scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/39884/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:06 +00:00
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
0fb93ed9de fix(vertex_ai): forward the per-turn-control beta for per-message output_config (#43558)
60fca8298e fix(otel): send cache and reasoning tokens in langfuse usage_details (#43553)
Compare 41 commits »
scriptoriumadmin synced commits to refs/pull/39888/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:06 +00:00
abc85c2651 fix(cost_calculator): bill chat per-second pricing once with a new cost_per_second field (#43614)
0fe4028cd9 fix(cost-map): lower fireworks up-to-4b size tier to the pricing page price (#43740)
5a5e563938 test(proxy): classify every credential-bearing param for the canary suite (#43298)
bda2763f2c chore(cost-map): add azure and openrouter gpt-6.1-sol rows (#43744)
Compare 33 commits »
scriptoriumadmin synced commits to refs/pull/38925/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
d46304900f fix(router): stream /v1/messages lifecycle frames live when no fallback can take over (#43600)
66db132627 refactor(rust): add shared llms wire type derives (#43730)
684a1edd44 docs(security): point readers to the security announcements mailing list signup (#43713)
9dfa42dcde refactor(types): replace Any with proven types in 7 files (#43704)
Compare 22 commits »
scriptoriumadmin synced commits to refs/pull/38925/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
63d8e24a03 fix: list llmman in provider_create_fields
3e04ac7837 Merge branch 'main' into feature/llmman-provider
39d14bd855 feat(fireworks_ai): route and list the auto, auto-instant and firerouter routers (#43641)
bd2ce26516 test: move llmman tests to tests/unit
91958c568e fix: address llmman provider review
Compare 7592 commits »
scriptoriumadmin synced commits to refs/pull/38959/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
9525452d37 perf(proxy): one post-call Redis pipeline per backend for spend, rate-limit, routing and response-cache writes (#43779)
c129ea4fc9 fix(mcp): scope OpenAPI listings to the exact server prefix and drop upstream OAuth metadata when a server is saved (#43608)
ffb15f946f perf(proxy): one request-scoped Redis pipeline for auth, spend, rate-limit and routing reads (#43407)
e7460f1cff chore(cost-map): take azure context limits from models-sold-directly (#43759)
Compare 74 commits »
scriptoriumadmin synced commits to refs/pull/39086/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
0fb93ed9de fix(vertex_ai): forward the per-turn-control beta for per-message output_config (#43558)
60fca8298e fix(otel): send cache and reasoning tokens in langfuse usage_details (#43553)
Compare 39 commits »
scriptoriumadmin synced commits to refs/pull/39090/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
0fb93ed9de fix(vertex_ai): forward the per-turn-control beta for per-message output_config (#43558)
Compare 21 commits »
scriptoriumadmin synced commits to refs/pull/39117/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
684a1edd44 docs(security): point readers to the security announcements mailing list signup (#43713)
9dfa42dcde refactor(types): replace Any with proven types in 7 files (#43704)
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
Compare 39 commits »
scriptoriumadmin synced commits to refs/pull/39122/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
abc85c2651 fix(cost_calculator): bill chat per-second pricing once with a new cost_per_second field (#43614)
0fe4028cd9 fix(cost-map): lower fireworks up-to-4b size tier to the pricing page price (#43740)
5a5e563938 test(proxy): classify every credential-bearing param for the canary suite (#43298)
bda2763f2c chore(cost-map): add azure and openrouter gpt-6.1-sol rows (#43744)
Compare 54 commits »
scriptoriumadmin synced commits to refs/pull/39135/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
abc85c2651 fix(cost_calculator): bill chat per-second pricing once with a new cost_per_second field (#43614)
0fe4028cd9 fix(cost-map): lower fireworks up-to-4b size tier to the pricing page price (#43740)
5a5e563938 test(proxy): classify every credential-bearing param for the canary suite (#43298)
bda2763f2c chore(cost-map): add azure and openrouter gpt-6.1-sol rows (#43744)
Compare 52 commits »
scriptoriumadmin synced commits to refs/pull/39255/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
684a1edd44 docs(security): point readers to the security announcements mailing list signup (#43713)
9dfa42dcde refactor(types): replace Any with proven types in 7 files (#43704)
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
Compare 15 commits »
scriptoriumadmin synced commits to refs/pull/39303/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
0fb93ed9de fix(vertex_ai): forward the per-turn-control beta for per-message output_config (#43558)
Compare 118 commits »
scriptoriumadmin synced commits to refs/pull/39324/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:05 +00:00
e1b4d744d7 test(clf_ai_gateway): move the provider tests to tests/unit/llms
4dbe4aa516 test(clf_ai_gateway): expect the re-measured reasoning_effort levels
e2b7e216ec fix(clf_ai_gateway): drop a rebind-ok that no longer suppresses anything
a9ac442857 fix(clf_ai_gateway): sync prices and reasoning_effort levels with the live catalog
e009e4ffea fix(clf_ai_gateway): list the provider in the proxy Add Model form
Compare 2966 commits »
scriptoriumadmin synced commits to refs/pull/38630/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
6684256136 feat(agents): add identity storage and validation contracts (#43720)
13d004fc5a perf(proxy): refresh auth management objects through the request Redis pipeline (#43776)
cae179e655 fix(bedrock): set gpt-6.1-sol max output tokens to 131072 (#43782)
9525452d37 perf(proxy): one post-call Redis pipeline per backend for spend, rate-limit, routing and response-cache writes (#43779)
Compare 95 commits »
scriptoriumadmin synced commits to refs/pull/38647/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
0fb93ed9de fix(vertex_ai): forward the per-turn-control beta for per-message output_config (#43558)
Compare 19 commits »
scriptoriumadmin synced commits to refs/pull/38688/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
24a7e89738 perf(responses): run aresponses through the async wrapper so the cache is read once (#43769)
2d034bb35b perf(proxy): hold one spend counter batch across admission and across post-call accounting (#43369)
d2a574b791 perf(router): fetch cooldown state and usage counters in one Redis round trip (#43320)
27c110cb71 feat(bedrock): add openai gpt-6.1-sol global and base rows (#43758)
Compare 60 commits »
scriptoriumadmin synced commits to refs/pull/38729/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
6684256136 feat(agents): add identity storage and validation contracts (#43720)
13d004fc5a perf(proxy): refresh auth management objects through the request Redis pipeline (#43776)
cae179e655 fix(bedrock): set gpt-6.1-sol max output tokens to 131072 (#43782)
9525452d37 perf(proxy): one post-call Redis pipeline per backend for spend, rate-limit, routing and response-cache writes (#43779)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/38737/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
684a1edd44 docs(security): point readers to the security announcements mailing list signup (#43713)
9dfa42dcde refactor(types): replace Any with proven types in 7 files (#43704)
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
Compare 39 commits »
scriptoriumadmin synced commits to refs/pull/38780/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
6684256136 feat(agents): add identity storage and validation contracts (#43720)
13d004fc5a perf(proxy): refresh auth management objects through the request Redis pipeline (#43776)
cae179e655 fix(bedrock): set gpt-6.1-sol max output tokens to 131072 (#43782)
9525452d37 perf(proxy): one post-call Redis pipeline per backend for spend, rate-limit, routing and response-cache writes (#43779)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/38812/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:04 +00:00
9dfa42dcde refactor(types): replace Any with proven types in 7 files (#43704)
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
85dc7cb62e fix(proxy): resolve model_group_alias in the zero-cost budget predicate (#43512)
7b2cbf6e7f fix(cost-map): add tool calling and reasoning flags, correct max output for nebius DeepSeek-V4.1-Flash (#43588)
Compare 19 commits »