Commit Graph

31022 Commits

Author SHA1 Message Date
Harshit Jain
87acdef899
feat: tpm-rpm limit in prometheus metrics (#19725)
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
2026-01-25 23:11:33 -08:00
Harshit Jain
79603b9c3a
fix: optimize logo fetching and resolve mcp import blockers (#19719) 2026-01-25 23:08:16 -08:00
Harshit Jain
344ea3d9f2
feat: add clientip and user agent in metrics (#19717)
* feat: add clientip and user agent in metrics

* fix: lint errors

* Add model id and other req labels

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
2026-01-25 23:07:19 -08:00
Harshit Jain
a65ac2af13
add callbacks and labels to prometheus (#19708) 2026-01-25 23:03:23 -08:00
jquinter
5666c725ce
Fix/non standard mcp url pattern (#19738)
* fix(mcp): Add standard MCP URL pattern support for OAuth discovery (#17272)

  OAuth discovery endpoints now support both URL patterns:
  - Standard MCP pattern: /mcp/{server_name} (new)
  - Legacy LiteLLM pattern: /{server_name}/mcp (backward compatible)

  The standard pattern is required by MCP-compliant clients like
  mcp-inspector and VSCode Copilot, which expect resource URLs
  following the /mcp/{server_name} convention per RFC 9728.

  Changes:
  - Add _build_oauth_protected_resource_response() helper
  - Add oauth_protected_resource_mcp_standard() endpoint
  - Add oauth_authorization_server_mcp_standard() endpoint
  - Keep legacy endpoints for backward compatibility
  - Add tests for both URL patterns

  Fixes #17272

* fix(mcp): Add standard MCP URL pattern support for OAuth discovery (#17272)

  OAuth discovery endpoints now support both URL patterns:
  - Standard MCP pattern: /mcp/{server_name} (new)
  - Legacy LiteLLM pattern: /{server_name}/mcp (backward compatible)

  The standard pattern is required by MCP-compliant clients like
  mcp-inspector and VSCode Copilot, which expect resource URLs
  following the /mcp/{server_name} convention per RFC 9728.

  Changes:
  - Add _build_oauth_protected_resource_response() helper
  - Add oauth_protected_resource_mcp_standard() endpoint
  - Add oauth_authorization_server_mcp_standard() endpoint
  - Keep legacy endpoints for backward compatibility
  - Add tests for both URL patterns

  Fixes #17272

* Test was relocated

* refactor(mcp): Extract helper methods from run_with_session to fix PLR0915

Split the large run_with_session method (55 statements) into smaller
helper methods to satisfy ruff's PLR0915 rule (max 50 statements):

- _create_transport_context(): Creates transport based on type
- _execute_session_operation(): Handles session lifecycle

Also changed cleanup exception handling from Exception to BaseException
to properly catch asyncio.CancelledError (which is a BaseException subclass
in Python 3.8+).

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* test(mcp): Fix flaky test by mocking health_check_server

The test_mcp_server_manager_config_integration_with_database test was
making real network calls to fake URLs which caused timeouts and
CancelledError exceptions.

Fixed by mocking health_check_server to return a proper
LiteLLM_MCPServerTable object instead of making network calls.

* test(mcp): Fix skip condition to properly detect claude model names

The skip condition for missing API keys was checking for "anthropic" in
the model name, but the test uses "claude-haiku-4-5" which doesn't match.
Updated to check for both "anthropic" and "claude" model patterns.

Also added skip condition for OpenAI models when OPENAI_API_KEY is not set.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* test(mcp): Fix skip condition to properly detect claude model names

The skip condition for missing API keys was checking for "anthropic" in
the model name, but the test uses "claude-haiku-4-5" which doesn't match.
Updated to check for both "anthropic" and "claude" model patterns.

Also added skip condition for OpenAI models when OPENAI_API_KEY is not set.

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-25 23:00:53 -08:00
Jay Prajapati
582d324a76
fix(proxy): support slashes in google generateContent model names (#19737)
* fix(proxy): support slashes in google route params

* fix(proxy): extract google model ids with slashes

* test(proxy): cover google model ids with slashes
2026-01-25 22:59:50 -08:00
Harshit Jain
667b9122e0
Merge pull request #19720 from Harshit28j/fix/model_alias_map-argument-error
fix: args issue & refactor into helper function to reduce bloat for b…
2026-01-25 10:51:28 +05:30
Harshit Jain
6df0406cf6
fix: args issue & refactor into helper function to reduce bloat for both(#19441) 2026-01-25 10:21:20 +05:30
yuneng-jiang
edfb1b8fe1
Merge pull request #19718 from BerriAI/litellm_ui_team_member_add_error
[Feature] UI - Virtual Keys: Auto Truncation of Table Values
2026-01-24 18:58:54 -08:00
yuneng-jiang
6ffd8a1d32 auto truncation of virtual keys table values 2026-01-24 18:03:32 -08:00
Ishaan Jaffer
e41b9c29a8 fix MCP tests 2026-01-24 18:00:22 -08:00
Ishaan Jaffer
f148207b11 fix patch reliability mock tests 2026-01-24 17:37:17 -08:00
Ishaan Jaffer
73dd1bd97a test_stream_transformation_error_sync 2026-01-24 17:19:21 -08:00
yuneng-jiang
06f7a7ec69
Merge pull request #19716 from BerriAI/ui_build_yj_0124_2
[Infra] Rebuilding UI
2026-01-24 16:28:22 -08:00
yuneng-jiang
3c94458f35 chore: update Next.js build artifacts (2026-01-25 00:27 UTC, node v22.16.0) 2026-01-24 16:27:30 -08:00
yuneng-jiang
8094aff8c5
Merge pull request #19715 from BerriAI/key_teams_fallback_docs
[Docs] UI Keys Teams Router Settings docs
2026-01-24 16:26:28 -08:00
yuneng-jiang
937ccf1977 UI Keys Teams Router Settings docs 2026-01-24 16:23:46 -08:00
Harshit Jain
05fdd099ba
fix(presidio): resolve runtime error by handling asyncio loops in bac… (#19714)
* fix(presidio): resolve runtime error by handling asyncio loops in background threads

* add test case for thread safety
2026-01-24 15:36:49 -08:00
Ishaan Jaffer
53d3868ff2 TestBedrockInvokeToolSearch 2026-01-24 15:36:30 -08:00
yuneng-jiang
99e9462ec9
Merge pull request #19713 from BerriAI/litellm_model_search_id_team
[Feature] UI - Model Page: Filter by Model ID and Team ID
2026-01-24 15:04:20 -08:00
yuneng-jiang
47810f1523 Model and Team filtering 2026-01-24 14:45:14 -08:00
Ishaan Jaffer
9f99e8231c test_retrieve_container_basic 2026-01-24 14:31:54 -08:00
Ishaan Jaffer
f2fd54ffcf test fixes 2026-01-24 14:27:56 -08:00
Ishaan Jaffer
d8e0c43a21 test fixes 2026-01-24 14:08:48 -08:00
Ishaan Jaffer
df3c54ec6a BUMP extras 2026-01-24 14:04:30 -08:00
Ishaan Jaffer
e4e76a4963 test_team_update_sc_2 2026-01-24 13:17:32 -08:00
Ishaan Jaffer
489c986cac test_hanging_request_azure 2026-01-24 13:14:48 -08:00
Ishaan Jaffer
a62ccd582d fix flaky tests 2026-01-24 13:04:20 -08:00
Ishaan Jaffer
31a4cb65bf test_get_default_unvicorn_init_args 2026-01-24 12:59:51 -08:00
Ishaan Jaffer
241c0c6d2a docs fix 2026-01-24 12:32:18 -08:00
Ishaan Jaffer
6c6ed0dad2 docs fix 2026-01-24 12:11:39 -08:00
Ishaan Jaffer
28a9003103 docs fix 2026-01-24 12:10:42 -08:00
Ishaan Jaffer
bbeb007f4e docs fix 2026-01-24 12:09:16 -08:00
Ishaan Jaffer
a081dc2ee2 docs fix 2026-01-24 11:41:16 -08:00
Ishaan Jaffer
a7e26460d0 fix unstable tests 2026-01-24 11:15:16 -08:00
Ishaan Jaffer
bd38374a45 fix: FLAKY tests 2026-01-24 11:13:44 -08:00
Alexsander Hamir
9cdd7a8fd2
Fix: log duplication when json_logs is enabled (#19705) 2026-01-24 11:09:04 -08:00
Ishaan Jaffer
6710abd1fa test_web_search 2026-01-24 11:06:23 -08:00
Ishaan Jaffer
6587cd228b test_partner_models_httpx_streaming 2026-01-24 10:58:35 -08:00
Ishaan Jaffer
1a7274aa4e fix: _apply_search_filter_to_models mypy linting 2026-01-24 09:24:50 -08:00
Ishaan Jaffer
489d587332 CI/CD fixes - split local testing 2026-01-24 09:23:03 -08:00
yuneng-jiang
387cb8fde8
Merge pull request #19703 from BerriAI/yj_ui_build_jan24
[Infra] Build UI for Release
2026-01-24 09:20:26 -08:00
yuneng-jiang
17aec96186 chore: update Next.js build artifacts (2026-01-24 17:18 UTC, node v22.16.0) 2026-01-24 09:18:58 -08:00
Ishaan Jaffer
006b810370 bump: version 1.81.2 → 1.81.3 2026-01-24 09:15:06 -08:00
yuneng-jiang
ed1b9529f7
Merge pull request #19601 from BerriAI/litellm_ui_update_org_model
[Feature] UI - Organization Edit Page: Reusable Model Select
2026-01-24 09:10:15 -08:00
yuneng-jiang
5e395db1dc
Merge pull request #19604 from BerriAI/litellm_team_update_org
[Fix] Team Update with Organization having All Proxy Models
2026-01-24 09:09:55 -08:00
yuneng-jiang
f88a32de05
Merge pull request #19622 from BerriAI/litellm_ui_model_backend
[Feature] UI - Models Page: Model Search
2026-01-24 09:09:03 -08:00
yuneng-jiang
b44ac6c682 Fixing ruff check 2026-01-24 09:08:29 -08:00
Ishaan Jaff
0bdb68dea7
Update OSS Adopters section with new table format 2026-01-24 09:07:03 -08:00
yuneng-jiang
09c7d67539
Merge pull request #19701 from BerriAI/litellm_ci_fix_yj_03
[Infra] Fixing CircleCI Config
2026-01-24 08:55:50 -08:00