scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/49019/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
fd594ab0cf fix: enforce LiteAdmin MCP route permissions (#48080)
e0778bc9dd refactor(types): replace Any with proven types in 21 files (#48921)
Compare 103 commits »
scriptoriumadmin synced commits to refs/pull/49009/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
f6287c88b5 fix(passthrough): forward the client's OpenAI-Beta only on agents, vaults, and ChatKit paths
560d514843 Merge remote-tracking branch 'origin/main' into litellm_openai_passthrough_agents_beta_header
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
Compare 29 commits »
scriptoriumadmin synced commits to refs/tags/v1.109.0-dev.2 at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
scriptoriumadmin synced commits to refs/pull/49010/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
0eacd95402 test(proxy): block messages through a real pre-call guardrail in endpoint tests
37ad875741 test(proxy): expect Anthropic events from a streamed messages guardrail block
a7581868d4 fix(proxy): keep post-call guardrails off the streamed messages block
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/49020/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
d8f162ea22 fix(guardrails): allow MCP call modes on the generic guardrail API (#48060)
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 76 commits »
scriptoriumadmin synced commits to refs/pull/49006/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
3e74a17531 Merge branch 'main' into litellm_dedupe_codex_additional_tools
5eb1042bbf fix(token_counter): count OpenAI models newer than tiktoken's table with o200k_base (#48728)
c068d1350b fix(responses): stream every citation batch before completion (#48747)
ff22f3de06 build(deps): bump langgraph and tornado and add dated scan ignores to clear osv-scan and image-scan (#48302)
3f5e42d032 fix(proxy): enforce team and key Allowed Vector Stores when no vector store registry is loaded (#48915)
Compare 18 commits »
scriptoriumadmin synced commits to refs/pull/49022/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
ee7e45f2ad test: keep the Terraform trigger test in the mapped workflow test file
40b70c919e ci: run the Terraform provider endpoint audit on enterprise route changes
af3e8a01f3 test: check make check and CI pick the same files for the API-type sync
3cbb932010 docs: name the full ui-api-types trigger set in the make check header and dashboard AGENTS.md
0aacbab705 chore: drop the spec_pattern comment
Compare 31 commits »
scriptoriumadmin synced new reference refs/tags/v1.109.0-dev.2 to scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
scriptoriumadmin synced commits to refs/pull/49011/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:22 +00:00
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
7aa0393cb6 feat(providers): add CLF AI Gateway as an OpenAI-compatible provider with ten models (#39324)
fd594ab0cf fix: enforce LiteAdmin MCP route permissions (#48080)
e0778bc9dd refactor(types): replace Any with proven types in 21 files (#48921)
Compare 107 commits »
scriptoriumadmin synced commits to refs/pull/48993/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
923c813d47 fix(cost): preserve pass-through accounting across cancellation
31aaa418e2 fix(cost): reconcile finalization with tracked callback enqueue
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
06cdee91da fix(guardrails): scan and rewrite streamed /v1/completions under post_call guardrails (#49035)
Compare 87 commits »
scriptoriumadmin synced commits to refs/pull/49002/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
18c8e7e00d fix(noma): keep masked choices when a later choice's scan fails open on a stream
b477ceb6a6 Merge remote-tracking branch 'origin/main' into HEAD
92501255a5 fix(noma): scan each choice of a multi-choice reply on its own
8d441ebc15 test(otel): give the Langfuse destination tests the otel callback's stdout exporter (#49129)
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
Compare 103 commits »
scriptoriumadmin synced commits to refs/pull/49001/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
474e60cdc5 fix(gateway): list the browser-picked team first so an older replica mid-deploy issues it
d790d05eea Merge remote-tracking branch 'origin/main' into litellm_gateway_team_picker
bad98c4b02 fix(responses): call the renamed drops_params helper on the compact path (#49030)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
a66dc50efb test(json_fragment_accumulator): assert peak allocation instead of a drain timing ratio (#43370)
Compare 27 commits »
scriptoriumadmin synced commits to refs/pull/49000/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
f32ac94ad1 fix(openai): keep the upstream error body on e.response for OpenAI and Azure errors (#49079)
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)
342ce6ae4a feat(zai): support response_format and max_completion_tokens, add glm-5v-turbo pricing (#48335)
Compare 120 commits »
scriptoriumadmin synced commits to refs/pull/48999/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
d8e8dcef53 fix(fallback): compare a restated config-file rule against its resolved env value
9f8fd4ac94 fix(fallback): replace a stored router_settings row that holds a non-JSON string
fb5bad80ef fix(fallback): keep the config-owned 400 for an unset env reference and replace a non-object stored row
d85848667a test(fallback): key the refused-DEL Redis double by cache key
1341a05781 test(fallback): run the real config reload in the fallback write tests
Compare 35 commits »
scriptoriumadmin synced commits to refs/pull/48998/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
38cbc93d6a Merge remote-tracking branch 'origin/main' into HEAD
83d6779158 fix(guardrails)!: make lakera_v2 on_flagged block reject PII-only detections, add mask (#48944)
ff42ff4512 fix(dashscope): keep the qwen-image-3.0 input-image fee out of the shared cost map row
a0a8ca97d9 fix(cost): finalize synchronous response cost once for header, spend log and rollups (#48993)
a1bd5feebe feat(router): infer custom classifier tiers from model mappings (#48987)
Compare 95 commits »
scriptoriumadmin synced commits to refs/pull/48997/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
feda51453a fix!: retain unattributed daily activity across reports and exports (#48925)
4bc157e281 feat(proxy): replace the pre-migration row check with a rolled-back dry run of the pending migrations (#48961)
c45b264024 fix(proxy): persist tag spend and drain success callbacks within the shutdown budget (#48988)
c98641fd5a feat(dashscope)!: derive protocol bases from one domain (#47812)
Compare 64 commits »
scriptoriumadmin synced commits to refs/pull/48988/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
01dc11e1a4 test(logging): isolate deferred callback completion
152d3fb253 chore(logging): explain shared callback ownership
4204f199ea fix(logging): track overflow callbacks through shutdown
Compare 3 commits »
scriptoriumadmin synced commits to refs/pull/48980/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
8e989a0637 fix(claude-code): keep the no-database hint on skill_hub and warn that the remove step uninstalls plugins
e30731c043 fix(claude-code): read the marketplace key setting from the UI config and answer database outages with 503
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/48979/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
ad4a71c2b9 fix(proxy): price websocket Responses turns by served tier and hosted tools, and bill turns a client walked out of
4a4c9cf7e3 feat(guardrails): opt-in response_masked_data on PANW Prisma AIRS block (#46219)
e63fc85b7b fix(anthropic): keep Mistral thinking text on streaming /v1/messages (#49059)
c213234783 feat(vertex_ai)!: use HTTP/2 httpx client for search_api vector store (#40631)
Compare 90 commits »
scriptoriumadmin synced commits to refs/pull/48979/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:49:21 +00:00
791bc4aad6 Merge remote-tracking branch 'origin/main' into litellm_openai_ws_frame_model_gate
9252709cab feat(ui): add i18next plumbing and move the Workflows page onto it (#49144)
68b5a737a1 fix(anthropic): retry /v1/messages without strict when Claude rejects strict tools under drop_params (#49102)
08b539e6a8 fix(proxy)!: bill streamed /v1/completions without stream_options like chat (#45366)
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
Compare 111 commits »