fix(anthropic): drop temperature from reasoning-family supported params
#26445Comparing
Anai-Guo:fix/anthropic-temperature-reasoning-models
(0cbe669
) withmain
(7b47dff
)0%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py0%
568.8 µs566 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80.6 µs80.3 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.7 µs138.3 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144 µs143.8 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.6 µs413.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
82 µs81.9 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.9 µs137 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.6 µs235.9 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.5 µs79.8 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141 µs141.5 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs80.1 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py-1%
540.7 µs544.9 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
542.6 µs547 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py-1%
182.8 µs185.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py-3%
78.8 µs81 µs
Commits
Click on a commit to change the comparison rangeBase
main
7b47dff
-0.35%
fix(anthropic): drop temperature from reasoning-family params
0cbe669
4 hours ago
by Anai-Guo