release: 0.2.18-alpha.1

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.2.17"
+  ".": "0.2.18-alpha.1"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 106
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-f59f1c7d33001d60b5190f68aa49eacec90f05dbe694620b8916152c3922051d.yml
-openapi_spec_hash: 804edd2e834493906dc430145402be3b
-config_hash: de16e52db65de71ac35adcdb665a74f5
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-c371abef4463f174f8d35ef3da4697fae5eb221db615f9c305319196472f313b.yml
+openapi_spec_hash: d9bb62faf229c2c2875c732715e9cfd1
+config_hash: e67fd054e95c1e82f78f4b834e96bb65

CHANGELOG.md

@@ -1,5 +1,23 @@
 # Changelog
 
+## 0.2.18-alpha.1 (2025-08-12)
+
+Full Changelog: [v0.2.17...v0.2.18-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.2.17...v0.2.18-alpha.1)
+
+### Features
+
+* **api:** update via SDK Studio ([8afae6c](https://github.com/llamastack/llama-stack-client-python/commit/8afae6c1e1a4614cc59db7ae511440693e0479a6))
+* **api:** update via SDK Studio ([143a973](https://github.com/llamastack/llama-stack-client-python/commit/143a973ea9ff81da1d93c421af8c85dbd171ef3c))
+* **api:** update via SDK Studio ([b8e32bb](https://github.com/llamastack/llama-stack-client-python/commit/b8e32bbbf68f8a75c956079119c6b65d7ac165e5))
+* **api:** update via SDK Studio ([1a2c77d](https://github.com/llamastack/llama-stack-client-python/commit/1a2c77df732eb9d0c031e0ff7558176fbf754ad8))
+* **api:** update via SDK Studio ([d66fb5f](https://github.com/llamastack/llama-stack-client-python/commit/d66fb5fe89acb66a55066d82b849bbf4d402db99))
+
+
+### Chores
+
+* **internal:** update comment in script ([8d599cd](https://github.com/llamastack/llama-stack-client-python/commit/8d599cd47f98f704f89c9bd979a55cc334895107))
+* update @stainless-api/prism-cli to v5.15.0 ([5f8ae94](https://github.com/llamastack/llama-stack-client-python/commit/5f8ae94955bb3403c0abe89f2999c2d49af97b07))
+
 ## 0.2.17 (2025-08-06)
 
 Full Changelog: [v0.2.15...v0.2.17](https://github.com/llamastack/llama-stack-client-python/compare/v0.2.15...v0.2.17)

api.md

@@ -89,7 +89,7 @@ Methods:
 
 - <code title="post /v1/openai/v1/responses">client.responses.<a href="./src/llama_stack_client/resources/responses/responses.py">create</a>(\*\*<a href="src/llama_stack_client/types/response_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/response_object.py">ResponseObject</a></code>
 - <code title="get /v1/openai/v1/responses/{response_id}">client.responses.<a href="./src/llama_stack_client/resources/responses/responses.py">retrieve</a>(response_id) -> <a href="./src/llama_stack_client/types/response_object.py">ResponseObject</a></code>
-- <code title="get /v1/openai/v1/responses">client.responses.<a href="./src/llama_stack_client/resources/responses/responses.py">list</a>(\*\*<a href="src/llama_stack_client/types/response_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/response_list_response.py">ResponseListResponse</a></code>
+- <code title="get /v1/openai/v1/responses">client.responses.<a href="./src/llama_stack_client/resources/responses/responses.py">list</a>(\*\*<a href="src/llama_stack_client/types/response_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/response_list_response.py">SyncOpenAICursorPage[ResponseListResponse]</a></code>
 
 ## InputItems
 
@@ -290,7 +290,7 @@ Methods:
 
 - <code title="post /v1/openai/v1/chat/completions">client.chat.completions.<a href="./src/llama_stack_client/resources/chat/completions.py">create</a>(\*\*<a href="src/llama_stack_client/types/chat/completion_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/chat/completion_create_response.py">CompletionCreateResponse</a></code>
 - <code title="get /v1/openai/v1/chat/completions/{completion_id}">client.chat.completions.<a href="./src/llama_stack_client/resources/chat/completions.py">retrieve</a>(completion_id) -> <a href="./src/llama_stack_client/types/chat/completion_retrieve_response.py">CompletionRetrieveResponse</a></code>
-- <code title="get /v1/openai/v1/chat/completions">client.chat.completions.<a href="./src/llama_stack_client/resources/chat/completions.py">list</a>(\*\*<a href="src/llama_stack_client/types/chat/completion_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/chat/completion_list_response.py">CompletionListResponse</a></code>
+- <code title="get /v1/openai/v1/chat/completions">client.chat.completions.<a href="./src/llama_stack_client/resources/chat/completions.py">list</a>(\*\*<a href="src/llama_stack_client/types/chat/completion_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/chat/completion_list_response.py">SyncOpenAICursorPage[CompletionListResponse]</a></code>
 
 # Completions
 
@@ -355,7 +355,7 @@ Methods:
 - <code title="post /v1/openai/v1/vector_stores">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">create</a>(\*\*<a href="src/llama_stack_client/types/vector_store_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_store.py">VectorStore</a></code>
 - <code title="get /v1/openai/v1/vector_stores/{vector_store_id}">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">retrieve</a>(vector_store_id) -> <a href="./src/llama_stack_client/types/vector_store.py">VectorStore</a></code>
 - <code title="post /v1/openai/v1/vector_stores/{vector_store_id}">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">update</a>(vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_store_update_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_store.py">VectorStore</a></code>
-- <code title="get /v1/openai/v1/vector_stores">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">list</a>(\*\*<a href="src/llama_stack_client/types/vector_store_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/list_vector_stores_response.py">ListVectorStoresResponse</a></code>
+- <code title="get /v1/openai/v1/vector_stores">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">list</a>(\*\*<a href="src/llama_stack_client/types/vector_store_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_store.py">SyncOpenAICursorPage[VectorStore]</a></code>
 - <code title="delete /v1/openai/v1/vector_stores/{vector_store_id}">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">delete</a>(vector_store_id) -> <a href="./src/llama_stack_client/types/vector_store_delete_response.py">VectorStoreDeleteResponse</a></code>
 - <code title="post /v1/openai/v1/vector_stores/{vector_store_id}/search">client.vector_stores.<a href="./src/llama_stack_client/resources/vector_stores/vector_stores.py">search</a>(vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_store_search_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_store_search_response.py">VectorStoreSearchResponse</a></code>
 
@@ -366,7 +366,6 @@ Types:
 ```python
 from llama_stack_client.types.vector_stores import (
     VectorStoreFile,
-    FileListResponse,
     FileDeleteResponse,
     FileContentResponse,
 )
@@ -377,7 +376,7 @@ Methods:
 - <code title="post /v1/openai/v1/vector_stores/{vector_store_id}/files">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">create</a>(vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_stores/file_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_stores/vector_store_file.py">VectorStoreFile</a></code>
 - <code title="get /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">retrieve</a>(file_id, \*, vector_store_id) -> <a href="./src/llama_stack_client/types/vector_stores/vector_store_file.py">VectorStoreFile</a></code>
 - <code title="post /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">update</a>(file_id, \*, vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_stores/file_update_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_stores/vector_store_file.py">VectorStoreFile</a></code>
-- <code title="get /v1/openai/v1/vector_stores/{vector_store_id}/files">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">list</a>(vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_stores/file_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_stores/file_list_response.py">FileListResponse</a></code>
+- <code title="get /v1/openai/v1/vector_stores/{vector_store_id}/files">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">list</a>(vector_store_id, \*\*<a href="src/llama_stack_client/types/vector_stores/file_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/vector_stores/vector_store_file.py">SyncOpenAICursorPage[VectorStoreFile]</a></code>
 - <code title="delete /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">delete</a>(file_id, \*, vector_store_id) -> <a href="./src/llama_stack_client/types/vector_stores/file_delete_response.py">FileDeleteResponse</a></code>
 - <code title="get /v1/openai/v1/vector_stores/{vector_store_id}/files/{file_id}/content">client.vector_stores.files.<a href="./src/llama_stack_client/resources/vector_stores/files.py">content</a>(file_id, \*, vector_store_id) -> <a href="./src/llama_stack_client/types/vector_stores/file_content_response.py">FileContentResponse</a></code>
 
@@ -589,6 +588,6 @@ Methods:
 
 - <code title="post /v1/openai/v1/files">client.files.<a href="./src/llama_stack_client/resources/files.py">create</a>(\*\*<a href="src/llama_stack_client/types/file_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/file.py">File</a></code>
 - <code title="get /v1/openai/v1/files/{file_id}">client.files.<a href="./src/llama_stack_client/resources/files.py">retrieve</a>(file_id) -> <a href="./src/llama_stack_client/types/file.py">File</a></code>
-- <code title="get /v1/openai/v1/files">client.files.<a href="./src/llama_stack_client/resources/files.py">list</a>(\*\*<a href="src/llama_stack_client/types/file_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/list_files_response.py">ListFilesResponse</a></code>
+- <code title="get /v1/openai/v1/files">client.files.<a href="./src/llama_stack_client/resources/files.py">list</a>(\*\*<a href="src/llama_stack_client/types/file_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/file.py">SyncOpenAICursorPage[File]</a></code>
 - <code title="delete /v1/openai/v1/files/{file_id}">client.files.<a href="./src/llama_stack_client/resources/files.py">delete</a>(file_id) -> <a href="./src/llama_stack_client/types/delete_file_response.py">DeleteFileResponse</a></code>
 - <code title="get /v1/openai/v1/files/{file_id}/content">client.files.<a href="./src/llama_stack_client/resources/files.py">content</a>(file_id) -> object</code>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.2.17"
+version = "0.2.18-alpha.1"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "MIT"

scripts/mock

@@ -21,7 +21,7 @@ echo "==> Starting mock server with URL ${URL}"
 
 # Run prism mock on the given spec
 if [ "$1" == "--daemon" ]; then
-  npm exec --package=@stainless-api/prism-cli@5.8.5 -- prism mock "$URL" &> .prism.log &
+  npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$URL" &> .prism.log &
 
   # Wait for server to come online
   echo -n "Waiting for server"
@@ -37,5 +37,5 @@ if [ "$1" == "--daemon" ]; then
 
   echo
 else
-  npm exec --package=@stainless-api/prism-cli@5.8.5 -- prism mock "$URL"
+  npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock "$URL"
 fi

scripts/test

@@ -0,0 +1,61 @@
+#!/usr/bin/env bash
+
+set -e
+
+cd "$(dirname "$0")/.."
+
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[0;33m'
+NC='\033[0m' # No Color
+
+function prism_is_running() {
+  curl --silent "http://localhost:4010" >/dev/null 2>&1
+}
+
+kill_server_on_port() {
+  pids=$(lsof -t -i tcp:"$1" || echo "")
+  if [ "$pids" != "" ]; then
+    kill "$pids"
+    echo "Stopped $pids."
+  fi
+}
+
+function is_overriding_api_base_url() {
+  [ -n "$TEST_API_BASE_URL" ]
+}
+
+if ! is_overriding_api_base_url && ! prism_is_running ; then
+  # When we exit this script, make sure to kill the background mock server process
+  trap 'kill_server_on_port 4010' EXIT
+
+  # Start the dev server
+  ./scripts/mock --daemon
+fi
+
+if is_overriding_api_base_url ; then
+  echo -e "${GREEN}✔ Running tests against ${TEST_API_BASE_URL}${NC}"
+  echo
+elif ! prism_is_running ; then
+  echo -e "${RED}ERROR:${NC} The test suite will not run without a mock Prism server"
+  echo -e "running against your OpenAPI spec."
+  echo
+  echo -e "To run the server, pass in the path or url of your OpenAPI"
+  echo -e "spec to the prism command:"
+  echo
+  echo -e "  \$ ${YELLOW}npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock path/to/your.openapi.yml${NC}"
+  echo
+
+  exit 1
+else
+  echo -e "${GREEN}✔ Mock prism server is running with your OpenAPI spec${NC}"
+  echo
+fi
+
+export DEFER_PYDANTIC_BUILD=false
+
+echo "==> Running tests"
+rye run pytest "$@"
+
+echo "==> Running Pydantic v1 tests"
+rye run nox -s test-pydantic-v1 -- "$@"

src/llama_stack_client/pagination.py

@@ -5,7 +5,7 @@
 
 from ._base_client import BasePage, PageInfo, BaseSyncPage, BaseAsyncPage
 
-__all__ = ["SyncDatasetsIterrows", "AsyncDatasetsIterrows"]
+__all__ = ["SyncDatasetsIterrows", "AsyncDatasetsIterrows", "SyncOpenAICursorPage", "AsyncOpenAICursorPage"]
 
 _T = TypeVar("_T")
 
@@ -48,3 +48,61 @@ def next_page_info(self) -> Optional[PageInfo]:
             return None
 
         return PageInfo(params={"start_index": next_index})
+
+
+class SyncOpenAICursorPage(BaseSyncPage[_T], BasePage[_T], Generic[_T]):
+    data: List[_T]
+    has_more: Optional[bool] = None
+    last_id: Optional[str] = None
+
+    @override
+    def _get_page_items(self) -> List[_T]:
+        data = self.data
+        if not data:
+            return []
+        return data
+
+    @override
+    def has_next_page(self) -> bool:
+        has_more = self.has_more
+        if has_more is not None and has_more is False:
+            return False
+
+        return super().has_next_page()
+
+    @override
+    def next_page_info(self) -> Optional[PageInfo]:
+        last_id = self.last_id
+        if not last_id:
+            return None
+
+        return PageInfo(params={"after": last_id})
+
+
+class AsyncOpenAICursorPage(BaseAsyncPage[_T], BasePage[_T], Generic[_T]):
+    data: List[_T]
+    has_more: Optional[bool] = None
+    last_id: Optional[str] = None
+
+    @override
+    def _get_page_items(self) -> List[_T]:
+        data = self.data
+        if not data:
+            return []
+        return data
+
+    @override
+    def has_next_page(self) -> bool:
+        has_more = self.has_more
+        if has_more is not None and has_more is False:
+            return False
+
+        return super().has_next_page()
+
+    @override
+    def next_page_info(self) -> Optional[PageInfo]:
+        last_id = self.last_id
+        if not last_id:
+            return None
+
+        return PageInfo(params={"after": last_id})

src/llama_stack_client/resources/chat/completions.py

@@ -18,8 +18,9 @@
     async_to_streamed_response_wrapper,
 )
 from ..._streaming import Stream, AsyncStream
+from ...pagination import SyncOpenAICursorPage, AsyncOpenAICursorPage
 from ...types.chat import completion_list_params, completion_create_params
-from ..._base_client import make_request_options
+from ..._base_client import AsyncPaginator, make_request_options
 from ...types.chat_completion_chunk import ChatCompletionChunk
 from ...types.chat.completion_list_response import CompletionListResponse
 from ...types.chat.completion_create_response import CompletionCreateResponse
@@ -466,7 +467,7 @@ def list(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> CompletionListResponse:
+    ) -> SyncOpenAICursorPage[CompletionListResponse]:
         """
         List all chat completions.
 
@@ -487,8 +488,9 @@ def list(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        return self._get(
+        return self._get_api_list(
             "/v1/openai/v1/chat/completions",
+            page=SyncOpenAICursorPage[CompletionListResponse],
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
@@ -504,7 +506,7 @@ def list(
                     completion_list_params.CompletionListParams,
                 ),
             ),
-            cast_to=CompletionListResponse,
+            model=CompletionListResponse,
         )
 
 
@@ -933,7 +935,7 @@ async def retrieve(
             cast_to=CompletionRetrieveResponse,
         )
 
-    async def list(
+    def list(
         self,
         *,
         after: str | NotGiven = NOT_GIVEN,
@@ -946,7 +948,7 @@ async def list(
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
-    ) -> CompletionListResponse:
+    ) -> AsyncPaginator[CompletionListResponse, AsyncOpenAICursorPage[CompletionListResponse]]:
         """
         List all chat completions.
 
@@ -967,14 +969,15 @@ async def list(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
-        return await self._get(
+        return self._get_api_list(
             "/v1/openai/v1/chat/completions",
+            page=AsyncOpenAICursorPage[CompletionListResponse],
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
                 extra_body=extra_body,
                 timeout=timeout,
-                query=await async_maybe_transform(
+                query=maybe_transform(
                     {
                         "after": after,
                         "limit": limit,
@@ -984,7 +987,7 @@ async def list(
                     completion_list_params.CompletionListParams,
                 ),
             ),
-            cast_to=CompletionListResponse,
+            model=CompletionListResponse,
         )