scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/40283/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:30 +00:00
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)
b777dd6f14 fix(router)!: scope context fallback precedence to the requested group (#49779)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/40264/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:30 +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 86 commits »
scriptoriumadmin synced commits to refs/pull/40241/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:30 +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 109 commits »
scriptoriumadmin synced commits to refs/pull/40240/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:30 +00:00
81258ccc55 fix: pass validated model_info to get_optional_params outside the args dict
b31e48f95a chore: drop *-ok markers that suppress nothing (LIT013)
2269446d4d refactor: validate thinking translation inputs instead of narrowing to unknown types
6e56321520 fix: drop inert model_info lookup from vLLM batch path
Compare 128 commits »
scriptoriumadmin synced commits to refs/pull/40239/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:30 +00:00
4b1d761d14 test(anthropic): cover sync /v1/messages context-1m path and pin tests to our beta constant
dc8f825b0d fix(anthropic): normalize [1m] models before capability lookups
840c3dfa51 feat(anthropic): auto-inject context-1m beta header for [1m] model suffix
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)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/40011/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 139 commits »
scriptoriumadmin synced commits to refs/pull/40004/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 180 commits »
scriptoriumadmin synced commits to refs/pull/40092/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
7a856f9be8 fix(ui): merge main and preserve localized navigation
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 232 commits »
scriptoriumadmin synced commits to refs/pull/40066/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
357cbbd909 test(vllm): cover the vLLM listings and no-slash wildcard aliases the patch left unrun
fef95dc90e fix(proxy): match a wildcard's own row pattern before asking its server
b7c443b440 fix(proxy): skip wildcard servers a key cannot reach on /v1/model/info
f35e49cb83 test(vllm): give the self-signed cert fixture fixed validity dates
Compare 4 commits »
scriptoriumadmin synced commits to refs/pull/39977/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
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)
b777dd6f14 fix(router)!: scope context fallback precedence to the requested group (#49779)
408773bb69 test(spend): assert Anthropic envelope for Messages budget refusals (#49800)
Compare 71 commits »
scriptoriumadmin synced commits to refs/pull/39874/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
044bd824c0 test(integration): align remaining release qualification checks (#49714)
05b76878b0 fix(cohere): map Cohere v2 finish_reason on non-streaming chat responses (#49529)
a4de720144 fix(count_tokens): count grok-4-1, grok-4.3 and DeepSeek V4.1 tool requests the way their hosts bill them (#49074)
6be98d8c75 fix(bedrock)!: give Invoke and Mantle Claude the model's own default max_tokens (#49692)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/39517/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 106 commits »
scriptoriumadmin synced commits to refs/pull/39734/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
b4a80d175c ci: remove workflows whose secrets are dead (#49722)
c720b23238 feat(proxy)!: honor model_info.max_input_tokens in the Codex catalog for stock models (#49701)
b3c397e964 feat(hosted_vllm)!: keep vLLM's stop_reason and token_ids on chat choices and stream chunks (#48393)
61da6fcb4d fix(mcp)!: answer 400 for a hosted MCP tool a translated route cannot run, drop it under drop_params (#48931)
Compare 83 commits »
scriptoriumadmin synced commits to refs/pull/39756/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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/39522/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 19 commits »
scriptoriumadmin synced commits to refs/pull/39888/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +00:00
3b62b6311c fix(proxy): make /update/sso_settings a true PATCH and send only changed SSO fields from the UI (#49527)
6f3251c7e3 fix(responses): serialize sequence_number on every bridged streaming event (#44944)
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)
Compare 7 commits »
scriptoriumadmin synced commits to refs/pull/39881/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 65 commits »
scriptoriumadmin synced commits to refs/pull/39753/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 531 commits »
scriptoriumadmin synced commits to refs/pull/39855/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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/39544/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:24:29 +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 19 commits »