Cesar Garcia
049d45ea90
fix(gemini): Preserve non-ASCII characters in function call arguments ( #16550 )
...
Fixes #16533
Before this fix, non-ASCII characters (Japanese, Spanish, Chinese, etc.)
in function call arguments were being escaped as Unicode sequences.
Example:
- Before: "やあ" → "\u3084\u3042"
- After: "やあ" → "やあ" (preserved)
Changes:
- Add ensure_ascii=False to json.dumps() in _transform_parts()
- Add test for Japanese and Spanish Unicode character preservation
This is not a breaking change as both formats are equivalent in JSON.
The fix improves readability and aligns with OpenAI's behavior.
2025-11-12 19:01:38 -08:00
Sameer Kankute
018bd2e039
Add Gemini image edit support ( #16430 )
...
* Add gemini image edit support
* fix lint errors
* fix lint errors
* fix lint errors
* Add docs
2025-11-12 18:48:27 -08:00
yuneng-jiang
8bf491c939
[Fix] /spend/logs/ui Access Control ( #16446 )
...
* RBAC for /spend/logs/ui
* Addressing comments
2025-11-12 18:44:21 -08:00
yuneng-jiang
cb27d6c456
[Fix] UI - Delete Callbacks Failing ( #16473 )
...
* Temp commit for branch switching
* Created normalize callback name util function and tests
2025-11-12 18:43:37 -08:00
Sameer Kankute
92bd12c862
Fix raising wrong 429 error on wrong exception ( #16482 )
...
* fix raising wrong 429 error on wrong exception
* remove double re import
2025-11-12 18:41:12 -08:00
Ishaan Jaffer
78c169a524
docs fix
2025-11-12 18:30:01 -08:00
Sameer Kankute
394da34a0b
Add all gemini image models support in image generation ( #16526 )
2025-11-12 18:26:44 -08:00
yuneng-jiang
898f15c33c
Add Langfuse OTEL and SQS to health check ( #16514 )
2025-11-12 18:25:30 -08:00
yuneng-jiang
c23b2c5023
Config Guardrails should not be deletable from table ( #16540 )
2025-11-12 18:23:31 -08:00
yuneng-jiang
35eece2b7b
Merge remote-tracking branch 'origin' into litellm_org_usage
2025-11-12 18:22:44 -08:00
yuneng-jiang
94da5c076c
Add Daily Org Spend Table, read path, and write path
2025-11-12 18:22:26 -08:00
Ishaan Jaff
b30439257b
[Feat] Add RunwayML Img Gen API support ( #16557 )
...
* TestRunwaymlImageGeneration
* fix RUNWAYML
* rename
* fix rename
* get_runwayml_image_generation_config
* get_runwayml_image_generation_config
* TestRunwaymlImageGeneration
* add RUNWAYML_POLLING_TIMEOUT
* fix rnwayml transform img gen
* runwayml_image_cost_calculator
* runwayml_image_cost_calculator
* docs runwayml
* fix runwayML polling
* test_get_first_default_fallback
2025-11-12 18:20:14 -08:00
Benjamin Chrobot
1393900c22
[Docs] Fix code block indentation for fallbacks page ( #16542 )
2025-11-12 18:08:52 -08:00
yuneng-jiang
f0c83e183e
SSO Modal Cosmetic Changes ( #16554 )
2025-11-12 17:55:05 -08:00
Krrish Dholakia
a05ad46394
feat: add litellm cloud self-serve to docs
2025-11-12 17:13:14 -08:00
Ishaan Jaffer
d7824d076e
docs project management
2025-11-12 16:24:23 -08:00
Ishaan Jaffer
5cf8f06b17
add to _get_spend_logs_metadata
2025-11-12 15:56:32 -08:00
Ishaan Jaffer
5147734426
add user_api_key_project_id in SpendLogsMetadata
2025-11-12 15:53:49 -08:00
Ishaan Jaffer
e5624c2d57
docs fix
2025-11-12 15:48:46 -08:00
Ishaan Jaffer
a6e16a82be
test proj endpoints
2025-11-12 15:42:33 -08:00
Ishaan Jaffer
c9a9aca8cf
test_new_project
2025-11-12 15:41:39 -08:00
Ishaan Jaffer
c093941e99
fix project mgmt
2025-11-12 15:35:23 -08:00
Ishaan Jaffer
b0c99de204
use 1 helper
2025-11-12 15:32:27 -08:00
Ishaan Jaffer
99f2cd1841
fix LiteLLM_ManagementEndpoint_MetadataFields
2025-11-12 15:20:09 -08:00
Ishaan Jaffer
0078d8a45f
update schema
2025-11-12 15:03:03 -08:00
Ishaan Jaffer
6163e26d2e
add model tpm/rpm limits
2025-11-12 14:59:01 -08:00
Ishaan Jaffer
228c683d2b
add model_rpm_limit/tpm
2025-11-12 14:58:45 -08:00
Ishaan Jaffer
a8f93d03d6
add model_rpm_limit and tpm limits
2025-11-12 14:58:38 -08:00
Ishaan Jaffer
a8237601bc
add project_router
2025-11-12 14:57:23 -08:00
Ishaan Jaffer
343af7db49
add project management APs
2025-11-12 14:55:23 -08:00
Ishaan Jaffer
12109c7d7e
add generate_key_helper_fn
2025-11-12 14:44:22 -08:00
Ishaan Jaffer
412f7e396a
init project apis
2025-11-12 14:43:47 -08:00
Ishaan Jaffer
a3c3f6ae74
add schema
2025-11-12 14:38:43 -08:00
Ishaan Jaffer
d29cb2bf5c
add projects schema
2025-11-12 14:38:15 -08:00
Krrish Dholakia
c14afa93b0
fix(responses_id_security.py): fix issue when no master key set
2025-11-12 14:09:11 -08:00
Yuge Zhang
f4a5196728
fix: Improve Azure auth parameter handling for None values ( #14436 )
...
* fix: Improve Azure auth parameter handling for None values
Previously, litellm_params.get() with default fallbacks could ignore
environment variables when the param existed but was None. Now explicitly
checks for None values before falling back to environment variables.
🤖 Generated with [Claude Code](https://claude.ai/code )
Co-Authored-By: Claude <noreply@anthropic.com>
* fix lint
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
2025-11-12 14:01:55 -08:00
Krrish Dholakia
48579f7539
feat(anthropic/chat/transformation.py): add minimal reasoning effort thinking support
...
Closes Slack issue
2025-11-12 13:57:14 -08:00
YutaSaito
2843dab7fe
fix: allow tool call even when server name prefix is missing ( #16425 )
...
* fix: allow tool call even when server name prefix is missing
* fix: test
* fix: test
* fix: test
2025-11-12 13:50:52 -08:00
Krrish Dholakia
ae3178d5d4
docs(deploy.md): document how to disable pulling live model prices (faster startup time) on docker deployment
2025-11-12 13:49:44 -08:00
Krrish Dholakia
020a66c01f
docs(model_access_guide.md): explain how model access works on litellm
2025-11-12 13:44:38 -08:00
Krrish Dholakia
c6d2714c52
docs(model_access_guide.md): document how model access works on litellm
2025-11-12 13:43:13 -08:00
yuneng-jiang
c5496fd61c
[Feature] UI - Move Budgets out of Experimental ( #16544 )
...
* Move budget out of experimental and delete budget with friction
* Fixed tests
* Revert non test change
2025-11-12 13:27:02 -08:00
Cesar Garcia
20350fa094
docs: update broken Slack invite links to support page ( #16546 )
...
Replace broken Slack links (litellmossslack.slack.com and expired invite URLs)
with the correct support page URL (https://www.litellm.ai/support ) across all
documentation files.
Files updated:
- CONTRIBUTING.md
- docs/my-website/docs/contact.md
- docs/my-website/docs/proxy/docker_quick_start.md
- docs/my-website/docs/troubleshoot.md
- docs/my-website/src/pages/contact.md
2025-11-12 12:41:55 -08:00
Ishaan Jaff
061b7b2713
[Fix] Bedrock Embeddings - Ensure correct aws_region is used when provided dynamically ( #16547 )
...
* test_bedrock_embedding_uses_correct_region_when_specified
* fix aws_region_name in bedrock embeddings
2025-11-12 12:38:58 -08:00
Ishaan Jaff
abde56391b
[Fix] - Bedrock Knowledge Bases - add support for filtering kb queries ( #16543 )
...
* test_e2e_bedrock_knowledgebase_retrieval_with_llm_api_call_with_tools_and_filters
* fix vs registry
* fix merging params
* test_bedrock_kb_request_body_has_transformed_filters
* fix typing / linting
2025-11-12 12:38:50 -08:00
Mubashir Osmani
e6bbf3ce81
fix: app_roles missing from jwt payload ( #16448 )
...
* fix: jwt app_roles missing
* add test
2025-11-12 12:07:04 -08:00
Jean-Adrien Ducastaing
086e557d78
fix: use vllm passthrough config for hosted vllm provider instead of raising error ( #16537 )
...
* fix(passthrough): use VLLM passthrough config for hosted VLLM provider instead of raising an error
* test(passthrough): add tests for hosted VLLM passthrough configuration and routing
* fix account linking for CLA
2025-11-12 09:12:14 -08:00
Jón Levy
63445f2f37
fix(agentcore): Convert SSE stream iterator to async for proper streaming support ( #16293 )
...
* fix(agentcore): support async agentcore runtime streaming
* revert: CLAUDE.md
* revert: .gitignore
* fix: map runtimeUserId to X-Amzn-Bedrock-AgentCore-Runtime-User-Id header for runtime oauth support
2025-11-11 19:21:53 -08:00
Sameer Kankute
517eb0ee10
Use safe loading of creds ( #16479 )
2025-11-11 19:16:29 -08:00
Francesco Bertolotti
06efc7631d
Update model logging format for custom LLM provider ( #16485 )
...
This avoids the annoying red message
```
Provider List: https://docs.litellm.ai/docs/providers
```
when there is a cache hit.
2025-11-11 19:13:42 -08:00