feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403)

Renames `inference_recorder.py` to `api_recorder.py` and extends it to
support recording/replaying tool invocations in addition to inference
calls.

This allows us to record web-search, etc. tool calls and thereafter
apply recordings for `tests/integration/responses`

## Test Plan

```
export OPENAI_API_KEY=...
export TAVILY_SEARCH_API_KEY=...

./scripts/integration-tests.sh --stack-config ci-tests \
   --suite responses --inference-mode record-if-missing
```
This commit is contained in:
Ashwin Bharambe 2025-10-09 14:27:51 -07:00 committed by GitHub
parent 26fd5dbd34
commit f50ce11a3b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
284 changed files with 296191 additions and 631 deletions

View file

@ -47,12 +47,14 @@ def test_response_text_format(compat_client, text_model_id, text_format):
@pytest.fixture
def vector_store_with_filtered_files(compat_client, text_model_id, tmp_path_factory):
"""Create a vector store with multiple files that have different attributes for filtering tests."""
def vector_store_with_filtered_files(compat_client, embedding_model_id, embedding_dimension, tmp_path_factory):
# """Create a vector store with multiple files that have different attributes for filtering tests."""
if isinstance(compat_client, LlamaStackAsLibraryClient):
pytest.skip("Responses API file search is not yet supported in library client.")
pytest.skip("upload_file() is not yet supported in library client somehow?")
vector_store = new_vector_store(compat_client, "test_vector_store_with_filters")
vector_store = new_vector_store(
compat_client, "test_vector_store_with_filters", embedding_model_id, embedding_dimension
)
tmp_path = tmp_path_factory.mktemp("filter_test_files")
# Create multiple files with different attributes