release: 0.4.0-alpha.10 (#303)

Automated Release PR
---


## 0.4.0-alpha.10 (2025-11-17)

Full Changelog:
[v0.4.0-alpha.9...v0.4.0-alpha.10](v0.4.0-alpha.9...v0.4.0-alpha.10)

### Bug Fixes

* **openapi:** restore embedded request wrappers
([261e364](261e364))

---
This pull request is managed by Stainless's [GitHub
App](https://github.com/apps/stainless-app).

The [semver version
number](https://semver.org/#semantic-versioning-specification-semver) is
based on included [commit
messages](https://www.conventionalcommits.org/en/v1.0.0/).
Alternatively, you can manually set the version number in the title of
this pull request.

For a better experience, it is recommended to use either rebase-merge or
squash-merge when merging this pull request.

🔗 Stainless [website](https://www.stainlessapi.com)
📚 Read the [docs](https://app.stainlessapi.com/docs)
🙋 [Reach out](mailto:[email protected]) for help or questions

---------

Co-authored-by: stainless-app[bot] <142633134+stainless-app[bot]@users.noreply.github.com>

Author: stainless-app[bot]

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.4.0-alpha.9"
+  ".": "0.4.0-alpha.10"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 103
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-2b99a80543f8bc8fa164167693c214651ac8e710f4726fb5869183b4d6c71a03.yml
-openapi_spec_hash: a5632057f5e4d956a71c20a79c0d879c
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-aab1b331382f758fc255f765e73b62fedf463cf0748bc11b2b08974de9ac816a.yml
+openapi_spec_hash: f717a21f47419aa51e4d9298aa68cc45
 config_hash: 0017f6c419cbbf7b949f9b2842917a79

CHANGELOG.md

@@ -1,5 +1,13 @@
 # Changelog
 
+## 0.4.0-alpha.10 (2025-11-17)
+
+Full Changelog: [v0.4.0-alpha.9...v0.4.0-alpha.10](https://github.com/llamastack/llama-stack-client-python/compare/v0.4.0-alpha.9...v0.4.0-alpha.10)
+
+### Bug Fixes
+
+* **openapi:** restore embedded request wrappers ([261e364](https://github.com/llamastack/llama-stack-client-python/commit/261e3640c942c60860af08cd4d205d8e402bb702))
+
 ## 0.4.0-alpha.9 (2025-11-14)
 
 Full Changelog: [v0.4.0-alpha.8...v0.4.0-alpha.9](https://github.com/llamastack/llama-stack-client-python/compare/v0.4.0-alpha.8...v0.4.0-alpha.9)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.4.0-alpha.9"
+version = "0.4.0-alpha.10"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "MIT"

src/llama_stack_client/resources/alpha/eval/eval.py

@@ -8,7 +8,7 @@
 
 from __future__ import annotations
 
-from typing import Dict, Iterable, Optional
+from typing import Dict, Iterable
 
 import httpx
 
@@ -20,7 +20,7 @@
     JobsResourceWithStreamingResponse,
     AsyncJobsResourceWithStreamingResponse,
 )
-from ...._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
+from ...._types import Body, Query, Headers, NotGiven, SequenceNotStr, not_given
 from ...._utils import maybe_transform, async_maybe_transform
 from ...._compat import cached_property
 from ...._resource import SyncAPIResource, AsyncAPIResource
@@ -164,9 +164,7 @@ def run_eval(
         self,
         benchmark_id: str,
         *,
-        eval_candidate: eval_run_eval_params.EvalCandidate,
-        num_examples: Optional[int] | Omit = omit,
-        scoring_params: Dict[str, eval_run_eval_params.ScoringParams] | Omit = omit,
+        benchmark_config: BenchmarkConfigParam,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -178,13 +176,7 @@ def run_eval(
         Run an evaluation on a benchmark.
 
         Args:
-          eval_candidate: A model candidate for evaluation.
-
-          num_examples: Number of examples to evaluate (useful for testing), if not provided, all
-              examples in the dataset will be evaluated
-
-          scoring_params: Map between scoring function id and parameters for each scoring function you
-              want to run
+          benchmark_config: A benchmark configuration for evaluation.
 
           extra_headers: Send extra headers
 
@@ -198,14 +190,7 @@ def run_eval(
             raise ValueError(f"Expected a non-empty value for `benchmark_id` but received {benchmark_id!r}")
         return self._post(
             f"/v1alpha/eval/benchmarks/{benchmark_id}/jobs",
-            body=maybe_transform(
-                {
-                    "eval_candidate": eval_candidate,
-                    "num_examples": num_examples,
-                    "scoring_params": scoring_params,
-                },
-                eval_run_eval_params.EvalRunEvalParams,
-            ),
+            body=maybe_transform({"benchmark_config": benchmark_config}, eval_run_eval_params.EvalRunEvalParams),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
@@ -216,9 +201,7 @@ def run_eval_alpha(
         self,
         benchmark_id: str,
         *,
-        eval_candidate: eval_run_eval_alpha_params.EvalCandidate,
-        num_examples: Optional[int] | Omit = omit,
-        scoring_params: Dict[str, eval_run_eval_alpha_params.ScoringParams] | Omit = omit,
+        benchmark_config: BenchmarkConfigParam,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -230,13 +213,7 @@ def run_eval_alpha(
         Run an evaluation on a benchmark.
 
         Args:
-          eval_candidate: A model candidate for evaluation.
-
-          num_examples: Number of examples to evaluate (useful for testing), if not provided, all
-              examples in the dataset will be evaluated
-
-          scoring_params: Map between scoring function id and parameters for each scoring function you
-              want to run
+          benchmark_config: A benchmark configuration for evaluation.
 
           extra_headers: Send extra headers
 
@@ -251,12 +228,7 @@ def run_eval_alpha(
         return self._post(
             f"/v1alpha/eval/benchmarks/{benchmark_id}/jobs",
             body=maybe_transform(
-                {
-                    "eval_candidate": eval_candidate,
-                    "num_examples": num_examples,
-                    "scoring_params": scoring_params,
-                },
-                eval_run_eval_alpha_params.EvalRunEvalAlphaParams,
+                {"benchmark_config": benchmark_config}, eval_run_eval_alpha_params.EvalRunEvalAlphaParams
             ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
@@ -385,9 +357,7 @@ async def run_eval(
         self,
         benchmark_id: str,
         *,
-        eval_candidate: eval_run_eval_params.EvalCandidate,
-        num_examples: Optional[int] | Omit = omit,
-        scoring_params: Dict[str, eval_run_eval_params.ScoringParams] | Omit = omit,
+        benchmark_config: BenchmarkConfigParam,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -399,13 +369,7 @@ async def run_eval(
         Run an evaluation on a benchmark.
 
         Args:
-          eval_candidate: A model candidate for evaluation.
-
-          num_examples: Number of examples to evaluate (useful for testing), if not provided, all
-              examples in the dataset will be evaluated
-
-          scoring_params: Map between scoring function id and parameters for each scoring function you
-              want to run
+          benchmark_config: A benchmark configuration for evaluation.
 
           extra_headers: Send extra headers
 
@@ -420,12 +384,7 @@ async def run_eval(
         return await self._post(
             f"/v1alpha/eval/benchmarks/{benchmark_id}/jobs",
             body=await async_maybe_transform(
-                {
-                    "eval_candidate": eval_candidate,
-                    "num_examples": num_examples,
-                    "scoring_params": scoring_params,
-                },
-                eval_run_eval_params.EvalRunEvalParams,
+                {"benchmark_config": benchmark_config}, eval_run_eval_params.EvalRunEvalParams
             ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
@@ -437,9 +396,7 @@ async def run_eval_alpha(
         self,
         benchmark_id: str,
         *,
-        eval_candidate: eval_run_eval_alpha_params.EvalCandidate,
-        num_examples: Optional[int] | Omit = omit,
-        scoring_params: Dict[str, eval_run_eval_alpha_params.ScoringParams] | Omit = omit,
+        benchmark_config: BenchmarkConfigParam,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -451,13 +408,7 @@ async def run_eval_alpha(
         Run an evaluation on a benchmark.
 
         Args:
-          eval_candidate: A model candidate for evaluation.
-
-          num_examples: Number of examples to evaluate (useful for testing), if not provided, all
-              examples in the dataset will be evaluated
-
-          scoring_params: Map between scoring function id and parameters for each scoring function you
-              want to run
+          benchmark_config: A benchmark configuration for evaluation.
 
           extra_headers: Send extra headers
 
@@ -472,12 +423,7 @@ async def run_eval_alpha(
         return await self._post(
             f"/v1alpha/eval/benchmarks/{benchmark_id}/jobs",
             body=await async_maybe_transform(
-                {
-                    "eval_candidate": eval_candidate,
-                    "num_examples": num_examples,
-                    "scoring_params": scoring_params,
-                },
-                eval_run_eval_alpha_params.EvalRunEvalAlphaParams,
+                {"benchmark_config": benchmark_config}, eval_run_eval_alpha_params.EvalRunEvalAlphaParams
             ),
             options=make_request_options(
                 extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout

src/llama_stack_client/resources/beta/datasets.py

@@ -10,6 +10,7 @@
 
 import typing_extensions
 from typing import Dict, Type, Iterable, Optional, cast
+from typing_extensions import Literal
 
 import httpx
 
@@ -205,21 +206,26 @@ def iterrows(
     def register(
         self,
         *,
-        purpose: object,
-        source: object,
-        dataset_id: object | Omit = omit,
-        metadata: object | Omit = omit,
+        purpose: Literal["post-training/messages", "eval/question-answer", "eval/messages-answer"],
+        source: dataset_register_params.Source,
+        dataset_id: Optional[str] | Omit = omit,
+        metadata: Optional[Dict[str, object]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> DatasetRegisterResponse:
-        """
-        Register a new dataset.
+        """Register a new dataset.
 
         Args:
+          purpose: Purpose of the dataset.
+
+        Each purpose has a required input data schema.
+
+          source: A dataset that can be obtained from a URI.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -452,21 +458,26 @@ async def iterrows(
     async def register(
         self,
         *,
-        purpose: object,
-        source: object,
-        dataset_id: object | Omit = omit,
-        metadata: object | Omit = omit,
+        purpose: Literal["post-training/messages", "eval/question-answer", "eval/messages-answer"],
+        source: dataset_register_params.Source,
+        dataset_id: Optional[str] | Omit = omit,
+        metadata: Optional[Dict[str, object]] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
         extra_query: Query | None = None,
         extra_body: Body | None = None,
         timeout: float | httpx.Timeout | None | NotGiven = not_given,
     ) -> DatasetRegisterResponse:
-        """
-        Register a new dataset.
+        """Register a new dataset.
 
         Args:
+          purpose: Purpose of the dataset.
+
+        Each purpose has a required input data schema.
+
+          source: A dataset that can be obtained from a URI.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request

src/llama_stack_client/resources/scoring_functions.py

@@ -9,7 +9,7 @@
 from __future__ import annotations
 
 import typing_extensions
-from typing import Type, cast
+from typing import Type, Optional, cast
 
 import httpx
 
@@ -112,12 +112,12 @@ def list(
     def register(
         self,
         *,
-        description: object,
-        return_type: object,
-        scoring_fn_id: object,
-        params: object | Omit = omit,
-        provider_id: object | Omit = omit,
-        provider_scoring_fn_id: object | Omit = omit,
+        description: str,
+        return_type: scoring_function_register_params.ReturnType,
+        scoring_fn_id: str,
+        params: Optional[scoring_function_register_params.Params] | Omit = omit,
+        provider_id: Optional[str] | Omit = omit,
+        provider_scoring_fn_id: Optional[str] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -129,6 +129,8 @@ def register(
         Register a scoring function.
 
         Args:
+          params: Parameters for LLM-as-judge scoring function configuration.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -273,12 +275,12 @@ async def list(
     async def register(
         self,
         *,
-        description: object,
-        return_type: object,
-        scoring_fn_id: object,
-        params: object | Omit = omit,
-        provider_id: object | Omit = omit,
-        provider_scoring_fn_id: object | Omit = omit,
+        description: str,
+        return_type: scoring_function_register_params.ReturnType,
+        scoring_fn_id: str,
+        params: Optional[scoring_function_register_params.Params] | Omit = omit,
+        provider_id: Optional[str] | Omit = omit,
+        provider_scoring_fn_id: Optional[str] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -290,6 +292,8 @@ async def register(
         Register a scoring function.
 
         Args:
+          params: Parameters for LLM-as-judge scoring function configuration.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request