scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/43160/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
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)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
1e7da87e1e fix(otel)!: give key/team Langfuse destinations user, tags and session on OTel v2 without global Langfuse keys (#48718)
Compare 153 commits »
scriptoriumadmin synced commits to refs/pull/42737/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
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)
c489aa7117 feat(proxy)!: add suppress_startup_output to turn off startup prints (#47708)
Compare 69 commits »
scriptoriumadmin synced commits to refs/pull/43290/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
fa9cd8fed3 fix(bedrock): treat a region path like the bare id when the cost map does not list it
1f2ca49601 fix(bedrock): judge lookaround support by model id on every route, ignore price-only rows
d42065a37d Merge branch 'main' into fix/bedrock-unmapped-converse-only-families
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)
Compare 122 commits »
scriptoriumadmin synced commits to refs/pull/42950/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
fd8b89fbec fix(mcp)!: restore upstream-token admission for legacy delegate servers (#48939)
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)
Compare 138 commits »
scriptoriumadmin synced commits to refs/pull/43314/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +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 294 commits »
scriptoriumadmin synced commits to refs/pull/43290/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
fa9cd8fed3 fix(bedrock): treat a region path like the bare id when the cost map does not list it
636e707089 fix(proxy)!: stop answering with the literal string "None" as error type and param on the proxy-server, auth, spend, and key health routes (#39540)
dacaaad72e build: allow filelock 4.x and sync package metadata (#49137)
d302096b5a feat(lite): offer each model group's reasoning efforts in pi, OpenCode and Codex (#48949)
Compare 114 commits »
scriptoriumadmin synced commits to refs/pull/42973/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
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)
3057c47d6d fix(caching): keep reasoning, citations, and audio on streamed cache hits (#32096)
Compare 218 commits »
scriptoriumadmin synced commits to refs/pull/43164/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
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)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
1e7da87e1e fix(otel)!: give key/team Langfuse destinations user, tags and session on OTel v2 without global Langfuse keys (#48718)
Compare 151 commits »
scriptoriumadmin synced commits to refs/pull/42993/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +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 »
scriptoriumadmin synced commits to refs/pull/42943/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +00:00
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)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 407 commits »
scriptoriumadmin synced commits to refs/pull/43172/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:24 +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 256 commits »
scriptoriumadmin synced commits to refs/pull/41869/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
ffcc4f7a70 fix(otel)!: print OTel v2 spans to stdout only when the operator asks (#48723)
a54204b583 feat(guardrails): scan sampled stream windows in the background (#48952)
1e7da87e1e fix(otel)!: give key/team Langfuse destinations user, tags and session on OTel v2 without global Langfuse keys (#48718)
83d6779158 fix(guardrails)!: make lakera_v2 on_flagged block reject PII-only detections, add mask (#48944)
Compare 151 commits »
scriptoriumadmin synced commits to refs/pull/42667/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
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)
733cfeba93 fix(cost): bill a provider reported usage.cost on every path unless the deployment is priced (#48953)
369f3cb5f0 feat(cost-map): add baseten joey-1 decision model (#49123)
Compare 261 commits »
scriptoriumadmin synced commits to refs/pull/42481/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
b25ea48c4b fix(anthropic)!: drop beta-gated body fields under drop_params (#48793)
1a05aab72a fix(bedrock)!: route region-prefixed embedding models to that region and bill its price (#49072)
784a52de79 test(router_strategy): keep foreign asyncio task noise out of the budget limiter caplog asserts (#43375)
4212f1af27 fix(passthrough): forward OpenAI-Beta and default agents=v1 on the OpenAI passthrough (#49009)
Compare 265 commits »
scriptoriumadmin synced commits to refs/pull/42539/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +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 225 commits »
scriptoriumadmin synced commits to refs/pull/42417/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
2383124b40 fix(cost): bill native /v1/messages from logging setup, as main did, to the end the proxy reports
77857f2fed test(anthropic): pin per-second-only pricing on native /v1/messages with a long-context-rate deployment
511b47ad8a Merge remote-tracking branch 'origin/main' into litellm_per_second_pricing_responses_messages
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 63 commits »
scriptoriumadmin synced commits to refs/pull/41818/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +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 150 commits »
scriptoriumadmin synced commits to refs/pull/41809/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
c1ac75cbc7 test(mcp): assert platform-header probe test observes the 401 for an unknown caller
scriptoriumadmin synced commits to refs/pull/42322/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
ebf84f8649 fix(caching): read the cache key's model group from the router's metadata for the call (#48917)
41602e318d fix(proxy): stream a guardrail block on /v1/messages as Anthropic events (#49010)
444423a5ca fix(cost): bill a deployment's per-second rates on native Anthropic /v1/messages (#42417)
cd42694b48 feat(providers): add Kyma API as an OpenAI-compatible provider (#48756)
Compare 271 commits »
scriptoriumadmin synced commits to refs/pull/42466/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:47:23 +00:00
d929ee6c6d Merge branch 'main' into fix/29142-end-user-max-budget-writeback
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 1235 commits »