mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-10 08:28:25 +00:00
79209b92a1
* test(e2e): add enum values, auto-discovering label gates and secret hiding for e2e metadata * test(e2e): tag guardrails and logging tests with Subject metadata and record client steps * test(e2e): leave the guardrails and logging harness unit tests untagged * test(e2e): let the inner create_model step name the guardrail backend deployment * docs(e2e): name every markerless harness test file that carries no Subject * test(e2e): keep the step discovery comprehensions to one for clause * test(e2e): declare the default guardrail backend model on the tests that drive it
84 lines
3.4 KiB
Python
84 lines
3.4 KiB
Python
"""Live e2e: Prometheus request metrics grow one series per virtual key.
|
|
|
|
The proxy exposes ``/metrics`` (prometheus is in the callbacks and
|
|
``require_auth_for_metrics_endpoint`` is off in the e2e config). The counter
|
|
``litellm_requests_metric_total`` carries an ``api_key_alias`` label, so driving
|
|
traffic through keys with distinct aliases must produce a distinct labeled series
|
|
per alias. This is the per-key cardinality contract: a regression that stops
|
|
stamping ``api_key_alias`` (or collapses every key onto one series) would drop
|
|
the aliases and fail here.
|
|
|
|
Scraping goes through ``transport.probe`` (raw text) and is parsed with
|
|
prometheus_client. ``/metrics`` is per-pod behind a round-robin LB and the metric
|
|
is eventually consistent (it increments on the success-logging callback), so the
|
|
poll unions the aliases seen across scrapes until the deadline: counters persist
|
|
on whichever pod served the driver call, so repeated scrapes converge without
|
|
re-sending any billable traffic.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import time
|
|
|
|
import pytest
|
|
from prometheus_client.parser import text_string_to_metric_families
|
|
|
|
from e2e_config import unique_marker
|
|
from e2e_metadata import Domain, Mode, Provider, Route, Subject, meta
|
|
from lifecycle import ResourceManager
|
|
from logging_client import LoggingClient
|
|
|
|
pytestmark = pytest.mark.e2e
|
|
|
|
DRIVER_MODEL = "gemini-2.5-flash"
|
|
REQUESTS_METRIC = "litellm_requests_metric_total"
|
|
ALIAS_LABEL = "api_key_alias"
|
|
DISTINCT_KEYS = 3
|
|
|
|
|
|
def _aliases_in_metric(exposition: str, metric: str, label: str) -> frozenset[str]:
|
|
"""The set of ``label`` values present on ``metric`` samples in a scrape."""
|
|
return frozenset(
|
|
sample.labels[label]
|
|
for family in text_string_to_metric_families(exposition)
|
|
for sample in family.samples
|
|
if sample.name == metric and label in sample.labels
|
|
)
|
|
|
|
|
|
class TestPrometheusPerKeyCardinality:
|
|
@pytest.mark.covers("logging.prometheus.success.exports_metric", exercised_on=[])
|
|
@meta(
|
|
Subject(
|
|
domain=Domain.OBSERVABILITY,
|
|
route=Route.METRICS,
|
|
providers=(Provider.GEMINI,),
|
|
models=(DRIVER_MODEL,),
|
|
mode=Mode.NONSTREAM,
|
|
)
|
|
)
|
|
def test_distinct_key_aliases_produce_distinct_series(
|
|
self, client: LoggingClient, resources: ResourceManager
|
|
) -> None:
|
|
aliases = tuple(f"e2e-prom-{unique_marker()}" for _ in range(DISTINCT_KEYS))
|
|
for alias in aliases:
|
|
key = client.key_with_alias(alias, models=[DRIVER_MODEL])
|
|
resources.defer(lambda k=key: client.delete_key(k))
|
|
response = client.chat(key, DRIVER_MODEL, f"reply with one word {alias}")
|
|
assert response.model, f"driver call for {alias} returned no model: {response}"
|
|
|
|
wanted = frozenset(aliases)
|
|
deadline = time.monotonic() + client.proxy.poll_timeout
|
|
seen: frozenset[str] = frozenset()
|
|
while time.monotonic() < deadline:
|
|
seen = seen | _aliases_in_metric(client.scrape_metrics(), REQUESTS_METRIC, ALIAS_LABEL)
|
|
if wanted <= seen:
|
|
break
|
|
time.sleep(client.proxy.poll_interval)
|
|
|
|
missing = wanted - seen
|
|
assert not missing, (
|
|
f"{REQUESTS_METRIC} never exposed a per-key series for aliases {sorted(missing)} "
|
|
f"on any scraped pod within the deadline; "
|
|
f"each distinct {ALIAS_LABEL} must grow its own series"
|
|
)
|