* 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
* refactor(responses/): refactor to move responses_to_completion in separate folder
future work to support completion_to_responses bridge
allow calling codex mini via chat completions (and other endpoints)
* Revert "refactor(responses/): refactor to move responses_to_completion in separate folder"
This reverts commit ff87cb895812283d107f47e8e528bcebe93d8015.
* feat: initial responses api bridge
write it like a custom llm - requires lesser 'new' components
* style: add __init__'s and bubble up the responses api bridge
* feat(responses/transformation): working sync completion -> responses and back bridge (non-streaming)
* feat(responses/): working async (non-streaming) completion <-> responses bridge
Allows calling codex mini via proxy
* feat(responses/): working sync + async streaming for base model response iterator
* fix: reduce function size
maintain <50 LOC
* fix(main.py): safely handle responses api model check
* fix: fix linting errors
* 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
* Feature/lasso guardrail (#9002)
* first version of lasso guardrail in litellm
* update to the new Lasso API
* change prod api_base and kill the request when lasso detect issue.
* change test for now api, local test pass
* add async tests
* all tests pass
* add docs for the new lasso guardrail
* Remove support for modes other than pre_call in Lasso guardrail
* code structure and naming
* only pre_call docs
* fix lint errors
* move test to the new location follows the same directory structure as litellm/.
* add lasso guard
* docs lasso docs
* add lasso guardrail
* fix lasso guardrail
---------
Co-authored-by: oroxenberg <oro@lasso.security>
* 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>
