chore: split CLAUDE.md by domain for lazy context loading
#26034Comparing
litellm_chore-split-claude-md
(30a5541
) withmain
(850fe59
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py+2%
80.3 µs78.9 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py+1%
183.4 µs182.3 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py0%
413.1 µs412.4 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py0%
235.5 µs235.2 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
138.1 µs138.1 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
81.7 µs81.9 µs
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py0%
80 µs80.2 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
79.8 µs80 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py0%
143.8 µs144.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
141.2 µs141.6 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
539.5 µs541.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
79.3 µs79.7 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
136.6 µs137.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py-1%
564.5 µs567.9 µs
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py-1%
539.1 µs542.7 µs
Commits
Click on a commit to change the comparison rangeBase
main
850fe59
-0.08%
chore: split CLAUDE.md by domain for lazy context loading
30a5541
2 days ago
by ryan-crabbe-berri