scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/46016/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 36 commits »
scriptoriumadmin synced commits to refs/pull/46015/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/46014/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 37 commits »
scriptoriumadmin synced commits to refs/pull/46012/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/46006/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
Compare 35 commits »
scriptoriumadmin synced commits to refs/pull/46004/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/45973/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
a2ab27373f fix(proxy): count the context_management edits /v1/messages applies on every bridged provider (#49234)
97cd5d0c6a fix(model-catalog): declare the tool and Responses token count framing keys (#49683)
aa95ac4cee fix(bedrock): price Web Search on the GPT-5.4 and later Mantle rows and the GovCloud West Mantle rows (#49687)
Compare 15 commits »
scriptoriumadmin synced commits to refs/pull/45972/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:58 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 534 commits »
scriptoriumadmin synced commits to refs/pull/45942/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
ff3983c1f6 fix(wandb): set DeepSeek-V3.1 and Llama-3.1-8B max_input_tokens from the CoreWeave Forge page (#49616)
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/45967/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
a018311912 style(openai): wrap json_mode finish_reason ternary for ruff format
e60cfd3725 fix(openai): only fold tool-call finish reasons to stop in json_mode
4846cc3885 fix(openai): json_mode stop finish_reason after folding tool call
ff3983c1f6 fix(wandb): set DeepSeek-V3.1 and Llama-3.1-8B max_input_tokens from the CoreWeave Forge page (#49616)
60fc121ce8 test(a2a): replace the third-party agent e2e test with an integration test (#49541)
Compare 1497 commits »
scriptoriumadmin synced commits to refs/pull/45967/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 439 commits »
scriptoriumadmin synced commits to refs/pull/45839/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 36 commits »
scriptoriumadmin synced commits to refs/pull/45952/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
34314a99f0 fix(messages): make rust messages copy python messages behaviour (#49611)
5e08cb0e63 test(messages): add rust vs python messages parity characterization suite (#49610)
216041e243 feat(decisions): add Parallel AI web-grounded decisions (#49188)
08b951a814 fix(vllm): list hosted_vllm wildcard models when the server has no api key (#40066)
Compare 111 commits »
scriptoriumadmin synced commits to refs/pull/45928/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
cc142a8191 fix(cost): add deepgram/streaming/nova-3-medical and update stale Nova-3 streaming rates (#49733)
250af8f027 fix(spend)!: save streamed /v1/responses spend rows under the encrypted resp_ id the client received (#49493)
4ede2c012f feat(model_info): add supports_continuation capability flag for Gemini long decode continuation (#49500)
Compare 62 commits »
scriptoriumadmin synced commits to refs/pull/45907/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
d4b003b95d fix(proxy): defer background reservation settlement until usage arrives
7dc0d5da43 fix(proxy): reconcile budget reservations when no database logger
0bd677afef test(integration): look up streamed Responses spend rows by the client-facing id (#49752)
4187e1ae89 fix(managed_files): keep the upload the managed id encodes when two target models share a deployment (#49420)
Compare 51 commits »
scriptoriumadmin synced commits to refs/pull/45907/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
d4b003b95d fix(proxy): defer background reservation settlement until usage arrives
7dc0d5da43 fix(proxy): reconcile budget reservations when no database logger
0bd677afef test(integration): look up streamed Responses spend rows by the client-facing id (#49752)
4187e1ae89 fix(managed_files): keep the upload the managed id encodes when two target models share a deployment (#49420)
acd084ab38 fix(mcp): answer bare OPTIONS on MCP routes without running LiteLLM auth (#49497)
Compare 50 commits »
scriptoriumadmin synced commits to refs/pull/45875/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 248 commits »
scriptoriumadmin synced commits to refs/pull/45941/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 37 commits »
scriptoriumadmin synced commits to refs/pull/45854/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
f4a2e2b3af fix(anthropic): send an https PDF image_url to Claude as a document (#49708)
0d697017b5 fix(cost-map)!: price Mistral Large 4 at its current list price (#49814)
4573fa1f31 fix(embeddings): honor the caller's timeout on Cohere sync and HuggingFace embedding requests (#48593)
4e007c6e81 docs: preserve author review when updating PR summaries (#49803)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/45790/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:57 +00:00
a2d27881e8 fix(bedrock): reserve DeepSeek V3.2 output capacity and date GovCloud West Llama 3 (#49732)
7fe6b1de34 fix(proxy)!: ignore stored general_settings keys no settings API manages (#48967)
523b87ec71 fix(proxy): charge budget windows when the cached key or team expired before the request ended (#47608)
10b3deae0d build(deps): allow huggingface-hub 2.x (#49056)
Compare 37 commits »