feat: OpenAI Responses API (#1989)

# What does this PR do?

This provides an initial [OpenAI Responses
API](https://platform.openai.com/docs/api-reference/responses)
implementation. The API is not yet complete, and this is more a
proof-of-concept to show how we can store responses in our key-value
stores and use them to support the Responses API concepts like
`previous_response_id`.

## Test Plan

I've added a new
`tests/integration/openai_responses/test_openai_responses.py` as part of
a test-driven development for this new API. I'm only testing this
locally with the remote-vllm provider for now, but it should work with
any of our inference providers since the only API it requires out of the
inference provider is the `openai_chat_completion` endpoint.

```
VLLM_URL="http://localhost:8000/v1" \
INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct" \
llama stack build --template remote-vllm --image-type venv --run
```

```
LLAMA_STACK_CONFIG="http://localhost:8321" \
python -m pytest -v \
  tests/integration/openai_responses/test_openai_responses.py \
  --text-model "meta-llama/Llama-3.2-3B-Instruct"
 ```

---------

Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>

llama_stack/providers/inline/agents/meta_reference/agents.py

@@ -23,6 +23,9 @@ from llama_stack.apis.agents import (
     Document,
     ListAgentSessionsResponse,
     ListAgentsResponse,
+    OpenAIResponseInputMessage,
+    OpenAIResponseInputTool,
+    OpenAIResponseObject,
     Session,
     Turn,
 )
@@ -40,6 +43,7 @@ from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_imp
 
 from .agent_instance import ChatAgent
 from .config import MetaReferenceAgentsImplConfig
+from .openai_responses import OpenAIResponsesImpl
 
 logger = logging.getLogger()
 logger.setLevel(logging.INFO)
@@ -63,9 +67,16 @@ class MetaReferenceAgentsImpl(Agents):
         self.tool_groups_api = tool_groups_api
 
         self.in_memory_store = InmemoryKVStoreImpl()
+        self.openai_responses_impl = None
 
     async def initialize(self) -> None:
         self.persistence_store = await kvstore_impl(self.config.persistence_store)
+        self.openai_responses_impl = OpenAIResponsesImpl(
+            self.persistence_store,
+            inference_api=self.inference_api,
+            tool_groups_api=self.tool_groups_api,
+            tool_runtime_api=self.tool_runtime_api,
+        )
 
         # check if "bwrap" is available
         if not shutil.which("bwrap"):
@@ -244,3 +255,23 @@ class MetaReferenceAgentsImpl(Agents):
         agent_id: str,
     ) -> ListAgentSessionsResponse:
         pass
+
+    # OpenAI responses
+    async def get_openai_response(
+        self,
+        id: str,
+    ) -> OpenAIResponseObject:
+        return await self.openai_responses_impl.get_openai_response(id)
+
+    async def create_openai_response(
+        self,
+        input: Union[str, List[OpenAIResponseInputMessage]],
+        model: str,
+        previous_response_id: Optional[str] = None,
+        store: Optional[bool] = True,
+        stream: Optional[bool] = False,
+        tools: Optional[List[OpenAIResponseInputTool]] = None,
+    ) -> OpenAIResponseObject:
+        return await self.openai_responses_impl.create_openai_response(
+            input, model, previous_response_id, store, stream, tools
+        )