fix(responses): reorder `function_call_output` adjacent to `function_call` before chat-completion conversion
#27953Comparing
parisni:fix/responses-to-chat-function-call-output-adjacency
(bcb17a8
) withmain
(e58a561
)-1%
- Untouched
- 16
Benchmarks
16 total
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
184.3 µs182.6 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py+1%
143 µs142.1 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
237 µs236 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.4 µs138.4 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
80.3 µs80.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
414 µs414.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
544.3 µs544.8 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
144.1 µs144.3 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py0%
136.8 µs137 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
544.1 µs545.7 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
563.6 µs570.4 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py-1%
1.7 ms1.7 ms
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py-2%
80.2 µs81.8 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py-2%
80 µs81.7 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py-3%
79.9 µs81.9 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py-3%
82.2 µs84.5 µs
Commits
Click on a commit to change the comparison rangeBase
main
e58a561
-0.66%
test(responses): cover `function_call_output` adjacency normalisation
bcb17a8
8 hours ago
by parisni