Avatar for the BerriAI user
BerriAI
litellm
BlogDocsChangelog

Performance History

Latest Results

fix(proxy): use actual request start_time for failed spend logs async_post_call_failure_hook was calling datetime.now() for both start_time and end_time, making every failed request show Duration: 0.000s. litellm_logging_obj (already fetched in the same method for trace ID propagation) carries the real request start_time — use it as actual_start_time with a datetime.now() fallback when absent. Add two regression tests covering the fix and the fallback path. Fixes #24888
Vedanshu7:fix/failure-hook-zero-duration-spend-logs
3 minutes ago
ignore mypy cache files
litellm_fix_test_bedrock_model
16 minutes ago
feat(ci): add coverage reporting to reusable unit test base workflows
joereyna:feat/codecov-full-coverage
23 minutes ago
ignore mypy cache files
litellm_fix_test_bedrock_model_clone
33 minutes ago

Latest Branches

CodSpeed Performance Gauge
0%
fix(proxy): use actual request start_time for failed spend logs#24936
6 minutes ago
33538a2
Vedanshu7:fix/failure-hook-zero-duration-spend-logs
CodSpeed Performance Gauge
+1%
fix(gemini): handle Gemini Files API URIs without fetching#24922
8 minutes ago
7e93206
voidborne-d:fix/gemini-files-api-uri-handling
CodSpeed Performance Gauge
0%
test fix us.anthropic.claude-haiku-4-5-20251001-v1:0#24931
38 minutes ago
2ad0f42
litellm_fix_test_bedrock_model
© 2026 CodSpeed Technology
Home Terms Privacy Docs