scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/41631/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:13 +00:00
2b42691c65 build(deps): bump serde_with from 3.16.1 to 3.21.0 in /litellm-rust
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)
7f95b5f361 refactor: clean up fresh tech debt from 2026-09-28 (#43674)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/41631/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:13 +00:00
2b42691c65 build(deps): bump serde_with from 3.16.1 to 3.21.0 in /litellm-rust
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)
Compare 42 commits »
scriptoriumadmin synced commits to refs/pull/41638/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:13 +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 2770 commits »
scriptoriumadmin synced commits to refs/pull/41670/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:13 +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 62 commits »
scriptoriumadmin synced commits to refs/pull/41691/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:13 +00:00
f69d5c56bb fix(batches): keep bodyless failed batch lines reaching callbacks
a7c9dedbf5 fix(batches): make the line-item claim release ownership-safe
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/41264/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
a01c55beb0 fix(proxy-extras): merge main, keep P3009 ledger logs in the v2 error only
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)
Compare 1899 commits »
scriptoriumadmin synced commits to refs/pull/41325/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
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)
e814532033 fix(streaming): keep the served service_tier on streamed chunks and spend rows (#42870)
273489824a refactor(rust): orchestrate Messages route execution (#43719)
Compare 83 commits »
scriptoriumadmin synced commits to refs/pull/41334/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
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)
e814532033 fix(streaming): keep the served service_tier on streamed chunks and spend rows (#42870)
273489824a refactor(rust): orchestrate Messages route execution (#43719)
Compare 85 commits »
scriptoriumadmin synced commits to refs/pull/41350/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +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 51 commits »
scriptoriumadmin synced commits to refs/pull/41363/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
a3552c451b chore(cost-map): add openai gpt-6.1-sol from the pricing page (#43738)
0c553f0398 feat(guardrails): send a configured gateway_name from noma_v2 to Noma (#43678)
d2cbc94fc6 feat(cost-map): add baseten DeepSeek-V4.1-Flash-Fast (#43735)
d46304900f fix(router): stream /v1/messages lifecycle frames live when no fallback can take over (#43600)
Compare 28 commits »
scriptoriumadmin synced commits to refs/pull/41389/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +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/41412/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +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 60 commits »
scriptoriumadmin synced commits to refs/pull/41430/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
4caf39425d fix(claude-code): echo installation_preference on the public skill hub
d51f84cc9c fix(claude-code): restrict installation_preference to the documented values
ad3275106b Merge remote-tracking branch 'origin/main' into litellm_marketplace_installation_preference
118ce3cc91 feat: add model leaderboard page (#43649)
39d14bd855 feat(fireworks_ai): route and list the auto, auto-instant and firerouter routers (#43641)
Compare 3608 commits »
scriptoriumadmin synced commits to refs/pull/41430/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
4caf39425d fix(claude-code): echo installation_preference on the public skill hub
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)
Compare 32 commits »
scriptoriumadmin synced commits to refs/pull/41477/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +00:00
46f7775157 bump: litellm-enterprise 0.1.71 -> 0.1.72, litellm-proxy-extras 0.4.102 -> 0.4.103, litellm 1.104.0 -> 1.105.0 (#43789)
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)
Compare 53 commits »
scriptoriumadmin synced commits to refs/pull/41482/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +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 60 commits »
scriptoriumadmin synced commits to refs/pull/41528/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:12 +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/41264/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:11 +00:00
a01c55beb0 fix(proxy-extras): merge main, keep P3009 ledger logs in the v2 error only
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)
e814532033 fix(streaming): keep the served service_tier on streamed chunks and spend rows (#42870)
Compare 4074 commits »
scriptoriumadmin synced commits to refs/pull/41163/head at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:11 +00:00
f8734fd815 fix(mcp): satisfy type discipline gate on listed-tool identity
0ae683b45b Merge remote-tracking branch 'origin/main' into litellm_mcp_listed_tool_metadata
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)
Compare 168 commits »
scriptoriumadmin synced commits to refs/pull/41219/merge at scriptoriumadmin/litellm from mirror 2026-09-30 01:53:11 +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 41 commits »