Commit graph

42355 commits

Author SHA1 Message Date
Xianzong Xie
fc30b92167 add polling via cache feature 2025-12-03 18:37:28 -08:00
yuneng-jiang
e29acb2f64
Merge pull request #16850 from BerriAI/litellm_user_info_404
[Fix] Return 404 when a user is not found on /user/info
2025-12-03 17:15:55 -08:00
yuneng-jiang
224c012e14
Merge pull request #17383 from BerriAI/litellm_vertex_api_base
[Fix] Change labeling around Vertex Fields
2025-12-03 17:14:14 -08:00
yuneng-jiang
d215576477 Add auto redirect to SSO to new login page 2025-12-03 17:07:12 -08:00
yuneng-jiang
73824c278a
Merge pull request #17443 from BerriAI/litellm_v2_login
[Feature] New Login Page
2025-12-03 16:23:47 -08:00
yuneng-jiang
c5670839b6
Merge pull request #17399 from BerriAI/litellm_ui_config_add_sso
[Feature] Add auto_redirect_to_sso to UI Config
2025-12-03 15:59:06 -08:00
yuneng-jiang
37c598441f Change is_sso_configured to auto_redirect_to_sso 2025-12-03 15:48:50 -08:00
yuneng-jiang
8a1cf104e0 Merge remote-tracking branch 'origin' into litellm_ui_config_add_sso 2025-12-03 15:36:33 -08:00
yuneng-jiang
ee63105e16
Merge pull request #17446 from BerriAI/litellm_ui_e2e_cicd_fix
[Fix] Change e2e test to look for Virtual Keys instead of API Keys
2025-12-03 15:35:22 -08:00
yuneng-jiang
de4b79851f Change e2e test to look for Virtual Keys instead of API Keys 2025-12-03 15:26:25 -08:00
dependabot[bot]
462d423d86
Bump mcp from 1.10.1 to 1.23.0 in /.circleci (#17363)
Bumps [mcp](https://github.com/modelcontextprotocol/python-sdk) from 1.10.1 to 1.23.0.
- [Release notes](https://github.com/modelcontextprotocol/python-sdk/releases)
- [Changelog](https://github.com/modelcontextprotocol/python-sdk/blob/main/RELEASE.md)
- [Commits](https://github.com/modelcontextprotocol/python-sdk/compare/v1.10.1...v1.23.0)

---
updated-dependencies:
- dependency-name: mcp
  dependency-version: 1.23.0
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-12-03 15:19:34 -08:00
yuneng-jiang
43da0793d3 Fixed typo 2025-12-03 15:13:19 -08:00
yuneng-jiang
b14b4a7112 New login screen using v2/login 2025-12-03 15:05:29 -08:00
Ishaan Jaff
100cfc11ac
[Bug Fix] Parallel Request Limiter with /messages (#17426)
* fix: use standard_logging_object for parallel request limiter

* fix test parallel request limtier
2025-12-03 14:13:28 -08:00
Ishaan Jaffer
9b3d8302cf docs fix stable 2025-12-03 14:12:50 -08:00
yuneng-jiang
5f43e7a2d2 New login page WIP 2025-12-03 13:18:33 -08:00
yuneng-jiang
9bb292f478 V2 login route 2025-12-03 12:41:45 -08:00
yuneng-jiang
8aa939dd67
Merge pull request #17317 from BerriAI/litellm_ui_cred_refresh
[Feature] Delete Credential Enhancements
2025-12-03 12:20:55 -08:00
yuneng-jiang
857614d586
Merge pull request #17436 from BerriAI/litellm_ui_model_page_scrollbars
[Fix] Remove second scrollbar when sidebar is expanded + tooltip z index
2025-12-03 12:20:00 -08:00
yuneng-jiang
9783f0ff6c Remove second scrollbar when sidebar is expanded + tooltip z index 2025-12-03 12:14:48 -08:00
Haji Akhundov
69b32dd870 Fix ruff linting errors: remove unused imports and variables 2025-12-03 21:06:32 +01:00
Haji Akhundov
e5baff780a Enforce SCIM 2.0 compliance: reject non-existent users in groups
- Reject group operations when users don't exist (security fix)
- Prevents unauthorized user provisioning via group membership
- Aligns with SCIM 2.0 protocol: users must exist before group membership
- Add validation for empty user IDs
- Update tests to verify rejection behavior

This is a breaking change but necessary for security and SCIM compliance.
Users must be created via POST /Users before being added to groups.
2025-12-03 20:44:54 +01:00
Alexsander Hamir
56328e6535
[Refactor#2] litellm/init – Lazy-load utils to reduce memory + import time (#17171)
* fix: lazy load utils.py imports

Lazy-load most functions and response types from utils.py to avoid loading
tiktoken and other heavy dependencies at import time. This significantly
reduces memory usage when importing completion from litellm.
2025-12-03 11:40:16 -08:00
yuneng-jiang
dcb7552b79
Merge pull request #17379 from BerriAI/litellm_login_route_refactor
[Refactor] /login route
2025-12-03 11:32:16 -08:00
Felipe Garé
82a8134d7a
fixing optional parameter default value (#17434) 2025-12-03 11:24:32 -08:00
yuneng-jiang
8df8a7ef95 Merge remote-tracking branch 'origin' into litellm_ui_cred_refresh 2025-12-03 11:04:09 -08:00
yuneng-jiang
cc92fdf90f Merge remote-tracking branch 'origin' into litellm_ui_callback_fix 2025-12-03 11:02:59 -08:00
yuneng-jiang
457840afed Merge remote-tracking branch 'origin' into litellm_user_info_404 2025-12-03 11:02:23 -08:00
yuneng-jiang
e6620fcdad Ruff checks 2025-12-03 11:01:10 -08:00
Felipe Garé
5ecebe2a57
adding status parameter as optinal for FileObject (#17431) 2025-12-03 11:00:18 -08:00
Alexsander Hamir
0a7602bb7c
fix: prevent memory leak in aiohttp connection pooling (#17388)
* fix: prevent memory leak in aiohttp connection pooling

Add connection limits to aiohttp TCPConnector to prevent unbounded
connection growth that causes memory leaks. Without these limits,
aiohttp's _wrap_create_connection can accumulate connections
indefinitely in long-running processes.

Changes:
- Set default limit of 300 total connections and 50 per host
- Apply limits to shared proxy session initialization
- Apply limits to HTTP handler transport creation
- Configurable via AIOHTTP_CONNECTOR_LIMIT and
  AIOHTTP_CONNECTOR_LIMIT_PER_HOST environment variables
- Set to 0 for unlimited (not recommended for production)

This fix covers:
- All standard LLM provider API calls (OpenAI, Anthropic, etc.)
- Proxy server shared session
- Most guardrail HTTP calls

Impact: Prevents memory exhaustion in high-traffic deployments and
long-running proxy servers that make thousands of API calls.

Testing: Verified connection limits are applied correctly and
existing functionality remains unchanged.
2025-12-03 10:43:27 -08:00
yuneng-jiang
b3c0ea5414 Merge remote-tracking branch 'origin' into litellm_login_route_refactor 2025-12-03 10:40:11 -08:00
Richard Song
546c7e19e6
Uncomment response_model in user_info endpoint
Fixes https://github.com/BerriAI/litellm/issues/17429
2025-12-03 13:22:33 -05:00
Cesar Garcia
5e791464af
docs: add Microsoft Agent Lightning to projects (#17422)
Add Agent Lightning, Microsoft's open-source framework for training
AI agents with RL, APO, and SFT. Uses LiteLLM Proxy for LLM routing
and trace collection.
2025-12-03 09:07:02 -08:00
Krrish Dholakia
be5dd234bf docs: fix list 2025-12-03 08:01:26 -08:00
Sameer Kankute
ece1e49fda
Merge pull request #17414 from BerriAI/litellm_ragflow_vector_store
Add vector store support for ragflow
2025-12-03 20:48:52 +05:30
Sameer Kankute
fcc2855baa
Merge pull request #17403 from BerriAI/litellm_streaming_gemini_3_fix
Fix gemini 3 last chunk thinking block
2025-12-03 20:48:13 +05:30
Sameer Kankute
7967da77c0
Merge pull request #17419 from BerriAI/litellm_fix_bedrock_models_model_map
Fix bedrock models in model map
2025-12-03 20:45:45 +05:30
Sameer Kankute
7e9c1ffb33
Merge pull request #17407 from BerriAI/litellm_enforce_enforce_user_param
Enforce support of enforce_user_param to openai post endpoints
2025-12-03 20:45:21 +05:30
Sameer Kankute
1fbe310444
Merge pull request #17405 from BerriAI/litellm_gemini_thought_sig_tool_beta
Make thought sign in tool call id as a beta feat
2025-12-03 20:43:53 +05:30
Haji Akhundov
8871a5670b Simplify SCIM tests to focus on core issue 2025-12-03 14:50:03 +01:00
Haji Akhundov
c01a4c6e57 Add tests for SCIM user_email UUID validation fix
- Test user with UUID in user_email (defensive fix scenario)
- Test user with None email (root cause fix scenario)
- Verifies transformation doesn't fail and emails array is empty for invalid emails
2025-12-03 14:41:10 +01:00
Haji Akhundov
da71c5fa16 Fix SCIM GET /Users error when user_email is UUID
Root cause fix:
- Set user_email=None instead of user_id when creating users without email (scim_v2.py line 313)
- Prevents UUIDs from being stored in user_email field in the first place

Defensive fix:
- Add validation in scim_transformations.py to check if user_email contains '@' before creating SCIMUserEmail
- Handles existing users in database that may have UUIDs in user_email field
- Prevents validation error when transforming users to SCIM format

Fixes issue where GET /Users returns 500 error with message:
'value is not a valid email address: An email address must have an @-sign'
2025-12-03 13:35:31 +01:00
Sameer Kankute
c9c7823f43 Fix bedrock models in model map 2025-12-03 17:31:20 +05:30
Sameer Kankute
dad0b2c111 Fix unused imports 2025-12-03 15:32:42 +05:30
Sameer Kankute
8eaabb4ad7 Add vector store support for ragflow 2025-12-03 15:29:47 +05:30
Sameer Kankute
52090c3f3e
Merge pull request #17350 from BerriAI/litellm_rag_chat_completion_api
Add ragflow support for chat completions API
2025-12-03 13:29:32 +05:30
Sameer Kankute
ba59cebb57
Merge pull request #17408 from BerriAI/main
merge main
2025-12-03 12:33:21 +05:30
Krish Dholakia
8edcc4ecc3
Guardrails API - add streaming support (#17400)
* fix(initial-commit): adding a way to get the right response type based on the api route

* feat(unified_guardrail.py): support streaming guardrails

* test: update tests

* fix: fix linting errors

* test: update tests
2025-12-02 22:52:09 -08:00
Krish Dholakia
74ba18df55
Litellm chainguard fixes 12 02 2025 p1 (#17406)
* build: update dockerfile non root

* build: update build

* build: update non root

* build: dockerfile fixes

* build: ensure dockerfile + dockerfile.database also work
2025-12-02 22:50:13 -08:00