Avatar for the BerriAI user
BerriAI
litellm
BlogDocsChangelog

Performance History

Latest Results

fix(proxy): preserve proxy hook setup compatibility
mphilippnv:litellm_fix_prisma_initial_recovery_38121
6 minutes ago
fix: tolerate stream chunks without a choices key in stream_chunk_builder (#34382) The Responses-API to /chat/completions bridge yields ModelResponseStream chunks that carry choices followed by a trailing event object that has no choices key. stream_chunk_builder assumed every chunk was subscriptable at "choices", so assembling those chunks raised KeyError('choices') and was re-wrapped as a 500 APIError building the streaming usage. Guard each choices access with .get("choices") so choices-less chunks are skipped instead of crashing. Behavior is unchanged for chunks that do carry choices, since .get("choices") is truthy only for a non-empty choices list. Adds a regression test that assembles content across chunks followed by a trailing chunk with no choices key. Co-authored-by: mubashir1osmani <mubashir.osmani777@gmail.com>
litellm_internal_staging
6 minutes ago
refactor(videos): make video upload param keyword-only on public edit fns Keeps positional callers of litellm.video_edit / avideo_edit binding timeout as before instead of misbinding it to the new video argument.
litellm_forward_video_edit_source_file
8 minutes ago
feat(ui): add error-code drilldown for failed requests on caching page /global/activity/cache_hits now returns an error_breakdown: failed spend logs bucketed per call_type by error code and error class, read from metadata->error_information. Clicking a red failed-requests segment on the cache activity chart opens a per-code bar chart; hovering a bar lists the error classes behind that code.
litellm_caching_error_drilldown
12 minutes ago
fix(anthropic): close sync streaming responses
blairjordan:litellm_fix_anthropic_stream_cleanup
15 minutes ago
chore: recompute lint budgets after merging staging
litellm_fix_context_manager_signatures
16 minutes ago
fix(proxy): drop unnecessary isinstance on SpendLogs api_key payload_api_key is already str | None; after the empty check, startswith is enough and basedpyright no longer flags reportUnnecessaryIsInstance. Co-authored-by: Yuzhong Zhang <BetterAndBetterII@users.noreply.github.com>
BetterAndBetterII:cursor/fix-verification-token-spend-ece7
18 minutes ago
Merge branch 'litellm_internal_staging' into fix-stream-chunk-builder-missing-choices
AkshaySasi:fix-stream-chunk-builder-missing-choices
19 minutes ago

Latest Branches

CodSpeed Performance Gauge
0%
fix(proxy): recover Prisma after initial startup failure#38152
1 hour ago
157733d
mphilippnv:litellm_fix_prisma_initial_recovery_38121
CodSpeed Performance Gauge
0%
chore(ci): promote internal staging to main#37913
52 minutes ago
fde3075
litellm_internal_staging
CodSpeed Performance Gauge
0%
fix(videos): forward uploaded source file on /v1/videos/edits to the provider#38155
50 minutes ago
eb00f46
litellm_forward_video_edit_source_file
© 2026 CodSpeed Technology
Home Terms Privacy Docs