scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge 3418ebb1d2 into 67c7b97fd2

Browse source
This commit is contained in:
Furkan Emre Güngör 2026-08-27 16:10:58 -05:00 • committed by GitHub
commit cd8dc82337
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 45 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/integrations/prometheus.py
View file

@ -2859,7 +2859,7 @@ class PrometheusLogger(CustomLogger):
label_context=label_context,
)
if remaining_requests:
if remaining_requests is not None:
"""
"model_group",
"api_provider",
@ -2873,7 +2873,7 @@ class PrometheusLogger(CustomLogger):
)
self.litellm_remaining_requests_metric.labels(**_labels).set(remaining_requests)
if remaining_tokens:
if remaining_tokens is not None:
_labels = prometheus_label_factory(
supported_enum_labels=self.get_labels_for_metric(metric_name="litellm_remaining_tokens_metric"),
enum_values=enum_values,

43
tests/test_litellm/integrations/test_prometheus_remaining_tokens_router_fallback.py
View file

@ -293,3 +293,46 @@ class TestRouterFallbackDefensivePaths:
)
prometheus_logger.litellm_remaining_tokens_metric.labels.assert_not_called()
class TestProviderHeaderPathEmitsZero:
"""The sibling path to the router fallback above.
When a provider does return `x-ratelimit-remaining-*`, the fallback
short-circuits and `set_llm_deployment_success_metrics` owns the emit. That
branch used to be guarded by `if remaining_requests:`, so a reported `0`
was dropped and the gauge kept serving its previous value: a dashboard
reading headroom while the quota was gone.
"""
def test_should_emit_both_gauges_when_provider_reports_zero(self, prometheus_logger):
payload = _build_payload(
custom_llm_provider="openai",
additional_headers={
"x_ratelimit_remaining_requests": 0,
"x_ratelimit_remaining_tokens": 0,
},
)
prometheus_logger.litellm_remaining_requests_metric = MagicMock()
prometheus_logger.litellm_remaining_tokens_metric = MagicMock()
prometheus_logger.litellm_deployment_success_responses = MagicMock()
prometheus_logger.litellm_deployment_total_requests = MagicMock()
prometheus_logger.litellm_deployment_latency_per_output_token = MagicMock()
prometheus_logger.litellm_overhead_latency_metric = MagicMock()
prometheus_logger.set_deployment_healthy = MagicMock()
prometheus_logger.set_llm_deployment_success_metrics(
request_kwargs={
"model": "gpt-5-nano",
"litellm_params": {"custom_llm_provider": "openai"},
"standard_logging_object": payload,
},
start_time=None,
end_time=None,
enum_values=_enum_values(),
output_tokens=10,
)
prometheus_logger.litellm_remaining_requests_metric.labels().set.assert_called_once_with(0)
prometheus_logger.litellm_remaining_tokens_metric.labels().set.assert_called_once_with(0)