scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49260/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:11 +00:00
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
27fbcd9895 fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192)
281bf4e48b ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394)
Compare 75 commits »
scriptoriumadmin synced commits to refs/pull/49257/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:11 +00:00
24dfb223d0 fix(proxy): send a fail-closed per-turn socket refusal with its 503 status
scriptoriumadmin synced commits to refs/pull/49216/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
c43a1addf2 refactor(router): extract PythonCore behind RouterCore and pass the router its config (#49119)
a5f980600c fix(a2a): answer proxy refusals on /a2a POST routes as JSON-RPC errors (#49476)
7143aeeb86 feat(passthrough): add Deepgram streaming text-to-speech WebSocket route (#49282)
3129e44848 ci: cut the weekly rc branch on Monday 3am PT instead of Friday (#49472)
Compare 48 commits »
scriptoriumadmin synced commits to refs/pull/49196/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
b2647116ca chore(cost-map): add openai gpt-6-astra-law from the pricing page (#49444)
8ff495be96 fix(proxy): price OpenAI pass-through /v1/decisions calls like native Decisions (#49392)
Compare 107 commits »
scriptoriumadmin synced commits to refs/pull/49189/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
dc478c8775 fix(redis-client): match redis-py command and failure behavior
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
1b3da63703 test: move Sail, Weave and Presidio e2e tests to integration tests (#49533)
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 167 commits »
scriptoriumadmin synced commits to refs/pull/49188/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
6f332b8c80 fix(decisions): bill a deployment's query price and accept Parallel bases that end in a route
6aa546303e docs(pr-template): wrap the agent-drafted summary in make-me-human-readable tags (#49494)
580b9266a1 feat(chat): resume replies after browser disconnects (#49461)
d2321581ec fix(cohere): emit streamed tool calls from v2 tool-call-start and tool-call-delta chunks (#47794)
Compare 79 commits »
scriptoriumadmin synced commits to refs/pull/49187/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
27fbcd9895 fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192)
281bf4e48b ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394)
Compare 105 commits »
scriptoriumadmin synced commits to refs/pull/49185/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
1b3da63703 test: move Sail, Weave and Presidio e2e tests to integration tests (#49533)
187f936cb3 fix(proxy)!: support reload with multiple workers (#45909)
a1c5829f6b fix(bedrock): raise GovCloud West Llama 3 max output to the model card 8K (#49543)
Compare 134 commits »
scriptoriumadmin synced commits to refs/pull/49199/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
0f4d5c6ad0 feat(ovalix)!: scan files, tool calls and tool results (#49309)
901b7f762f test(mcp): cancel disconnected HTTP tool handlers (#49436)
28679bb9c3 fix(chat): describe general chat and deep research on the chat home (#49531)
8c46b2c0d6 test(router): trace the deployment index lock in the file that owns it (#49520)
Compare 67 commits »
scriptoriumadmin synced commits to refs/pull/49212/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
d2321581ec fix(cohere): emit streamed tool calls from v2 tool-call-start and tool-call-delta chunks (#47794)
f7b2cd0000 fix(anthropic): answer 400 naming a non-string role or tool call id instead of 500 (#49237)
c43a1addf2 refactor(router): extract PythonCore behind RouterCore and pass the router its config (#49119)
a5f980600c fix(a2a): answer proxy refusals on /a2a POST routes as JSON-RPC errors (#49476)
Compare 119 commits »
scriptoriumadmin synced commits to refs/pull/49225/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
febd340120 fix(guardrails)!: keep the upstream error when a /v1/messages stream ends in one (#49088)
27fbcd9895 fix(anthropic): map pause_turn and return refusal explanations on chat and responses (#49192)
281bf4e48b ci(circleci): clone the public repo over HTTPS so main jobs stop failing at checkout (#49394)
Compare 87 commits »
scriptoriumadmin synced commits to refs/pull/49224/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
1595adfb2f docs(model-catalog): explain meter, band, channel and When (#49447)
3cb2e60de0 fix(cost): split a provider-reported total between input and output by the cost map rate ratio (#49357)
b2647116ca chore(cost-map): add openai gpt-6-astra-law from the pricing page (#49444)
8ff495be96 fix(proxy): price OpenAI pass-through /v1/decisions calls like native Decisions (#49392)
Compare 29 commits »
scriptoriumadmin synced commits to refs/pull/49214/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
3129e44848 ci: cut the weekly rc branch on Monday 3am PT instead of Friday (#49472)
d610dee7d0 docs(pr-template): add a handwritten 1-3 sentence description section (#49475)
ced995df6e fix(logging): drop a first-token time left over from a previous attempt (#47541)
3155aacda4 fix(caching): stop counting an unrun server tool call mark, and follow #49192 and #35602 in their integration tests (#49468)
Compare 113 commits »
scriptoriumadmin synced commits to refs/pull/49192/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
02b2ccf32e fix(responses): scan refusal parts in Responses guardrails
a1b098f4c4 Merge remote-tracking branch 'origin/main' into litellm_fix_claude_stop_reasons_pause_turn_refusal
a7b66dd8b9 fix(openai): stop stripping cache_control from the caller's own messages and tools (#35602)
e5aa3d32cd fix(proxy): forward a valid metadata.user_id to Anthropic Messages on pass-through routes (#49333)
af070e7cd0 build(deps): bump pyasn1, pypdf and minimatch to clear osv-scan (#49362)
Compare 21 commits »
scriptoriumadmin synced commits to refs/pull/49216/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
ae1d8aa7f7 fix(anthropic): keep the Azure credential of an azure_ai deployment that sets its own api_base on bridged /v1/messages calls
cb77c44025 fix(anthropic): skip the sign-in lookup for chatgpt and github_copilot model prefixes on bridged /v1/messages calls
ea5f02e8dd fix(anthropic): keep an azure deployment's Entra credential over the env key on bridged /v1/messages calls
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/49194/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:10 +00:00
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 70 commits »