release: 0.4.0-alpha.1

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.3.1-alpha.2"
+  ".": "0.4.0-alpha.1"
 }

.stats.yml

@@ -1,4 +1,4 @@
-configured_endpoints: 104
+configured_endpoints: 111
 openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-35c6569e5e9fcc85084c9728eb7fc7c5908297fcc77043d621d25de3c850a990.yml
 openapi_spec_hash: 0f95bbeee16f3205d36ec34cfa62c711
-config_hash: a3829dbdaa491194d01f399784d532cd
+config_hash: ef275cc002a89629459fd73d0cf9cba9

CHANGELOG.md

@@ -1,5 +1,32 @@
 # Changelog
 
+## 0.4.0-alpha.1 (2025-10-30)
+
+Full Changelog: [v0.3.1-alpha.2...v0.4.0-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.3.1-alpha.2...v0.4.0-alpha.1)
+
+### ⚠ BREAKING CHANGES
+
+* **api:** /v1/inspect only lists v1 apis by default
+* **api:** /v1/inspect only lists v1 apis by default
+
+### Features
+
+* **api:** Adding prompts API to stainless config ([114198b](https://github.com/llamastack/llama-stack-client-python/commit/114198bef4244ec27f7e163beb2e554da0dbd213))
+* **api:** manual updates??! ([d8ab6cb](https://github.com/llamastack/llama-stack-client-python/commit/d8ab6cb77267af53f3f2e9ff3ebaab9364a754c7))
+
+
+### Bug Fixes
+
+* clean pre-commit ([799b908](https://github.com/llamastack/llama-stack-client-python/commit/799b9084266c390604829dd1eef483bf3b941134))
+* **client:** close streams without requiring full consumption ([d861708](https://github.com/llamastack/llama-stack-client-python/commit/d8617084062acbb81c26b6c22ea613e397aa969b))
+* **headers:** add a newline ([55a8efc](https://github.com/llamastack/llama-stack-client-python/commit/55a8efc0a60f44c8c93e18b2b60215f051405be4))
+
+
+### Chores
+
+* **api:** /v1/inspect only lists v1 apis by default ([209de45](https://github.com/llamastack/llama-stack-client-python/commit/209de45599de19183a1cd14bc3567e34d2374184))
+* **api:** /v1/inspect only lists v1 apis by default ([b36e2ab](https://github.com/llamastack/llama-stack-client-python/commit/b36e2ab8661e4913838c2cb4501156b290876da0))
+
 ## 0.3.1-alpha.2 (2025-10-27)
 
 Full Changelog: [v0.3.1-alpha.1...v0.3.1-alpha.2](https://github.com/llamastack/llama-stack-client-python/compare/v0.3.1-alpha.1...v0.3.1-alpha.2)

api.md

@@ -102,6 +102,29 @@ Methods:
 
 - <code title="get /v1/responses/{response_id}/input_items">client.responses.input_items.<a href="./src/llama_stack_client/resources/responses/input_items.py">list</a>(response_id, \*\*<a href="src/llama_stack_client/types/responses/input_item_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/responses/input_item_list_response.py">InputItemListResponse</a></code>
 
+# Prompts
+
+Types:
+
+```python
+from llama_stack_client.types import ListPromptsResponse, Prompt, PromptListResponse
+```
+
+Methods:
+
+- <code title="post /v1/prompts">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">create</a>(\*\*<a href="src/llama_stack_client/types/prompt_create_params.py">params</a>) -> <a href="./src/llama_stack_client/types/prompt.py">Prompt</a></code>
+- <code title="get /v1/prompts/{prompt_id}">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">retrieve</a>(prompt_id, \*\*<a href="src/llama_stack_client/types/prompt_retrieve_params.py">params</a>) -> <a href="./src/llama_stack_client/types/prompt.py">Prompt</a></code>
+- <code title="post /v1/prompts/{prompt_id}">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">update</a>(prompt_id, \*\*<a href="src/llama_stack_client/types/prompt_update_params.py">params</a>) -> <a href="./src/llama_stack_client/types/prompt.py">Prompt</a></code>
+- <code title="get /v1/prompts">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">list</a>() -> <a href="./src/llama_stack_client/types/prompt_list_response.py">PromptListResponse</a></code>
+- <code title="delete /v1/prompts/{prompt_id}">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">delete</a>(prompt_id) -> None</code>
+- <code title="post /v1/prompts/{prompt_id}/set-default-version">client.prompts.<a href="./src/llama_stack_client/resources/prompts/prompts.py">set_default_version</a>(prompt_id, \*\*<a href="src/llama_stack_client/types/prompt_set_default_version_params.py">params</a>) -> <a href="./src/llama_stack_client/types/prompt.py">Prompt</a></code>
+
+## Versions
+
+Methods:
+
+- <code title="get /v1/prompts/{prompt_id}/versions">client.prompts.versions.<a href="./src/llama_stack_client/resources/prompts/versions.py">list</a>(prompt_id) -> <a href="./src/llama_stack_client/types/prompt_list_response.py">PromptListResponse</a></code>
+
 # Conversations
 
 Types:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.3.1-alpha.2"
+version = "0.4.0-alpha.1"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "MIT"

src/llama_stack_client/_client.py

@@ -48,6 +48,7 @@
         routes,
         safety,
         inspect,
+        prompts,
         scoring,
         shields,
         providers,
@@ -80,6 +81,7 @@
     from .resources.completions import CompletionsResource, AsyncCompletionsResource
     from .resources.moderations import ModerationsResource, AsyncModerationsResource
     from .resources.models.models import ModelsResource, AsyncModelsResource
+    from .resources.prompts.prompts import PromptsResource, AsyncPromptsResource
     from .resources.scoring_functions import ScoringFunctionsResource, AsyncScoringFunctionsResource
     from .resources.responses.responses import ResponsesResource, AsyncResponsesResource
     from .resources.synthetic_data_generation import (
@@ -183,6 +185,12 @@ def responses(self) -> ResponsesResource:
 
         return ResponsesResource(self)
 
+    @cached_property
+    def prompts(self) -> PromptsResource:
+        from .resources.prompts import PromptsResource
+
+        return PromptsResource(self)
+
     @cached_property
     def conversations(self) -> ConversationsResource:
         from .resources.conversations import ConversationsResource
@@ -493,6 +501,12 @@ def responses(self) -> AsyncResponsesResource:
 
         return AsyncResponsesResource(self)
 
+    @cached_property
+    def prompts(self) -> AsyncPromptsResource:
+        from .resources.prompts import AsyncPromptsResource
+
+        return AsyncPromptsResource(self)
+
     @cached_property
     def conversations(self) -> AsyncConversationsResource:
         from .resources.conversations import AsyncConversationsResource
@@ -752,6 +766,12 @@ def responses(self) -> responses.ResponsesResourceWithRawResponse:
 
         return ResponsesResourceWithRawResponse(self._client.responses)
 
+    @cached_property
+    def prompts(self) -> prompts.PromptsResourceWithRawResponse:
+        from .resources.prompts import PromptsResourceWithRawResponse
+
+        return PromptsResourceWithRawResponse(self._client.prompts)
+
     @cached_property
     def conversations(self) -> conversations.ConversationsResourceWithRawResponse:
         from .resources.conversations import ConversationsResourceWithRawResponse
@@ -897,6 +917,12 @@ def responses(self) -> responses.AsyncResponsesResourceWithRawResponse:
 
         return AsyncResponsesResourceWithRawResponse(self._client.responses)
 
+    @cached_property
+    def prompts(self) -> prompts.AsyncPromptsResourceWithRawResponse:
+        from .resources.prompts import AsyncPromptsResourceWithRawResponse
+
+        return AsyncPromptsResourceWithRawResponse(self._client.prompts)
+
     @cached_property
     def conversations(self) -> conversations.AsyncConversationsResourceWithRawResponse:
         from .resources.conversations import AsyncConversationsResourceWithRawResponse
@@ -1044,6 +1070,12 @@ def responses(self) -> responses.ResponsesResourceWithStreamingResponse:
 
         return ResponsesResourceWithStreamingResponse(self._client.responses)
 
+    @cached_property
+    def prompts(self) -> prompts.PromptsResourceWithStreamingResponse:
+        from .resources.prompts import PromptsResourceWithStreamingResponse
+
+        return PromptsResourceWithStreamingResponse(self._client.prompts)
+
     @cached_property
     def conversations(self) -> conversations.ConversationsResourceWithStreamingResponse:
         from .resources.conversations import ConversationsResourceWithStreamingResponse
@@ -1191,6 +1223,12 @@ def responses(self) -> responses.AsyncResponsesResourceWithStreamingResponse:
 
         return AsyncResponsesResourceWithStreamingResponse(self._client.responses)
 
+    @cached_property
+    def prompts(self) -> prompts.AsyncPromptsResourceWithStreamingResponse:
+        from .resources.prompts import AsyncPromptsResourceWithStreamingResponse
+
+        return AsyncPromptsResourceWithStreamingResponse(self._client.prompts)
+
     @cached_property
     def conversations(self) -> conversations.AsyncConversationsResourceWithStreamingResponse:
         from .resources.conversations import AsyncConversationsResourceWithStreamingResponse

src/llama_stack_client/_streaming.py

@@ -63,9 +63,8 @@ def __stream__(self) -> Iterator[_T]:
         for sse in iterator:
             yield process_data(data=sse.json(), cast_to=cast_to, response=response)
 
-        # Ensure the entire stream is consumed
-        for _sse in iterator:
-            ...
+        # As we might not fully consume the response stream, we need to close it explicitly
+        response.close()
 
     def __enter__(self) -> Self:
         return self
@@ -127,9 +126,8 @@ async def __stream__(self) -> AsyncIterator[_T]:
         async for sse in iterator:
             yield process_data(data=sse.json(), cast_to=cast_to, response=response)
 
-        # Ensure the entire stream is consumed
-        async for _sse in iterator:
-            ...
+        # As we might not fully consume the response stream, we need to close it explicitly
+        await response.aclose()
 
     async def __aenter__(self) -> Self:
         return self

src/llama_stack_client/resources/__init__.py

@@ -78,6 +78,14 @@
     InspectResourceWithStreamingResponse,
     AsyncInspectResourceWithStreamingResponse,
 )
+from .prompts import (
+    PromptsResource,
+    AsyncPromptsResource,
+    PromptsResourceWithRawResponse,
+    AsyncPromptsResourceWithRawResponse,
+    PromptsResourceWithStreamingResponse,
+    AsyncPromptsResourceWithStreamingResponse,
+)
 from .scoring import (
     ScoringResource,
     AsyncScoringResource,
@@ -216,6 +224,12 @@
     "AsyncResponsesResourceWithRawResponse",
     "ResponsesResourceWithStreamingResponse",
     "AsyncResponsesResourceWithStreamingResponse",
+    "PromptsResource",
+    "AsyncPromptsResource",
+    "PromptsResourceWithRawResponse",
+    "AsyncPromptsResourceWithRawResponse",
+    "PromptsResourceWithStreamingResponse",
+    "AsyncPromptsResourceWithStreamingResponse",
     "ConversationsResource",
     "AsyncConversationsResource",
     "ConversationsResourceWithRawResponse",

src/llama_stack_client/resources/prompts/__init__.py

@@ -0,0 +1,33 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from .prompts import (
+    PromptsResource,
+    AsyncPromptsResource,
+    PromptsResourceWithRawResponse,
+    AsyncPromptsResourceWithRawResponse,
+    PromptsResourceWithStreamingResponse,
+    AsyncPromptsResourceWithStreamingResponse,
+)
+from .versions import (
+    VersionsResource,
+    AsyncVersionsResource,
+    VersionsResourceWithRawResponse,
+    AsyncVersionsResourceWithRawResponse,
+    VersionsResourceWithStreamingResponse,
+    AsyncVersionsResourceWithStreamingResponse,
+)
+
+__all__ = [
+    "VersionsResource",
+    "AsyncVersionsResource",
+    "VersionsResourceWithRawResponse",
+    "AsyncVersionsResourceWithRawResponse",
+    "VersionsResourceWithStreamingResponse",
+    "AsyncVersionsResourceWithStreamingResponse",
+    "PromptsResource",
+    "AsyncPromptsResource",
+    "PromptsResourceWithRawResponse",
+    "AsyncPromptsResourceWithRawResponse",
+    "PromptsResourceWithStreamingResponse",
+    "AsyncPromptsResourceWithStreamingResponse",
+]