Comparing
afoninsky:afoninsky/chatgpt-proxy-bridge-fixes
(246d924
) withlitellm_oss_staging_04_21_2026
(97f722f
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+1%
88.7 µs87.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
84.7 µs85.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
414.4 µs418 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
567.3 µs571.6 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py-1%
143.1 µs144 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
239.3 µs240.3 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
147.3 µs147 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
541.3 µs542.4 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
86.5 µs86.3 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.3 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.3 µs87.5 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
543 µs543.6 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
141.7 µs141.8 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.2 µs187.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
148.9 µs149 µs
Commits
Click on a commit to change the comparison rangeBase
main
97f722f
-0.4%
test(chatgpt): cover SSE error and bridge recovery paths
b2776f0
4 months ago
by afoninsky+0.02%
fix(chatgpt): reuse SSE helpers and output item constants
761221d
4 months ago
by afoninsky+0.26%
fix(ci): avoid SSE import cycle and stabilize prompt version tests
246d924
4 months ago
by afoninsky