list responses

# What does this PR do?


## Test Plan

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):