway_frame_flow.drivers.kokonna.client import KokonnaClient
from pigway_frame_flow.errors import FlowError
@pytest.fixture(autouse=True)
def transport_clock(monkeypatch):
import pigway_frame_flow.drivers.kokonna.client as module
clock = SimpleNamespace(now=0.0, waits=[])
def sleep(seconds):
clock.waits.append(seconds)
clock.now += seconds
monkeypatch.setattr(
module, "time", SimpleNamespace(monotonic=lambda: clock.now, sleep=sleep)
)
return clock
def session(body=None, status=200):
s = Mock()
s.request.return_value.status_code = status
s.request.return_value.json.return_value = body or {}
s.request.return_value.content = b"image"
s.request.return_value.headers = {}
return s
@@ -88,7 +106,7 @@ def test_timeout_redaction_no_retry(write):
c.display(1) if write else c.get_device()
assert "secret" not in str(e.value)
assert e.value.code == ("WRITE_RESULT_UNKNOWN" if write else "CLOUD_UNAVAILABLE")
assert s.request.call_count == 1
assert s.request.call_count == (1 if write else 3)
@pytest.mark.parametrize("status", [401, 429, 500, 530])
@@ -109,15 +127,14 @@ def test_invalid_upload_id(tmp_path):
assert e.value.code == "WRITE_RESULT_UNKNOWN"
def test_rate_budget():
def test_rate_budget(transport_clock):
s = session({"nickname": "x"})
c = KokonnaClient("secret", session=s)
for _ in range(18):
c.get_device()
with pytest.raises(FlowError) as e:
c.get_device()
assert e.value.code == "RATE_LIMITED"
assert s.request.call_count == 18
c.get_device()
assert s.request.call_count == 19
assert transport_clock.waits == [60]
@pytest.mark.parametrize(
@@ -137,7 +154,160 @@ def test_transport_failure_records_safe_category_without_replay(exception, categ
c = KokonnaClient("secret", True, s)
with pytest.raises(FlowError) as error:
c.display(1)
assert error.value.code == "WRITE_RESULT_UNKNOWN"
assert error.value.details == {"transport_error": category}
assert error.value.code == (
"CLOUD_UNAVAILABLE" if category == "connect_timeout" else "WRITE_RESULT_UNKNOWN"
)
assert error.value.details["transport_error"] == category
assert error.value.details["attempts"] == (
3 if category == "connect_timeout" else 1
)
assert "secret" not in str(error.value.details)
assert s.request.call_count == (3 if category == "connect_timeout" else 1)
@pytest.mark.parametrize("write", [False, True])
def test_connect_timeout_retries_then_succeeds(write, transport_clock):
s = session({"success": True})
response = s.request.return_value
s.request.side_effect = [requests.ConnectTimeout("private"), response]
c = KokonnaClient("private", True, s)
c.display(1) if write else c.get_device()
assert s.request.call_count == 2
assert transport_clock.waits == [1]
@pytest.mark.parametrize(
"message,code,kind",
[
("image not found", "NOT_FOUND", "image_not_found"),
("imageId is empty", "INVALID_REQUEST", "invalid_image_id"),
("can not find robot private", "CONFIG_REQUIRED", "device_key_invalid"),
],
)
def test_documented_500_rejection_does_not_lock_or_retry(message, code, kind):
s = session({"message": message}, 500)
c = KokonnaClient("private", True, s)
with pytest.raises(FlowError) as error:
c.display(1)
assert error.value.code == code
assert error.value.details["write_outcome"] == "rejected"
assert error.value.details["failure_kind"] == kind
assert "private" not in str(error.value.details)
assert s.request.call_count == 1
@pytest.mark.parametrize("status", [500, 502, 503, 530])
def test_generic_5xx_read_retries_but_write_never_replays(status):
for write in [False, True]:
s = session({"message": "unknown failure private"}, status)
c = KokonnaClient("private", True, s)
with pytest.raises(FlowError) as error:
c.display(1) if write else c.get_device()
assert s.request.call_count == (1 if write else 3)
assert error.value.code == (
"WRITE_RESULT_UNKNOWN" if write else "CLOUD_UNAVAILABLE"
)
assert "private" not in str(error.value.details)
def test_rate_limit_honors_retry_after_and_closes_response(transport_clock):
s = session({"message": "rate limited"}, 429)
first = s.request.return_value
first.headers = {"Retry-After": "7"}
second = session({"success": True}).request.return_value
s.request.side_effect = [first, second]
KokonnaClient("private", True, s).display(1)
assert s.request.call_count == 2
assert transport_clock.waits == [7]
first.close.assert_called_once()
second.close.assert_called_once()
def test_long_retry_after_preserves_cooldown_without_early_request(transport_clock):
s = session({"message": "rate limited"}, 429)
s.request.return_value.headers = {"Retry-After": "120"}
c = KokonnaClient("private", True, s)
for _ in range(2):
with pytest.raises(FlowError) as error:
c.display(1)
assert error.value.code == "RATE_LIMITED"
assert s.request.call_count == 1
assert transport_clock.waits == []
@pytest.mark.parametrize("header", [None, "bad", "nan", "inf"])
def test_invalid_retry_after_defaults_to_one_minute(header):
from pigway_frame_flow.drivers.kokonna.client import SafeTransport
assert SafeTransport._retry_after(header) == 60
def test_retry_after_accepts_http_date():
from datetime import UTC, datetime, timedelta
from email.utils import format_datetime
from pigway_frame_flow.drivers.kokonna.client import SafeTransport
future = format_datetime(datetime.now(UTC) + timedelta(seconds=30), usegmt=True)
assert 28 <= SafeTransport._retry_after(future) <= 30
def test_invalid_write_response_is_never_retried():
s = session({"success": False, "message": "private"})
with pytest.raises(FlowError) as error:
KokonnaClient("private", True, s).display(1)
assert error.value.code == "WRITE_RESULT_UNKNOWN"
assert error.value.details["failure_kind"] == "invalid_response"
assert s.request.call_count == 1
@pytest.mark.parametrize(
"failure,expected",
[
("connect_timeout", "CLOUD_UNAVAILABLE"),
("business_rejection", "CONFIG_REQUIRED"),
("rate_limit", "RATE_LIMITED"),
],
)
def test_proven_upload_failures_end_failed_without_device_lock(
service, monkeypatch, failure, expected
):
from test_display import submit
s = session({"message": "can not find robot private"}, 500)
if failure == "rate_limit":
s.request.return_value.status_code = 429
if failure == "connect_timeout":
s.request.side_effect = requests.ConnectTimeout("private")
c = KokonnaClient("private", True, s)
monkeypatch.setattr(service.registry.get("living-room"), "upload", c.upload)
operation = submit(service)
service.process_one()
op = service.operation(operation)
assert op["status"] == "FAILED"
assert op["error"]["code"] == expected
assert not service.blocked("living-room")
@pytest.mark.parametrize("value", [True, False, 0, -1, "12", None])
def test_invalid_upload_id_never_becomes_confirmed(tmp_path, value):
path = tmp_path / "image.jpg"
path.write_bytes(b"jpeg")
s = session({"id": value})
with pytest.raises(FlowError) as error:
KokonnaClient("private", True, s).upload(path, "image.jpg")
assert error.value.code == "WRITE_RESULT_UNKNOWN"
assert s.request.call_count == 1
def test_ambiguous_failure_after_safe_rejection_stops_retrying(transport_clock):
s = session({"message": "limited"}, 429)
first = s.request.return_value
first.headers = {"Retry-After": "1"}
s.request.side_effect = [first, requests.ReadTimeout("private")]
with pytest.raises(FlowError) as error:
KokonnaClient("private", True, s).display(1)
assert error.value.code == "WRITE_RESULT_UNKNOWN"
assert error.value.details["attempts"] == 2
assert s.request.call_count == 2
assert transport_clock.waits == [1]
+109
View File
@@ -0,0 +1,109 @@
from datetime import UTC, datetime, timedelta
from test_display import submit
from pigway_frame_flow.display.service import DisplayService
from pigway_frame_flow.errors import ErrorCode, FlowError
def unknown_upload(service, monkeypatch):
def fail(*args):
raise FlowError(ErrorCode.WRITE_RESULT_UNKNOWN, "Response lost", 502)
monkeypatch.setattr(service.registry.get("living-room"), "upload", fail)
operation = submit(service)
service.process_one()
return operation
def test_missing_upload_is_visible_without_unsafe_unlock(client, service, monkeypatch):
operation = unknown_upload(service, monkeypatch)
service.sync()
recovery = client.get("/api/v1/operations/" + operation).json()["recovery"]
assert recovery["reason"] == "gallery_match_missing"
assert recovery["state"] == "checking"
assert not recovery["requires_manual_review"]
assert service.blocked("living-room")
assert service.registry.get("living-room").client.uploads == 0
def test_persistent_block_escalates_once_survives_restart_and_preserves_evidence(
service, monkeypatch
):
operation = unknown_upload(service, monkeypatch)
original = service.operation(operation)
service.db.execute(
"UPDATE operations SET created_at=? WHERE id=?",
(
(datetime.now(UTC) - timedelta(hours=1)).isoformat(),
operation,
),
)
service.sync()
first = service.operation(operation)["recovery"]
assert first["state"] == "manual_review"
assert first["reason"] == "gallery_match_missing"
service.unknown_checked.clear()
service.sync()
restarted = DisplayService(
service.db, service.settings, service.registry, service.assets, service.renderer
)
restarted.sync()
assert (
len(service.db.all("SELECT * FROM events WHERE event_type='operation.blocked'"))
== 1
)
assert (
service.db.one(
"SELECT COUNT(*) AS n FROM history WHERE result='MANUAL_REVIEW_REQUIRED'"
)["n"]
== 1
)
assert service.operation(operation)["recovery"]["checks"] == 3
assert service.operation(operation)["result"] == original["result"]
service.reconcile(operation, acknowledge=True)
assert service.operation(operation)["recovery"]["state"] == "resolved"
assert not service.operation(operation)["recovery"]["requires_manual_review"]
assert not service.blocked("living-room")
def test_missing_legacy_evidence_escalates_without_cloud_write(service):
operation = submit(service)
service._start_write(operation)
service.update(operation, "UNKNOWN")
service.sync()
assert (
service.operation(operation)["recovery"]["reason"] == "missing_upload_evidence"
)
assert service.blocked("living-room")
def test_delete_unknown_requires_manual_review_without_replay(service):
operation = service.submit(
"delete", {"image_id": 1}, "living-room", "admin", "test"
)
service._start_write(operation)
service.update(operation, "UNKNOWN")
service.sync()
assert (
service.operation(operation)["recovery"]["reason"]
== "manual_reconciliation_required"
)
assert service.blocked("living-room")
assert service.registry.get("living-room").images()[0].image_id == 1
def test_malformed_reconciliation_does_not_abort_other_background_work(
service, monkeypatch
):
operation = unknown_upload(service, monkeypatch)
def invalid_metadata(*args):
raise ValueError("vendor metadata with private data")
monkeypatch.setattr(service.upload_reconciliation, "check", invalid_metadata)
service.sync()
op = service.operation(operation)
assert op["recovery"]["reason"] == "reconciliation_error"
assert "private" not in str(op["recovery"])
assert service.blocked("living-room")