feat: add list responses API (#2233)

# What does this PR do?
This is not part of the official OpenAI API, but we'll use this for the
logs UI.
In order to support more filtering options, I'm adopting the newly
introduced sql store in in place of the kv store.

## Test Plan
Added integration/unit tests.

llama_stack/apis/agents/agents.py

@@ -13,7 +13,7 @@ from typing import Annotated, Any, Literal, Protocol, runtime_checkable
 from pydantic import BaseModel, ConfigDict, Field
 
 from llama_stack.apis.common.content_types import URL, ContentDelta, InterleavedContent
-from llama_stack.apis.common.responses import PaginatedResponse
+from llama_stack.apis.common.responses import Order, PaginatedResponse
 from llama_stack.apis.inference import (
     CompletionMessage,
     ResponseFormat,
@@ -31,6 +31,7 @@ from llama_stack.apis.tools import ToolDef
 from llama_stack.schema_utils import json_schema_type, register_schema, webmethod
 
 from .openai_responses import (
+    ListOpenAIResponseObject,
     OpenAIResponseInput,
     OpenAIResponseInputTool,
     OpenAIResponseObject,
@@ -611,3 +612,21 @@ class Agents(Protocol):
         :returns: An OpenAIResponseObject.
         """
         ...
+
+    @webmethod(route="/openai/v1/responses", method="GET")
+    async def list_openai_responses(
+        self,
+        after: str | None = None,
+        limit: int | None = 50,
+        model: str | None = None,
+        order: Order | None = Order.desc,
+    ) -> ListOpenAIResponseObject:
+        """List all OpenAI responses.
+
+        :param after: The ID of the last response to return.
+        :param limit: The number of responses to return.
+        :param model: The model to filter responses by.
+        :param order: The order to sort responses by when sorted by created_at ('asc' or 'desc').
+        :returns: A ListOpenAIResponseObject.
+        """
+        ...

llama_stack/apis/agents/openai_responses.py

@@ -219,3 +219,17 @@ register_schema(OpenAIResponseInputTool, name="OpenAIResponseInputTool")
 class OpenAIResponseInputItemList(BaseModel):
     data: list[OpenAIResponseInput]
     object: Literal["list"] = "list"
+
+
+@json_schema_type
+class OpenAIResponseObjectWithInput(OpenAIResponseObject):
+    input: list[OpenAIResponseInput]
+
+
+@json_schema_type
+class ListOpenAIResponseObject(BaseModel):
+    data: list[OpenAIResponseObjectWithInput]
+    has_more: bool
+    first_id: str
+    last_id: str
+    object: Literal["list"] = "list"

llama_stack/apis/common/responses.py

@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+from enum import Enum
 from typing import Any
 
 from pydantic import BaseModel
@@ -11,6 +12,11 @@ from pydantic import BaseModel
 from llama_stack.schema_utils import json_schema_type
 
 
+class Order(Enum):
+    asc = "asc"
+    desc = "desc"
+
+
 @json_schema_type
 class PaginatedResponse(BaseModel):
     """A generic paginated response that follows a simple format.

llama_stack/apis/inference/inference.py

@@ -19,6 +19,7 @@ from pydantic import BaseModel, Field, field_validator
 from typing_extensions import TypedDict
 
 from llama_stack.apis.common.content_types import ContentDelta, InterleavedContent, InterleavedContentItem
+from llama_stack.apis.common.responses import Order
 from llama_stack.apis.models import Model
 from llama_stack.apis.telemetry.telemetry import MetricResponseMixin
 from llama_stack.models.llama.datatypes import (
@@ -833,11 +834,6 @@ class ListOpenAIChatCompletionResponse(BaseModel):
     object: Literal["list"] = "list"
 
 
-class Order(Enum):
-    asc = "asc"
-    desc = "desc"
-
-
 @runtime_checkable
 @trace_protocol
 class InferenceProvider(Protocol):