GitHub Actions run
CPU Simulation
2 hours ago a413c2d shivamrawat1:litellm_failover_for_guardrails pull_requestCompare
Base
Search a run
Head
Comparefeat(proxy): Optional on_error for guardrail pipeline (API / technical failures)
#24831
shivamrawat1:litellm_failover_for_guardrails
2 hours ago
CPU Simulation
16 total
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py148.9 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py187 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py87 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py146.5 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py1.7 ms
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py417.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py542.8 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py568 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py239.1 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py85 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py542.8 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py142.2 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py143 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py85.8 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py84.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py87.4 µs