ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 14c0a2b3e2
         feat(prometheus): emit per-token-type detail metrics (LIT-3220) (#28372) (#28378) ishaan-berri 2026-05-23 12:17:42 -0700
  • 5e16f20962
         test(proxy): phase-4 payload behavior pinning for tier-2/3 key + team management endpoints (#28681) yuneng-jiang 2026-05-23 12:16:29 -0700
  • 203b529c9d
         feat(azure): add speech transcription config support (#27482) ishaan-berri 2026-05-23 12:16:01 -0700
  • 2eab9ee2c0
         perf: reduce per-request and per-chunk overhead across Anthropic streaming hot paths (#28289) Yassin Kortam 2026-05-23 12:15:59 -0700
  • 3b2ce201d8
         encrypt callback_vars in key/team metadata at rest (#27141) Michael-RZ-Berri 2026-05-23 12:15:44 -0700
  • 492891cad8
         CI: copy of #25177 (OCI GenAI: embeddings, streaming/reasoning fixes, model catalog) (#28223) Mateo Wang 2026-05-23 12:15:41 -0700
  • 7270f723de
         fix(mcp): forward upstream initialize instructions on cold gateway init (#28231) milan-berri 2026-05-23 02:00:47 +0300
  • f35e7eb2f6
         feat(guardrails): add Microsoft Purview DLP guardrail (#24966) Sameer Kankute 2026-05-23 04:29:04 +0530
  • 574ee7526d
         test(streaming): tolerate Vertex 429 wrapped in MidStreamFallbackError (#28669) yuneng-jiang 2026-05-22 15:57:29 -0700
  • 1b141bc588
         fix(bedrock): decouple STS region from Bedrock aws_region_name (#28245) milan-berri 2026-05-23 00:39:24 +0300
  • a3c953ed4e
         style: apply black formatting to fix lint CI (LIT-3274) (#28639) (#28641) Krrish Dholakia 2026-05-22 12:10:37 -0700
  • 9600fda2cc
         fix(sagemaker): send native Cohere embed payload to Cohere SageMaker endpoints (#28613) milan-berri 2026-05-22 22:00:42 +0300
  • 643989989f
         chore(test): remove dead old Playwright e2e suite (#28632) ryan-crabbe-berri 2026-05-22 11:29:17 -0700
  • f62ae93e13
         test(proxy): behavior-pinning matrix for tier-2/3 key + team management endpoints (#28620) yuneng-jiang 2026-05-22 11:24:41 -0700
  • 985574b6be
         fix(check_licenses): read PEP 639 license-expression metadata (#28529) yuneng-jiang 2026-05-22 11:22:38 -0700
  • b0b25ae4b9
         Include team alias in CLI JWT token (#28621) Mateo Wang 2026-05-22 10:40:59 -0700
  • e9f0eddbd1
         Litellm oss staging 2 (#28582) Sameer Kankute 2026-05-22 22:34:23 +0530
  • 21a21e01f7
         fix(responses): use OpenAI SSEDecoder for Responses API streaming (#28566) Sameer Kankute 2026-05-22 22:33:36 +0530
  • 50a3f10a92
         feat(proxy): persist allowlisted OIDC claims in CLI SSO poll (#28463) Sameer Kankute 2026-05-22 22:28:50 +0530
  • ef36e89638
         feat(mcp): Add tool call and tool list support via UI for Oauth mcps (#28454) Sameer Kankute 2026-05-22 21:34:04 +0530
  • 7a93cceb9f
         Add error_description and hint for oauth flows (#28471) Sameer Kankute 2026-05-22 21:30:39 +0530
  • d96e26064f
         Fix conflicts and UI (#28477) Sameer Kankute 2026-05-22 21:25:28 +0530
  • d04373f4ce
         Add granian as a ASGI compliant web server. Provider better throughput stability, (#26027) harish-berri 2026-05-21 19:08:37 -0700
  • 07bcd2c19e
         test(e2e): forward LITELLM_LICENSE to UI e2e proxy (#28398) ryan-crabbe-berri 2026-05-21 18:17:03 -0700
  • 9fcd424318
         chore(deps): bump deps (#28528) yuneng-jiang 2026-05-21 17:42:21 -0700
  • 2a5dfcd5bc
         build(deps-dev): bump black to 26.3.1 and apply formatting (#28525) yuneng-jiang 2026-05-21 17:24:18 -0700
  • 0715ed3359
         build(deps): bump next from 16.2.4 to 16.2.6 in /ui/litellm-dashboard (#27665) (#28524) yuneng-jiang 2026-05-21 17:13:56 -0700
  • f1abe03ed6
         fix(docker): restore npm to non_root builder image (#28519) yuneng-jiang 2026-05-21 17:02:42 -0700
  • 3f953dfa96
         test(vertex_ai): tolerate transient 500 in google maps grounding test (#28503) yuneng-jiang 2026-05-21 17:01:49 -0700
  • 67e6e5e1df
         test(proxy): behavior-pinning matrix for team management endpoints (#28441) yuneng-jiang 2026-05-21 16:57:25 -0700
  • 10bd7406e0
         feat: add guardrail violation span attributes and fix missing spans on pre-call blocks (#28364) Yassin Kortam 2026-05-21 15:49:42 -0700
  • b55749248d
         fix(logging): recalculate cost after router retry failures (#28476) milan-berri 2026-05-22 00:07:05 +0300
  • b60d4677cd
         fix(vertex_gemma): strip context_management from request body (#28438) Mateo Wang 2026-05-21 10:40:33 -0700
  • 697a90ea77
         fix: end user logs (#27758) (#28290) yuneng-jiang 2026-05-20 23:37:19 -0700
  • b7e978a5c3
         Litellm oss staging 04 21 2026 2 (#26569) Sameer Kankute 2026-05-21 09:55:19 +0530
  • 37ef8d9059
         fix(proxy): hydrate wildcard discovery credentials (#28284) (#28419) yuneng-jiang 2026-05-20 20:03:05 -0700
  • 79a5a7abad
         feat(tests): behavior-pinning harness + Key Tier-1 matrix (#28321) yuneng-jiang 2026-05-20 19:27:44 -0700
  • e23d06dda4
         test(realtime): expect session.created as xAI realtime initial event (#28424) yuneng-jiang 2026-05-20 19:01:31 -0700
  • f99fb5f27f
         chore(ci): merge dev branch (#28314) yuneng-jiang 2026-05-20 17:47:33 -0700
  • 35520adb4f
         fix: serialize guardrail_response to JSON in OTEL traces (#28362) Yassin Kortam 2026-05-20 17:34:36 -0700
  • 988196911a
         Litellm oss staging 1 (#28337) Sameer Kankute 2026-05-21 05:57:03 +0530
  • 2f9ac77b24
         fix(proxy): expose Prisma idle/connect timeout + extra DB URL params (#28395) Yassin Kortam 2026-05-20 17:19:24 -0700
  • 8acf64e16c
         fix(interactions): never drop streamed text deltas; always emit terminal completion (#28394) Mateo Wang 2026-05-20 16:41:40 -0700
  • 718c4637a8
         feat(mcp): allow native MCP OAuth support for cursor (#28327) Sameer Kankute 2026-05-21 03:58:44 +0530
  • fecf212d70
         fix(vertex_ai): omit function_call id on Vertex Gemini 3.5+ tool turns (#28324) Sameer Kankute 2026-05-21 03:22:50 +0530
  • f82ff7ee2a
         test(ui-e2e): admin key creation with a specific proxy model (#28365) ryan-crabbe-berri 2026-05-20 13:37:17 -0700
  • f3a669fc5d
         feat(interactions): migrate to Google Interactions API steps schema (May 2026) (#28153) Sameer Kankute 2026-05-21 02:02:12 +0530
  • 68efe6970c
         fix(mcp): JWT on tools/list and REST tools/call server resolution (#28227) Sameer Kankute 2026-05-21 02:01:44 +0530
  • fb73995c40
         feat(ui): team passthrough routes create parity + edit load fix (#28098) ryan-crabbe-berri 2026-05-20 12:35:49 -0700
  • 5a00cb1592
         test(e2e): migrate runner to uv, add All Proxy Models key test (#28313) ryan-crabbe-berri 2026-05-20 12:35:29 -0700
  • 2eeca2d096
         fix(ui): restore log filter loading indicator (#28282) ryan-crabbe-berri 2026-05-20 12:35:06 -0700
  • 7f563b2593
         fix(router): use forwarded model_id for native Azure container IDs (#27921) Sameer Kankute 2026-05-21 01:02:34 +0530
  • 183092d797
         fix(proxy): normalize batch file IDs before ManagedObjectTable write (#28339) Sameer Kankute 2026-05-21 00:43:56 +0530
  • 0fb710400f
         fix(spend_counter): seed Redis counter via SET NX to prevent cross-pod double-seed (#27854) milan-berri 2026-05-20 20:57:08 +0300
  • 99a63d5180
         feat(gemini): add gemini-3.1-flash-lite model cost map (#28320) Sameer Kankute 2026-05-20 22:33:14 +0530
  • e59e34bed3
         Gemini managed agents support (#28270) Sameer Kankute 2026-05-20 04:32:03 +0530
  • 3c3d131f01
         Day 0 support : Gemini 3.5 Flash (#28268) Sameer Kankute 2026-05-20 04:20:54 +0530
  • cde4b1a94d
         feat: propagate team_id and team_alias to all child OTEL spans (#28273) Yassin Kortam 2026-05-19 15:31:25 -0700
  • 1480ec698b
         chore(ci): bump versions (#28287) yuneng-jiang 2026-05-19 15:10:37 -0700
  • 92de7423ef
         fix(tests): replace shut-down gpt-4o-audio-preview with gpt-audio-1.5 (#28281) yuneng-jiang 2026-05-19 14:48:30 -0700
  • 727a471ae9
         [Refactor] UI - Spend Logs: consolidate filter state and extract components (#25847) ryan-crabbe-berri 2026-05-19 10:58:48 -0700
  • cff3e0b75e
         refactor(bedrock/sagemaker): switch to lazy loading for response stre… (#28189) harish-berri 2026-05-18 23:21:04 -0700
  • 0290c7bc00
         fix(proxy): decode bytes and pass-through SSE for Google-native streamGenerateContent (#27444) (#28213) Sameer Kankute 2026-05-19 11:16:11 +0530
  • 581882879d
         feat(ui): add Interactions API endpoint to playground with SSE streaming (#28156) Sameer Kankute 2026-05-19 08:25:40 +0530
  • 761c280a6e
         fix(deepseek): use native /anthropic/v1/messages endpoint and sanitize tools (#28200) Mateo Wang 2026-05-18 18:14:13 -0700
  • 761ab19209
         fix(bedrock): sanitize batch metadata to prevent Pydantic ValidationError (#28202) Mateo Wang 2026-05-18 18:00:18 -0700
  • a7f3dbcbe3
         test(callbacks): harden flaky proxy callback-leak detector (#28195) yuneng-jiang 2026-05-18 16:39:02 -0700
  • 73e32a31bf
         feat(prometheus): add user_email and user_alias to user budget metrics (#28155) Sameer Kankute 2026-05-19 04:58:14 +0530
  • 36c494fdd2
         Litellm oss staging (#28161) Sameer Kankute 2026-05-19 04:57:44 +0530
  • 477b63c5ea
         fix(caching): replay openai/responses bridge cache hits as chat streams (#28158) Sameer Kankute 2026-05-19 04:57:06 +0530
  • ce87c411bf
         fix(tests): migrate realtime + rerank tests off shut-down upstream models (#28191) yuneng-jiang 2026-05-18 15:41:51 -0700
  • 8c6625216b
         fix(bedrock/cohere): send embedding_types as JSON array, not string (#28172) ishaan-berri 2026-05-18 12:16:20 -0700
  • bb448b0031
         fix(tests): stabilize image-edit VCR cassettes to stop live gpt-image-1 spend (#28110) Mateo Wang 2026-05-18 09:15:39 -0700
  • fe63650ebd
         fix(proxy): gate team allowed_passthrough_routes to proxy admins (#28097) ryan-crabbe-berri 2026-05-18 08:56:25 -0700
  • cf9b5e4fa7
         [Infra] Bump versions (#28094) yuneng-jiang 2026-05-16 18:31:43 -0700
  • 1b0ae3af83
         fix(mcp-oauth): PROXY_BASE_URL escape hatch + diagnostic logging for {"detail":"invalid_request"} (#28086) Mateo Wang 2026-05-16 17:48:03 -0700
  • 3d5a9ede05
         feat: add Terraform stacks for deploying LiteLLM on AWS and GCP (#27673) Yassin Kortam 2026-05-16 17:26:20 -0700
  • fbe0ee81f1
         fix(proxy): sort BYOK models by their displayed name in /v2/model/info (#28079) Shivam Rawat 2026-05-16 15:46:21 -0700
  • cd551f6fdb
         chore: update Next.js build artifacts (2026-05-16 22:22 UTC, node v20.20.2) (#28095) yuneng-jiang 2026-05-16 15:32:18 -0700
  • 86f73e5e8a
         feat(otel): set http.response.status_code on the success SERVER span (#28090) ryan-crabbe-berri 2026-05-16 15:29:56 -0700
  • 1b9acecbb3
         feat(model_catalog): add Azure AI Foundry GPT-5.4 model metadata (#28030) Shivam Rawat 2026-05-16 15:08:10 -0700
  • fbb39ef94d
         build(deps): pin openai==2.33.0 in uv.lock (#28088) yuneng-jiang 2026-05-16 14:49:31 -0700
  • 0300333753
         feat(otel): OTel-standard attributes on the proxy SERVER span (status code, route/path, preprocessing latency) (#28040) ryan-crabbe-berri 2026-05-16 13:45:08 -0700
  • 62dca9e977
         fix(ci): flag codecov uploads, enable carryforward, close coverage gaps (#28028) yuneng-jiang 2026-05-16 10:56:32 -0700
  • 57e5e4a3b7
         Merge pull request #28036 from BerriAI/litellm_grid-v4-e2e-tests-cZRwz yuneng-jiang 2026-05-16 09:38:40 -0700
  • 014cb8fa9d
         feat: add componentized proxy deployment with gateway, backend, ui, and migrations (#27557) Yassin Kortam 2026-05-16 09:25:17 -0700
  • 4e8ac3151d
         Merge branch 'litellm_internal_staging' into litellm_grid-v4-e2e-tests-cZRwz Mateo Wang 2026-05-16 16:19:38 +0000
  • f9485f1bf6
         refactor: strip PR-introduced docstrings and explanatory comments Mateo Wang 2026-05-16 15:33:29 +0000
  • fb7091ef79
         refactor(reasoning_effort_grid): tighten test helpers per Greptile review Mateo Wang 2026-05-16 15:11:36 +0000
  • 18c932210a
         fix(test_gemini): skip after pytest.raises catches the 429-wrapped ImageFetchError Mateo Wang 2026-05-16 07:54:57 +0000
  • 2b00ea9ee4
         test(ci): skip Fireworks tests on 404 + Gemini image-size test on 429 Mateo Wang 2026-05-16 07:47:25 +0000
  • e29ea53c31
         fix(reasoning_effort_grid): classify status by exception status_code, not class Mateo Wang 2026-05-16 07:32:25 +0000
  • 90cdbb92d7
         fix(tests): use litellm.anthropic_messages entrypoint + drop unstable openapi field Mateo Wang 2026-05-16 06:59:08 +0000
  • ec2f3aadb8
         Merge pull request #28039 from BerriAI/litellm_/nostalgic-johnson-eeb7c3 yuneng-jiang 2026-05-15 23:18:56 -0700
  • 8c537f70a3
         test(gemini): drop 100MB allocation in size-limit mock Yuneng Jiang 2026-05-15 23:10:38 -0700
  • 2130bdc5b6
         Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_/nostalgic-johnson-eeb7c3 Yuneng Jiang 2026-05-15 22:40:08 -0700
  • 1cf2d7f286
         test(gemini): de-flake test_gemini_image_size_limit_exceeded Yuneng Jiang 2026-05-15 22:34:57 -0700
  • 935a1c0eb9
         Merge pull request #28037 from BerriAI/litellm_/wonderful-lehmann-265845 yuneng-jiang 2026-05-15 22:34:43 -0700
  • b5db7ed37d
         test(fireworks): mock remaining live smoke tests Yuneng Jiang 2026-05-15 22:28:27 -0700
  • 9770efe9e1
         test(fireworks): mock document-inlining test instead of live call Yuneng Jiang 2026-05-15 22:25:37 -0700