scriptoriumadmin
  • Joined on 2026-03-01
scriptoriumadmin synced commits to refs/pull/46861/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:06 +00:00
547013a7f3 fix(vllm): send VLLM_API_KEY when a router model with no api_base is forwarded to VLLM_API_BASE
32e2f7fe0a fix(vllm): send no placeholder key from keyless router models and stop doubling /v1 on the VLLM_API_BASE route
9eaefc88e7 Merge remote-tracking branch 'origin/main' into fix/vllm-passthrough-api-key
6e19a7f6ce fix(vllm): send only the bearer on router models and stop doubling /v1 on /vllm
1a2b443a32 ci: run the extensions integration group with 48 workers (#49134)
Compare 897 commits »
scriptoriumadmin synced commits to refs/pull/46860/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
4be4340328 fix(guardrails): keep calls still in flight out of the inspected response
4cf4510928 fix(otel): label guardrail spans with the choice they inspected
Compare 2 commits »
scriptoriumadmin synced commits to refs/pull/46859/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
23595f7fe5 fix(bedrock): backfill published regional service tier prices (#49113)
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
Compare 149 commits »
scriptoriumadmin synced commits to refs/pull/46844/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
e93e01ca4b fix(ci): build base native extension for OpenAPI lint (#49136)
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)
Compare 749 commits »
scriptoriumadmin synced commits to refs/pull/46860/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
23595f7fe5 fix(bedrock): backfill published regional service tier prices (#49113)
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
a7030a5a2c fix(vertex_ai): batch Claude models in Anthropic's native row shape (#45715)
Compare 160 commits »
scriptoriumadmin synced commits to refs/pull/46858/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
8173ba619f Merge remote-tracking branch 'origin/litellm_guardrail_choice_isolation' into litellm_guardrail_stream_inspection
4be4340328 fix(guardrails): keep calls still in flight out of the inspected response
4212f1af27 fix(passthrough): forward OpenAI-Beta and default agents=v1 on the OpenAI passthrough (#49009)
ebf84f8649 fix(caching): read the cache key's model group from the router's metadata for the call (#48917)
Compare 126 commits »
scriptoriumadmin synced commits to refs/pull/46858/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
8173ba619f Merge remote-tracking branch 'origin/litellm_guardrail_choice_isolation' into litellm_guardrail_stream_inspection
4be4340328 fix(guardrails): keep calls still in flight out of the inspected response
4cf4510928 fix(otel): label guardrail spans with the choice they inspected
5de1fcda40 Merge remote-tracking branch 'origin/litellm_guardrail_choice_isolation' into litellm_guardrail_stream_inspection
a9cdd82337 fix(guardrails): hold back finish_reason while a choice still owes guardrailed text
Compare 14 commits »
scriptoriumadmin synced commits to refs/pull/46845/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:05 +00:00
85af2f65c9 refactor(helm)!: connect both charts to a separately deployed Lens (#49169)
44cd858697 fix(cost): bill the requested model's rates when the response names an unpriced model (#48900)
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)
Compare 112 commits »
scriptoriumadmin synced commits to refs/pull/46799/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:04 +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/46811/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:04 +00:00
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)
3e3362d461 fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough (#48978)
e7d3b24d7c fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888)
Compare 259 commits »
scriptoriumadmin synced commits to refs/pull/46810/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:04 +00:00
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)
3e3362d461 fix(cohere): price native Cohere embed calls on Foundry relays and the Cohere passthrough (#48978)
e7d3b24d7c fix(logging): mark mirrored silent_model calls with is_silent_experiment in spend logs (#48888)
Compare 259 commits »
scriptoriumadmin synced commits to refs/pull/46833/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:04 +00:00
60601ca995 feat(pass-through): add eu/jev decision API pass-through with spend tracking (#46875)
bbc68e21f9 feat(dashscope): add image edits and text-to-speech (#48998)
a6fda5a17e bump: litellm-enterprise 0.1.80 -> 0.1.81, litellm-proxy-extras 0.4.111 -> 0.4.112 (#49149)
2b4cb92c8b fix(context_management)!: run clear_tool_uses in the gateway on the Responses API path (#47861)
Compare 129 commits »
scriptoriumadmin synced commits to refs/pull/46844/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:04 +00:00
8f03dfb047 fix(proxy): send the Gemini pass-through key in the x-goog-api-key header
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 832 commits »
scriptoriumadmin synced commits to refs/pull/46706/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +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 212 commits »
scriptoriumadmin synced commits to refs/pull/46771/head at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +00:00
10aef0c400 feat(reasoning): add disable_inline_reasoning_extraction to keep inline think tags in content
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 714 commits »
scriptoriumadmin synced commits to refs/pull/46771/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +00:00
10aef0c400 feat(reasoning): add disable_inline_reasoning_extraction to keep inline think tags in content
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 560 commits »
scriptoriumadmin synced commits to refs/pull/46707/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +00:00
0ba4e85496 refactor: make cross-API bridges call native executors instead of re-entering acompletion and aresponses
e0778bc9dd refactor(types): replace Any with proven types in 21 files (#48921)
19e538ab11 fix(cost-map): set together_ai Qwen3.7-Max back to the published price (#49125)
53ce41625f chore(databricks): retirement dates for DeepSeek V4 Flash (0731), V4 Pro (0813) and Inkling (#49124)
Compare 562 commits »
scriptoriumadmin synced commits to refs/pull/46689/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +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 361 commits »
scriptoriumadmin synced commits to refs/pull/46676/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +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 158 commits »
scriptoriumadmin synced commits to refs/pull/46643/merge at scriptoriumadmin/litellm from mirror 2026-10-30 06:48:03 +00:00
c102fcc213 refactor: clean up fresh tech debt in responses stream usage cost, bedrock count tokens comments and router return types
dff474e450 fix(responses): replay the original Responses item order, phase, and boundaries on the next chat turn (#48912)
96bb57b565 Merge remote-tracking branch 'origin/main' into litellm_techdebt_20261015
3f01341f0a fix(health)!: openai realtime health check reports healthy with a missing or invalid api key (#41233)
Compare 164 commits »