Comparing
litellm_skip-system-message-unified-guardrails
(2abfaa5
) withlitellm_internal_staging_04_11_2026
(d0e347a
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
89 µs87.6 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-1%
142.6 µs144.2 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-1%
85.2 µs85.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-1%
85 µs85.5 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-1%
87.3 µs87.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py-1%
146.8 µs147.5 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.8 µs544.5 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.8 µs149.4 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
572.7 µs574.9 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.8 µs142.3 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.1 µs187.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543.2 µs544.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
418 µs417.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
85.8 µs85.8 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
240.3 µs240.4 µs
Commits
Click on a commit to change the comparison rangeBase
main
d0e347a
-0.32%
feat(guardrails): optional skip system message in unified guardrail inputs
9665af2
5 months ago
by Sameerlite-0.16%
feat(dashboard): skip_system_message_in_guardrail in guardrail UI
62f315e
5 months ago
by Sameerlite+0.26%
fix(guardrails): type structured_messages as AllMessageValues for mypy
2abfaa5
4 months ago
by Sameerlite