fix(bedrock/thinking/websearch): beta headers, thinking fixes, API key loading, guardrails null safety
#23523Comparing
Quentin-M:fix/websearch-bedrock-thinking
(bdf1260
) withmain
(278c9ba
)0%
- Untouched
- 16
Benchmarks
16 total
test_get_model_info_openai
tests/benchmarks/test_benchmarks.py+2%
88 µs86.3 µs
test_token_counter_multi_turn
tests/benchmarks/test_benchmarks.py+1%
571.6 µs567.5 µs
test_token_counter_simple_message
tests/benchmarks/test_benchmarks.py+1%
240.5 µs238.8 µs
test_get_model_cost_key_exact_match
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.2 µs
test_token_counter_long_content
tests/benchmarks/test_benchmarks.py0%
1.7 ms1.7 ms
test_cost_per_token_anthropic
tests/benchmarks/test_benchmarks.py0%
543.4 µs544.2 µs
test_get_model_cost_key_case_insensitive
tests/benchmarks/test_benchmarks.py0%
87.4 µs87.5 µs
test_get_model_info_with_provider
tests/benchmarks/test_benchmarks.py0%
85.2 µs85.4 µs
test_token_counter_raw_text
tests/benchmarks/test_benchmarks.py0%
187.3 µs187.7 µs
test_get_model_info_anthropic
tests/benchmarks/test_benchmarks.py0%
84.9 µs85.2 µs
test_cost_per_token_openai
tests/benchmarks/test_benchmarks.py0%
542.7 µs544.7 µs
test_get_llm_provider_openai
tests/benchmarks/test_benchmarks.py0%
143.4 µs144.1 µs
test_get_llm_provider_anthropic
tests/benchmarks/test_benchmarks.py0%
146.8 µs147.5 µs
test_token_counter_with_tools
tests/benchmarks/test_benchmarks.py-1%
416.1 µs418.8 µs
test_get_llm_provider_with_prefix
tests/benchmarks/test_benchmarks.py-1%
141.8 µs143.2 µs
test_get_llm_provider_azure
tests/benchmarks/test_benchmarks.py-1%
148.7 µs150.3 µs
Commits
Click on a commit to change the comparison rangeBase
main
278c9ba
-0.1%
fix(websearch_interception): load API keys from router configuration
bdf1260
11 days ago
by Quentin-M