ci: test safety with starter (#2628)

# What does this PR do?

We are now testing the safety capability with the starter image. This
includes a few changes:

* Enable the safety integration test
* Relax the shield model requirements from llama-guard to make it work
  with llama-guard3:8b coming from Ollama
* Expose a shield for each inference provider in the starter distro. The
  shield will only be registered if the provider is enabled.

Closes: https://github.com/meta-llama/llama-stack/issues/2528

Signed-off-by: Sébastien Han <seb@redhat.com>

llama_stack/providers/remote/inference/together/models.py

@@ -11,6 +11,16 @@ from llama_stack.providers.utils.inference.model_registry import (
     build_hf_repo_model_entry,
 )
 
+SAFETY_MODELS_ENTRIES = [
+    build_hf_repo_model_entry(
+        "meta-llama/Llama-Guard-3-8B",
+        CoreModelId.llama_guard_3_8b.value,
+    ),
+    build_hf_repo_model_entry(
+        "meta-llama/Llama-Guard-3-11B-Vision-Turbo",
+        CoreModelId.llama_guard_3_11b_vision.value,
+    ),
+]
 MODEL_ENTRIES = [
     build_hf_repo_model_entry(
         "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
@@ -40,14 +50,6 @@ MODEL_ENTRIES = [
         "meta-llama/Llama-3.3-70B-Instruct-Turbo",
         CoreModelId.llama3_3_70b_instruct.value,
     ),
-    build_hf_repo_model_entry(
-        "meta-llama/Meta-Llama-Guard-3-8B",
-        CoreModelId.llama_guard_3_8b.value,
-    ),
-    build_hf_repo_model_entry(
-        "meta-llama/Llama-Guard-3-11B-Vision-Turbo",
-        CoreModelId.llama_guard_3_11b_vision.value,
-    ),
     ProviderModelEntry(
         provider_model_id="togethercomputer/m2-bert-80M-8k-retrieval",
         model_type=ModelType.embedding,
@@ -78,4 +80,4 @@ MODEL_ENTRIES = [
             "together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
         ],
     ),
-]
+] + SAFETY_MODELS_ENTRIES