scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49903/head at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:53 +00:00
eb77fc1651 fix(proxy): preserve rate-limit reset timing after Redis store migration
bbc7de1ccb chore(cost-map): add the openai o1 deprecation source from the deprecations page (#50402)
d1cde1002e fix(chatgpt): forward text and max_output_tokens to the Codex backend (#38086)
febbe38326 fix(anthropic)!: do not surface server_tool_use as client tool_calls (#48385)
2a4f8b1d19 fix(bedrock): drop another model's signed thinking when replaying to a non-Claude Converse target (#50073)
Compare 205 commits »
scriptoriumadmin synced commits to refs/pull/49836/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
36c64ce85d feat(bedrock): default to native structured output on Opus 5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 (#50221)
6e66b8281f test(cost): sync Azure GPT flex price fields with the real cost map (#50410)
ddd162439f fix(proxy): stop /tag/update 500 when the body carries the tag's budget_id (#50324)
5d69250cd0 fix(model-map): add verified Mistral retirement dates (#50294)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/49841/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49859/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 69 commits »
scriptoriumadmin synced commits to refs/pull/49847/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
aeede53112 feat(guardrails): add mcp_block_behavior to raise 400 on MCP tool blocks (#50284)
0057804dca fix(ui): stop parsing formatted dates and spend back into values (#50350)
de0b389205 feat(router): add the Switchyard stage router as an auto router strategy (#50407)
8013d5b8c1 chore(model_prices): absorb #50415 and #50332, add Perplexity gpt-5.5 cached >272k rate (#50436)
Compare 42 commits »
scriptoriumadmin synced commits to refs/pull/49858/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
36c64ce85d feat(bedrock): default to native structured output on Opus 5.5, Fable 5.1, Sonnet 5 and Haiku 5.5 (#50221)
6e66b8281f test(cost): sync Azure GPT flex price fields with the real cost map (#50410)
ddd162439f fix(proxy): stop /tag/update 500 when the body carries the tag's budget_id (#50324)
5d69250cd0 fix(model-map): add verified Mistral retirement dates (#50294)
Compare 26 commits »
scriptoriumadmin synced commits to refs/pull/49860/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49874/head at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
2732dfe43e Merge remote-tracking branch 'origin/main' into litellm_fips_b1_password_pbkdf2
14683b502b fix(ui): support model_info.logo_url in Model Management (#50056) (#50371)
e790d9bbb2 fix(ui): simplify collapsed workspace dropdown (#50369)
6fc9555f83 fix(vertex_ai): honor vertex_location for the Cloud Text-to-Speech endpoint (#50255)
848c267b76 test(e2e): wait for saved MCP credentials before deleting the server (#50366)
Compare 21 commits »
scriptoriumadmin synced commits to refs/pull/49879/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
aeede53112 feat(guardrails): add mcp_block_behavior to raise 400 on MCP tool blocks (#50284)
0057804dca fix(ui): stop parsing formatted dates and spend back into values (#50350)
de0b389205 feat(router): add the Switchyard stage router as an auto router strategy (#50407)
8013d5b8c1 chore(model_prices): absorb #50415 and #50332, add Perplexity gpt-5.5 cached >272k rate (#50436)
Compare 36 commits »
scriptoriumadmin synced commits to refs/pull/49880/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
eacb670b6e bump: litellm-enterprise 0.1.81 -> 0.1.83, litellm-proxy-extras 0.4.112 -> 0.4.114, litellm 1.109.0 -> 1.110.0 (#50437)
150f4b706b fix(router): count embedding batches per input in pre-call checks (#49851)
1f15088fc9 feat(proxy): mixed Codex model picker and LiteLLM routing on native codex routes (#49408)
a94118c6cd test(bedrock): expect native output on Opus 4.8 profiles after #50222 (#50343)
Compare 95 commits »
scriptoriumadmin synced commits to refs/pull/49882/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
e9b1c11098 fix(xai): honor deployment image pixel pricing (#50490)
94861ecdf7 feat(xai): bill image calls from cost_in_usd_ticks and add grok-imagine-image-2.0 resolution prices (#50481)
6b745635c8 fix(bedrock): forward Codex agent messages that carry encrypted content intact (#50457)
98acc01e0d feat(videos): add first-class OpenRouter video request fields (#50319)
Compare 100 commits »
scriptoriumadmin synced commits to refs/pull/49885/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
e9b1c11098 fix(xai): honor deployment image pixel pricing (#50490)
94861ecdf7 feat(xai): bill image calls from cost_in_usd_ticks and add grok-imagine-image-2.0 resolution prices (#50481)
6b745635c8 fix(bedrock): forward Codex agent messages that carry encrypted content intact (#50457)
98acc01e0d feat(videos): add first-class OpenRouter video request fields (#50319)
Compare 88 commits »
scriptoriumadmin synced commits to refs/pull/49864/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49855/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49853/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49851/head at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
319381a540 fix(router): read embedding media off the event loop and wait on the count limiter in the fairness test
8a99b36e1e fix(router): count long embedding batches in slices so chat counts do not wait behind them
b1302558e5 fix(router): check embedding text batches only with an exact OpenAI tokenizer
1022bcfb28 fix(router): keep embedding images out of the pre-call count when any backend in the group embeds images
ed45d31192 fix(router): keep embedding images out of the pre-call count only on image backends, and skip tokenizing inputs that fit by bytes
Compare 165 commits »
scriptoriumadmin synced commits to refs/pull/49870/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
e9b1c11098 fix(xai): honor deployment image pixel pricing (#50490)
94861ecdf7 feat(xai): bill image calls from cost_in_usd_ticks and add grok-imagine-image-2.0 resolution prices (#50481)
6b745635c8 fix(bedrock): forward Codex agent messages that carry encrypted content intact (#50457)
98acc01e0d feat(videos): add first-class OpenRouter video request fields (#50319)
Compare 88 commits »
scriptoriumadmin synced commits to refs/pull/49873/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:52 +00:00
aeede53112 feat(guardrails): add mcp_block_behavior to raise 400 on MCP tool blocks (#50284)
0057804dca fix(ui): stop parsing formatted dates and spend back into values (#50350)
de0b389205 feat(router): add the Switchyard stage router as an auto router strategy (#50407)
8013d5b8c1 chore(model_prices): absorb #50415 and #50332, add Perplexity gpt-5.5 cached >272k rate (#50436)
Compare 42 commits »
scriptoriumadmin synced commits to refs/pull/49811/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:51 +00:00
72228db5c6 fix(caching): don't cache or replay a reply that has no output (#50057)
c36acd6e29 feat(azure_ai): add cohere-rerank-v5-pro and -fast from the Azure retail price feed (#50499)
8f19607259 fix(proxy)!: preserve Responses SSE event framing (#47980)
b3c4a1c3e4 feat(spend-logs): turn off prompt storage per key or team (#50135)
Compare 66 commits »
scriptoriumadmin synced commits to refs/pull/49801/merge at scriptoriumadmin/litellm from mirror 2026-11-07 07:59:51 +00:00
2d2290067c fix(bedrock): run realtime guardrails on Nova Sonic sessions (#49833)
b5a72c2042 fix(router): pin /v1/responses requests for prompt caching affinity (#50321)
aeede53112 feat(guardrails): add mcp_block_behavior to raise 400 on MCP tool blocks (#50284)
0057804dca fix(ui): stop parsing formatted dates and spend back into values (#50350)
Compare 85 commits »