feat: allow using llama-stack-library-client from verifications (#2238)

Having to run (and re-run) a server while running verifications can be
annoying while you are iterating on code. This makes it so you can use
the library client -- and because it is OpenAI client compatible, it all
works.

## Test Plan

```
pytest -s -v tests/verifications/openai_api/test_responses.py \
   --provider=stack:together \
   --model meta-llama/Llama-4-Scout-17B-16E-Instruct
```

tests/verifications/conftest.py

@@ -25,6 +25,11 @@ def pytest_addoption(parser):
         action="store",
         help="Provider to use for testing",
     )
+    parser.addoption(
+        "--model",
+        action="store",
+        help="Model to use for testing",
+    )
 
 
 pytest_plugins = [