mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-07 07:58:09 +00:00
ab78459097
Response transformation crashed with TypeError when counting tokens for multimodal (dict-shaped) embedding inputs, since encoding.encode() was called directly on the dict instead of its text parts. Also removed a dead, equally-buggy duplicate of the same loop in _transform_response. Separately, the embeddings guardrail handler silently skipped multimodal dict inputs instead of scanning them, letting prohibited text/image content bypass the configured guardrail. It now extracts and scans the text parts while leaving image parts untouched.
21 lines
705 B
YAML
21 lines
705 B
YAML
name: "LiteLLM CodeQL config"
|
|
|
|
queries:
|
|
- uses: security-and-quality
|
|
|
|
# Known OOM queries on large Python codebases:
|
|
# CodeQL builds a full data flow graph in memory. These two queries trace
|
|
# sensitive data through every log call / regex pattern, causing combinatorial
|
|
# path explosion on codebases with extensive logging like LiteLLM (>2 GiB
|
|
# result sets). This is a known CodeQL scaling limitation, not a code issue.
|
|
# Re-test periodically as CodeQL improves or the codebase refactors logging.
|
|
query-filters:
|
|
- exclude:
|
|
id: py/clear-text-logging-sensitive-data # CWE-312
|
|
- exclude:
|
|
id: py/polynomial-redos # CWE-730
|
|
|
|
paths-ignore:
|
|
- tests
|
|
- docs
|
|
- "**/*.md"
|