feat: create unregister shield API endpoint in Llama Stack (#2853)

# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->

Extend the Shields Protocol and implement the capability to unregister
previously registered shields and CLI for shields management.

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes #2581 

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->

First of, test API for shields
1. Install and start Ollama:

`ollama serve`


2. Pull Llama Guard Model in Ollama:

`ollama pull llama-guard3:8b`

3. Configure env variables:

```
export ENABLE_OLLAMA=ollama
export OLLAMA_URL=http://localhost:11434
```

4. Build Llama Stack distro:

`llama stack build --template starter --image-type venv  `

5. Start Llama Stack server:

`llama stack run starter --port 8321`

6. Check if Ollama model is available:

`curl -X GET http://localhost:8321/v1/models | jq '.data[] |
select(.provider_id=="ollama")'`

7. Register a new Shield using Ollama provider:

```
curl -X POST http://localhost:8321/v1/shields \
 -H "Content-Type: application/json" \
 -d '{
   "shield_id": "test-shield",
   "provider_id": "llama-guard",
   "provider_shield_id": "ollama/llama-guard3:8b",
   "params": {}
 }'
```

`{"identifier":"test-shield","provider_resource_id":"ollama/llama-guard3:8b","provider_id":"llama-guard","type":"shield","owner":{"principal":"","attributes":{}},"params":{}}%
`

8. Check if shield was registered:

`curl -X GET http://localhost:8321/v1/shields/test-shield`


`{"identifier":"test-shield","provider_resource_id":"ollama/llama-guard3:8b","provider_id":"llama-guard","type":"shield","owner":{"principal":"","attributes":{}},"params":{}}%
`

9. Run shield:

```
curl -X POST http://localhost:8321/v1/safety/run-shield \
  -H "Content-Type: application/json" \
  -d '{
    "shield_id": "test-shield",
    "messages": [
      {
        "role": "user",
        "content": "How can I hack into someone computer?"
      }
    ],
    "params": {}
  }'
```

`{"violation":{"violation_level":"error","user_message":"I can't answer
that. Can I help with something
else?","metadata":{"violation_type":"S2"}}}% `

10. Unregister shield:

`curl -X DELETE http://localhost:8321/v1/shields/test-shield`

`null% `

11. Verify shield was deleted:

`curl -X GET http://localhost:8321/v1/shields/test-shield`

`{"detail":"Invalid value: Shield 'test-shield' not found"}%`

All tests passed ✅

```
========================================================================== 430 passed, 194 warnings in 19.54s ==========================================================================
/Users/iamiller/GitHub/llama-stack/.venv/lib/python3.12/site-packages/litellm/llms/custom_httpx/async_client_cleanup.py:78: RuntimeWarning: coroutine 'close_litellm_async_clients' was never awaited
  loop.close()
RuntimeWarning: Enable tracemalloc to get the object allocation traceback
Wrote HTML report to htmlcov-3.12/index.html

```

llama_stack/apis/shields/shields.py

@@ -83,3 +83,11 @@ class Shields(Protocol):
         :returns: A Shield.
         """
         ...
+
+    @webmethod(route="/shields/{identifier:path}", method="DELETE")
+    async def unregister_shield(self, identifier: str) -> None:
+        """Unregister a shield.
+
+        :param identifier: The identifier of the shield to unregister.
+        """
+        ...

llama_stack/core/routers/safety.py

@@ -43,6 +43,10 @@ class SafetyRouter(Safety):
         logger.debug(f"SafetyRouter.register_shield: {shield_id}")
         return await self.routing_table.register_shield(shield_id, provider_shield_id, provider_id, params)
 
+    async def unregister_shield(self, identifier: str) -> None:
+        logger.debug(f"SafetyRouter.unregister_shield: {identifier}")
+        return await self.routing_table.unregister_shield(identifier)
+
     async def run_shield(
         self,
         shield_id: str,

llama_stack/core/routing_tables/common.py

@@ -60,6 +60,8 @@ async def unregister_object_from_provider(obj: RoutableObject, p: Any) -> None:
         return await p.unregister_vector_db(obj.identifier)
     elif api == Api.inference:
         return await p.unregister_model(obj.identifier)
+    elif api == Api.safety:
+        return await p.unregister_shield(obj.identifier)
     elif api == Api.datasetio:
         return await p.unregister_dataset(obj.identifier)
     elif api == Api.tool_runtime:

llama_stack/core/routing_tables/shields.py

@@ -55,3 +55,7 @@ class ShieldsRoutingTable(CommonRoutingTableImpl, Shields):
         )
         await self.register_object(shield)
         return shield
+
+    async def unregister_shield(self, identifier: str) -> None:
+        existing_shield = await self.get_shield(identifier)
+        await self.unregister_object(existing_shield)

llama_stack/providers/datatypes.py

@@ -65,6 +65,8 @@ class ModelsProtocolPrivate(Protocol):
 class ShieldsProtocolPrivate(Protocol):
     async def register_shield(self, shield: Shield) -> None: ...
 
+    async def unregister_shield(self, identifier: str) -> None: ...
+
 
 class VectorDBsProtocolPrivate(Protocol):
     async def register_vector_db(self, vector_db: VectorDB) -> None: ...

llama_stack/providers/inline/safety/llama_guard/llama_guard.py

@@ -150,6 +150,11 @@ class LlamaGuardSafetyImpl(Safety, ShieldsProtocolPrivate):
         if not model_id:
             raise ValueError("Llama Guard shield must have a model id")
 
+    async def unregister_shield(self, identifier: str) -> None:
+        # LlamaGuard doesn't need to do anything special for unregistration
+        # The routing table handles the removal from the registry
+        pass
+
     async def run_shield(
         self,
         shield_id: str,

llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py

@@ -46,6 +46,9 @@ class PromptGuardSafetyImpl(Safety, ShieldsProtocolPrivate):
         if shield.provider_resource_id != PROMPT_GUARD_MODEL:
             raise ValueError(f"Only {PROMPT_GUARD_MODEL} is supported for Prompt Guard. ")
 
+    async def unregister_shield(self, identifier: str) -> None:
+        pass
+
     async def run_shield(
         self,
         shield_id: str,

llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -52,6 +52,9 @@ class BedrockSafetyAdapter(Safety, ShieldsProtocolPrivate):
                 f"Shield {shield.provider_resource_id} with version {shield.params['guardrailVersion']} not found in Bedrock"
             )
 
+    async def unregister_shield(self, identifier: str) -> None:
+        pass
+
     async def run_shield(
         self, shield_id: str, messages: list[Message], params: dict[str, Any] = None
     ) -> RunShieldResponse:

llama_stack/providers/remote/safety/nvidia/nvidia.py

@@ -40,6 +40,9 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
         if not shield.provider_resource_id:
             raise ValueError("Shield model not provided.")
 
+    async def unregister_shield(self, identifier: str) -> None:
+        pass
+
     async def run_shield(
         self, shield_id: str, messages: list[Message], params: dict[str, Any] | None = None
     ) -> RunShieldResponse:

llama_stack/providers/remote/safety/sambanova/sambanova.py

@@ -68,6 +68,9 @@ class SambaNovaSafetyAdapter(Safety, ShieldsProtocolPrivate, NeedsRequestProvide
         ):
             logger.warning(f"Shield {shield.provider_resource_id} not available in {list_models_url}")
 
+    async def unregister_shield(self, identifier: str) -> None:
+        pass
+
     async def run_shield(
         self, shield_id: str, messages: list[Message], params: dict[str, Any] | None = None
     ) -> RunShieldResponse: