Commit graph

18 commits

Author SHA1 Message Date
Krrish Dholakia
fcc8d8a8a0 test: add unit test 2025-03-24 14:45:20 -07:00
Ishaan Jaff
52f5a21449 test tool call cost tracking 2025-03-22 19:47:13 -07:00
Ishaan Jaff
907b2c1c0a test_is_chunk_non_empty_with_annotations 2025-03-22 11:41:53 -07:00
Krrish Dholakia
4d56992407 fix(ollama/completions/transformation.py): pass prompt, untemplated on /completions request
Fixes https://github.com/BerriAI/litellm/issues/6900
2025-03-17 18:35:44 -07:00
Krrish Dholakia
7446038d26 fix(streaming_handler.py): pass complete streaming response on completion 2025-03-16 20:22:12 -07:00
Krrish Dholakia
82320a9b65 refactor(litellm_logging.py): delegate returning a complete response to the streaming_handler
Removes incorrect logic for calculating complete streaming response from litellm logging
2025-03-15 09:55:33 -07:00
Krrish Dholakia
ff412c40ec test(test_streaming_handler.py): add unit test to ensure model response stream with usage is always used 2025-03-15 09:35:48 -07:00
Krrish Dholakia
303bf7628c test(test_streaming_handler.py): assert chunk is non-empty when usage block given 2025-03-15 09:26:01 -07:00
Ishaan Jaff
571ef58045 Bug fix - String data: stripped from entire content in streamed Gemini responses (#9070)
* _strip_sse_data_from_chunk

* use _strip_sse_data_from_chunk

* use _strip_sse_data_from_chunk

* use _strip_sse_data_from_chunk

* _strip_sse_data_from_chunk

* test_strip_sse_data_from_chunk

* _strip_sse_data_from_chunk

* testing

* _strip_sse_data_from_chunk
2025-03-07 21:06:39 -08:00
Ishaan Jaff
bfbbac38fc [Feat] - Display thinking tokens on OpenWebUI (Bedrock, Anthropic, Deepseek) (#9029)
* if merge_reasoning_content_in_choices

* _optional_combine_thinking_block_in_choices

* stash changes

* working merge_reasoning_content_in_choices with bedrock

* fix litellm_params accessor

* fix streaming handler

* merge_reasoning_content_in_choices

* _optional_combine_thinking_block_in_choices

* test_bedrock_stream_thinking_content_openwebui

* merge_reasoning_content_in_choices

* fix for _optional_combine_thinking_block_in_choices

* linting error fix
2025-03-06 18:32:58 -08:00
Krish Dholakia
159d5ddaf5 Fix deepseek 'reasoning_content' error (#8963)
* fix(streaming_handler.py): fix deepseek reasoning content streaming

Fixes https://github.com/BerriAI/litellm/issues/8939

* test(test_streaming_handler.py): add unit test to streaming handle 'is_chunk_non_empty' function

ensures 'reasoning_content' is handled correctly
2025-03-03 14:34:10 -08:00
Ishaan Jaff
4d50dcd417 Revert "(bug fix) - don't log messages, prompt, input in model_parameters in StandardLoggingPayload (#8923)"
This reverts commit a119cb420b.
2025-03-01 11:05:33 -08:00
Ishaan Jaff
dce5c3e16b (bug fix) - dd tracer, only send traces when user opts into sending dd-trace (#8928)
* fix dd tracing null tracer bug

* fix dd tracing

* fix base aws llm

* test_should_use_dd_tracer
2025-03-01 10:53:36 -08:00
Ishaan Jaff
44cfa7eed3 (bug fix) - don't log messages, prompt, input in model_parameters in StandardLoggingPayload (#8923)
* fix _get_model_parameters

* test litellm logging

* test litellm logging
2025-03-01 10:27:24 -08:00
Ishaan Jaff
c3335ac90a (Bug fix) dd-trace used by default on litellm proxy (#8817)
* fix _should_use_dd_tracer

* fix _should_use_dd_tracer

* _should_use_dd_tracer

* _should_use_dd_tracer

* _should_use_dd_tracer

* _init_dd_tracer

* _should_use_dd_tracer

* fix should use dd-tracer

* fix dd tracer
2025-02-25 19:54:22 -08:00
Ishaan Jaff
f940392971 (Observability) - Add more detailed dd tracing on Proxy Auth, Bedrock Auth (#8693)
* add dd tracer

* fix dd tracing

* add @tracer.wrap() on def user_api_key_auth

* add async_function_with_retries

* remove dead code

* add tracer.wrap on base aws llm

* add tracer.wrap on base aws llm

* fix print verbose

* fix dd tracing

* trace base aws llm

* fix test base aws llm

* fix converse transform

* test base aws llm

* BASE_AWS_LLM_PATH

* BASE_AWS_LLM_PATH

* test dd tracing
2025-02-20 18:00:41 -08:00
Ishaan Jaff
b571213569 (Bug fix) - Cache Health not working when configured with prometheus service logger (#8687)
* fix serialize on safe json dumps

* test_non_standard_dict_keys_complex

* ui fix HealthCheckCacheParams

* fix HealthCheckCacheParams

* fix code qa

* test_cache_ping_failure

* test_cache_ping_health_check_includes_only_cache_attributes

* test_cache_ping_health_check_includes_only_cache_attributes
2025-02-20 13:41:56 -08:00
Ishaan Jaff
752e93cbdb (UI + Proxy) Cache Health Check Page - Cleanup/Improvements (#8665)
* fixes for redis cache ping serialization

* fix cache ping check

* fix cache health check ui

* working error details on ui

* ui expand / collapse error

* move cache health check to diff file

* fix displaying error from cache health check

* ui allow copying errors

* ui cache health fixes

* show redis details

* clean up cache health page

* ui polish fixes

* fix error handling on cache health page

* fix redis_cache_params on cache ping response

* error handling

* cache health ping response

* fx error response from cache ping

* parsedLitellmParams

* fix cache health check

* fix cache health page

* cache safely handle json dumps issues

* test caching routes

* test_primitive_types

* fix caching routes

* litellm_mapped_tests

* fix pytest-mock

* fix _serialize

* fix linting on safe dumps

* test_default_max_depth

* pip install "pytest-mock==3.12.0"

* litellm_mapped_tests_coverage

* add readme on new litellm test dir
2025-02-19 19:08:50 -08:00