chore: Change moderations api response to Provider returned categories (#3098)

# What does this PR do?
To be compliant with model policies for LLAMA, just return the
categories as is from provider, we will lose the OAI compat in
moderations api response.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
`SAFETY_MODEL=llama-guard3:8b LLAMA_STACK_CONFIG=starter uv run pytest
-v tests/integration/safety/test_safety.py
--text-model=llama3.2:3b-instruct-fp16
--embedding-model=all-MiniLM-L6-v2 --safety-shield=ollama`

docs/_static/llama-stack-spec.html

@@ -16569,7 +16569,7 @@
                         "additionalProperties": {
                             "type": "number"
                         },
-                        "description": "A list of the categories along with their scores as predicted by model. Required set of categories that need to be in response - violence - violence/graphic - harassment - harassment/threatening - hate - hate/threatening - illicit - illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent - self-harm/instructions"
+                        "description": "A list of the categories along with their scores as predicted by model."
                     },
                     "user_message": {
                         "type": "string"

docs/_static/llama-stack-spec.yaml

@@ -12322,10 +12322,6 @@ components:
             type: number
           description: >-
             A list of the categories along with their scores as predicted by model.
-            Required set of categories that need to be in response - violence - violence/graphic
-            - harassment - harassment/threatening - hate - hate/threatening - illicit
-            - illicit/violent - sexual - sexual/minors - self-harm - self-harm/intent
-            - self-harm/instructions
         user_message:
           type: string
         metadata: