llamastack · stainless-app · Mar 27, 2026 · Mar 11, 2026 · Mar 13, 2026 · Mar 13, 2026
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -1,12 +1,14 @@
 name: CI
 on:
   push:
-    branches-ignore:
-      - 'generated'
-      - 'codegen/**'
-      - 'integrated/**'
-      - 'stl-preview-head/**'
-      - 'stl-preview-base/**'
+    branches:
+      - '**'
+      - '!integrated/**'
+      - '!stl-preview-head/**'
+      - '!stl-preview-base/**'
+      - '!generated'
+      - '!codegen/**'
+      - 'codegen/stl/**'
   pull_request:
     branches-ignore:
       - 'stl-preview-head/**'
@@ -18,7 +20,7 @@ jobs:
     timeout-minutes: 10
     name: lint
     runs-on: ${{ github.repository == 'stainless-sdks/llama-stack-client-python' && 'depot-ubuntu-24.04' || 'ubuntu-latest' }}
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.fork
+    if: (github.event_name == 'push' || github.event.pull_request.head.repo.fork) && (github.event_name != 'push' || github.event.head_commit.message != 'codegen metadata')
     steps:
       - uses: actions/checkout@v6
 
@@ -34,7 +36,7 @@ jobs:
         run: ./scripts/lint
 
   build:
-    if: github.event_name == 'push' || github.event.pull_request.head.repo.fork
+    if: (github.event_name == 'push' || github.event.pull_request.head.repo.fork) && (github.event_name != 'push' || github.event.head_commit.message != 'codegen metadata')
     timeout-minutes: 10
     name: build
     permissions:

diff --git a/.release-please-manifest.json b/.release-please-manifest.json
@@ -1,3 +1,3 @@
 {
-  ".": "0.6.1-alpha.1"
+  ".": "0.7.0-alpha.1"
 }
diff --git a/.stats.yml b/.stats.yml
@@ -1,4 +1,4 @@
-configured_endpoints: 108
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-1b387ba7b0e0d1aa931032ac2101e5a473b9fa42975e6575cf889feace342b80.yml
-openapi_spec_hash: a144868005520bd3f8f9dc3d8cac1c22
-config_hash: ef1f9b33e203c71cfc10d91890c1ed2d
+configured_endpoints: 94
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-ce0519da94b80140cbcd7c35fa41c78daa192530a7525b3452f2a0b2e998cfc8.yml
+openapi_spec_hash: 8a9ec9c7c3a1216ec0e8580ad598a529
+config_hash: 7d5765272a641656f8231509937663a7
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,53 @@
 # Changelog
 
+## 0.7.0-alpha.1 (2026-03-28)
+
+Full Changelog: [v0.6.1-alpha.1...v0.7.0-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.6.1-alpha.1...v0.7.0-alpha.1)
+
+### ⚠ BREAKING CHANGES
+
+* eliminate GET /chat/completions/{completion_id} conformance issues
+* rename agents API to responses API
+* eliminate /files/{file_id} GET differences
+
+### Features
+
+* Add stream_options parameter support ([b4c2f15](https://github.com/llamastack/llama-stack-client-python/commit/b4c2f15b16872730a9c254b1b2dfc02aba223a71))
+* eliminate /files/{file_id} GET differences ([1f28d73](https://github.com/llamastack/llama-stack-client-python/commit/1f28d730824b6cb721415985194c5f4567e42ea7))
+* eliminate GET /chat/completions/{completion_id} conformance issues ([dad9f54](https://github.com/llamastack/llama-stack-client-python/commit/dad9f546400133d34a0cd650a227800be78b0d1f))
+* **internal:** implement indices array format for query and form serialization ([6694121](https://github.com/llamastack/llama-stack-client-python/commit/6694121eee689fb7033704bad2b698a4640e2431))
+* **responses:** add cancel endpoint for background responses ([d9bc91a](https://github.com/llamastack/llama-stack-client-python/commit/d9bc91afecb64ec27b97d37699d5ff6c1222d369))
+
+
+### Bug Fixes
+
+* **deps:** bump minimum typing-extensions version ([50ea4d7](https://github.com/llamastack/llama-stack-client-python/commit/50ea4d7fd98a86726f6825d911507b7fc96e2e60))
+* **inference:** improve chat completions OpenAI conformance ([147b88b](https://github.com/llamastack/llama-stack-client-python/commit/147b88b44eb83bceb7cd6204cd79d8dafe8f8e7a))
+* **pydantic:** do not pass `by_alias` unless set ([f6836f9](https://github.com/llamastack/llama-stack-client-python/commit/f6836f9dacef1b9b26774fcfaf82689ae00f374a))
+* remove duplicate dataset_id parameter in append-rows endpoint ([d6a79d0](https://github.com/llamastack/llama-stack-client-python/commit/d6a79d0a830bad4e82b70d7ab9e007ebc16e0f05))
+* sanitize endpoint path params ([9b288d5](https://github.com/llamastack/llama-stack-client-python/commit/9b288d553ae83860fbe1d8ee9352532ed04ddd9b))
+
+
+### Chores
+
+* **ci:** skip lint on metadata-only changes ([b096c2c](https://github.com/llamastack/llama-stack-client-python/commit/b096c2ce513a5d2de9a17e7841609feb30d1b0b2))
+* **internal:** tweak CI branches ([1df7e26](https://github.com/llamastack/llama-stack-client-python/commit/1df7e2605e78572eccc53aa8db1e44d987106a9b))
+* **internal:** update gitignore ([0e98cfd](https://github.com/llamastack/llama-stack-client-python/commit/0e98cfdcf7779ca24ef4dbd7e9e8d9c75fa2a751))
+* **internal:** version bump ([f468096](https://github.com/llamastack/llama-stack-client-python/commit/f46809696ddf1f179cc26984facfcbb7f9264730))
+* **tests:** bump steady to v0.19.4 ([f5ad8f8](https://github.com/llamastack/llama-stack-client-python/commit/f5ad8f801078d79c03ec7723cd64b1c9895def2d))
+* **tests:** bump steady to v0.19.5 ([55689e1](https://github.com/llamastack/llama-stack-client-python/commit/55689e1ddee55d81efff681dbb3523b0ed09d658))
+* **tests:** bump steady to v0.19.6 ([87cb87e](https://github.com/llamastack/llama-stack-client-python/commit/87cb87e8ecd52d95b5a375f8b4c00f5837e4feeb))
+* **tests:** bump steady to v0.19.7 ([10f6ed7](https://github.com/llamastack/llama-stack-client-python/commit/10f6ed745b38d89be2d6a5eb007427b015e84e23))
+
+
+### Refactors
+
+* remove fine_tuning API ([021bd5e](https://github.com/llamastack/llama-stack-client-python/commit/021bd5e6138574884befe6f20ba86ceeefee1767))
+* remove tool_groups from public API and auto-register from provider specs ([c0df2dc](https://github.com/llamastack/llama-stack-client-python/commit/c0df2dcf9bb38600f73db746dc38d3277e74e7b9))
+* rename agents API to responses API ([f5c27db](https://github.com/llamastack/llama-stack-client-python/commit/f5c27db9d2716098a116d516cc5ad673ee621988))
+* rename rag-runtime provider to file-search ([94a14da](https://github.com/llamastack/llama-stack-client-python/commit/94a14dad88ed55d3f2baf1de8eb30ba529fb9818))
+* **tests:** switch from prism to steady ([23d591c](https://github.com/llamastack/llama-stack-client-python/commit/23d591c70549c7f00b7be136a19893dbdd65f43c))
+
 ## 0.6.1-alpha.1 (2026-03-13)
 
 Full Changelog: [v0.5.0-alpha.2...v0.6.1-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.5.0-alpha.2...v0.6.1-alpha.1)

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -85,7 +85,7 @@ $ pip install ./path-to-wheel-file.whl
 
 ## Running tests
 
-Most tests require you to [set up a mock server](https://github.com/stoplightio/prism) against the OpenAPI spec to run the tests.
+Most tests require you to [set up a mock server](https://github.com/dgellow/steady) against the OpenAPI spec to run the tests.
 
 ```sh
 $ ./scripts/mock

diff --git a/README.md b/README.md
@@ -253,11 +253,12 @@ from llama_stack_client import LlamaStackClient
 
 client = LlamaStackClient()
 
-client.toolgroups.register(
-    provider_id="provider_id",
-    toolgroup_id="toolgroup_id",
-    mcp_endpoint={"uri": "uri"},
+response_object = client.responses.create(
+    input="string",
+    model="model",
+    prompt={"id": "id"},
 )
+print(response_object.prompt)
 ```
 
 ## File uploads

diff --git a/api.md b/api.md
@@ -18,47 +18,6 @@ from llama_stack_client.types import (
 )
 ```
 
-# Toolgroups
-
-Types:
-
-```python
-from llama_stack_client.types import ListToolGroupsResponse, ToolGroup, ToolgroupListResponse
-```
-
-Methods:
-
-- <code title="get /v1/toolgroups">client.toolgroups.<a href="./src/llama_stack_client/resources/toolgroups.py">list</a>() -> <a href="./src/llama_stack_client/types/toolgroup_list_response.py">ToolgroupListResponse</a></code>
-- <code title="get /v1/toolgroups/{toolgroup_id}">client.toolgroups.<a href="./src/llama_stack_client/resources/toolgroups.py">get</a>(toolgroup_id) -> <a href="./src/llama_stack_client/types/tool_group.py">ToolGroup</a></code>
-- <code title="post /v1/toolgroups">client.toolgroups.<a href="./src/llama_stack_client/resources/toolgroups.py">register</a>(\*\*<a href="src/llama_stack_client/types/toolgroup_register_params.py">params</a>) -> None</code>
-- <code title="delete /v1/toolgroups/{toolgroup_id}">client.toolgroups.<a href="./src/llama_stack_client/resources/toolgroups.py">unregister</a>(toolgroup_id) -> None</code>
-
-# Tools
-
-Types:
-
-```python
-from llama_stack_client.types import ToolListResponse
-```
-
-Methods:
-
-- <code title="get /v1/tools">client.tools.<a href="./src/llama_stack_client/resources/tools.py">list</a>(\*\*<a href="src/llama_stack_client/types/tool_list_params.py">params</a>) -> <a href="./src/llama_stack_client/types/tool_list_response.py">ToolListResponse</a></code>
-- <code title="get /v1/tools/{tool_name}">client.tools.<a href="./src/llama_stack_client/resources/tools.py">get</a>(tool_name) -> <a href="./src/llama_stack_client/types/tool_def.py">ToolDef</a></code>
-
-# ToolRuntime
-
-Types:
-
-```python
-from llama_stack_client.types import ToolDef, ToolInvocationResult, ToolRuntimeListToolsResponse
-```
-
-Methods:
-
-- <code title="post /v1/tool-runtime/invoke">client.tool_runtime.<a href="./src/llama_stack_client/resources/tool_runtime.py">invoke_tool</a>(\*\*<a href="src/llama_stack_client/types/tool_runtime_invoke_tool_params.py">params</a>) -> <a href="./src/llama_stack_client/types/tool_invocation_result.py">ToolInvocationResult</a></code>
-- <code title="get /v1/tool-runtime/list-tools">client.tool_runtime.<a href="./src/llama_stack_client/resources/tool_runtime.py">list_tools</a>(\*\*<a href="src/llama_stack_client/types/tool_runtime_list_tools_params.py">params</a>) -> <a href="./src/llama_stack_client/types/tool_runtime_list_tools_response.py">ToolRuntimeListToolsResponse</a></code>
-
 # Responses
 
 Types:
@@ -409,7 +368,12 @@ Methods:
 Types:
 
 ```python
-from llama_stack_client.types import DeleteFileResponse, File, ListFilesResponse
+from llama_stack_client.types import (
+    DeleteFileResponse,
+    File,
+    ListFilesResponse,
+    FileContentResponse,
+)
 ```
 
 Methods:
@@ -418,7 +382,7 @@ Methods:
 - <code title="get /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/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/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/files/{file_id}/content">client.files.<a href="./src/llama_stack_client/resources/files.py">content</a>(file_id) -> object</code>
+- <code title="get /v1/files/{file_id}/content">client.files.<a href="./src/llama_stack_client/resources/files.py">content</a>(file_id) -> str</code>
 
 # Batches
 
@@ -442,42 +406,6 @@ Methods:
 
 # Alpha
 
-## PostTraining
-
-Types:
-
-```python
-from llama_stack_client.types.alpha import (
-    AlgorithmConfig,
-    ListPostTrainingJobsResponse,
-    PostTrainingJob,
-)
-```
-
-Methods:
-
-- <code title="post /v1alpha/post-training/preference-optimize">client.alpha.post_training.<a href="./src/llama_stack_client/resources/alpha/post_training/post_training.py">preference_optimize</a>(\*\*<a href="src/llama_stack_client/types/alpha/post_training_preference_optimize_params.py">params</a>) -> <a href="./src/llama_stack_client/types/alpha/post_training_job.py">PostTrainingJob</a></code>
-- <code title="post /v1alpha/post-training/supervised-fine-tune">client.alpha.post_training.<a href="./src/llama_stack_client/resources/alpha/post_training/post_training.py">supervised_fine_tune</a>(\*\*<a href="src/llama_stack_client/types/alpha/post_training_supervised_fine_tune_params.py">params</a>) -> <a href="./src/llama_stack_client/types/alpha/post_training_job.py">PostTrainingJob</a></code>
-
-### Job
-
-Types:
-
-```python
-from llama_stack_client.types.alpha.post_training import (
-    JobListResponse,
-    JobArtifactsResponse,
-    JobStatusResponse,
-)
-```
-
-Methods:
-
-- <code title="get /v1alpha/post-training/jobs">client.alpha.post_training.job.<a href="./src/llama_stack_client/resources/alpha/post_training/job.py">list</a>() -> <a href="./src/llama_stack_client/types/alpha/post_training/job_list_response.py">JobListResponse</a></code>
-- <code title="get /v1alpha/post-training/jobs/{job_uuid}/artifacts">client.alpha.post_training.job.<a href="./src/llama_stack_client/resources/alpha/post_training/job.py">artifacts</a>(job_uuid) -> <a href="./src/llama_stack_client/types/alpha/post_training/job_artifacts_response.py">JobArtifactsResponse</a></code>
-- <code title="post /v1alpha/post-training/jobs/{job_uuid}/cancel">client.alpha.post_training.job.<a href="./src/llama_stack_client/resources/alpha/post_training/job.py">cancel</a>(job_uuid) -> None</code>
-- <code title="get /v1alpha/post-training/jobs/{job_uuid}/status">client.alpha.post_training.job.<a href="./src/llama_stack_client/resources/alpha/post_training/job.py">status</a>(job_uuid) -> <a href="./src/llama_stack_client/types/alpha/post_training/job_status_response.py">JobStatusResponse</a></code>
-
 ## Benchmarks
 
 Types:
@@ -558,7 +486,7 @@ Methods:
 
 - <code title="get /v1beta/datasets/{dataset_id}">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">retrieve</a>(dataset_id) -> <a href="./src/llama_stack_client/types/beta/dataset_retrieve_response.py">DatasetRetrieveResponse</a></code>
 - <code title="get /v1beta/datasets">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">list</a>() -> <a href="./src/llama_stack_client/types/beta/dataset_list_response.py">DatasetListResponse</a></code>
-- <code title="post /v1beta/datasetio/append-rows/{dataset_id}">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">appendrows</a>(path_dataset_id, \*\*<a href="src/llama_stack_client/types/beta/dataset_appendrows_params.py">params</a>) -> None</code>
+- <code title="post /v1beta/datasetio/append-rows/{dataset_id}">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">appendrows</a>(dataset_id, \*\*<a href="src/llama_stack_client/types/beta/dataset_appendrows_params.py">params</a>) -> None</code>
 - <code title="get /v1beta/datasetio/iterrows/{dataset_id}">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">iterrows</a>(dataset_id, \*\*<a href="src/llama_stack_client/types/beta/dataset_iterrows_params.py">params</a>) -> <a href="./src/llama_stack_client/types/beta/dataset_iterrows_response.py">DatasetIterrowsResponse</a></code>
 - <code title="post /v1beta/datasets">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">register</a>(\*\*<a href="src/llama_stack_client/types/beta/dataset_register_params.py">params</a>) -> <a href="./src/llama_stack_client/types/beta/dataset_register_response.py">DatasetRegisterResponse</a></code>
 - <code title="delete /v1beta/datasets/{dataset_id}">client.beta.datasets.<a href="./src/llama_stack_client/resources/beta/datasets.py">unregister</a>(dataset_id) -> None</code>
diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.6.1-alpha.1"
+version = "0.7.0-alpha.1"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "MIT"
@@ -9,7 +9,7 @@ authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }]
 dependencies = [
   "httpx>=0.23.0, <1",
   "pydantic>=1.9.0, <3",
-    "typing-extensions>=4.7, <5",
+    "typing-extensions>=4.7, <5", "typing-extensions>=4.14, <5",
   "anyio>=3.5.0, <5",
   "distro>=1.7.0, <2",
   "sniffio",

diff --git a/requirements-dev.lock b/requirements-dev.lock
@@ -7,15 +7,15 @@ anyio==4.12.1
     # via
     #   httpx
     #   llama-stack-client
-black==26.1.0
+black==26.3.1
 certifi==2026.1.4
     # via
     #   httpcore
     #   httpx
     #   requests
 cfgv==3.5.0
     # via pre-commit
-charset-normalizer==3.4.4
+charset-normalizer==3.4.6
     # via requests
 click==8.3.1
     # via
@@ -33,8 +33,10 @@ distro==1.9.0
     # via llama-stack-client
 execnet==2.1.2
     # via pytest-xdist
-filelock==3.20.3
-    # via virtualenv
+filelock==3.25.2
+    # via
+    #   python-discovery
+    #   virtualenv
 fire==0.7.1
     # via llama-stack-client
 h11==0.16.0
@@ -45,7 +47,7 @@ httpx==0.28.1
     # via
     #   llama-stack-client
     #   respx
-identify==2.6.16
+identify==2.6.18
     # via pre-commit
 idna==3.11
     # via
@@ -68,21 +70,22 @@ nodeenv==1.10.0
     # via
     #   pre-commit
     #   pyright
-numpy==2.4.2
+numpy==2.4.3
     # via pandas
 packaging==25.0
     # via
     #   black
     #   pytest
-pandas==3.0.0
+pandas==3.0.1
     # via llama-stack-client
 pathspec==1.0.3
     # via
     #   black
     #   mypy
-platformdirs==4.5.1
+platformdirs==4.9.4
     # via
     #   black
+    #   python-discovery
     #   virtualenv
 pluggy==1.6.0
     # via pytest
@@ -108,13 +111,15 @@ pytest-asyncio==1.3.0
 pytest-xdist==3.8.0
 python-dateutil==2.9.0.post0
     # via pandas
+python-discovery==1.2.1
+    # via virtualenv
 pytokens==0.4.1
     # via black
 pyyaml==6.0.3
     # via
     #   pre-commit
     #   pyaml
-requests==2.32.5
+requests==2.33.0
     # via llama-stack-client
 respx==0.22.0
 rich==14.2.0
@@ -147,7 +152,7 @@ tzdata==2025.3 ; sys_platform == 'emscripten' or sys_platform == 'win32'
     # via pandas
 urllib3==2.6.3
     # via requests
-virtualenv==20.36.1
+virtualenv==21.2.0
     # via pre-commit
 wcwidth==0.6.0
     # via prompt-toolkit

diff --git a/scripts/mock b/scripts/mock
@@ -26,11 +26,11 @@ echo "==> Modifying SSE schemas for the mock server"
 yq -i '(.. | select(has("text/event-stream")).["text/event-stream"].schema) = {"type": "string"}' "$SPEC_PATH"
 echo "==> Starting mock server with file ${SPEC_PATH}"
 
-# Run prism mock on the given spec
+# Run steady mock on the given spec
 if [ "$1" == "--daemon" ]; then
   npm exec --package=@mockoon/cli@9.3.0 -- mockoon-cli start --data "$SPEC_PATH" --port 4010 &>.mockoon.log &
 
-  # Wait for server to come online (max 30s)
+  # Wait for server to come online via health endpoint (max 30s)
   echo -n "Waiting for server"
   while ! grep -q "Error: \|Server started on port 4010" ".mockoon.log"; do
     echo -n "."

diff --git a/scripts/test b/scripts/test
@@ -45,14 +45,14 @@ elif ! prism_is_running; then
   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 -e "spec to the steady command:"
   echo
-  echo -e "  \$ ${YELLOW}npm exec --package=@stainless-api/prism-cli@5.15.0 -- prism mock path/to/your.openapi.yml${NC}"
+  echo -e "  \$ ${YELLOW}npm exec --package=@stdy/cli@0.19.7 -- steady path/to/your.openapi.yml --host 127.0.0.1 -p 4010 --validator-query-array-format=comma --validator-form-array-format=comma --validator-query-object-format=brackets --validator-form-object-format=brackets${NC}"
   echo
 
   exit 1
 else
-  echo -e "${GREEN}✔ Mock prism server is running with your OpenAPI spec${NC}"
+  echo -e "${GREEN}✔ Mock steady server is running with your OpenAPI spec${NC}"
   echo
 fi