[client sdk test] add options for inference_model, safety_shield, embedding_model (#843)

# What does this PR do?
Default inference_model for testing: "meta-llama/Llama-3.1-8B-Instruct"
Default vision inference_model for testing:
"meta-llama/Llama-3.2-11B-Vision-Instruct"


## Test Plan
`/opt/miniconda3/envs/stack/bin/pytest -s -v
--inference-model=meta-llama/Llama-3.2-3B-Instruct
tests/client-sdk/agents`


`/opt/miniconda3/envs/stack/bin/pytest -s -v
--embedding-model=all-MiniLM-L6-v2 tests/client-sdk/vector_io`

`/opt/miniconda3/envs/stack/bin/pytest -s -v
--safety-shield=meta-llama/Llama-Guard-3-1B tests/client-sdk/safety`

## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

tests/client-sdk/conftest.py

@@ -20,6 +20,10 @@ def pytest_configure(config):
         config.pluginmanager.register(Report())
 
 
+TEXT_MODEL = "meta-llama/Llama-3.1-8B-Instruct"
+VISION_MODEL = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+
+
 def pytest_addoption(parser):
     parser.addoption(
         "--report",
@@ -27,10 +31,18 @@ def pytest_addoption(parser):
         action="store_true",
         help="Knob to determine if we should generate report, e.g. --output=True",
     )
-
-
-TEXT_MODEL = "meta-llama/Llama-3.1-8B-Instruct"
-INFERENCE_MODEL = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+    parser.addoption(
+        "--inference-model",
+        action="store",
+        default=TEXT_MODEL,
+        help="Specify the inference model to use for testing",
+    )
+    parser.addoption(
+        "--vision-inference-model",
+        action="store",
+        default=VISION_MODEL,
+        help="Specify the vision inference model to use for testing",
+    )
 
 
 @pytest.fixture(scope="session")
@@ -61,3 +73,18 @@ def llama_stack_client(provider_data):
     else:
         raise ValueError("LLAMA_STACK_CONFIG or LLAMA_STACK_BASE_URL must be set")
     return client
+
+
+def pytest_generate_tests(metafunc):
+    if "text_model_id" in metafunc.fixturenames:
+        metafunc.parametrize(
+            "text_model_id",
+            [metafunc.config.getoption("--inference-model")],
+            scope="session",
+        )
+    if "vision_model_id" in metafunc.fixturenames:
+        metafunc.parametrize(
+            "vision_model_id",
+            [metafunc.config.getoption("--vision-inference-model")],
+            scope="session",
+        )