Commit graph

30946 commits

Author SHA1 Message Date
jquinter
f43757f71b
Feature/guardrail model argument (#19619)
* [Feat] Add model parameter to Generic Guardrail API

Add model information to guardrail requests, allowing guardrails to make
model-specific security decisions.

Changes:
- Add `model` field to GenericGuardrailAPIInputs TypedDict
- Add `model` field to GenericGuardrailAPIRequest Pydantic model
- Update OpenAI and Anthropic handlers to pass model from request/response
- Add unit tests for model parameter handling

* [Feat] Add model parameter to all guardrail_translation handlers

Extend model parameter support to all guardrail handlers for consistent
implementation across all endpoint types:
- OpenAI Responses API (input/output + streaming)
- OpenAI Image Generation (input only)
- OpenAI Text Completion (input/output)
- OpenAI Text-to-Speech (input only)
- OpenAI Audio Transcription (output only)
- Cohere Rerank (input only)
- Pass-through Endpoints (input/output)
- MCP Server (input only)

This addresses the review feedback requesting consistent model parameter
handling across all guardrail_translation/handler.py files.

---------

Co-authored-by: Igal Boxerman <igal@pillar.security>
2026-01-23 20:48:42 -08:00
John Greek
4c5351f43b
[Fix] Password comparison with non-ASCII characters (#19559) (#19568) 2026-01-23 20:27:42 -08:00
Marcos Griselli
6b1ce4e766
fix(rag): use router for completion in RAG query pipeline (#19550)
The RAG query endpoint was failing with "Object of type Router is not
JSON serializable" when called through the proxy. This was caused by two
issues:

1. The Router object passed via kwargs was leaking into the request
   payload sent to providers like Bedrock, causing JSON serialization
   errors.

2. The RAG query pipeline was calling litellm.acompletion() directly
   instead of using the router, so virtual model names configured in the
   proxy weren't being resolved to actual provider model IDs.

This fix:
- Extracts the router from kwargs and uses router.acompletion() when
  available, falling back to litellm.acompletion() otherwise
- Adds "Router" to the list of non-serializable types in
  filter_exceptions_from_params as a defensive measure

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 20:11:17 -08:00
Priyam Manna
ac0ab214fb
fix(ui): Change default key type from 'Default' to 'LLM API' for improved security (#19516)
- Changed initial keyType state to 'llm_api' instead of 'default'
- Updated reset functions (handleOk, handleCancel) to use 'llm_api'
- Updated form initialValue and Select defaultValue to 'llm_api'

Addresses #19492
2026-01-23 19:58:49 -08:00
houdataali
7ffc1a718a
a2a agent Header-Based Context Propagation (#19504)
* a2a agent Header-Based Context Propagation

* docs: add guide for A2A context header forwarding
2026-01-23 19:56:04 -08:00
Misha
de538456e3
feat: support role_mappings from environment variables (#19498)
* feat: support role_mappings from environment variables

* fix linter
2026-01-23 19:54:23 -08:00
Alexsander Hamir
5c61586e65
Add GCS mock mode for testing without API calls (#19683) 2026-01-23 16:25:32 -08:00
Alexsander Hamir
56883add3c
Add Langfuse mock mode for testing without API calls (#19676) 2026-01-23 15:33:40 -08:00
yuneng-jiang
22a268c544
Merge pull request #19673 from BerriAI/litellm_ui_router_fallbacks_02
[Feature] UI - Fallbacks: New Add Fallbacks Modal
2026-01-23 14:33:30 -08:00
yuneng-jiang
3ba9b13390 adding tests 2026-01-23 14:28:47 -08:00
yuneng-jiang
7e6fc6af2c New add fallbacks modal 2026-01-23 14:21:32 -08:00
Ishaan Jaffer
5b341ee842 fix linting 2026-01-23 13:46:02 -08:00
milan-berri
37b7dff194
add spend-queue-troubleshooting docs (#19659)
* add spend-queue-troubleshooting docs

* adjust spend-queue-troubleshooting docs
2026-01-23 13:44:41 -08:00
mubashir1osmani
c41963c949
fix: add openinference span kinds to arize phoenix
fix: add openinference span kinds to arize phoenix
2026-01-23 16:32:49 -05:00
Ishaan Jaffer
c945677ea8 BUMP pyproject 2026-01-23 13:28:06 -08:00
mubashir1osmani
0993dca4e2 fix lint 2026-01-23 16:27:32 -05:00
mubashir1osmani
33a216d02a remove imports from functions 2026-01-23 16:18:21 -05:00
Ishaan Jaffer
b4dd0e4d19 fix schema.prisma 2026-01-23 13:17:52 -08:00
Ishaan Jaffer
c3b278e488 add migrtion 2026-01-23 13:17:06 -08:00
Ishaan Jaffer
9e02a38002 add schema.prisma 2026-01-23 13:16:58 -08:00
mubashir1osmani
744d15e068 remove imports from functions 2026-01-23 16:16:33 -05:00
Ishaan Jaffer
6621c7b2ef docs fix 2026-01-23 12:54:30 -08:00
Ishaan Jaff
fc19085230
[Feat] Guardrail Policy Management - Allow using UI to manage guardrail policies (#19668)
* init UI

* init schema.prisma

* fix: policy_crud_router

* UI fixes

* update gitignore

* working v0 for policy mgmt

* fix: endpoints to resolve guardrails

* fix code QA checks

* ui build issues

* schema fixes

* fix checks
2026-01-23 12:44:22 -08:00
yuneng-jiang
28bc83e394
Merge pull request #19662 from BerriAI/litellm_yj_ci_01
[Infra] CI/CD - Linting
2026-01-23 12:27:24 -08:00
yuneng-jiang
fbe5ae9e17 fixing flaky tests 2026-01-23 12:20:27 -08:00
yuneng-jiang
8b5b343841 attempt fix flaky tests 2026-01-23 12:10:08 -08:00
yuneng-jiang
5cacf56507 security scan 2026-01-23 11:55:56 -08:00
yuneng-jiang
647a6898a9 skipping non root tests entirely 2026-01-23 11:51:38 -08:00
yuneng-jiang
89bf7e50c4 skipping flaky tests 2026-01-23 11:43:39 -08:00
yuneng-jiang
a28911845f fixing config 2026-01-23 11:11:11 -08:00
Ishaan Jaffer
19141e180e docs fix 2026-01-23 11:06:02 -08:00
yuneng-jiang
a0b2832300 fixing security checks 2026-01-23 11:03:18 -08:00
yuneng-jiang
06b78208dd resetting poetry and requirements 2026-01-23 10:41:35 -08:00
yuneng-jiang
2d4c0f4e65 ci cd fixes - linting security 2026-01-23 10:37:16 -08:00
xqe2011
ca8c2c3938
fix #19620: SSO user roles are not updated for existing users (#19621)
* Fix: SSO user roles are not updated for existing users
Fixes #19620

* Refactor: Remove redundant user_info retrieval in SSOAuthenticationHandler

* Test: add new tests for user creation and updates in get_user_info_from_db
2026-01-23 09:05:29 -08:00
Sameer Kankute
9894721285
Merge pull request #19548 from BerriAI/litellm_staging_01_22_2026
Litellm staging 01 22 2026
2026-01-23 20:03:11 +05:30
Sameer Kankute
23f7d4f0b0
Merge pull request #19645 from BerriAI/litellm_gigachat_big_fix
Add tool choice mapping for giga chat
2026-01-23 19:52:35 +05:30
Sameer Kankute
a240eb7630
Merge pull request #19649 from BerriAI/litellm_fix_responses_api_logging_eror
Fix: Responses API logging error for StopIteration
2026-01-23 19:51:45 +05:30
Sameer Kankute
fe5fac17b3 Remove f string 2026-01-23 19:50:13 +05:30
Sameer Kankute
a4bf14f6e7 Fix: test_nova_invoke_streaming_chunk_parsing 2026-01-23 19:49:42 +05:30
Sameer Kankute
8357d05615 Fix: Responses API logging error for StopIteration 2026-01-23 18:42:33 +05:30
YutaSaito
8ac1d96d90
Merge pull request #19634 from BerriAI/litellm_feat_hashicorp_rotate
[feat] hashicorp vault rotate support
2026-01-23 21:08:55 +09:00
Sameer Kankute
acf5ad1155 Add tool choice mapping for giga chat 2026-01-23 16:29:19 +05:30
YutaSaito
83da74b12c
Merge pull request #19640 from BerriAI/litellm_fix_mcp_completions_spend_logs
[fix] include tool arguments in proxy_server_request for spend logs ca…
2026-01-23 18:45:42 +09:00
Sameer Kankute
12463809bd
Merge pull request #19638 from BerriAI/main
merge main in stagin 1 22 26
2026-01-23 14:54:17 +05:30
Yuta Saito
695fbf4ec5 feat: hashicorp vault rotate support 2026-01-23 17:32:55 +09:00
Yuta Saito
919033a6d0 fix: include tool arguments in proxy_server_request for spend logs callbacks 2026-01-23 16:36:37 +09:00
YutaSaito
4381e7f98f
Merge pull request #19624 from BerriAI/litellm_test_responses_api_with_mcp_tools
[test] Skip anthropic model test when ANTHROPIC_API_KEY is not set
2026-01-23 15:58:19 +09:00
YutaSaito
12bc66aa5b
Merge pull request #19623 from BerriAI/litellm_fix_completions_mcp_output_ordering
[fix] completions mcp output ordering
2026-01-23 15:56:02 +09:00
Yuta Saito
1ae9189ff8 test: Skip anthropic model test when ANTHROPIC_API_KEY is not set 2026-01-23 15:50:56 +09:00