* fix(handle_jwt.py): check user object, if jwt user is proxy admin
correctly return user role - if jwt user has role updated in UI
* test(test_handle_jwt.py): add unit test for passing correct user role
* feat(model_info_view.tsx): separate UI component for updating edit model component
* feat(model_info_view.tsx): allow updating model access group on UI
show all available access groups in ui component
* docs: minor fixes
* feat(ui_sso.py): allow admin to specify additional headers for sso provider
some sso providers require special headers to return a json response
* test(test_ui_sso.py): add unit tests to ensure custom headers are respect3ed
* docs(config_settings.md): document new header param
* fix(litellm_pre_call_utils.py): add spend tag tracking by user agent
allows checking spend for cli tools like claude code
* feat(litellm_pre_call_utils.py): track spend by user agent part if user agent contains "/"
allows tracking spend across user agent versions
Better cost tracking for claude cod
* test(test_litellm_pre_call_utils.py): add testing for pre call utils, user agent parsing
* fix: fix linting check
* feat: update the feature of ollama_embeddings to work on a sync api
Signed-off-by: Abinand P <abinand0911@gmail.com>
* lint:fixing of the lint file
Signed-off-by: Abinand P <abinand0911@gmail.com>
* fix:test
Signed-off-by: Abinand P <abinand0911@gmail.com>
* chore: added test for ollama embedding and refactored handler
Signed-off-by: Abinand P <abinand0911@gmail.com>
* fix:lint error
Signed-off-by: Abinand P <abinand0911@gmail.com>
---------
Signed-off-by: Abinand P <abinand0911@gmail.com>
* fix(prometheus.py): remove request increment from inside the log success event
it's only done on post-call success/failure
* fix(litellm_logging.py): add additional validation step for checking if 'stream' is true
prevent double counting on non-stream requests
* test: add unit testing to ensure stream is not incorrectly set to true
* feat(litellm_logging.py): emit request route in standard logging payload
used by prometheus streaming metrics for route
* fix: fix otel test
* fix: fix linting errors
* test: update test
* fix: fix linting error
* feat: Add health check functionality and endpoints
- Introduced methods for saving health check results to the database, including validation and cleaning of data.
- Added new health check endpoints to retrieve health check history and latest health statuses for models.
- Updated model prices and context window configuration for new Azure transcription models.
* test: Add unit tests for health check functionality
- Introduced tests for PrismaClient health check methods, including saving results and retrieving health check history.
- Added tests for the _save_health_check_to_db function to ensure proper handling of healthy and unhealthy endpoints.
- Implemented mock objects to simulate database interactions and validate method behaviors.
* Refactor health endpoint model ID handling and improve logging
- Updated health endpoint to use `get_deployment` for retrieving model names based on model IDs, enhancing error handling for missing models.
- Changed health check result saving to the database to be non-blocking by using `asyncio.create_task`.
- Cleaned up code for better readability and maintainability.
* Refactor utility functions in proxy module for improved readability and error handling
- Removed unused imports and simplified exception handling in `_get_redoc_url` and `_get_docs_url` functions to manage circular imports.
- Cleaned up logging statements for consistency and clarity.
- Streamlined error message formatting in `handle_exception_on_proxy` function.
* Enhance type hinting and default values in ProxyUpdateSpend class for improved clarity and robustness
- Added type hints for `_end_user_list_transactions` to specify it as a dictionary mapping end user IDs to spend amounts.
- Updated default values for optional fields in `SpendLogsPayload` to ensure they are initialized properly, enhancing error handling.
- Refactored `_premium_user_check` function to improve model validation logic and error handling.
* Fix disable_spend_updates method to handle None return value gracefully
- Updated the disable_spend_updates method to return False if the environment variable DISABLE_SPEND_UPDATES is not set or is None, improving robustness in configuration handling.
* Refactor join_paths function in utils.py for improved path handling
- Enhanced the join_paths function to better manage leading and trailing slashes, ensuring correct path concatenation.
- Added logic to handle cases where either base_path or route is empty, improving robustness and usability.
* Enhance health check functionality and improve error handling
- Introduced a new method `_save_health_check_to_db` for saving health check results to the database, utilizing safe JSON functions for data integrity.
- Refactored existing health check methods to streamline the process and improve error logging.
- Updated email sending logic to ensure secure connections and better error handling.
- Improved spend update logic with batch processing and retry mechanisms for database operations.
- Added utility functions for projected spend calculations and enhanced validation for team configurations.
* Add health check methods for database interaction
- Introduced `save_health_check_result` method to save health check results with detailed logging and validation.
- Added `get_health_check_history` method for retrieving health check records with optional filtering.
- Implemented `get_all_latest_health_checks` method to fetch the latest health checks for each model.
- Enhanced error handling and logging for all new methods to improve reliability and traceability.
* Refactor health check result saving to use typed arguments
- Updated the `_save_health_check_to_db` function to call `save_health_check_result` with explicitly typed arguments instead of a dictionary spread, enhancing code clarity and type safety.
- Removed unused method bindings in the mock Prisma client tests to streamline the test setup.
* Remove unused `_save_health_check_to_db` function from utils.py to streamline code and improve maintainability.
* Implement response time validation and details cleaning in health check result saving
- Added `_validate_response_time` method to ensure response time values are valid and handle exceptions gracefully.
- Introduced `_clean_details` method to validate and clean details JSON, improving data integrity.
- Refactored `save_health_check_result` to utilize these new methods for optional fields, enhancing code clarity and maintainability.
- Updated tests to bind new methods to the mock Prisma client for comprehensive testing.
* Add health check utility functions and refactor existing endpoints
- Introduced `_convert_health_check_to_dict` to standardize health check record conversion to dictionary format for JSON responses.
- Added `_check_prisma_client` helper function to streamline database availability checks and improve error handling.
- Refactored health check endpoints to utilize the new utility functions, enhancing code clarity and maintainability.
* Refactor health check tests for improved clarity and coverage
- Simplified the mock PrismaClient setup by consolidating method bindings.
- Updated health check result saving tests to use parameterized scenarios for better coverage.
- Added tests for health check history retrieval and graceful handling when no database client is provided.
- Removed redundant mock functions to streamline the test suite.
* Implement helper function for health check and database saving
- Added `_perform_health_check_and_save` to encapsulate health check execution and optional database saving.
- Refactored health endpoint logic to utilize the new helper function, improving code clarity and reducing redundancy.
- Enhanced error handling and streamlined the process of saving health check results to the database.
* docs(index.md): add stable pip package
* fix(anthropic/chat/transformation.py): add 'none' tool choice mapping
Allows disabling anthropic tool calling
Maintain parity
* fix(transformation.py): if tool_choice="none" ignore 'disable_parallel_Tool_use'
unsupported param from anthropic - makes sense as the 'none' implies no tool calls are being made
* fix(anthropic/chat/transformation.py): append prefix to start of assistant response, if set
ensures assistant response contains complete response
* fix(anthropic/chat/transformation.py): add flag to allow user to opt out of enabling prefix in prompt
* fix(anthropic/chat/transformation.py): working e2e support for prefix prompt in assistant response
* feat(networking.tsx): always include model access groups on UI
show admin created access groups when giving key/user/team model permissions
* feat(add_model_tab.tsx): initial ui component for adding to an existing model access group
allows user to add model to an access group (simplify giving users/keys/teams model access)
* feat(proxy_server.py): add 'only_model_access_groups' flag support to `/v1/models`
simplifies listing available access groups on UI
* test: add e2e test for new only_model_access_groups param
* feat(add_model_tab.tsx): allow adding+viewing model access groups on models tab
make feature functional on UI
* feat(view_users.tsx): route edit user to user info page
more detailed user edit
* feat(columns.tsx): route edit user to user info page
more detailed user edit
* fix(columns.tsx): fix linting error
* build(ui/): fix linting errors
* feat(anthropic/passthrough): pass dynamic api key/api base params to litellm.completion
allows calls to work with config.yaml
* fix(responses_api/transformation): fix passing dynamic params to responses api from .completion()
Allows responses api to work with config.yaml
* fix(langfuse.py): fix responses api usage logging to langfuse
* refactor(litellm_logging.py): add more generic solution for responses api usage logging
ensures it works across all logging integrations
* fix(litellm_logging.py): patch for anthropic messages not returning a pydantic object
it should ideally return a pydantic object, which would simplify checks and reduce errors
* fix(handler.py): correctly bubble up empty choices errors to litellm.completion
causes downstream errors as it is expected there is at least one choice set
* feat(litellm_logging.py): prevent double logging litellm responses
ensures accurate spend tracking for calls when bridges are used
* fix(litellm_logging.py): ensure logging is consistently enforced across all call types
* fix: patch - set calltype before entering bridge api
ensures logging object is applying the correct logic on the event hooks
* fix(types/router.py): loosen type hint for mock response
* change space_key header to space_id for Arize (#11595)
* feat(schema): add additional indexes to LiteLLM_SpendLogs for improved query performance (#11675)
* Revert "feat(schema): add additional indexes to LiteLLM_SpendLogs for improve…" (#11683)
This reverts commit 2a7f113fde.
* [Feat] Use dedicated Rest endpoints for list, calling MCP tools (#11684)
* fix: (fix) use specific rest endpoints for MCP
* ui - use rest mcp endpoints
* fix imports
* docs DISABLE_AIOHTTP_TRUST_ENV
* docs(caching.md): remove batch redis get recommendation - old code path, no longer necessary
* fix(vertex_and_google_ai_studio_gemini.py): handle gemini not passing audio token usage data
* Chat Completions <-> Responses API Bridge Improvements (#11685)
* feat(anthropic/passthrough): pass dynamic api key/api base params to litellm.completion
allows calls to work with config.yaml
* fix(responses_api/transformation): fix passing dynamic params to responses api from .completion()
Allows responses api to work with config.yaml
* fix(langfuse.py): fix responses api usage logging to langfuse
* refactor(litellm_logging.py): add more generic solution for responses api usage logging
ensures it works across all logging integrations
* fix(litellm_logging.py): patch for anthropic messages not returning a pydantic object
it should ideally return a pydantic object, which would simplify checks and reduce errors
* fix(handler.py): correctly bubble up empty choices errors to litellm.completion
causes downstream errors as it is expected there is at least one choice set
* fix(response_metadata.py): allow model_info to be none
* fix(litellm_logging.py): copy object before mutating
* fix: fix lint check
* fix: fix linting error
* fix: fix linting error
---------
Co-authored-by: vanities <mischkeaa@gmail.com>
Co-authored-by: Cole McIntosh <82463175+colesmcintosh@users.noreply.github.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
* feat(anthropic/passthrough): pass dynamic api key/api base params to litellm.completion
allows calls to work with config.yaml
* fix(responses_api/transformation): fix passing dynamic params to responses api from .completion()
Allows responses api to work with config.yaml
* fix(langfuse.py): fix responses api usage logging to langfuse
* refactor(litellm_logging.py): add more generic solution for responses api usage logging
ensures it works across all logging integrations
* fix(litellm_logging.py): patch for anthropic messages not returning a pydantic object
it should ideally return a pydantic object, which would simplify checks and reduce errors
* fix(handler.py): correctly bubble up empty choices errors to litellm.completion
causes downstream errors as it is expected there is at least one choice set
* fix(response_metadata.py): allow model_info to be none
* fix(litellm_logging.py): copy object before mutating
* fix: fix lint check
- Updated the `_add_reasoning_system_prompt_if_needed` method to maintain the original format of list content when prepending the reasoning prompt.
- Adjusted tests to verify that both string and list content types are correctly handled, ensuring the reasoning prompt is added without altering the content structure.
- Updated the `_add_reasoning_system_prompt_if_needed` method to convert list content to strings before prepending the reasoning prompt.
- Adjusted tests to verify that system messages with list content are correctly transformed into strings, ensuring original content is preserved.
- Revised the reasoning support indicators in the Mistral model documentation for clarity.
- Improved the `_add_reasoning_system_prompt_if_needed` method to handle both string and list content types for system messages, ensuring the reasoning prompt is correctly prepended.
- Added a new test case to verify the functionality of adding the reasoning system prompt when the existing content is a list.
* fix(utils.py): convert stringified numbers to numbers
Closes https://github.com/BerriAI/litellm/issues/11266
* fix(convert_dict_to_model_response_object/): bubble up azure content_filter_results
* fix: fix linting error
* fix: fix linting errors
* fix(types/utils.py): ensure choices is correctly set
* fix: delete field if not set
* fix: expand scope of choicelogprobs value
* feat(parallel_request_limiter_v3.py): allows admin to enforce token rate limit based on just output tokens
Useful when trying to rate limit for primarily self hosted model use-cases
* test(test_parallel_request_limiter_v3.py): add unit test for token rate limit type
* feat(parallel_request_limiter_v3.py): return remaining token limits in header
* feat: return rate limit headers in response
* feat(parallel_request_limiter_v3.py): working rate limit response headers
* feat(parallel_request_limiter_v3.py): fix rate limit tracking for tpm when rpm also set
* feat(parallel_request_limiter_v3.py): show headers for key/user/team
* feat(parallel_request_limiter_v3.py): decrement max parallel request limiter on failure event
* feat(parallel_request_limiter_v3.py): add in-memory cache implementation of parallel request rate limiter
allows rate limiter to work even without redis cache setup
Work for GA of parallel request limiter v3
* refactor(proxy/hooks/__init__.py): replace with new parallel request handler
* test: update testing
* fix: fix ruff check
* fix: revert ga of multi instance rate limiting - needs more work to pass testing
* Added support for reasoning parameters in magistral models, including "reasoning_effort" and "thinking".
* Updated the MistralConfig class to handle reasoning system prompts.
* Implemented tests to verify reasoning functionality and ensure correct parameter mapping for magistral models.
* Enhanced the model prices JSON to reflect new reasoning capabilities.
* Checkpoint before follow-up message
* Add comprehensive tests for Deepgram transcription functionality
* clean up transform
* just use 1 test
* test cleanup
* test fix get_complete_url
* test rename file
* refactor deepgram URL construction
* add logging_obj.pre_call
* fix unused imports
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
* fix(internal_user_endpoints.py): support user with `+` in email on user info
ensures user is correctly parsed from input
* fix(factory.py): support vertex function call args as None
handles empty string in args for vertex gemini calls
* docs(langfuse_integration.md): pin langfuse sdk version on docs
* fix(vertex_ai/): return empty dict, instead of none when empty string given
* refactor: reduce function size
* fix: fix linting errors
* fix: revert check
* fix(internal_user_endpoints.py): fix check
* test: update tests
* test: update tests
* docs(deploy.md): move docker recommendation to `main-stable`
* feat(enterprise/internal_user_endpoints.py): expose endpoint for checking available premium users
* feat(usage_indictor.tsx): add new element to help track remaining premium users
* feat(usage_indicator.tsx): show premium user remaining usage
allows users with user caps to know how much is left
* fix(vertex_and_google_ai_studio_gemini.py): bubble up stream is not finished, even if stop reason is given
prevents early completion of stream
Closes https://github.com/BerriAI/litellm/issues/11549
* fix(streaming_handler.py): respect is_finished = False in hidden params
internal logic for preventing ending stream early
* fix(litellm_license.py): add function to check if user is over limit
* fix(internal_user_endpoints.py): add function to check if user is over limit
* refactor: move test
* docs(customer_endpoints.py): document new param
* fix: fixes for transfer encoding error on aiohttp transport
* Update tests/test_litellm/llms/custom_httpx/test_aiohttp_transport.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix(streaming_handler.py): maintain same 'created' across all chunks
Fixes https://github.com/BerriAI/litellm/issues/11437
* test: add unit test to ensure created is always the same across all chunks
* fix(types/utils.py): set a tool call id, if missing in delta tool call
Ensures stream chunk builder can reconstruct tool calls correctly
Fixes https://github.com/BerriAI/litellm/issues/11262
* fix(responses/transformation.py): support passing mcp server tool call to anthropic
allows switching between openai and anthropic for mcp tool calling
* fix(ollama/chat/transformation.py): set tool call id's when missing
* fix(onboarding_link.tsx): fix adding ui/invitation id
* fix(onboarding_link.tsx): update invitation link function to handle w/ and w/out custom server path cases
* fix(model_checks.py): ensure team only models returned when all proxy models set for team
* feat(anthropic/): initial commit adding working mcp tool call support
pass in mcp tool via `tools` and litellm will handle translating it to the right anthropic param
* feat(anthropic/): map openai mcp tool to anthropic mcp tool
allows usage within responses api
* fix(databricks/transformation.py): fix databricks linting error
* test(test_anthropic_chat_transformation.py): fix test
* test: update test
* fix(anthropic/chat/transformation.py): add dummy tool call
* refactor: comment out circuit breaker
causes incorrect rate limiting in high traffic
* fix(base_routing_strategy.py): don't reset value if redis val is lower than current in-memory value
Fixes issue where redis might be trailing in-memory value
* fix(parallel_request_limiter_v2.py): if in-memory higher than redis, don't reset value; add previous slot keys to redis increment to correctly 'get' them
* fix(parallel_request_limiter_v3.py): v3 implementation of parallel request limiter
does not use background redis syncing - increments redis in call
simplify rate limiting logic, to improve accuracy
* fix: fix ruff errors
* fix(parallel_request_limiter_v3.py): don't decrement limit on post call success - causes double decrements
* fix(parallel_request_limiter_v3.py): working accurate multi-instance logic
ensured just 100 requests allowed on 100 users, 10 ramp up, 100 rpm limit key, 2 instances
* fix(parallel_request_limiter_v3.py): working accurate rate limiting with time window resets
allows rate limiting to work across multiple windows
* test: add unit tests for v3 rate limiter
* fix(parallel_request_limiter_v3.py): return window value into in-memory cache
allows in-memory cache checks to be used correctly
* refactor(parallel_request_limiter_v3.py): refactor rate limiting to work for multiple window/counter key pairs
enables using for user/team/model rate limiting
* feat(parallel_request_limiter_v3.py): working rate limiting, across key/user/team/end-user
* fix(parallel_request_limiter_v3.py): add model specific rate limiting
* fix(parallel_request_limiter_v3.py): ignore if no rate limits set
skip unecessary rate limit checks - if no limits set
* fix(parallel_request_limiter_v3.py): initial commit bringing token rate limits back
* fix(parallel_request_limiter_v3.py): increment by value in list + update assertions to handle tokens + max parallel requests
* test(parallel_request_limiter_v3.py): more testing
* fix(parallel_request_limiter.py): working in-memory cache limiter
* fix(redis_cache.py): ignore linting error - use safe hasattr
* fix(parallel_request_limiter_v3.py): fix linting error
* refactor: remove redundant parallel_Request_limiter_v2.py
old / inaccurate implementation
* test: update tests
* style: cleanup
* test: update test
* docs(config_settings.md): document new env var
* test(test_base_routing_strategy.py): update test
* Enhance proxy CLI with Rich formatting and improved user experience
- Integrated Rich library for better console output in `proxy_cli.py`, including version display, health check results, and test completion responses.
- Updated health check and test completion methods to provide progress indicators and formatted tables.
- Refactored feedback display in `proxy_server.py` to use Rich for a more visually appealing user interface.
- Adjusted tests in `test_proxy_cli.py` to mock console output instead of using print statements, ensuring compatibility with Rich formatting.
* fix linting error
* refactor(proxy_cli.py): simplify DB setup logging
- Removed progress indicators for IAM token generation and environment variable decryption to simplify the code.
- Consolidated the logic for generating the database URL and setting environment variables.
- Enhanced error handling for configuration loading and database setup, ensuring clearer feedback
* Update test-linting workflow to include proxy-dev dependencies in Poetry installation
* Enhance proxy server initialization with Rich console for improved model display. Added support for loading model parameters from environment variables and refined provider identification logic. Fallback to original print formatting if Rich is not available.
* Refactor feedback handling: Moved feedback message generation and custom warning display to utils.py. Enhanced feedback box with rich formatting and fallback to ASCII for environments without rich. Cleaned up proxy_server.py by removing obsolete code.
* fix linting error
* Refactor model initialization display: Moved model initialization logic to a new utility function `display_model_initialization` for improved readability and maintainability. Enhanced model provider extraction with a dedicated function. Fallback to basic logging if Rich console is unavailable.
* Refactor model provider extraction: Replace the `_extract_provider_from_model` function with a more robust approach using `get_llm_provider`. Implement fallback logic for provider identification and improve error handling. Ensure compatibility with Rich console for model initialization display.
* Refactor get_end_user_id_from_request_body to support user ID retrieval from custom headers and multiple request body formats. Enhance tests to cover various scenarios including header precedence and fallback mechanisms.
* Refactor get_end_user_id_from_request_body function to accept request_body as the first parameter, improving clarity and flexibility. Update tests for compatibility and add new cases to ensure correct functionality across various request body formats.
* Update _user_api_key_auth_builder and user_api_key_auth to pass request object to get_end_user_id_from_request_body, enhancing user ID retrieval from request data.
* refactor(auth_utils.py): update get_end_user_id_from_request_body to accept request_headers instead of request, and adjust related function calls in user_api_key_auth and tests
* refactor(tests): update mock request handling in LLM pass-through endpoint tests
- Replaced the Request object with a Mock for better flexibility in testing.
- Enhanced mock setup to include user API key handling and virtual key retrieval.
- Updated test calls to reflect changes in mock request structure and added necessary patches for new dependencies.
* refactor(vertex_and_google_ai_studio_gemini.py): remove redundant variable declaration for url_context_metadata, linting error
* Handle file content type transformation in responses api (#11310)
* Handle file content type transformation in responses api
* change to use input_file
* -
* TestLiteLLMCompletionResponsesConfig
* test: TestLiteLLMCompletionResponsesConfig
* fix: fix linting
---------
Co-authored-by: Jayme Gordon <jayme_gordon@icloud.com>
