`AlertManager.send` swallowed every delivery failure, so the alerts screen's Test button answered 200 whatever happened — the one thing it exists for. It takes `raise_on_error` now, which only the test route passes; the per-channel loop keeps the swallow, because one dead channel must not stop the others hearing about the same fault. A refused delivery answers 502 with whatever the sender said. Renaming a flow left its values under the old name for good: the delete path already swept them, the rename path never did. It calls the same `forget_flow`, which covers the messages and the `__ts__`/`__version__`/`__history__` bookkeeping keyed by message name. Cleanup, not migration — they repopulate under the new name on the next run. Triggering a node by hand ran `Node.__call__` with nothing catching it, so a node that raised produced a 500 and a stack trace in the server log, and nothing at all on the canvas. `Pipeline.publish_error` is the reporting half of `_execute_node` lifted out; both paths go through it, so a manual failure now reads the same on the canvas and in the metrics as a queued one. The route answers 400 with the node's error. `MemoryWorkQueue.stats()` counts claimed-but-unacknowledged work rather than reporting zero, so the health tile means something without Redis. The metrics collector's held tracebacks are capped at `DETAIL_CAP` and swept on the same `RUN_STALE_S` cutoff the open runs use, instead of one untruncated traceback per node kept for the life of the process — a traceback still survives the flush between the log and the failure it belongs to. `GET /observability/events` takes `since`/`until`, the window `/runs` already took, so a failures list can cover the span the charts beside it are drawn from. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XC2jX6Hdj7pxGGKzBTrbqB
67 lines
1.8 KiB
Python
67 lines
1.8 KiB
Python
"""The Test button: it exists to tell a working channel from a broken one."""
|
|
|
|
from typing import Any
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
from app.core.config import settings
|
|
from app.flow.alerts import AlertsConfig, Channel
|
|
|
|
PREFIX = f"{settings.API_V1_STR}/alerts"
|
|
|
|
|
|
def _one_channel(client: TestClient) -> Any:
|
|
alerts = client.app.state.flow_controller.alerts # type: ignore[attr-defined]
|
|
alerts.config = AlertsConfig(
|
|
channels=[Channel(name="phone", kind="ntfy", config={"topic": "t"})]
|
|
)
|
|
return alerts
|
|
|
|
|
|
def test_a_channel_that_cannot_deliver_is_not_a_success(
|
|
client: TestClient,
|
|
superuser_token_headers: dict[str, str],
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
alerts = _one_channel(client)
|
|
|
|
async def refuse(_config: dict[str, Any], _alert: Any) -> None:
|
|
raise RuntimeError("nobody home")
|
|
|
|
monkeypatch.setattr(alerts, "_send_ntfy", refuse)
|
|
|
|
response = client.post(f"{PREFIX}/test/phone", headers=superuser_token_headers)
|
|
|
|
assert response.status_code == 502
|
|
assert "nobody home" in response.json()["detail"]
|
|
|
|
|
|
def test_a_channel_that_delivers_says_so(
|
|
client: TestClient,
|
|
superuser_token_headers: dict[str, str],
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
alerts = _one_channel(client)
|
|
sent = []
|
|
|
|
async def accept(_config: dict[str, Any], alert: Any) -> None:
|
|
sent.append(alert)
|
|
|
|
monkeypatch.setattr(alerts, "_send_ntfy", accept)
|
|
|
|
response = client.post(f"{PREFIX}/test/phone", headers=superuser_token_headers)
|
|
|
|
assert response.status_code == 200
|
|
assert len(sent) == 1
|
|
|
|
|
|
def test_an_unknown_channel_is_a_404(
|
|
client: TestClient, superuser_token_headers: dict[str, str]
|
|
) -> None:
|
|
_one_channel(client)
|
|
|
|
response = client.post(f"{PREFIX}/test/nowhere", headers=superuser_token_headers)
|
|
|
|
assert response.status_code == 404
|