feat: introduce APIs for retrieving chat completion requests (#2145)

# What does this PR do?
This PR introduces APIs to retrieve past chat completion requests, which
will be used in the LS UI.

Our current `Telemetry` is ill-suited for this purpose as it's untyped
so we'd need to filter by obscure attribute names, making it brittle.

Since these APIs are 'provided by stack' and don't need to be
implemented by inference providers, we introduce a new InferenceProvider
class, containing the existing inference protocol, which is implemented
by inference providers.

The APIs are OpenAI-compliant, with an additional `input_messages`
field.


## Test Plan
This PR just adds the API and marks them provided_by_stack. S
tart stack server -> doesn't crash

llama_stack/apis/inference/inference.py

@@ -820,15 +820,32 @@ class BatchChatCompletionResponse(BaseModel):
     batch: list[ChatCompletionResponse]
 
 
+class OpenAICompletionWithInputMessages(OpenAIChatCompletion):
+    input_messages: list[OpenAIMessageParam]
+
+
+@json_schema_type
+class ListOpenAIChatCompletionResponse(BaseModel):
+    data: list[OpenAICompletionWithInputMessages]
+    has_more: bool
+    first_id: str
+    last_id: str
+    object: Literal["list"] = "list"
+
+
+class Order(Enum):
+    asc = "asc"
+    desc = "desc"
+
+
 @runtime_checkable
 @trace_protocol
-class Inference(Protocol):
-    """Llama Stack Inference API for generating completions, chat completions, and embeddings.
-
-    This API provides the raw interface to the underlying models. Two kinds of models are supported:
-    - LLM models: these models generate "raw" and "chat" (conversational) completions.
-    - Embedding models: these models generate embeddings to be used for semantic search.
+class InferenceProvider(Protocol):
     """
+    This protocol defines the interface that should be implemented by all inference providers.
+    """
+
+    API_NAMESPACE: str = "Inference"
 
     model_store: ModelStore | None = None
 
@@ -1062,3 +1079,39 @@ class Inference(Protocol):
         :returns: An OpenAIChatCompletion.
         """
         ...
+
+
+class Inference(InferenceProvider):
+    """Llama Stack Inference API for generating completions, chat completions, and embeddings.
+
+    This API provides the raw interface to the underlying models. Two kinds of models are supported:
+    - LLM models: these models generate "raw" and "chat" (conversational) completions.
+    - Embedding models: these models generate embeddings to be used for semantic search.
+    """
+
+    @webmethod(route="/openai/v1/chat/completions", method="GET")
+    async def list_chat_completions(
+        self,
+        after: str | None = None,
+        limit: int | None = 20,
+        model: str | None = None,
+        order: Order | None = Order.desc,
+    ) -> ListOpenAIChatCompletionResponse:
+        """List all chat completions.
+
+        :param after: The ID of the last chat completion to return.
+        :param limit: The maximum number of chat completions to return.
+        :param model: The model to filter by.
+        :param order: The order to sort the chat completions by: "asc" or "desc". Defaults to "desc".
+        :returns: A ListOpenAIChatCompletionResponse.
+        """
+        raise NotImplementedError("List chat completions is not implemented")
+
+    @webmethod(route="/openai/v1/chat/completions/{completion_id}", method="GET")
+    async def get_chat_completion(self, completion_id: str) -> OpenAICompletionWithInputMessages:
+        """Describe a chat completion by its ID.
+
+        :param completion_id: ID of the chat completion.
+        :returns: A OpenAICompletionWithInputMessages.
+        """
+        raise NotImplementedError("Get chat completion is not implemented")