Files
app/backend/tests/api/routes/test_observability.py
T
stroblmeandClaude Opus 5 a1265450df Health: a flow that cannot run says so, and the brain marks which neurons
A dependency loop is flagged on the canvas and was invisible everywhere else:
/observability/summary answered "ok" with an empty problems list while the
published flow could not run at all. It now reports the flows validation
blocks, and the brain graph carries the reason on each neuron the issue names
so the view built to find broken wiring can show it.

Node errors stay counted once, as the nodes that failed to load, and an
advisory like an unauthenticated webhook marks nothing — it is worth saying,
but the flow still runs.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XC2jX6Hdj7pxGGKzBTrbqB
2026-08-17 14:39:07 +02:00

215 lines
6.8 KiB
Python

from datetime import datetime, timedelta, timezone
from fastapi.testclient import TestClient
from sqlmodel import Session
from app.core.config import settings
from app.models import EngineEvent, FlowRun, MetricBucket
PREFIX = f"{settings.API_V1_STR}/observability"
FLOW = "observability-test"
def _seed(db: Session) -> None:
now = datetime.now(timezone.utc).replace(second=0, microsecond=0)
db.add(
MetricBucket(
flow=FLOW,
node=f"{FLOW}.calc",
bucket=now - timedelta(minutes=1),
executions=4,
errors=1,
messages=6,
duration_sum_ms=40.0,
duration_max_ms=25.0,
lag_sum_ms=100.0,
lag_max_ms=60.0,
items=4,
)
)
db.add(
EngineEvent(
ts=now,
type="node_error",
flow=FLOW,
node=f"{FLOW}.calc",
detail="ValueError: bad input\nTraceback",
)
)
db.add(
EngineEvent(
ts=now, type="audit", flow=FLOW, detail="published", actor="a@example.com"
)
)
db.add(
FlowRun(
id="9-0",
flow=FLOW,
source="external",
started_at=now,
finished_at=now,
status="ok",
nodes=3,
duration_ms=12.5,
)
)
db.commit()
def test_observability_requires_authentication(client: TestClient) -> None:
assert client.get(f"{PREFIX}/summary").status_code == 401
def test_the_summary_answers_even_when_degraded(
client: TestClient, superuser_token_headers: dict[str, str]
) -> None:
response = client.get(f"{PREFIX}/summary", headers=superuser_token_headers)
assert response.status_code == 200
body = response.json()
assert body["status"] in {"ok", "degraded"}
assert set(body["flows"]) == {
"total",
"running",
"paused",
"quarantined",
"invalid",
}
assert "error" in body["nodes"]
def test_a_flow_that_cannot_run_makes_the_summary_degraded(
client: TestClient, superuser_token_headers: dict[str, str]
) -> None:
"""A loop on the canvas has to reach the health screen.
Validation runs on a build, not on this request, so what the engine already
knows is what this reports — and reporting it is the whole point: a flow
with a dependency loop cannot run, and the screen used to say "ok".
"""
from app.flow.pipeline import ValidationIssue
controller = client.app.state.flow_controller
before = controller.issues
controller.issues = [
ValidationIssue(
code="cycle",
message="These nodes depend on each other in a loop",
flow="looping",
nodes=["looping.a", "looping.b"],
),
# Already counted as a node that failed to load, so not again here.
ValidationIssue(
code="node_error", message="boom", flow="broken", node="broken.x"
),
ValidationIssue(
code="unauthenticated_hook", message="open", flow="hooky", node="hooky.h"
),
]
try:
body = client.get(f"{PREFIX}/summary", headers=superuser_token_headers).json()
finally:
controller.issues = before
assert body["status"] == "degraded"
assert body["flows"]["invalid"] == 1
assert any("looping" in problem for problem in body["problems"])
assert not any("broken" in problem for problem in body["problems"])
assert not any("hooky" in problem for problem in body["problems"])
def test_the_history_reads_back(
client: TestClient, superuser_token_headers: dict[str, str], db: Session
) -> None:
_seed(db)
points = client.get(f"{PREFIX}/timeseries", headers=superuser_token_headers).json()
mine = [point for point in points if point["executions"]]
assert mine and mine[-1]["avg_ms"] > 0
flows = client.get(f"{PREFIX}/flows", headers=superuser_token_headers).json()
row = next(entry for entry in flows if entry["flow"] == FLOW)
assert (row["executions"], row["errors"], row["messages"]) == (4, 1, 6)
assert len(row["spark"]) == 60
assert row["last_error_ts"] is not None
runs = client.get(f"{PREFIX}/runs", headers=superuser_token_headers).json()
assert any(run["id"] == "9-0" and run["status"] == "ok" for run in runs)
failures = client.get(f"{PREFIX}/events", headers=superuser_token_headers).json()
assert any("Traceback" in event["detail"] for event in failures)
assert all(event["type"] != "audit" for event in failures)
audit = client.get(
f"{PREFIX}/events", headers=superuser_token_headers, params={"kind": "audit"}
).json()
assert any(event["actor"] == "a@example.com" for event in audit)
dead = client.get(f"{PREFIX}/dead-letter", headers=superuser_token_headers)
assert dead.status_code == 200
assert isinstance(dead.json(), list)
def test_runs_narrow_to_one_minute(
client: TestClient, superuser_token_headers: dict[str, str], db: Session
) -> None:
"""A minute picked off a chart reaches past what the recent list holds."""
minute = datetime.now(timezone.utc).replace(second=0, microsecond=0) - timedelta(
hours=3
)
db.add(FlowRun(id="minute-in", flow=FLOW, started_at=minute, status="ok"))
db.add(
FlowRun(
id="minute-after",
flow=FLOW,
started_at=minute + timedelta(minutes=1),
status="ok",
)
)
db.commit()
runs = client.get(
f"{PREFIX}/runs",
headers=superuser_token_headers,
params={
"since": minute.isoformat(),
"until": (minute + timedelta(minutes=1)).isoformat(),
},
).json()
# The upper bound is exclusive, so the run starting the next minute is not
# in this one.
assert [run["id"] for run in runs] == ["minute-in"]
def test_events_narrow_to_one_minute(
client: TestClient, superuser_token_headers: dict[str, str], db: Session
) -> None:
"""The failures list reaches as far back as the charts beside it."""
minute = datetime.now(timezone.utc).replace(second=0, microsecond=0) - timedelta(
hours=4
)
db.add(EngineEvent(ts=minute, type="node_error", flow=FLOW, detail="minute-in"))
db.add(
EngineEvent(
ts=minute + timedelta(minutes=1),
type="node_error",
flow=FLOW,
detail="minute-after",
)
)
db.commit()
events = client.get(
f"{PREFIX}/events",
headers=superuser_token_headers,
params={
"flow": FLOW,
"since": minute.isoformat(),
"until": (minute + timedelta(minutes=1)).isoformat(),
},
).json()
# The upper bound is exclusive, so the failure a minute later is not in it.
assert [event["detail"] for event in events] == ["minute-in"]