scriptoriumadmin

scriptoriumadmin synced commits to refs/pull/48829/head at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:25 +00:00

f5bb555720 Merge remote-tracking branch 'origin/main' into litellm_drop_non_finite_spend_cost

f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)

4f65bb08c8 Merge remote-tracking branch 'origin/main' into litellm_drop_non_finite_spend_cost

ccc56d27ad fix(azure): add batch prices to the unversioned o3, o4-mini, o3-mini, gpt-4o and gpt-4o-mini rows (#49182)

b91fc92b6d fix(router): cap the default OTPM reservation and reconcile token counters after each call (#49054)

Compare 65 commits »

scriptoriumadmin synced commits to refs/pull/48837/head at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:25 +00:00

17307df6e8 test(exceptions): use SGLang's real top-level error body in overflow regression

scriptoriumadmin synced commits to refs/pull/48843/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:25 +00:00

ab899acb52 Merge 59b9d68ad9 into 837f36e872

837f36e872 fix(proxy): log router-refused image generation requests (#49349)

a9b181489b fix(gemini): add the batch, flex and priority text output prices to gemini-2.5-flash-image (#49358)

458463a20d fix(search): forward Perplexity search filters (#49344)

969ded2b54 fix(guardrails): drop the response pipeline steps that never ran from x-litellm-applied-guardrails (#49264)

Compare 79 commits »

scriptoriumadmin synced commits to refs/pull/48698/head at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

41a857c34e fix(token_counter): count SDK tool call objects and flat custom tools, keep Anthropic options tools as functions

8641c86f2c Merge remote-tracking branch 'origin/main' into HEAD

43c07a0f12 fix(router)!: check and count deployment itpm and otpm on every Responses WebSocket turn (#49069)

4786dd861b fix(proxy)!: scope /health by wildcard keys and team model allowlists the way auth does (#49155)

160a0b72cf fix(mcp): bill both calls of a streamed chat completions MCP auto-execute (#48899)

Compare 294 commits »

scriptoriumadmin synced commits to refs/pull/48725/head at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

ba70a3a182 Merge remote-tracking branch 'origin/main' into litellm_responses_ws_frame_guardrails

73aaf9e3da fix(mistral): forward prompt_cache_key to the Mistral API (#47432)

e81dd348a4 fix(proxy)!: log and bill Responses-style bodies sent to /cursor/chat/completions (#30277)

cfb77ecc3a fix(proxy): list only routable models for a wildcard alias over a provider org (#49152)

56388fd13d fix(count_tokens): count a history that carries a compaction block (#44784)

Compare 49 commits »

scriptoriumadmin synced commits to refs/pull/48729/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

6e836a3c17 Merge 2a5631c27b into 837f36e872

837f36e872 fix(proxy): log router-refused image generation requests (#49349)

a9b181489b fix(gemini): add the batch, flex and priority text output prices to gemini-2.5-flash-image (#49358)

458463a20d fix(search): forward Perplexity search filters (#49344)

969ded2b54 fix(guardrails): drop the response pipeline steps that never ran from x-litellm-applied-guardrails (#49264)

Compare 193 commits »

scriptoriumadmin synced commits to refs/pull/48732/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

aead60de84 Merge d6f24c6a32 into d1758cda91

d1758cda91 fix(router)!: keep a deployment's own model_id over the request body's (#49045)

373f1752d3 fix(anthropic): send PDF image_url content to Claude as document blocks (#46984)

4c8b90945f fix(realtime)!: send the Gemini Live setup at the first content so session.update settings apply (#39864)

73aaf9e3da fix(mistral): forward prompt_cache_key to the Mistral API (#47432)

Compare 75 commits »

scriptoriumadmin synced commits to refs/pull/48772/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

5ba0499880 Merge b2bbc31923 into 4c8b90945f

4c8b90945f fix(realtime)!: send the Gemini Live setup at the first content so session.update settings apply (#39864)

73aaf9e3da fix(mistral): forward prompt_cache_key to the Mistral API (#47432)

e81dd348a4 fix(proxy)!: log and bill Responses-style bodies sent to /cursor/chat/completions (#30277)

cfb77ecc3a fix(proxy): list only routable models for a wildcard alias over a provider org (#49152)

Compare 89 commits »

scriptoriumadmin synced commits to refs/pull/48776/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

11e2730377 Merge cea101402d into 372c096388

372c096388 fix(proxy): evict a deleted key from every worker's auth cache (#47609)

ab3f6caddc fix(gemini): flag computer use support on the four models the Gemini computer use docs list (#49252)

9432bf6b8e perf(streaming): stop raising caught AttributeErrors inside pydantic on every streamed chunk (#49166)

8ac9b75737 fix(model_prices): rolling registry audit, add Gemini batch and Azure Astra flex tiers (#49114)

Compare 33 commits »

scriptoriumadmin synced commits to refs/pull/48698/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

f192f681e9 Merge 41a857c34e into 7e37c20748

7e37c20748 fix(responses): run the guardrails a Responses WebSocket frame selects (#48725)

467847b2e9 fix(ui): restore Z.AI credential fields in provider catalog (#49325)

a42c1c138a fix(exceptions): classify SGLang context window overflow (#48837)

516c796e86 fix(rerank): preserve token usage in spend logs (#49308)

Compare 138 commits »

scriptoriumadmin synced commits to refs/pull/48714/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

7c409899fb Merge 02fd30121a into 17d1f58336

17d1f58336 fix(ui): preserve team model grants on unrelated settings saves (#49258)

372c096388 fix(proxy): evict a deleted key from every worker's auth cache (#47609)

ab3f6caddc fix(gemini): flag computer use support on the four models the Gemini computer use docs list (#49252)

9432bf6b8e perf(streaming): stop raising caught AttributeErrors inside pydantic on every streamed chunk (#49166)

Compare 59 commits »

scriptoriumadmin synced commits to refs/pull/48727/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

e7ccffbcce Merge 05f9e0afa9 into a44e44b980

a44e44b980 fix(cache_control): pick the chat-path dialect from the deployment's provider prefix (#45295)

87fec5467f fix(sso): keep CLI SSO and Claude Code gateway team lists in the user record's order (#49033)

02ef44c388 fix(streaming): convert upstream logprobs so streams with logprobs end with their finish chunk (#33549)

0070ce23b3 fix(router)!: apply content_policy_fallbacks when router settings update at runtime (#45428)

Compare 114 commits »

scriptoriumadmin synced commits to refs/pull/48740/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

fa836bec50 Merge 555a65f1ca into a44e44b980

a44e44b980 fix(cache_control): pick the chat-path dialect from the deployment's provider prefix (#45295)

87fec5467f fix(sso): keep CLI SSO and Claude Code gateway team lists in the user record's order (#49033)

02ef44c388 fix(streaming): convert upstream logprobs so streams with logprobs end with their finish chunk (#33549)

0070ce23b3 fix(router)!: apply content_policy_fallbacks when router settings update at runtime (#45428)

Compare 57 commits »

scriptoriumadmin synced commits to refs/pull/48749/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

f8272fecf8 Merge f752e2aa96 into 080e643edc

080e643edc fix(proxy): apply new model rows on every worker as soon as they are written (#49034)

d1758cda91 fix(router)!: keep a deployment's own model_id over the request body's (#49045)

373f1752d3 fix(anthropic): send PDF image_url content to Claude as document blocks (#46984)

4c8b90945f fix(realtime)!: send the Gemini Live setup at the first content so session.update settings apply (#39864)

Compare 52 commits »

scriptoriumadmin synced commits to refs/pull/48757/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

2afa605254 Merge 9a2d61680c into a392a39627

a392a39627 fix(vertex_ai): bill Claude web search per request on deployments priced in model_info (#49160)

d1d6d55063 fix(hosted_vllm): accept the vLLM production-stack router's file and batch objects (#49068)

afec145edc feat(passthrough): let a WebSocket relay bill a session from its client text (#49281)

84617874b8 fix(ui): resolve auto router templates through ids a * catch-all lists over a partial wildcard (#49331)

Compare 92 commits »

scriptoriumadmin synced commits to refs/pull/48762/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:24 +00:00

80ee47465a Merge 8f0eae1c89 into b195d15b93

b195d15b93 fix(vertex_ai,azure_ai)!: auto-add the compaction, thinking display, and tool change betas on Claude routes (#44747)

d18efdfe13 fix(vllm): send the pass-through key as a bearer on both /vllm routes (#46861)

5d5e3685c1 fix(logging): warn when drop_params drops a requested reasoning level on the remaining paths (#48933)

df47ec0171 fix(spend): keep a NaN or infinite cost from wedging daily spend writes (#48829)

Compare 65 commits »

scriptoriumadmin synced commits to refs/pull/48671/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:23 +00:00

e289f7c1ac Merge 22e8bf1969 into 8ac9b75737

8ac9b75737 fix(model_prices): rolling registry audit, add Gemini batch and Azure Astra flex tiers (#49114)

a084d13635 fix(passthrough): log the URL model and declared provider on Gemini and Vertex failures (#49075)

b195d15b93 fix(vertex_ai,azure_ai)!: auto-add the compaction, thinking display, and tool change betas on Claude routes (#44747)

d18efdfe13 fix(vllm): send the pass-through key as a bearer on both /vllm routes (#46861)

Compare 74 commits »

scriptoriumadmin synced commits to refs/pull/48685/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:23 +00:00

9c3377a784 Merge c7fa3584ce into ef9385c712

ef9385c712 refactor(proxy): inject gateway activity through a typed repository (#49116)

fbc157437c fix(guardrails): name only the request pipeline steps that ran in x-litellm-applied-guardrails (#49262)

ee2d7991df refactor(proxy): inject deployment warning ignores through repositories (#48592)

c919f3d9f3 refactor(proxy): inject database repositories through per-repository dependencies (#48507)

Compare 124 commits »

scriptoriumadmin synced commits to refs/pull/48697/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:23 +00:00

5d07cb7d11 Merge 250bc03936 into d1758cda91

d1758cda91 fix(router)!: keep a deployment's own model_id over the request body's (#49045)

373f1752d3 fix(anthropic): send PDF image_url content to Claude as document blocks (#46984)

4c8b90945f fix(realtime)!: send the Gemini Live setup at the first content so session.update settings apply (#39864)

73aaf9e3da fix(mistral): forward prompt_cache_key to the Mistral API (#47432)

Compare 87 commits »

scriptoriumadmin synced commits to refs/pull/48693/merge at scriptoriumadmin/litellm from mirror 2026-10-31 07:12:23 +00:00

0156841a5e Merge 8d1489085f into 837f36e872

837f36e872 fix(proxy): log router-refused image generation requests (#49349)

a9b181489b fix(gemini): add the batch, flex and priority text output prices to gemini-2.5-flash-image (#49358)

458463a20d fix(search): forward Perplexity search filters (#49344)

969ded2b54 fix(guardrails): drop the response pipeline steps that never ran from x-litellm-applied-guardrails (#49264)

Compare 299 commits »