scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(rubrik): drop RUBRIK_MAX_QUEUE_SIZE env knob, hardcode 10k cap

Browse source 
The doc-validation CI scans for os.getenv() calls and requires each key
to appear in litellm-docs config_settings.md. Adding the env var here
without a matching docs PR fails the docs and code-quality checks, and
the extra env-parsing block in __init__ also tripped ruff PLR0915.

The hard cap at 10k still bounds memory on a Rubrik webhook outage,
which is the actual bug being fixed -- operators don't need to tune
this knob to get the safety guarantee.
This commit is contained in:
mateo-berri 2026-05-21 01:29:48 +00:00
parent 944008b52b
commit 70d01a6e4c
No known key found for this signature in database
1 changed files with 2 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
litellm/integrations/rubrik.py
View file

@ -37,7 +37,7 @@ if TYPE_CHECKING:
_ENDPOINT_ANTHROPIC_MESSAGES = "/v1/messages"
_WEBHOOK_PATH_TOOL_BLOCKING = "/v1/after_completion/openai/v1"
_WEBHOOK_PATH_LOGGING_BATCH = "/v1/litellm/batch"
_DEFAULT_MAX_QUEUE_SIZE = 10_000
_MAX_QUEUE_SIZE = 10_000
_DROP_WARNING_INTERVAL_SECONDS = 60.0
@ -101,23 +101,7 @@ class RubrikLogger(CustomGuardrail, CustomBatchLogger):
# authenticated traffic accumulate prompt/response payloads until the
# proxy runs out of memory. Once the cap is reached, oldest events are
# dropped to make room for fresh ones (drop-oldest backpressure).
self.max_queue_size = _DEFAULT_MAX_QUEUE_SIZE
_max_queue_size = os.getenv("RUBRIK_MAX_QUEUE_SIZE")
if _max_queue_size:
try:
parsed_max = int(_max_queue_size)
if parsed_max > 0:
self.max_queue_size = parsed_max
else:
verbose_logger.warning(
f"RUBRIK_MAX_QUEUE_SIZE={_max_queue_size!r} must be > 0; "
f"using default {_DEFAULT_MAX_QUEUE_SIZE}"
)
except ValueError:
verbose_logger.warning(
f"Invalid RUBRIK_MAX_QUEUE_SIZE: {_max_queue_size!r}, "
f"using default {_DEFAULT_MAX_QUEUE_SIZE}"
)
self.max_queue_size = _MAX_QUEUE_SIZE
self._dropped_since_warning = 0
self._last_drop_warning_time = 0.0