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/templates/hf-endpoint/build.yaml

@@ -3,7 +3,7 @@ distribution_spec:
   description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
   providers:
     inference: remote::hf::endpoint
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference