scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49490/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/49487/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/49484/head at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
baf5749b63 chore(ui): merge main into teams users and organizations i18n
0aa7079f04 fix(spend): read only the newest rows when paging sessions (LIT-8513) (#48886)
add7dea9aa fix(vertex-ai): drop batch prices from gemini-robotics-er-2-preview (#49895)
36cd03f10d fix(gemini): lower the gemini-3.5-flash-lite batch cache price and date the gemini-2.5-pro and 2.5-flash shutdown (#49871)
1cc7da6274 fix(proxy): list slash-less wildcard groups like claude-* on /v1/models and /model/info (#49832)
Compare 115 commits »
scriptoriumadmin synced commits to refs/pull/49477/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
add7dea9aa fix(vertex-ai): drop batch prices from gemini-robotics-er-2-preview (#49895)
36cd03f10d fix(gemini): lower the gemini-3.5-flash-lite batch cache price and date the gemini-2.5-pro and 2.5-flash shutdown (#49871)
1cc7da6274 fix(proxy): list slash-less wildcard groups like claude-* on /v1/models and /model/info (#49832)
baddc67041 fix(anthropic)!: carry prompt_cache_breakpoint to cache_control on chat completions to Claude (#49783)
Compare 22 commits »
scriptoriumadmin synced commits to refs/pull/49467/head at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
d1eb5f4431 refactor(proxy): share the cost map pricing lookup for the response cost header
b588663df2 Merge remote-tracking branch 'origin/main' into HEAD
add7dea9aa fix(vertex-ai): drop batch prices from gemini-robotics-er-2-preview (#49895)
36cd03f10d fix(gemini): lower the gemini-3.5-flash-lite batch cache price and date the gemini-2.5-pro and 2.5-flash shutdown (#49871)
1cc7da6274 fix(proxy): list slash-less wildcard groups like claude-* on /v1/models and /model/info (#49832)
Compare 130 commits »
scriptoriumadmin synced commits to refs/pull/49466/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
ff182c194e fix(logging): keep the caller's call_type when chat completions are bridged to the Responses API (#49710)
7bd342d7ea fix(proxy): let a config license unlock enterprise settings and spell "environment" right in license errors (#49745)
28b4300be2 fix(typesafe): mark jev-latest as answering Box questions now that it points to Jev 1.14 (#49835)
482f3c37ed fix(azure_ai): keep azure_ad_token out of the request body (#49769)
Compare 47 commits »
scriptoriumadmin synced commits to refs/pull/49464/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/49457/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:59 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/49456/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 77 commits »
scriptoriumadmin synced commits to refs/pull/49450/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
e3b12fe703 feat(proxy): configure the request header buffer size (#49883)
Compare 92 commits »
scriptoriumadmin synced commits to refs/pull/49416/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
add7dea9aa fix(vertex-ai): drop batch prices from gemini-robotics-er-2-preview (#49895)
36cd03f10d fix(gemini): lower the gemini-3.5-flash-lite batch cache price and date the gemini-2.5-pro and 2.5-flash shutdown (#49871)
1cc7da6274 fix(proxy): list slash-less wildcard groups like claude-* on /v1/models and /model/info (#49832)
baddc67041 fix(anthropic)!: carry prompt_cache_breakpoint to cache_control on chat completions to Claude (#49783)
Compare 19 commits »
scriptoriumadmin synced commits to refs/pull/49417/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
ce73cf8b9d chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974)
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
Compare 78 commits »
scriptoriumadmin synced commits to refs/pull/49435/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
ce73cf8b9d chore(cost-map): remove the 52 rows whose provider retired them before 2026 (#49974)
e9a6a25fe3 feat(providers): add Wally as an OpenAI-compatible provider (#45662)
de7bb21887 fix(credentials): preserve stored info when patching credentials (#49919)
d1e4b50d6a fix(router): keep a deployment's token limits off the shared backend cost map key (#49952)
Compare 73 commits »
scriptoriumadmin synced commits to refs/pull/49448/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
527d882508 test(responses): isolate cancel wire checks from background polling (#50002)
0150896a50 test(spend): run explained reads within real read transactions (#49996)
767613bd40 refactor(cache): remove experimental Redis and v2 caches (#50005)
640223719f feat(mcp): add an opt-in per-server setting to skip MCP tool output validation (#49961)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/49453/head at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
19e1c1e056 fix(guardrails): send Bedrock search result text to Lakera
9e8ecc48b2 Merge remote-tracking branch 'origin/main' into litellm_lakera_v2_bedrock_passthrough
6db7001c05 feat(ui): show user names instead of raw ids on detail pages (#47181)
883a2d1572 revert(bedrock): restore STS identity probe behavior before #49763 (#49939)
c7a6657449 feat(cost-map): record the provider's recommended replacement as successor_model on deprecating rows and report it from /model/deprecations (#49789)
Compare 158 commits »
scriptoriumadmin synced commits to refs/pull/49453/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
19e1c1e056 fix(guardrails): send Bedrock search result text to Lakera
3b35ae340d fix(rate-limit): estimate embedding image and audio data URIs as media in TPM pre-call checks (#49831)
391c8013c9 fix(proxy): cancel /team/spend/by_user in Postgres after 30s (#49922)
9e8ecc48b2 Merge remote-tracking branch 'origin/main' into litellm_lakera_v2_bedrock_passthrough
Compare 42 commits »
scriptoriumadmin synced commits to refs/pull/49442/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
ff182c194e fix(logging): keep the caller's call_type when chat completions are bridged to the Responses API (#49710)
7bd342d7ea fix(proxy): let a config license unlock enterprise settings and spell "environment" right in license errors (#49745)
28b4300be2 fix(typesafe): mark jev-latest as answering Box questions now that it points to Jev 1.14 (#49835)
482f3c37ed fix(azure_ai): keep azure_ad_token out of the request body (#49769)
Compare 47 commits »
scriptoriumadmin synced commits to refs/pull/49441/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
200ecdb6e6 fix(proxy): defer optional Prisma imports in SSO settings (#49771)
f52e5057f9 refactor(ui): move teams, users and orgs text onto i18n (#49484)
cba5bcb17e feat(model-catalog): read successor_model, the provider's recommended replacement for a deprecating row (#49791)
083961731c fix(model_prices): consolidate verified provider metadata and pricing (#49361)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/49439/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:58 +00:00
cbe361d970 feat(ui): rebuild the public AI Hub as a searchable list with a details pane (#49496)
b9ad61d4f6 fix(agentic)!: surface a failed agentic follow-up call instead of the pre-loop tool call (#49227)
d5ca88900c fix(anthropic): answer an upstream Anthropic 529 as 529 overloaded_error on /v1/messages (#46063)
2a9fad611f ci: run the OSV scan on rc branches (#49987)
Compare 72 commits »
scriptoriumadmin synced commits to refs/pull/49405/merge at scriptoriumadmin/litellm from mirror 2026-11-04 07:29:57 +00:00
200ecdb6e6 fix(proxy): defer optional Prisma imports in SSO settings (#49771)
f52e5057f9 refactor(ui): move teams, users and orgs text onto i18n (#49484)
cba5bcb17e feat(model-catalog): read successor_model, the provider's recommended replacement for a deprecating row (#49791)
083961731c fix(model_prices): consolidate verified provider metadata and pricing (#49361)
Compare 74 commits »