mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-07 07:58:09 +00:00
fix(accounting): keep spend commits working when prometheus_client is not installed (#50230)
* fix(accounting): keep spend commits working when prometheus_client is not installed The delivery worker imported the ledger metrics module, which imported prometheus_client at module level. update_database imports the worker outside its try block, so installs without the proxy-runtime extra failed every spend commit. The metrics now register only when prometheus_client is importable and are skipped otherwise Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * style(accounting): note why prometheus_client can be missing Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Joshua Valluru <326636767+joshua-berri@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
joshua-berri
GitHub
parent
f25fff42a6
commit
85bc58085e
2 changed files with 81 additions and 35 deletions
|
|
@ -1,30 +1,55 @@
|
|||
from typing import Final
|
||||
|
||||
from prometheus_client import Gauge, Histogram
|
||||
from dataclasses import dataclass
|
||||
from typing import TYPE_CHECKING, Final
|
||||
|
||||
from litellm.repositories.accounting_delivery_repository import DeliveryMetrics
|
||||
|
||||
_PENDING: Final = Gauge("litellm_accounting_pending", "Pending SpendLogs deliveries", multiprocess_mode="livemax")
|
||||
_PARKED: Final = Gauge("litellm_accounting_parked", "Parked SpendLogs deliveries", multiprocess_mode="livemax")
|
||||
_OLDEST: Final = Gauge(
|
||||
"litellm_accounting_oldest_pending_seconds",
|
||||
"Age of the oldest pending SpendLogs delivery",
|
||||
multiprocess_mode="livemax",
|
||||
)
|
||||
_BATCH_TIME: Final = Histogram("litellm_accounting_batch_seconds", "SpendLogs delivery worker batch time")
|
||||
_BATCH_COUNT: Final = Gauge(
|
||||
"litellm_accounting_batch_deliveries", "Retained batch deliveries", multiprocess_mode="livemax"
|
||||
)
|
||||
_TABLE_BYTES: Final = Gauge(
|
||||
"litellm_accounting_delivery_table_bytes", "Delivery table size in bytes", multiprocess_mode="livemax"
|
||||
)
|
||||
if TYPE_CHECKING:
|
||||
from prometheus_client import Gauge, Histogram
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class _Instruments:
|
||||
pending: "Gauge"
|
||||
parked: "Gauge"
|
||||
oldest: "Gauge"
|
||||
batch_time: "Histogram"
|
||||
batch_count: "Gauge"
|
||||
table_bytes: "Gauge"
|
||||
|
||||
|
||||
def _instruments() -> _Instruments | None:
|
||||
try:
|
||||
# prometheus-client ships only in the proxy-runtime extra, so a plain litellm[proxy] install lands here
|
||||
from prometheus_client import Gauge, Histogram
|
||||
except ImportError:
|
||||
return None
|
||||
return _Instruments(
|
||||
pending=Gauge("litellm_accounting_pending", "Pending SpendLogs deliveries", multiprocess_mode="livemax"),
|
||||
parked=Gauge("litellm_accounting_parked", "Parked SpendLogs deliveries", multiprocess_mode="livemax"),
|
||||
oldest=Gauge(
|
||||
"litellm_accounting_oldest_pending_seconds",
|
||||
"Age of the oldest pending SpendLogs delivery",
|
||||
multiprocess_mode="livemax",
|
||||
),
|
||||
batch_time=Histogram("litellm_accounting_batch_seconds", "SpendLogs delivery worker batch time"),
|
||||
batch_count=Gauge(
|
||||
"litellm_accounting_batch_deliveries", "Retained batch deliveries", multiprocess_mode="livemax"
|
||||
),
|
||||
table_bytes=Gauge(
|
||||
"litellm_accounting_delivery_table_bytes", "Delivery table size in bytes", multiprocess_mode="livemax"
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
_INSTRUMENTS: Final = _instruments()
|
||||
|
||||
|
||||
def record_deliveries(metrics: DeliveryMetrics, seconds: float) -> None:
|
||||
_PENDING.set(metrics.pending_count)
|
||||
_PARKED.set(metrics.parked_count)
|
||||
_OLDEST.set(max(0.0, metrics.oldest_pending_seconds))
|
||||
_BATCH_TIME.observe(seconds)
|
||||
|
||||
_BATCH_COUNT.set(metrics.batch_count)
|
||||
_TABLE_BYTES.set(metrics.table_bytes)
|
||||
if _INSTRUMENTS is None:
|
||||
return
|
||||
_INSTRUMENTS.pending.set(metrics.pending_count)
|
||||
_INSTRUMENTS.parked.set(metrics.parked_count)
|
||||
_INSTRUMENTS.oldest.set(max(0.0, metrics.oldest_pending_seconds))
|
||||
_INSTRUMENTS.batch_time.observe(seconds)
|
||||
_INSTRUMENTS.batch_count.set(metrics.batch_count)
|
||||
_INSTRUMENTS.table_bytes.set(metrics.table_bytes)
|
||||
|
|
|
|||
|
|
@ -1,9 +1,17 @@
|
|||
import importlib.util
|
||||
import sys
|
||||
|
||||
import pytest
|
||||
from prometheus_client.metrics import MetricWrapperBase
|
||||
|
||||
from litellm.accounting import metrics
|
||||
from litellm.accounting.metrics import record_deliveries
|
||||
from litellm.repositories.accounting_delivery_repository import DeliveryMetrics
|
||||
|
||||
_DELIVERY_METRICS = DeliveryMetrics(
|
||||
pending_count=4, parked_count=1, oldest_pending_seconds=-3.0, batch_count=7, table_bytes=8192
|
||||
)
|
||||
|
||||
|
||||
def _sample(metric: MetricWrapperBase, suffix: str = "") -> float:
|
||||
family = metric.collect()[0]
|
||||
|
|
@ -11,18 +19,31 @@ def _sample(metric: MetricWrapperBase, suffix: str = "") -> float:
|
|||
|
||||
|
||||
def test_delivery_metrics_publish_backlog_and_clamp_clock_skew() -> None:
|
||||
batches_before = _sample(metrics._BATCH_TIME, "_count")
|
||||
instruments = metrics._INSTRUMENTS
|
||||
assert instruments is not None
|
||||
batches_before = _sample(instruments.batch_time, "_count")
|
||||
|
||||
record_deliveries(
|
||||
DeliveryMetrics(pending_count=4, parked_count=1, oldest_pending_seconds=-3.0, batch_count=7, table_bytes=8192),
|
||||
0.5,
|
||||
)
|
||||
record_deliveries(_DELIVERY_METRICS, 0.5)
|
||||
|
||||
assert (
|
||||
_sample(metrics._PENDING),
|
||||
_sample(metrics._PARKED),
|
||||
_sample(metrics._OLDEST),
|
||||
_sample(metrics._BATCH_COUNT),
|
||||
_sample(metrics._TABLE_BYTES),
|
||||
_sample(instruments.pending),
|
||||
_sample(instruments.parked),
|
||||
_sample(instruments.oldest),
|
||||
_sample(instruments.batch_count),
|
||||
_sample(instruments.table_bytes),
|
||||
) == (4.0, 1.0, 0.0, 7.0, 8192.0)
|
||||
assert _sample(metrics._BATCH_TIME, "_count") == batches_before + 1
|
||||
assert _sample(instruments.batch_time, "_count") == batches_before + 1
|
||||
|
||||
|
||||
def test_delivery_metrics_are_skipped_when_prometheus_client_is_not_installed(
|
||||
monkeypatch: pytest.MonkeyPatch,
|
||||
) -> None:
|
||||
monkeypatch.setitem(sys.modules, "prometheus_client", None)
|
||||
spec = importlib.util.spec_from_file_location("accounting_metrics_without_prometheus", metrics.__file__)
|
||||
assert spec is not None and spec.loader is not None
|
||||
module = importlib.util.module_from_spec(spec)
|
||||
monkeypatch.setitem(sys.modules, spec.name, module)
|
||||
|
||||
spec.loader.exec_module(module)
|
||||
|
||||
assert module.record_deliveries(_DELIVERY_METRICS, 0.5) is None
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue