scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49525/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:41 +00:00
84373ee188 feat(redis): move router cooldown and usage stores into Rust
bad662428d refactor(redis): encapsulate router cooldown and usage stores
Compare 36 commits »
scriptoriumadmin synced commits to refs/pull/49504/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:41 +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 45 commits »
scriptoriumadmin synced commits to refs/pull/49481/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
bad662428d refactor(redis): encapsulate router cooldown and usage stores
1690a561cf feat(redis-client): declare ops into a RedisBatch and flush them as one pipeline
2fc8ace23c feat(redis): rotating cloud credentials for Redis
581ad431ac feat(config): resolve Redis settings the way litellm/_redis.py does
de6371cc29 fix(redis-client): match redis-py command and failure behavior
Compare 27 commits »
scriptoriumadmin synced commits to refs/pull/49477/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
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)
2a94bb3835 fix(spend): bill web search interception follow-ups once under the outer request (#49762)
be50cbe9d8 fix(responses)!: authorize and decode comparison response IDs (#49402)
Compare 63 commits »
scriptoriumadmin synced commits to refs/pull/49466/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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/49456/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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/49496/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 33 commits »
scriptoriumadmin synced commits to refs/pull/49500/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
f6bd08f17c fix(router): count only a boolean true supports_continuation when building a model group
6f61f99c85 fix(cost-map): flag vertex_ai/gemini-4-argon-cyber-permissive with supports_continuation
4055b1ce33 fix(router): keep a deployment's supports_continuation override on that deployment
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/49464/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 84 commits »
scriptoriumadmin synced commits to refs/pull/49503/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
43e5539e77 fix(passthrough): apply per-model rate limits to the Deepgram and Vertex Live WebSocket routes
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 34 commits »
scriptoriumadmin synced commits to refs/pull/49503/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 38 commits »
scriptoriumadmin synced commits to refs/pull/49493/head at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
ace4006d3e test(responses): run the DELETE wire test that pins the echoed client id
71a8b5e1db test(deepeval): annotate the background cost span test's locals with Final
9eb66858c2 fix(integrations): give background cost events their own ClickHouse request id and DeepEval span id
d70360e31e Merge remote-tracking branch 'origin/main' into HEAD
10186ef13c fix(integrations): keep OpenMeter and DynamoDB logging working without the proxy extras
Compare 261 commits »
scriptoriumadmin synced commits to refs/pull/49490/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 64 commits »
scriptoriumadmin synced commits to refs/pull/49488/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 18 commits »
scriptoriumadmin synced commits to refs/pull/49487/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 33 commits »
scriptoriumadmin synced commits to refs/pull/49484/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 18 commits »
scriptoriumadmin synced commits to refs/pull/49481/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +00:00
bad662428d refactor(redis): encapsulate router cooldown and usage stores
1690a561cf feat(redis-client): declare ops into a RedisBatch and flush them as one pipeline
Compare 34 commits »
scriptoriumadmin synced commits to refs/pull/49457/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:40 +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 79 commits »
scriptoriumadmin synced commits to refs/pull/49453/merge at scriptoriumadmin/litellm from mirror 2026-11-03 07:25:39 +00:00
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 101 commits »
scriptoriumadmin synced commits to refs/pull/49443/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 5 commits »