scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/48548/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:03 +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 216 commits »
scriptoriumadmin synced commits to refs/pull/48354/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48333/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
e708343309 test: deflake the json accumulator drain test and the armed routing prefetch test (#49505)
da5ea59667 refactor(ui): remove dead API calls from networking.tsx (#49507)
6aa546303e docs(pr-template): wrap the agent-drafted summary in make-me-human-readable tags (#49494)
3c19ed5057 fix(vllm): log native pooling passthrough responses
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/48340/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48393/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
1f942122a8 Merge remote-tracking branch 'origin/main' into litellm_pr48393_head
efc2304b7e fix(streaming)!: fail a stream that ends without a finish reason (#47665)
aea0e4f2d4 test(cost): expect cohere rerank-v4 prompt_tokens from billed_units.total_tokens (#49455)
54892d6a62 fix(oci): preserve all Gemini system instructions (#48813) (#49458)
6e27da8af9 fix(router): inspect image content without translating routed requests (#49371)
Compare 40 commits »
scriptoriumadmin synced commits to refs/pull/48333/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
3c19ed5057 fix(vllm): log native pooling passthrough responses
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 543 commits »
scriptoriumadmin synced commits to refs/pull/48385/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +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 46 commits »
scriptoriumadmin synced commits to refs/pull/48345/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48349/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48348/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
4db92de5ab fix(router): normalize numeric deployment weights
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 571 commits »
scriptoriumadmin synced commits to refs/pull/48348/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
4db92de5ab fix(router): normalize numeric deployment weights
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)
Compare 383 commits »
scriptoriumadmin synced commits to refs/pull/48385/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
2389eafaf9 fix(guardrails): scan replayed Claude server calls and hosted web calls
a29804a7d9 fix(anthropic): keep a pending server call and its thinking when the turn also waits on a client tool
21724eb913 Merge remote-tracking branch 'origin/main' into fix-anthropic-server-tool-use-chat
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
197b34725a test(guardrails): type the fake Pillar client like its Protocol
Compare 84 commits »
scriptoriumadmin synced commits to refs/pull/48371/head at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
c0e94903d4 Merge remote-tracking branch 'upstream/main' into litellm_responses_reasoning_summary
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)
cee72ffdd6 fix(proxy): count native Responses WebSocket turn tokens toward key and tag TPM limits (#49257)
Compare 513 commits »
scriptoriumadmin synced commits to refs/pull/48355/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
be4f3d36ce feat(accounting): capture request usage through the durable meter (#49133)
a713ed6bab fix(gemini): add thought_signature_in_tool_call_id to keep tool call ids short for clients that cap them (#47692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/48393/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +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 53 commits »
scriptoriumadmin synced commits to refs/pull/48371/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:02 +00:00
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)
137fd7cd66 fix(docs): replace stale docs/proxy/enterprise links with the current docs pages (#49491)
Compare 103 commits »
scriptoriumadmin synced commits to refs/pull/48253/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:01 +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 123 commits »
scriptoriumadmin synced commits to refs/pull/48324/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:01 +00:00
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)
f4f5e2c80f fix(cost-map): add 2026-11-04 deprecation_date to together_ai Qwen3.8-2.4T-A95B (#49542)
68dbf54b09 chore(e2e): remove the unused arize_phoenix callback from the stage mirror config (#49538)
Compare 82 commits »
scriptoriumadmin synced commits to refs/pull/48262/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:01 +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 147 commits »
scriptoriumadmin synced commits to refs/pull/48309/merge at scriptoriumadmin/litellm from mirror 2026-11-01 07:04:01 +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 70 commits »