mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-28 08:11:59 +00:00
a713221280
In the Responses API, we convert incoming response requests to chat completion requests. When streaming the resulting chunks of those chat completion requests, inference providers that use OpenAI clients will often return a `type=None` value in the tool call parts of the response. This causes issues when we try to dump and load that response into our pydantic model, because type cannot be None in the Responses API model we're loading these into. So, strip the "type" field, if present, off those chat completion tool call results before dumping and loading them as our typed pydantic models, which will apply our default value for that type field. This was found via manual testing of the Responses API with codex, where I was getting errors in some tool call situations. I added a unit test to simulate this scenario and verify the fix, as well as manual codex testing to verify the fix. Signed-off-by: Ben Browning <bbrownin@redhat.com> |
||
|---|---|---|
| .. | ||
| cli | ||
| distribution | ||
| models | ||
| providers | ||
| rag | ||
| registry | ||
| server | ||
| __init__.py | ||
| conftest.py | ||
| fixtures.py | ||
| README.md | ||
Llama Stack Unit Tests
You can run the unit tests by running:
source .venv/bin/activate
./scripts/unit-tests.sh [PYTEST_ARGS]
Any additional arguments are passed to pytest. For example, you can specify a test directory, a specific test file, or any pytest flags (e.g., -vvv for verbosity). If no test directory is specified, it defaults to "tests/unit", e.g:
./scripts/unit-tests.sh tests/unit/registry/test_registry.py -vvv
If you'd like to run for a non-default version of Python (currently 3.10), pass PYTHON_VERSION variable as follows:
source .venv/bin/activate
PYTHON_VERSION=3.13 ./scripts/unit-tests.sh