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.)

docs/source/distribution_dev/building_distro.md

@@ -36,9 +36,9 @@ the provider types (implementations) you want to use for these APIs.
 Tip: use <TAB> to see options for the providers.
 
 > Enter provider for API inference: meta-reference
-> Enter provider for API safety: meta-reference
+> Enter provider for API safety: inline::llama-guard
 > Enter provider for API agents: meta-reference
-> Enter provider for API memory: meta-reference
+> Enter provider for API memory: inline::faiss
 > Enter provider for API datasetio: meta-reference
 > Enter provider for API scoring: meta-reference
 > Enter provider for API eval: meta-reference
@@ -203,8 +203,8 @@ distribution_spec:
   description: Like local, but use ollama for running LLM inference
   providers:
     inference: remote::ollama
-    memory: meta-reference
-    safety: meta-reference
+    memory: inline::faiss
+    safety: inline::llama-guard
     agents: meta-reference
     telemetry: meta-reference
 image_type: conda