fix(gemini): prevent duplicate model path generation when api_base includes full route
#24786Comparing
OnHighEngineer:fix-gemini-api-base-duplicate
(650b782
) withmain
(5812053
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.8 µs85.5 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs143 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
147 µs146.6 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
568.8 µs567.2 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.4 µs85.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.5 µs87.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
142.2 µs142 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
149 µs149 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.7 µs545 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
542.1 µs544.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
414.3 µs416.5 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
186.5 µs187.5 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py-1%
239.2 µs240.9 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-1%
87.7 µs88.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-1%
85.1 µs86.1 µs
Commits
Click on a commit to change the comparison rangeBase
main
5812053
-0.23%
fix(gemini): prevent duplicate model path generation when api_base includes full route
650b782
2 months ago
by OnHighEngineer