scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/47415/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
83d6779158 fix(guardrails)!: make lakera_v2 on_flagged block reject PII-only detections, add mask (#48944)
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)
5dcc3a1bbf docs: link README to Python SDK and autorouter guides (#48986)
Compare 150 commits »
scriptoriumadmin synced commits to refs/pull/47448/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
c1157c3211 refactor(proxy): drop leftover group_by=tag branch and the tag page SQL-text test
29cdadc799 fix(proxy): honor exclude_team_ids on the team tags page
51b3032fb8 fix(proxy): allowlist team tag activity endpoint
Compare 155 commits »
scriptoriumadmin synced commits to refs/pull/47430/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
95d9b96442 test(proxy): drop the mock-echo failure-hook tag team test
188173b02e fix(logging): keep the virtual-key flag out of the standard logging payload
e121952e17 test(proxy): drop the SQL-text check for the tag team upsert
ae52e40e67 test(proxy): pin the tag team upsert rule and drop the schema check changes
466dcc022c fix(proxy): carry the virtual-key flag in the key's logged metadata
Compare 393 commits »
scriptoriumadmin synced commits to refs/pull/47484/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
15f8086684 test(least-busy): give callback fixtures a fixed call-start time
67bc809393 fix(least-busy): release a pick whose call ends before reaching the provider
854231f823 fix(least-busy): lock the reservation read-and-update so threaded sync calls keep each other's picks
b6e27dd5dc style(router): wrap the least-busy reservation store line
b83aa99cfc Merge remote-tracking branch 'origin/main' into HEAD
Compare 642 commits »
scriptoriumadmin synced commits to refs/pull/47483/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
e24a7b9b94 test(http_handler): drop the capture list from the connect timeout tests
scriptoriumadmin synced commits to refs/pull/47345/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
Compare 183 commits »
scriptoriumadmin synced commits to refs/pull/47430/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
95d9b96442 test(proxy): drop the mock-echo failure-hook tag team test
188173b02e fix(logging): keep the virtual-key flag out of the standard logging payload
e121952e17 test(proxy): drop the SQL-text check for the tag team upsert
ae52e40e67 test(proxy): pin the tag team upsert rule and drop the schema check changes
Compare 147 commits »
scriptoriumadmin synced commits to refs/pull/47479/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
96e3bed303 fix(ui): say the Spend Per Tag card counts only the team's virtual keys
32d7ed6410 fix(ui): make rows per page work on the Spend Per Tag card
fb6c72e3c5 refactor(ui): inline the one-team check for the Spend Per Tag card
67220b08e3 fix(ui): update tag spend formatting and mock
d7d0a293ea feat(ui): page the Spend Per Tag card through the team tags report
Compare 407 commits »
scriptoriumadmin synced commits to refs/pull/47479/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
96e3bed303 fix(ui): say the Spend Per Tag card counts only the team's virtual keys
32d7ed6410 fix(ui): make rows per page work on the Spend Per Tag card
Compare 163 commits »
scriptoriumadmin synced commits to refs/pull/47483/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:18 +00:00
e24a7b9b94 test(http_handler): drop the capture list from the connect timeout tests
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 345 commits »
scriptoriumadmin synced commits to refs/pull/47336/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
70363966aa Merge branch 'main' of github.com:BerriAI/litellm into feat/aistupidlevel-provider
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 222 commits »
scriptoriumadmin synced commits to refs/pull/47279/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
4ce724e3df fix(caching): key cached async clients by a per-loop token instead of id(loop) (#48877)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
Compare 183 commits »
scriptoriumadmin synced commits to refs/pull/47322/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +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 218 commits »
scriptoriumadmin synced commits to refs/pull/47312/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
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)
d884167bf2 fix(responses): only merge repeated Codex tools when drop_params is on (#49112)
62b8ee78de ci: run the integration groups on GitHub Actions (#48985)
Compare 184 commits »
scriptoriumadmin synced commits to refs/pull/47315/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
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)
ead221995e refactor(router): move router callers onto the entry points and invert the proxy imports (#48847)
57f6e1b39f fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039)
Compare 287 commits »
scriptoriumadmin synced commits to refs/pull/47336/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
70363966aa Merge branch 'main' of github.com:BerriAI/litellm into feat/aistupidlevel-provider
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)
b7da9a2755 fix(credentials): keep the stored secret when PATCH echoes its masked read-back (#48950)
Compare 221 commits »
scriptoriumadmin synced commits to refs/pull/47293/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
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)
ead221995e refactor(router): move router callers onto the entry points and invert the proxy imports (#48847)
57f6e1b39f fix(proxy): keep the litellm command light so spawned workers answer uvicorn's first health ping (#45039)
Compare 287 commits »
scriptoriumadmin synced commits to refs/pull/47304/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
71babd931b fix(llms): move later developer messages for models declared system-first (#48897)
d037d86a94 fix(token_counter)!: keep a loaded Hugging Face tokenizer when a slower download fails (#48916)
c87a25a357 feat(proxy)!: general_settings.claude_code_marketplace_auth_required puts the Claude Code marketplace behind a LiteLLM key (#48980)
e8f0735d8a feat(proxy): let a Claude Code gateway user choose the session team (#49001)
Compare 174 commits »
scriptoriumadmin synced commits to refs/pull/47321/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +00:00
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)
c666df3dac docs(qa): allow focused proof for mechanical PRs (#49031)
Compare 117 commits »
scriptoriumadmin synced commits to refs/pull/47310/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:17 +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 302 commits »