scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49566/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49568/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49577/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +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/49580/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49583/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49582/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
183212e8be feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689)
Compare 58 commits »
scriptoriumadmin synced commits to refs/pull/49576/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +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/49578/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49586/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49581/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:43 +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/49552/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
01d6812f30 fix(model-catalog): declare the thinking_on_by_default key (#49720)
4e268c2c55 test(gemini): assert vertex lists on content chunks (#49734)
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)
Compare 39 commits »
scriptoriumadmin synced commits to refs/pull/49561/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49560/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49558/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 59 commits »
scriptoriumadmin synced commits to refs/pull/49544/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
de89b838e7 Merge remote-tracking branch 'origin/main' into litellm_spend_logs_latest_turn
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
183212e8be feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49536/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
1bc94cb972 refactor(responses): drop docstrings that restate the logprob helpers
1c7b6a3f08 test(responses): declare the guardrail logprob test locals Final
968600031a fix(responses): enable chat logprobs when include names message.output_text.logprobs
6be98d8c75 fix(bedrock)!: give Invoke and Mantle Claude the model's own default max_tokens (#49692)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/49536/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
1bc94cb972 refactor(responses): drop docstrings that restate the logprob helpers
1c7b6a3f08 test(responses): declare the guardrail logprob test locals Final
968600031a fix(responses): enable chat logprobs when include names message.output_text.logprobs
94a46a07ce Merge origin/main into litellm_responses_bridge_logprobs
40e4e512d0 fix(anthropic): stream azure_ai natively on an Azure OpenAI host on /v1/messages (#49216)
Compare 27 commits »
scriptoriumadmin synced commits to refs/pull/49556/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +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/49544/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
de89b838e7 Merge remote-tracking branch 'origin/main' into litellm_spend_logs_latest_turn
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
183212e8be feat(anthropic): pick the beta allowlist row per deployment and surface input_transformations (#49689)
e63067a23b fix(anthropic_endpoints)!: return Anthropic error envelopes on /v1/messages auth failures (#48466)
Compare 68 commits »
scriptoriumadmin synced commits to refs/pull/49549/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:42 +00:00
704e73d6fe fix(cost-map): give the bare gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini aliases their 2027-01-14 shutdown date (#49707)
28c80048ed fix(tool_choice): accept OpenAI allowed_tools on chat completions and flatten it for the Responses bridge (#49043)
20cb3ea439 test(integration): repair release qualification timing and labels (#49737)
94b5b6386a fix(bedrock): send native structured output for json_schema on Claude models that cannot force a tool (#49703)
Compare 60 commits »