yuneng-jiang
470e4c26c3
Merge pull request #18593 from BerriAI/litellm_ui_sso_role_mapping
...
[Feature] UI - Allow Adding Role Mappings for SSO
2026-01-02 18:31:11 -08:00
yuneng-jiang
546fba9849
tests
2026-01-02 18:28:10 -08:00
yuneng-jiang
f16fb63434
New SSO Settings Page
2026-01-02 18:22:37 -08:00
YutaSaito
61e666c457
Merge pull request #18597 from BerriAI/litellm_fix_openapi_to_mcp
...
fix openapi to mcp
2026-01-03 09:43:06 +09:00
Yuta Saito
8e633ab513
fix: reuse shared async client in mcp openapi generator
2026-01-03 09:33:12 +09:00
Yuta Saito
101fa6bdc6
refactor: extract http request helper for mcp openapi tools
2026-01-03 09:07:59 +09:00
Yuta Saito
6168e500a8
fix: add checking path param
2026-01-03 08:57:54 +09:00
Alexsander Hamir
2983b556d3
Lazy load 9 heavy imports in litellm/utils.py ( #18595 )
2026-01-02 14:54:09 -08:00
yuneng-jiang
0f0da07661
fixing build
2026-01-02 14:00:55 -08:00
yuneng-jiang
0a2e241651
Allow adding role mapping in UI
2026-01-02 13:57:28 -08:00
Alexsander Hamir
3b1792d728
feat: lazy load heavy imports to reduce memory usage at import time ( #18592 )
...
- Lazy load remove_index_from_tool_calls via __getattr__
- Lazy load _service_logger module via __getattr__ in __init__.py
- Lazy load audio_utils.utils with module-level caching in utils.py
- Remove direct imports that trigger heavy module loading
These changes reduce import-time memory usage by deferring imports
until they are actually needed, while maintaining performance through
caching for subsequent accesses.
2026-01-02 13:51:28 -08:00
kevinpauer
705b54bf04
Feat/add watsonx fields ( #18569 )
2026-01-03 02:53:17 +05:30
Alexsander Hamir
44d309f270
refactor: Add lazy loading for get_llm_provider ( #18591 )
2026-01-02 13:18:57 -08:00
Alexsander Hamir
e2f3eaefab
Add UnboundedDataStructurePattern to memory test detector ( #18590 )
2026-01-02 11:49:32 -08:00
Small
05a78fb0cf
add dimensions for ollama embedding ( #18536 )
2026-01-03 00:58:27 +05:30
Alexsander Hamir
b732710ed0
Add memory pattern detection test and fix bad memory patterns ( #18589 )
2026-01-02 10:52:25 -08:00
Harshit Jain
cc659b8702
fix(logging_worker): handle event loop changes in multiprocessing by checking bound_loop ( #18423 )
2026-01-03 00:19:14 +05:30
Daniel Yudelevich
af27c7d7ff
fix: add deprecation_date for discontinued Google models ( #18550 )
...
Add deprecation dates for Google models that have been discontinued
per https://ai.google.dev/gemini-api/docs/changelog :
- Gemini 1.5 Flash/Pro models: 2025-09-29
- imagen-3.0-generate-002: 2025-11-10
- veo-3.0 preview models: 2025-11-12
- gemini-2.0-flash image generation: 2025-11-14
- gemini-2.5-flash preview models: 2025-11-18
- gemini-2.0-flash-thinking-exp, pro previews: 2025-12-02
- gemini-2.0-flash-live-001: 2025-12-09
- text-embedding-004: 2026-01-14
- gemini-2.5-flash-image-preview: 2026-01-15
Co-authored-by: Daniel Yudelevich <yudelevi@users.noreply.github.com>
2026-01-03 00:12:58 +05:30
Alex Gertz
3bd309f808
fix: return empty data array instead of 500 when no models configured ( #18556 )
...
- /v2/model/info now returns {"data": []} when llm_router is None or model_list is empty
- /model_group/info now returns {"data": []} when llm_model_list is None or empty
- Fixes UI crash on fresh installs with STORE_MODEL_IN_DB=True
- Added 4 unit tests for empty model list scenarios
2026-01-02 23:36:05 +05:30
Chetan Choudhary
687adc6024
Add log_format parameter to GenericAPILogger ( #18587 )
...
Adds log_format parameter supporting json_array (default), ndjson, and single formats. NDJSON format enables webhook integrations like Sumo Logic to parse individual log records at ingest time. Defaults to json_array for backward compatibility.
2026-01-02 23:28:30 +05:30
Cesar Garcia
c8950a5ba2
fix(cost_calculator): correct gpt-image-1 cost calculation using token-based pricing ( #17906 )
...
* fix(cost_calculator): correct gpt-image-1 cost calculation using token-based pricing (#13847 )
gpt-image-1 uses token-based pricing (like chat models), not pixel-based pricing
like DALL-E. The old code was calculating incorrect costs by treating it as DALL-E.
Changes:
- Update model pricing JSON with correct token-based costs for gpt-image-1
- Add dedicated cost calculator for OpenAI gpt-image models
- Route gpt-image-1 to token-based calculator in cost router
- Add comprehensive tests for the new calculator
* refactor: simplify gpt-image-1 cost calculator using responses API helper
Reuse _transform_response_api_usage_to_chat_usage and generic_cost_per_token
for gpt-image-1 cost calculation since ImageUsage has the same spec as
ResponseAPIUsage.
2026-01-02 23:08:52 +05:30
Sameer Kankute
c380ad70d5
Merge pull request #18588 from BerriAI/litellm_fix_sameer_cicd
...
fix background cost tracking tests
2026-01-02 21:52:44 +05:30
Sameer Kankute
5ed83756eb
Merge pull request #18583 from BerriAI/litellm_block_negative_budget
...
Add validation for negative budget
2026-01-02 21:52:15 +05:30
Sameer Kankute
233ba9d4b8
fix mock tests
2026-01-02 21:40:27 +05:30
Sameer Kankute
ed59a9b376
fix background cost tracking tests
2026-01-02 21:12:25 +05:30
Sameer Kankute
c8bb92afdc
Merge pull request #18579 from BerriAI/litellm_remove_prompt_chaching_header
...
Remove prompt caching headers as the support has been removed
2026-01-02 21:01:50 +05:30
Sameer Kankute
973f850cf3
Merge pull request #18581 from BerriAI/litellm_gemini_non_tool_call_thought_sign
...
Add thought signature for non tool call requests
2026-01-02 21:01:07 +05:30
Sameer Kankute
7512b327d4
Merge pull request #18585 from BerriAI/litellm_gemini_system_instructions
...
Preserve system instructions for gemini
2026-01-02 20:59:44 +05:30
Sameer Kankute
ecbc678771
Merge pull request #18586 from BerriAI/litellm_fix_image_cost_track
...
Add all resolution for gpt-image-1.5
2026-01-02 20:58:59 +05:30
Sameer Kankute
05e37e0600
fix ruff check
2026-01-02 20:55:35 +05:30
Sameer Kankute
0543ab5e77
Update the logic to work with GET request
2026-01-02 20:49:12 +05:30
Sameer Kankute
bbb883ffa9
Merge pull request #18483 from yurekami/fix/deepseek-v3p2-pricing
...
fix: correct deepseek-v3p2 pricing for Fireworks AI
2026-01-02 17:09:12 +05:30
Sameer Kankute
bfbe13bbd4
Merge pull request #18190 from RensDimmendaal/add-gemini-img-tool-result-support
...
Fix Gemini 3 imgs in tool response
2026-01-02 17:06:51 +05:30
Sameer Kankute
ec1403ada0
Merge pull request #18496 from Chesars/feat/add-minimax-provider-ui
...
feat: Add MiniMax provider support to UI dashboard
2026-01-02 16:53:24 +05:30
Sameer Kankute
ccdbe921e1
Merge pull request #18514 from xuan07t2/fix/vertex-ai-tools-one-type-per-object
...
fix(vertex_ai): separate Tool objects for each tool type per API spec
2026-01-02 16:21:17 +05:30
Sameer Kankute
6e91364004
Add all sizes and resolution for gpt-image-1.5 to model map
2026-01-02 15:40:52 +05:30
Sameer Kankute
9aa280fde9
Add all sizes and resolution for gpt-image-1.5 to model map
2026-01-02 15:40:13 +05:30
Sameer Kankute
65e60a16d3
Merge pull request #18497 from DevajMody/fix/vertex-ai-anthropic-image-urls
...
fix(vertex_ai): convert image URLs to base64 for Vertex AI Anthropic
2026-01-02 14:50:04 +05:30
Sameer Kankute
81cbd7a8d8
Preserve system instructions for gemini
2026-01-02 14:39:25 +05:30
YutaSaito
e9365c496d
Merge pull request #18580 from BerriAI/litellm_feat_support_metaurl_on_ui
...
feat: add UI support for configuring meta URLs
2026-01-02 17:54:26 +09:00
Yuta Saito
da05b56756
feat: add user email to cloudzero
2026-01-02 17:48:16 +09:00
YutaSaito
26c733b361
Merge pull request #18578 from BerriAI/litellm_feat_select_mcp_server_to_playground
...
add selectable mcp servers to the playground
2026-01-02 17:42:18 +09:00
Yuta Saito
7107da2fb7
fix: test mock
2026-01-02 17:38:52 +09:00
YutaSaito
4b131a77a0
Merge pull request #18573 from BerriAI/litellm_fix_normalize-model-name
...
fix: unify model names to provider-defined names
2026-01-02 17:37:28 +09:00
Lukas de Boer
edc8413f1e
Add Kubernetes ServiceAccount JWT authentication support ( #18055 )
...
* Allow get_nested_value dot notation to support escaping for Kubernetes JWT Support
* Add support for team and org alias fields, add docs, tests
* Fix lint issue with max statements in handle jwt logic
2026-01-02 14:02:31 +05:30
Yuta Saito
84944320a4
fix: npm run build error
2026-01-02 17:20:26 +09:00
Yuta Saito
0e01d225ff
fix: test_edit_mcp_server_redacts_credentials error
2026-01-02 17:13:31 +09:00
Yuta Saito
0b16482cec
fix: npm build
2026-01-02 16:39:22 +09:00
Yuta Saito
89ce8091bb
fix: test
2026-01-02 16:32:33 +09:00
Sameer Kankute
57c373c5d8
Add validation for negative budget
2026-01-02 12:57:39 +05:30
