Split safety into (llama-guard, prompt-guard, code-scanner) (#400)

Splits the meta-reference safety implementation into three distinct providers:

- inline::llama-guard
- inline::prompt-guard
- inline::code-scanner

Note that this PR is a backward incompatible change to the llama stack server. I have added deprecation_error field to ProviderSpec -- the server reads it and immediately barfs. This is used to direct the user with a specific message on what action to perform. An automagical "config upgrade" is a bit too much work to implement right now :/

(Note that we will be gradually prefixing all inline providers with inline:: -- I am only doing this for this set of new providers because otherwise existing configuration files will break even more badly.)

llama_stack/providers/tests/agents/conftest.py

@@ -18,7 +18,7 @@ DEFAULT_PROVIDER_COMBINATIONS = [
     pytest.param(
         {
             "inference": "meta_reference",
-            "safety": "meta_reference",
+            "safety": "llama_guard",
             "memory": "meta_reference",
             "agents": "meta_reference",
         },
@@ -28,7 +28,7 @@ DEFAULT_PROVIDER_COMBINATIONS = [
     pytest.param(
         {
             "inference": "ollama",
-            "safety": "meta_reference",
+            "safety": "llama_guard",
             "memory": "meta_reference",
             "agents": "meta_reference",
         },
@@ -38,7 +38,7 @@ DEFAULT_PROVIDER_COMBINATIONS = [
     pytest.param(
         {
             "inference": "together",
-            "safety": "meta_reference",
+            "safety": "llama_guard",
             # make this work with Weaviate which is what the together distro supports
             "memory": "meta_reference",
             "agents": "meta_reference",