feat: add support for /responses background parameter

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 108
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-bffd917aa2197580fd7c0a210643e586c4a9658086c7f6559657ea35bd07f855.yml
-openapi_spec_hash: cd0e3133ee5fe5b0d6f4fa071cd44cc8
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-373eb8eb3cc02e6f8a9fa33079a5e735886fbf62958ee83e3cdef7bb4c41be37.yml
+openapi_spec_hash: fe1fa50161da4f095d128b0de7787e96
 config_hash: 6aa61d4143c3e3df785972c0287d1370

src/llama_stack_client/resources/responses/responses.py

@@ -78,6 +78,7 @@ def create(
             ],
         ],
         model: str,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -128,6 +129,9 @@ def create(
 
           model: The underlying LLM used for completions.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -197,6 +201,7 @@ def create(
         ],
         model: str,
         stream: Literal[True],
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -248,6 +253,9 @@ def create(
 
           stream: Whether to stream the response.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -315,6 +323,7 @@ def create(
         ],
         model: str,
         stream: bool,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -366,6 +375,9 @@ def create(
 
           stream: Whether to stream the response.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -432,6 +444,7 @@ def create(
             ],
         ],
         model: str,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -480,6 +493,7 @@ def create(
                 {
                     "input": input,
                     "model": model,
+                    "background": background,
                     "conversation": conversation,
                     "guardrails": guardrails,
                     "include": include,
@@ -676,6 +690,7 @@ async def create(
             ],
         ],
         model: str,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -726,6 +741,9 @@ async def create(
 
           model: The underlying LLM used for completions.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -795,6 +813,7 @@ async def create(
         ],
         model: str,
         stream: Literal[True],
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -846,6 +865,9 @@ async def create(
 
           stream: Whether to stream the response.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -913,6 +935,7 @@ async def create(
         ],
         model: str,
         stream: bool,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -964,6 +987,9 @@ async def create(
 
           stream: Whether to stream the response.
 
+          background: Whether to run the model response in the background. When true, returns
+              immediately with status 'queued'.
+
           conversation: Optional ID of a conversation to add the response to.
 
           guardrails: List of guardrails to apply during response generation.
@@ -1030,6 +1056,7 @@ async def create(
             ],
         ],
         model: str,
+        background: bool | Omit = omit,
         conversation: Optional[str] | Omit = omit,
         guardrails: Optional[SequenceNotStr[response_create_params.Guardrail]] | Omit = omit,
         include: Optional[
@@ -1078,6 +1105,7 @@ async def create(
                 {
                     "input": input,
                     "model": model,
+                    "background": background,
                     "conversation": conversation,
                     "guardrails": guardrails,
                     "include": include,

src/llama_stack_client/types/response_create_params.py

@@ -87,6 +87,12 @@ class ResponseCreateParamsBase(TypedDict, total=False):
     model: Required[str]
     """The underlying LLM used for completions."""
 
+    background: bool
+    """Whether to run the model response in the background.
+
+    When true, returns immediately with status 'queued'.
+    """
+
     conversation: Optional[str]
     """Optional ID of a conversation to add the response to."""
 

src/llama_stack_client/types/response_list_response.py

@@ -1151,6 +1151,8 @@ class ResponseListResponse(BaseModel):
 
     store: bool
 
+    background: Optional[bool] = None
+
     completed_at: Optional[int] = None
 
     error: Optional[Error] = None

src/llama_stack_client/types/response_object.py

@@ -755,6 +755,8 @@ def output_text(self) -> str:
 
     store: bool
 
+    background: Optional[bool] = None
+
     completed_at: Optional[int] = None
 
     error: Optional[Error] = None

tests/api_resources/test_responses.py

@@ -41,6 +41,7 @@ def test_method_create_with_all_params_overload_1(self, client: LlamaStackClient
         response = client.responses.create(
             input="string",
             model="model",
+            background=True,
             conversation="conversation",
             guardrails=["string"],
             include=["web_search_call.action.sources"],
@@ -129,6 +130,7 @@ def test_method_create_with_all_params_overload_2(self, client: LlamaStackClient
             input="string",
             model="model",
             stream=True,
+            background=True,
             conversation="conversation",
             guardrails=["string"],
             include=["web_search_call.action.sources"],
@@ -332,6 +334,7 @@ async def test_method_create_with_all_params_overload_1(self, async_client: Asyn
         response = await async_client.responses.create(
             input="string",
             model="model",
+            background=True,
             conversation="conversation",
             guardrails=["string"],
             include=["web_search_call.action.sources"],
@@ -420,6 +423,7 @@ async def test_method_create_with_all_params_overload_2(self, async_client: Asyn
             input="string",
             model="model",
             stream=True,
+            background=True,
             conversation="conversation",
             guardrails=["string"],
             include=["web_search_call.action.sources"],