litellm/tests/litellm
Christopher Baer 589c6cdad0
fix(gemini-embeddings): convert task_type to camelCase taskType for Gemini API (#24191)
The Gemini REST API documents the embedding task type parameter as
camelCase `taskType`. The existing transformation functions convert
`dimensions` to `outputDimensionality` but miss the parallel
`task_type` to `taskType` conversion. This adds that conversion to
both `transform_openai_input_gemini_content` (batchEmbedContents path)
and `transform_openai_input_gemini_embed_content` (embedContent path).

Fixes #24190
2026-03-20 22:32:22 +05:30
..
a2a_protocol/providers/pydantic_ai_agents [Feat] New provider - Agent Gateway, add pydantic ai agents (#18013) 2025-12-15 17:40:58 -08:00
integrations/helicone test: add provider_url routing test for vertex_ai/gemini models 2026-03-03 15:20:51 -03:00
litellm_core_utils test: create fresh ModelResponse per test to avoid shared mutable state 2026-03-03 14:54:11 -03:00
llms fix(gemini-embeddings): convert task_type to camelCase taskType for Gemini API (#24191) 2026-03-20 22:32:22 +05:30
proxy fix(proxy): Windows compatibility for Prisma engine watchdog (#23494) 2026-03-12 16:02:37 -07:00
test_batch_completion_models_all_responses.py fix(batch_completion): submit all model futures before waiting (#20705) 2026-02-11 15:44:37 +05:30
test_bedrock_extended_beta_models.py feat(bedrock): add support for 4 new beta models (#20974) 2026-02-13 18:32:12 +05:30
test_no_hardcoded_secrets.py test(ci): add secret scan test and CI job to prevent hardcoded credentials 2026-02-26 12:46:42 -03:00
test_proxy_auth.py feat(sdk): add proxy_auth for auto OAuth2/JWT token management (#20238) 2026-02-02 22:04:08 -08:00
test_router_retry_backoff_headers.py fix(router): use current retry exception for retry backoff (#20725) 2026-02-10 22:44:25 -08:00
test_stream_chunk_builder_images.py fix(types): remove StreamingChoices from ModelResponse, use ModelResponseStream 2026-02-20 17:47:42 -03:00