Performance History
Latest Results
fix(proxy): preserve trusted forwarded protocol chains
litellm_trusted_proxy_middleware
15 seconds ago
Merge remote-tracking branch 'origin/main' into litellm_realtime_model_family
# Conflicts:
# tests/unit/proxy/proxy_server/test_routes_audio.py
emerzon:litellm_realtime_model_family
2 minutes ago
chore(proxy): drop the team_id comment from the tag spend schema
litellm_lit8516_tag_team_id
4 minutes ago
refactor(proxy): drop leftover group_by=tag branch and the tag page SQL-text test
The aggregated team report no longer reads the tag table, so the extra table check and its
comment did nothing. The tag page SQL-text test is replaced by the integration tests that
read real rows for team filtering, User-Agent exclusion, ordering and paging
litellm_lit8516_team_group_by_tag
4 minutes ago
fix(anthropic): dedupe the message-threads beta map rows and annotate test finals
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
litellm_anthropic_message_threads
9 minutes ago
fix(spend): bill web search interception follow-ups once under the outer request
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
litellm_fix_interception_followup_single_spend_owner
12 minutes ago
fix(logging): log bridged text completions and /v1/messages as served, with the request's options
Bridged rows were translated without the request's options, so structured
output and replay fields could differ from what the client got. Text
completions and non-streamed /v1/messages through the chat bridge also kept
a Responses API object or the encoded id.
zoveki:litellm_bridge_keep_chat_call_type
13 minutes ago
Latest Branches
0%
10 minutes ago
06827e3
litellm_trusted_proxy_middleware
0%
23 minutes ago
020c6bd
emerzon:litellm_realtime_model_family
0%
2 days ago
9aaddc1
litellm_lit8516_tag_team_id