* add pass through ui
* fix accordion for route path
* working route path renderer
* fix use sections
* clean up add pass through form
* docs fix add pass through routing
* clean up route preview
* add route preview
* feat - add websearch tools to responses to chat transform
* test_basic_google_ai_studio_responses_api_with_tools
* fix web search to responses api
* linting fixes
* fix(vertex_ai): Handle missing tokenCount in promptTokensDetails (#11581)
This PR is a Solution to the Error converting to a valid response block='tokenCount'. File an issue if litellm error - https://github.com/BerriAI/litellm/issues
It's happening because vertex_ai is not sometimes sending the token count for the audio modality.
* test_vertex_ai_usage_metadata_missing_token_count
---------
Co-authored-by: Nishith Jain <167524748+KingNish24@users.noreply.github.com>
* Enable Tool Calling for `meta_llama` (#11825)
* feat: enable tools and function_call features
* fix: ignore pydantic warnings for StreamingChoices from llama-api
* docs: add tool calling examples
* docs: change default models to Maverick
* docs: fix output of tool use
* test_map_openai_params
---------
Co-authored-by: Young Han <110819238+seyeong-han@users.noreply.github.com>
* feat(internal_user_endpoints.py): allow passing team-specific details when creating new user with team
allows assigning users to teams on creation
* feat(internal_user_endpoints.py): support for setting team values in default internal user params
Ensures admin can assign all new users to a default team
* test(test_internal_user_endpoints.py): add unit tests
* feat(ui/): allow setting default team on admin UI
easier onboarding for users
* fix(internal_user_endpoints.py): fix exception check
* fix(spend_tracking_utils.py): add user agent tags from standard logging payload, in spend logs payload
* feat(litellm_logging.py): identify user agent tags as `User-Agent: ..` and allow admin to disable storing user agent as tag
* fix(azure_ai/): pass content type header in azure ai request
Fixes https://github.com/BerriAI/litellm/issues/11227
* test: add unit test
* fix(router.py): fix passing dynamic credentials to retrieve batch
Fixes batch retrieval when using router
* test: add more unit tests
* use cost_per_request
* fix cost_per_request
* fixes cost_per_request
* fixes for cost per request for pass through
* ui fix param name
* fixes for _set_cost_per_request
* test cost per request pass through endpoints
* Update tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* tests pass through endpoints
* rename left nav
* move pass through to models + endpoints
* move pass through under models
* add pt info view
* add get/update pt
* fixes for PT ui
* allow updating pt endpoints
* fix pass through quick actions
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix SCIM memberships Patch
* fixes for SCIM updates
* fixes for SCIM
* working provisioning for teams on SCIM
* working user patch / PUT ops SCIM
* fixes SCIM
* test_scim_v2_endpoints.py
* handle_existing_user_by_email
* fixes for provisioning SCIMUser
* fixes SCIM provisioning
* test scim v2
* fixes for linting
* fix _apply_patch_ops
* fixes code QA check for team membership checks
* use cost_per_request
* fix cost_per_request
* fixes cost_per_request
* fixes for cost per request for pass through
* ui fix param name
* fixes for _set_cost_per_request
* test cost per request pass through endpoints
* Update tests/test_litellm/proxy/pass_through_endpoints/test_pass_through_endpoints.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* tests pass through endpoints
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* feat: add summarize parameter to /spend/logs endpoint for individual transaction logs
- Introduced a new `summarize` parameter to control data format when querying spend logs.
- `summarize=true` (default) returns aggregated data, while `summarize=false` provides individual transaction logs.
- Updated documentation and added tests to validate the new functionality.
* fix: wrap boto3.Session() with tracer for observability - Add tracer.trace wrapper around boto3.Session() call in _get_aws_region_name method - Ensures all boto3 initializations in base_aws_llm.py are properly instrumented - Fixes test_boto3_init_tracer_wrapping test failure - Maintains consistency with other boto3 calls in the same file
* fix(litellm_pre_call_utils.py): add user agent tags to spend logs in standard logging payload logic
avoid clash when tag based routing is enabled
* test: remove redundant test
* test: rename oidc test to run earlier
quicker debuging
* fix(azure.py): return more detailed error message
* fix(azure/common_utils.py): use default scope, if scope is none
fixes oidc test
* fix: always default to cognitiveservices.azure.com
* test: update test
* feat: Implement health check functionality for models
- Added individual model health check API call and integrated it into the dashboard.
- Introduced health check history and latest health checks retrieval.
- Enhanced model dashboard to display health status, last check time, and error details.
- Created a new health check columns component for better organization of health data.
- Added error pattern handling for meaningful error messages.
- Updated UI components to support health check actions and display loading states.
* refactor: extract health check functionality into a new component
- Removed individual health check logic from ModelDashboard and encapsulated it within HealthCheckComponent for better modularity and maintainability.
- Updated ModelDashboard to utilize the new HealthCheckComponent, streamlining the health check process and improving code organization.
- Cleaned up unused state variables and imports related to health checks in ModelDashboard.
- Enhanced error handling and status management within the new component, ensuring a more robust health check experience.
* fix: add access token check in HealthCheckComponent to prevent unauthorized API calls
- Implemented a check for the presence of an access token before making API calls to fetch the latest health checks, enhancing security and preventing potential errors when the token is missing.
