scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49420/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
9a4d86e4ad fix(managed_files): file each repeat-upload delete under the upload that made its copy
695c01642a fix(managed_files): pass the parent call id to the cleanup deletes
b8d1ec83a5 fix(managed_files): delete the copy a managed id carries as an internal call
d1b7af1e66 fix(managed_files): read the copy DELETE removes from the id's gateway-written fields
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/49439/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
acd084ab38 fix(mcp): answer bare OPTIONS on MCP routes without running LiteLLM auth (#49497)
81969e4afc refactor(ui): move admin and settings text onto i18n (#49546)
b84493d9a7 fix(proxy): log each endpoint's own call type on failed audio, moderation, image, and rerank spend rows (#49684)
105b7cba16 refactor(ui): move agents and knowledge text onto i18n (#49530)
Compare 104 commits »
scriptoriumadmin synced commits to refs/pull/49437/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
1046716b6d fix(anthropic)!: sync the beta header allowlist with what anthropic, vertex_ai, and azure_ai accept (#49409)
ff91b89b8d fix(router): keep encrypted reasoning when a fallback hops between same-key deployments with no api_base (#49396)
572832dea1 fix(gemini)!: answer 400 for an unsupported chat audio format, drop it under drop_params (#49423)
ff3983c1f6 fix(wandb): set DeepSeek-V3.1 and Llama-3.1-8B max_input_tokens from the CoreWeave Forge page (#49616)
Compare 14 commits »
scriptoriumadmin synced commits to refs/pull/49441/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
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)
Compare 17 commits »
scriptoriumadmin synced commits to refs/pull/49415/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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/49416/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
fcef9cd0a3 feat(videos): serve custom_provider_map BaseVideoConfig providers on /v1/videos (#49785)
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)
Compare 68 commits »
scriptoriumadmin synced commits to refs/pull/49417/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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/49422/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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/49450/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
6be98d8c75 fix(bedrock)!: give Invoke and Mantle Claude the model's own default max_tokens (#49692)
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/49448/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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 114 commits »
scriptoriumadmin synced commits to refs/pull/49442/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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/49435/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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 54 commits »
scriptoriumadmin synced commits to refs/pull/49414/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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 96 commits »
scriptoriumadmin synced commits to refs/pull/49413/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +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 66 commits »
scriptoriumadmin synced commits to refs/pull/49391/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
6be98d8c75 fix(bedrock)!: give Invoke and Mantle Claude the model's own default max_tokens (#49692)
f8f12a270a test(integration): repair stale contract fixtures (#49700)
508a98586e fix(databricks): join plain text blocks for non-Claude json_object requests (#49385)
f91774e2f9 fix(fireworks): keep developer items in place for models that accept a later system message (#49399)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/49381/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
c8601d733b fix(logging): apply a callback's own message redaction to its failure events
98f95187d8 fix(proxy): keep the request's redaction opt-in on proxy-only failure logs
c920180bac fix(otel): keep only the request text per span so a failed request's span can be freed
4fa1e66e4a fix(proxy): scrub the prompt out of proxy failure hook errors when message logging is redacted
Compare 8 commits »
scriptoriumadmin synced commits to refs/pull/49393/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +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/49401/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +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 106 commits »
scriptoriumadmin synced commits to refs/pull/49389/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
28b649e04a refactor(e2e): validate Codex rollout lines with the models directly
5b3694c39f test(e2e): add the Codex auto-compaction row
306d5ab5f6 test(e2e): make the Codex long session prove every earlier command output reached the model
cf71fbaeaa test(e2e): add the Codex file edit and long session rows
00a085fa6e test(e2e): record a step when the Codex harness sets up its home and workspace
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/49396/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:38 +00:00
414443ac58 fix(router): resolve a changed named credential at once in the cached boundary and take an injected clock