Litellm dev 04 05 2025 p2 (#9774)

* test: move test to just checking async

* fix(transformation.py): handle function call with no schema

* fix(utils.py): handle pydantic base model in message tool calls

Fix https://github.com/BerriAI/litellm/issues/9321

* fix(vertex_and_google_ai_studio.py): handle tools=[]

Fixes https://github.com/BerriAI/litellm/issues/9080

* test: remove max token restriction

* test: fix basic test

* fix(get_supported_openai_params.py): fix check

* fix(converse_transformation.py): support fake streaming for meta.llama3-3-70b-instruct-v1:0

* fix: fix test

* fix: parse out empty dictionary on dbrx streaming + tool calls

* fix(handle-'strict'-param-when-calling-fireworks-ai): fireworks ai does not support 'strict' param

* fix: fix ruff check

'

* fix: handle no strict in function

* fix: revert bedrock change - handle in separate PR
This commit is contained in:
Krish Dholakia 2025-04-07 21:02:52 -07:00 committed by GitHub
parent d8f47fc9e5
commit fcf17d114f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 214 additions and 11 deletions

View file

@ -562,8 +562,9 @@ def test_groq_parallel_function_call():
@pytest.mark.parametrize(
"model",
[
"anthropic.claude-3-sonnet-20240229-v1:0",
"claude-3-haiku-20240307",
# "anthropic.claude-3-sonnet-20240229-v1:0",
# "claude-3-haiku-20240307",
"databricks/databricks-claude-3-7-sonnet"
],
)
def test_anthropic_function_call_with_no_schema(model):