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.)

distributions/meta-reference-gpu/run.yaml

@@ -13,7 +13,7 @@ apis:
 - safety
 providers:
   inference:
-  - provider_id: meta-reference-inference
+  - provider_id: inference0
     provider_type: meta-reference
     config:
       model: Llama3.2-3B-Instruct
@@ -21,7 +21,7 @@ providers:
       torch_seed: null
       max_seq_len: 4096
       max_batch_size: 1
-  - provider_id: meta-reference-safety
+  - provider_id: inference1
     provider_type: meta-reference
     config:
       model: Llama-Guard-3-1B
@@ -31,11 +31,14 @@ providers:
       max_batch_size: 1
   safety:
   - provider_id: meta0
-    provider_type: meta-reference
+    provider_type: inline::llama-guard
     config:
-      llama_guard_shield:
-        model: Llama-Guard-3-1B
-        excluded_categories: []
+      model: Llama-Guard-3-1B
+      excluded_categories: []
+  - provider_id: meta1
+    provider_type: inline::prompt-guard
+    config:
+      model: Prompt-Guard-86M
 # Uncomment to use prompt guard
 #      prompt_guard_shield:
 #        model: Prompt-Guard-86M