* ensure original client is disconnected when re-creating
* test_recreate_prisma_client_successful_disconnect
* test_recreate_prisma_client_successful_disconnect
* disable background health checks for specific models
* test_background_health_check_skip_disabled_models
* Disable Background Health Checks For Specific Models
* fix(proxy_cli.py): make use_prisma_migrate proxy default
Fixes https://github.com/BerriAI/litellm/issues/13046
Prisma migrate deploy prevents resetting db
* fix(auth_checks.py): resolve team only models while doing auth checks on model access groups
Fixes issue where key had access via an access group, but team only model could not be called
* test(test_router.py): add unit testing
* feat(provider_specific_fields.tsx): add aws sagemaker on UI
* feat: Add dot notation support for all JWT fields
- Updated all JWT field access methods to use get_nested_value for dot notation support
- Enhanced get_team_id to properly handle team_id_default fallback with nested fields
- Added comprehensive unit tests for nested JWT field access and edge cases
- Updated documentation to reflect dot notation support across all JWT fields
- Maintains full backward compatibility with existing flat field configurations
Supported fields with dot notation:
- team_id_jwt_field, team_ids_jwt_field, user_id_jwt_field
- user_email_jwt_field, org_id_jwt_field, object_id_jwt_field
- end_user_id_jwt_field (roles_jwt_field was already supported)
Example: user_id_jwt_field: 'user.sub' accesses token['user']['sub']
* fix: Add type annotations to resolve mypy errors
- Add explicit type annotation for team_ids variable in get_team_ids_from_jwt
- Add type ignore comment for sentinel object return in get_team_id
- Resolves mypy errors while maintaining functionality
* fix: Resolve mypy type error in get_team_ids_from_jwt
- Remove explicit List[str] type annotation that conflicts with get_nested_value return type
- Simplify return logic to use 'team_ids or []' ensuring always returns List[str]
- Fixes: Incompatible types in assignment (expression has type 'list[str] | None', variable has type 'list[str]')
* fix: Add proper type annotation for team_ids variable
- Use Optional[List[str]] type annotation to satisfy mypy requirements
- Resolves: Need type annotation for 'team_ids' [var-annotated]
- Maintains functionality while ensuring type safety
* refactor: remove outdated JWT unit tests and consolidate JWT-related functionality
- Deleted the test_jwt.py file as it contained outdated and redundant tests.
- Consolidated JWT-related tests into test_handle_jwt.py for better organization and maintainability.
- Updated tests to ensure proper functionality of JWT handling, including token validation and role mapping.
- Enhanced test coverage for JWT field access and nested claims handling.
* test: add comprehensive unit tests for JWT authentication
- Introduced a new test file `test_jwt.py` containing unit tests for JWT authentication.
- Implemented tests for loading configuration with custom role names, validating tokens, and handling team tokens.
- Enhanced coverage for JWT field access, nested claims, and role-based access control.
- Added fixtures for Prisma client and public JWT key generation to support testing.
- Ensured proper handling of valid and invalid tokens, including user and team scenarios.
* revert test_handle_jwt.py
* rename file
* test: remove outdated JWT nesting tests and add new nested field access tests
- Deleted the `test_jwt_nesting.py` file as it contained outdated tests.
- Introduced new tests in `test_handle_jwt.py` to verify nested JWT field access.
- Enhanced coverage for accessing nested values using dot notation and ensured backward compatibility with flat field names.
- Added tests for handling missing nested paths and appropriate default values.
- Improved handling of metadata prefixes in nested field access.
* restore file
* Fix: Add support for GOOGLE_API_KEY environment variables for Gemini API authentication
* added test cases
* incoperated feedback to make it more maintainable
* fix failed linting CI
- Fixed 'missing finish_reason for choice 1' error with reasoning_effort
- Anthropic sends multiple content blocks with different indices
- OpenAI expects all content in a single choice at index=0
- Added comprehensive tests for text-only, text+tool, and multiple tools
* Fix security vulnerability in list_team_v2 endpoint
- Add missing allowed_route_check_inside_route security check to list_team_v2
- Add @management_endpoint_wrapper decorator for consistency with list_team
- Add comprehensive tests to verify security checks work correctly
- Ensure non-admin users can only query their own teams
- Ensure admin users can query all teams
This fixes a security bug where non-admin users could potentially access
team information they shouldn't have access to through the list_team_v2
endpoint, which was missing the authorization check present in list_team.
* Fix test
* Test fixes
* Fixed test
* Restored invalid delete
* Revert
---------
Co-authored-by: openhands <openhands@all-hands.dev>
* fix(azure/chat/gpt_transformation.py): support api_version="preview"
Fixes https://github.com/BerriAI/litellm/issues/12945
* Fix anthropic passthrough logging handler model fallback for streaming requests (#13022)
* fix: anthropic passthrough logging handler model fallback for streaming requests
- Add fallback logic to retrieve model from logging_obj.model_call_details when request_body.model is empty
- Fixes issue #12933 where streaming requests to anthropic passthrough endpoints would crash due to missing model field
- Ensures downstream logging and cost calculation work correctly for all streaming scenarios
- Maintains backwards compatibility with existing non-streaming requests
* test: add minimal tests for anthropic passthrough logging handler model fallback
- Add unit tests for the model fallback logic in _handle_logging_anthropic_collected_chunks
- Test existing behavior when request_body.model is present
- Test fallback logic when request_body.model is empty but logging_obj.model_call_details has model
- Test edge cases where both sources are empty or missing
- Ensure backwards compatibility and graceful degradation
* fix(anthropic_passthrough_logging_handler.py): add provider to model name (accurate cost tracking)
* fix(anthropic_passthrough_logging_handler.py): don't reset custom llm provider, if already set
* fix: fix check
---------
Co-authored-by: Haggai Shachar <haggai.shachar@backline.ai>
