diff --git a/docs/openapi_generator/pyopenapi/operations.py b/docs/openapi_generator/pyopenapi/operations.py
index ad8f2952e..f4238f6f8 100644
--- a/docs/openapi_generator/pyopenapi/operations.py
+++ b/docs/openapi_generator/pyopenapi/operations.py
@@ -315,7 +315,20 @@ def get_endpoint_operations(
                 )
         else:
             event_type = None
-            response_type = return_type
+
+            def process_type(t):
+                if typing.get_origin(t) is collections.abc.AsyncIterator:
+                    # NOTE(ashwin): this is SSE and there is no way to represent it. either we make it a List
+                    # or the item type. I am choosing it to be the latter
+                    args = typing.get_args(t)
+                    return args[0]
+                elif typing.get_origin(t) is typing.Union:
+                    types = [process_type(a) for a in typing.get_args(t)]
+                    return typing._UnionGenericAlias(typing.Union, tuple(types))
+                else:
+                    return t
+
+            response_type = process_type(return_type)
 
         # set HTTP request method based on type of request and presence of payload
         if not request_params:
diff --git a/docs/resources/llama-stack-spec.html b/docs/resources/llama-stack-spec.html
index e790dcff1..de52131b5 100644
--- a/docs/resources/llama-stack-spec.html
+++ b/docs/resources/llama-stack-spec.html
@@ -21,7 +21,7 @@
     "info": {
         "title": "[DRAFT] Llama Stack Specification",
         "version": "0.0.1",
-        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-10-30 16:17:03.919702"
+        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-10-31 10:35:38.305313"
     },
     "servers": [
         {
@@ -320,11 +320,11 @@
             "post": {
                 "responses": {
                     "200": {
-                        "description": "OK",
+                        "description": "A single turn in an interaction with an Agentic System.",
                         "content": {
                             "text/event-stream": {
                                 "schema": {
-                                    "$ref": "#/components/schemas/AgentTurnResponseStreamChunk"
+                                    "$ref": "#/components/schemas/Turn"
                                 }
                             }
                         }
@@ -3832,214 +3832,6 @@
                     "messages"
                 ]
             },
-            "AgentTurnResponseEvent": {
-                "type": "object",
-                "properties": {
-                    "payload": {
-                        "oneOf": [
-                            {
-                                "$ref": "#/components/schemas/AgentTurnResponseStepStartPayload"
-                            },
-                            {
-                                "$ref": "#/components/schemas/AgentTurnResponseStepProgressPayload"
-                            },
-                            {
-                                "$ref": "#/components/schemas/AgentTurnResponseStepCompletePayload"
-                            },
-                            {
-                                "$ref": "#/components/schemas/AgentTurnResponseTurnStartPayload"
-                            },
-                            {
-                                "$ref": "#/components/schemas/AgentTurnResponseTurnCompletePayload"
-                            }
-                        ]
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "payload"
-                ],
-                "title": "Streamed agent execution response."
-            },
-            "AgentTurnResponseStepCompletePayload": {
-                "type": "object",
-                "properties": {
-                    "event_type": {
-                        "type": "string",
-                        "const": "step_complete",
-                        "default": "step_complete"
-                    },
-                    "step_type": {
-                        "type": "string",
-                        "enum": [
-                            "inference",
-                            "tool_execution",
-                            "shield_call",
-                            "memory_retrieval"
-                        ]
-                    },
-                    "step_details": {
-                        "oneOf": [
-                            {
-                                "$ref": "#/components/schemas/InferenceStep"
-                            },
-                            {
-                                "$ref": "#/components/schemas/ToolExecutionStep"
-                            },
-                            {
-                                "$ref": "#/components/schemas/ShieldCallStep"
-                            },
-                            {
-                                "$ref": "#/components/schemas/MemoryRetrievalStep"
-                            }
-                        ]
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event_type",
-                    "step_type",
-                    "step_details"
-                ]
-            },
-            "AgentTurnResponseStepProgressPayload": {
-                "type": "object",
-                "properties": {
-                    "event_type": {
-                        "type": "string",
-                        "const": "step_progress",
-                        "default": "step_progress"
-                    },
-                    "step_type": {
-                        "type": "string",
-                        "enum": [
-                            "inference",
-                            "tool_execution",
-                            "shield_call",
-                            "memory_retrieval"
-                        ]
-                    },
-                    "step_id": {
-                        "type": "string"
-                    },
-                    "model_response_text_delta": {
-                        "type": "string"
-                    },
-                    "tool_call_delta": {
-                        "$ref": "#/components/schemas/ToolCallDelta"
-                    },
-                    "tool_response_text_delta": {
-                        "type": "string"
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event_type",
-                    "step_type",
-                    "step_id"
-                ]
-            },
-            "AgentTurnResponseStepStartPayload": {
-                "type": "object",
-                "properties": {
-                    "event_type": {
-                        "type": "string",
-                        "const": "step_start",
-                        "default": "step_start"
-                    },
-                    "step_type": {
-                        "type": "string",
-                        "enum": [
-                            "inference",
-                            "tool_execution",
-                            "shield_call",
-                            "memory_retrieval"
-                        ]
-                    },
-                    "step_id": {
-                        "type": "string"
-                    },
-                    "metadata": {
-                        "type": "object",
-                        "additionalProperties": {
-                            "oneOf": [
-                                {
-                                    "type": "null"
-                                },
-                                {
-                                    "type": "boolean"
-                                },
-                                {
-                                    "type": "number"
-                                },
-                                {
-                                    "type": "string"
-                                },
-                                {
-                                    "type": "array"
-                                },
-                                {
-                                    "type": "object"
-                                }
-                            ]
-                        }
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event_type",
-                    "step_type",
-                    "step_id"
-                ]
-            },
-            "AgentTurnResponseStreamChunk": {
-                "type": "object",
-                "properties": {
-                    "event": {
-                        "$ref": "#/components/schemas/AgentTurnResponseEvent"
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event"
-                ]
-            },
-            "AgentTurnResponseTurnCompletePayload": {
-                "type": "object",
-                "properties": {
-                    "event_type": {
-                        "type": "string",
-                        "const": "turn_complete",
-                        "default": "turn_complete"
-                    },
-                    "turn": {
-                        "$ref": "#/components/schemas/Turn"
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event_type",
-                    "turn"
-                ]
-            },
-            "AgentTurnResponseTurnStartPayload": {
-                "type": "object",
-                "properties": {
-                    "event_type": {
-                        "type": "string",
-                        "const": "turn_start",
-                        "default": "turn_start"
-                    },
-                    "turn_id": {
-                        "type": "string"
-                    }
-                },
-                "additionalProperties": false,
-                "required": [
-                    "event_type",
-                    "turn_id"
-                ]
-            },
             "InferenceStep": {
                 "type": "object",
                 "properties": {
@@ -7055,43 +6847,19 @@
     ],
     "tags": [
         {
-            "name": "Inference"
-        },
-        {
-            "name": "Memory"
-        },
-        {
-            "name": "Inspect"
-        },
-        {
-            "name": "PostTraining"
-        },
-        {
-            "name": "Models"
+            "name": "Safety"
         },
         {
             "name": "Scoring"
         },
-        {
-            "name": "DatasetIO"
-        },
         {
             "name": "BatchInference"
         },
         {
-            "name": "Agents"
+            "name": "DatasetIO"
         },
         {
-            "name": "Shields"
-        },
-        {
-            "name": "MemoryBanks"
-        },
-        {
-            "name": "Datasets"
-        },
-        {
-            "name": "SyntheticDataGeneration"
+            "name": "Models"
         },
         {
             "name": "Eval"
@@ -7099,11 +6867,35 @@
         {
             "name": "Telemetry"
         },
+        {
+            "name": "Shields"
+        },
+        {
+            "name": "Datasets"
+        },
+        {
+            "name": "Memory"
+        },
+        {
+            "name": "PostTraining"
+        },
         {
             "name": "ScoringFunctions"
         },
         {
-            "name": "Safety"
+            "name": "SyntheticDataGeneration"
+        },
+        {
+            "name": "Inspect"
+        },
+        {
+            "name": "MemoryBanks"
+        },
+        {
+            "name": "Inference"
+        },
+        {
+            "name": "Agents"
         },
         {
             "name": "BuiltinTool",
@@ -7289,34 +7081,6 @@
             "name": "CreateAgentTurnRequest",
             "description": "<SchemaDefinition schemaRef=\"#/components/schemas/CreateAgentTurnRequest\" />"
         },
-        {
-            "name": "AgentTurnResponseEvent",
-            "description": "Streamed agent execution response.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseEvent\" />"
-        },
-        {
-            "name": "AgentTurnResponseStepCompletePayload",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseStepCompletePayload\" />"
-        },
-        {
-            "name": "AgentTurnResponseStepProgressPayload",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseStepProgressPayload\" />"
-        },
-        {
-            "name": "AgentTurnResponseStepStartPayload",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseStepStartPayload\" />"
-        },
-        {
-            "name": "AgentTurnResponseStreamChunk",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseStreamChunk\" />"
-        },
-        {
-            "name": "AgentTurnResponseTurnCompletePayload",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseTurnCompletePayload\" />"
-        },
-        {
-            "name": "AgentTurnResponseTurnStartPayload",
-            "description": "<SchemaDefinition schemaRef=\"#/components/schemas/AgentTurnResponseTurnStartPayload\" />"
-        },
         {
             "name": "InferenceStep",
             "description": "<SchemaDefinition schemaRef=\"#/components/schemas/InferenceStep\" />"
@@ -7665,13 +7429,6 @@
                 "AgentCreateResponse",
                 "AgentSessionCreateResponse",
                 "AgentStepResponse",
-                "AgentTurnResponseEvent",
-                "AgentTurnResponseStepCompletePayload",
-                "AgentTurnResponseStepProgressPayload",
-                "AgentTurnResponseStepStartPayload",
-                "AgentTurnResponseStreamChunk",
-                "AgentTurnResponseTurnCompletePayload",
-                "AgentTurnResponseTurnStartPayload",
                 "Attachment",
                 "BatchChatCompletionRequest",
                 "BatchChatCompletionResponse",
diff --git a/docs/resources/llama-stack-spec.yaml b/docs/resources/llama-stack-spec.yaml
index 67181ab42..0cf378168 100644
--- a/docs/resources/llama-stack-spec.yaml
+++ b/docs/resources/llama-stack-spec.yaml
@@ -86,137 +86,6 @@ components:
       required:
       - step
       type: object
-    AgentTurnResponseEvent:
-      additionalProperties: false
-      properties:
-        payload:
-          oneOf:
-          - $ref: '#/components/schemas/AgentTurnResponseStepStartPayload'
-          - $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload'
-          - $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload'
-          - $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload'
-          - $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload'
-      required:
-      - payload
-      title: Streamed agent execution response.
-      type: object
-    AgentTurnResponseStepCompletePayload:
-      additionalProperties: false
-      properties:
-        event_type:
-          const: step_complete
-          default: step_complete
-          type: string
-        step_details:
-          oneOf:
-          - $ref: '#/components/schemas/InferenceStep'
-          - $ref: '#/components/schemas/ToolExecutionStep'
-          - $ref: '#/components/schemas/ShieldCallStep'
-          - $ref: '#/components/schemas/MemoryRetrievalStep'
-        step_type:
-          enum:
-          - inference
-          - tool_execution
-          - shield_call
-          - memory_retrieval
-          type: string
-      required:
-      - event_type
-      - step_type
-      - step_details
-      type: object
-    AgentTurnResponseStepProgressPayload:
-      additionalProperties: false
-      properties:
-        event_type:
-          const: step_progress
-          default: step_progress
-          type: string
-        model_response_text_delta:
-          type: string
-        step_id:
-          type: string
-        step_type:
-          enum:
-          - inference
-          - tool_execution
-          - shield_call
-          - memory_retrieval
-          type: string
-        tool_call_delta:
-          $ref: '#/components/schemas/ToolCallDelta'
-        tool_response_text_delta:
-          type: string
-      required:
-      - event_type
-      - step_type
-      - step_id
-      type: object
-    AgentTurnResponseStepStartPayload:
-      additionalProperties: false
-      properties:
-        event_type:
-          const: step_start
-          default: step_start
-          type: string
-        metadata:
-          additionalProperties:
-            oneOf:
-            - type: 'null'
-            - type: boolean
-            - type: number
-            - type: string
-            - type: array
-            - type: object
-          type: object
-        step_id:
-          type: string
-        step_type:
-          enum:
-          - inference
-          - tool_execution
-          - shield_call
-          - memory_retrieval
-          type: string
-      required:
-      - event_type
-      - step_type
-      - step_id
-      type: object
-    AgentTurnResponseStreamChunk:
-      additionalProperties: false
-      properties:
-        event:
-          $ref: '#/components/schemas/AgentTurnResponseEvent'
-      required:
-      - event
-      type: object
-    AgentTurnResponseTurnCompletePayload:
-      additionalProperties: false
-      properties:
-        event_type:
-          const: turn_complete
-          default: turn_complete
-          type: string
-        turn:
-          $ref: '#/components/schemas/Turn'
-      required:
-      - event_type
-      - turn
-      type: object
-    AgentTurnResponseTurnStartPayload:
-      additionalProperties: false
-      properties:
-        event_type:
-          const: turn_start
-          default: turn_start
-          type: string
-        turn_id:
-          type: string
-      required:
-      - event_type
-      - turn_id
-      type: object
     Attachment:
       additionalProperties: false
       properties:
@@ -2997,7 +2866,7 @@ info:
   description: "This is the specification of the llama stack that provides\n     \
     \           a set of endpoints and their corresponding interfaces that are tailored\
     \ to\n                best leverage Llama Models. The specification is still in\
-    \ draft and subject to change.\n                Generated at 2024-10-30 16:17:03.919702"
+    \ draft and subject to change.\n                Generated at 2024-10-31 10:35:38.305313"
   title: '[DRAFT] Llama Stack Specification'
   version: 0.0.1
 jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@@ -3190,8 +3059,8 @@ paths:
           content:
             text/event-stream:
               schema:
-                $ref: '#/components/schemas/AgentTurnResponseStreamChunk'
-          description: OK
+                $ref: '#/components/schemas/Turn'
+          description: A single turn in an interaction with an Agentic System.
       tags:
       - Agents
   /agents/turn/get:
@@ -4276,23 +4145,23 @@ security:
 servers:
 - url: http://any-hosted-llama-stack.com
 tags:
-- name: Inference
-- name: Memory
-- name: Inspect
-- name: PostTraining
-- name: Models
+- name: Safety
 - name: Scoring
-- name: DatasetIO
 - name: BatchInference
-- name: Agents
-- name: Shields
-- name: MemoryBanks
-- name: Datasets
-- name: SyntheticDataGeneration
+- name: DatasetIO
+- name: Models
 - name: Eval
 - name: Telemetry
+- name: Shields
+- name: Datasets
+- name: Memory
+- name: PostTraining
 - name: ScoringFunctions
-- name: Safety
+- name: SyntheticDataGeneration
+- name: Inspect
+- name: MemoryBanks
+- name: Inference
+- name: Agents
 - description: <SchemaDefinition schemaRef="#/components/schemas/BuiltinTool" />
   name: BuiltinTool
 - description: <SchemaDefinition schemaRef="#/components/schemas/CompletionMessage"
@@ -4437,29 +4306,6 @@ tags:
 - description: <SchemaDefinition schemaRef="#/components/schemas/CreateAgentTurnRequest"
     />
   name: CreateAgentTurnRequest
-- description: 'Streamed agent execution response.
-
-
-    <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseEvent" />'
-  name: AgentTurnResponseEvent
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseStepCompletePayload"
-    />
-  name: AgentTurnResponseStepCompletePayload
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseStepProgressPayload"
-    />
-  name: AgentTurnResponseStepProgressPayload
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseStepStartPayload"
-    />
-  name: AgentTurnResponseStepStartPayload
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseStreamChunk"
-    />
-  name: AgentTurnResponseStreamChunk
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseTurnCompletePayload"
-    />
-  name: AgentTurnResponseTurnCompletePayload
-- description: <SchemaDefinition schemaRef="#/components/schemas/AgentTurnResponseTurnStartPayload"
-    />
-  name: AgentTurnResponseTurnStartPayload
 - description: <SchemaDefinition schemaRef="#/components/schemas/InferenceStep" />
   name: InferenceStep
 - description: <SchemaDefinition schemaRef="#/components/schemas/MemoryRetrievalStep"
@@ -4720,13 +4566,6 @@ x-tagGroups:
   - AgentCreateResponse
   - AgentSessionCreateResponse
   - AgentStepResponse
-  - AgentTurnResponseEvent
-  - AgentTurnResponseStepCompletePayload
-  - AgentTurnResponseStepProgressPayload
-  - AgentTurnResponseStepStartPayload
-  - AgentTurnResponseStreamChunk
-  - AgentTurnResponseTurnCompletePayload
-  - AgentTurnResponseTurnStartPayload
   - Attachment
   - BatchChatCompletionRequest
   - BatchChatCompletionResponse
diff --git a/llama_stack/distribution/client.py b/llama_stack/distribution/client.py
index a8184f18a..cd8db9e8f 100644
--- a/llama_stack/distribution/client.py
+++ b/llama_stack/distribution/client.py
@@ -36,7 +36,13 @@ def extract_async_iterator_type(type_hint):
     return None
 
 
+_CLIENT_CLASSES = {}
+
+
 def create_api_client_class(protocol) -> Type:
+    if protocol in _CLIENT_CLASSES:
+        return _CLIENT_CLASSES[protocol]
+
     class APIClient:
         def __init__(self, base_url: str):
             self.base_url = base_url.rstrip("/")
@@ -124,7 +130,6 @@ def create_api_client_class(protocol) -> Type:
             else:
                 data.update(convert(kwargs))
 
-            print(f"{data=}")
             return dict(
                 method=webmethod.method or "POST",
                 url=url,
@@ -148,6 +153,7 @@ def create_api_client_class(protocol) -> Type:
 
     # Name the class after the protocol
     APIClient.__name__ = f"{protocol.__name__}Client"
+    _CLIENT_CLASSES[protocol] = APIClient
     return APIClient