diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 7d8140ed..dd3f6e2b 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -7,6 +7,10 @@ on:
       - 'integrated/**'
       - 'stl-preview-head/**'
       - 'stl-preview-base/**'
+  pull_request:
+    branches-ignore:
+      - 'stl-preview-head/**'
+      - 'stl-preview-base/**'
 
 jobs:
   lint:
@@ -30,6 +34,30 @@ jobs:
       - name: Run lints
         run: ./scripts/lint
 
+  upload:
+    if: github.repository == 'stainless-sdks/llama-stack-client-python'
+    timeout-minutes: 10
+    name: upload
+    permissions:
+      contents: read
+      id-token: write
+    runs-on: depot-ubuntu-24.04
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Get GitHub OIDC Token
+        id: github-oidc
+        uses: actions/github-script@v6
+        with:
+          script: core.setOutput('github_token', await core.getIDToken());
+
+      - name: Upload tarball
+        env:
+          URL: https://pkg.stainless.com/s
+          AUTH: ${{ steps.github-oidc.outputs.github_token }}
+          SHA: ${{ github.sha }}
+        run: ./scripts/utils/upload-artifact.sh
+
   test:
     timeout-minutes: 10
     name: test
diff --git a/.github/workflows/publish-pypi.yml b/.github/workflows/publish-pypi.yml
new file mode 100644
index 00000000..e62e7dd5
--- /dev/null
+++ b/.github/workflows/publish-pypi.yml
@@ -0,0 +1,31 @@
+# This workflow is triggered when a GitHub release is created.
+# It can also be run manually to re-publish to PyPI in case it failed for some reason.
+# You can run this workflow by navigating to https://www.github.com/llamastack/llama-stack-client-python/actions/workflows/publish-pypi.yml
+name: Publish PyPI
+on:
+  workflow_dispatch:
+
+  release:
+    types: [published]
+
+jobs:
+  publish:
+    name: publish
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Rye
+        run: |
+          curl -sSf https://rye.astral.sh/get | bash
+          echo "$HOME/.rye/shims" >> $GITHUB_PATH
+        env:
+          RYE_VERSION: '0.44.0'
+          RYE_INSTALL_OPTION: '--yes'
+
+      - name: Publish to PyPI
+        run: |
+          bash ./bin/publish-pypi
+        env:
+          PYPI_TOKEN: ${{ secrets.LLAMA_STACK_CLIENT_PYPI_TOKEN || secrets.PYPI_TOKEN }}
diff --git a/.github/workflows/release-doctor.yml b/.github/workflows/release-doctor.yml
new file mode 100644
index 00000000..1ac94793
--- /dev/null
+++ b/.github/workflows/release-doctor.yml
@@ -0,0 +1,21 @@
+name: Release Doctor
+on:
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  release_doctor:
+    name: release doctor
+    runs-on: ubuntu-latest
+    if: github.repository == 'llamastack/llama-stack-client-python' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch' || startsWith(github.head_ref, 'release-please') || github.head_ref == 'next')
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Check release environment
+        run: |
+          bash ./bin/check-release-environment
+        env:
+          PYPI_TOKEN: ${{ secrets.LLAMA_STACK_CLIENT_PYPI_TOKEN || secrets.PYPI_TOKEN }}
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
new file mode 100644
index 00000000..ba6c3483
--- /dev/null
+++ b/.release-please-manifest.json
@@ -0,0 +1,3 @@
+{
+  ".": "0.1.0-alpha.1"
+}
\ No newline at end of file
diff --git a/.stats.yml b/.stats.yml
index fa112235..32b2676c 100644
--- a/.stats.yml
+++ b/.stats.yml
@@ -1,4 +1,4 @@
 configured_endpoints: 91
 openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/llamastack%2Fllama-stack-client-0e756984d87c3fd1eb96d486947b3bc2086d5afcf299e8119b6b89bbd86dbe75.yml
 openapi_spec_hash: 7c519a25bb9a094d4b4bda17bb20dd88
-config_hash: b83ca660b1609a8903f32e3d54b4ff00
+config_hash: d1f21dfdbf5d9925eecf56b6c1fab755
diff --git a/CHANGELOG.md b/CHANGELOG.md
new file mode 100644
index 00000000..ee3351d8
--- /dev/null
+++ b/CHANGELOG.md
@@ -0,0 +1,42 @@
+# Changelog
+
+## 0.1.0-alpha.1 (2025-06-27)
+
+Full Changelog: [v0.0.1-alpha.0...v0.1.0-alpha.1](https://github.com/llamastack/llama-stack-client-python/compare/v0.0.1-alpha.0...v0.1.0-alpha.1)
+
+### Features
+
+* **client:** add follow_redirects request option ([a77a9ee](https://github.com/llamastack/llama-stack-client-python/commit/a77a9eed9038782ba6b93ce0d3147ee4a6b8a3b7))
+* **client:** add support for aiohttp ([d78982b](https://github.com/llamastack/llama-stack-client-python/commit/d78982b197c5e0a0fb67afcb44e9644fd8d931be))
+
+
+### Bug Fixes
+
+* **ci:** release-doctor — report correct token name ([6f3a4e2](https://github.com/llamastack/llama-stack-client-python/commit/6f3a4e24d8b357d7dc01adb0d9f736989fa9517d))
+* **client:** correctly parse binary response | stream ([85d6bbd](https://github.com/llamastack/llama-stack-client-python/commit/85d6bbd97efac7509cbff0bb2d461a80d09b5e61))
+* **package:** support direct resource imports ([a862d55](https://github.com/llamastack/llama-stack-client-python/commit/a862d551553aac41573306ce39480e1eb16ea3d3))
+* **tests:** fix: tests which call HTTP endpoints directly with the example parameters ([347a4bf](https://github.com/llamastack/llama-stack-client-python/commit/347a4bffa920f5727a4c02eba18bd207001698b5))
+
+
+### Chores
+
+* change publish docs url ([fdd7a07](https://github.com/llamastack/llama-stack-client-python/commit/fdd7a075564ac206e91b2d06bf130c4de9473838))
+* **ci:** enable for pull requests ([c9b6347](https://github.com/llamastack/llama-stack-client-python/commit/c9b6347f084acb1566b8e8283cf0bcfde7f6562c))
+* **ci:** fix installation instructions ([40d9854](https://github.com/llamastack/llama-stack-client-python/commit/40d9854bd2630a471f1ca93d249e4d44b73fa864))
+* **ci:** upload sdks to package manager ([2d2282b](https://github.com/llamastack/llama-stack-client-python/commit/2d2282bb49d58daef1f32fa0f1e5a356abf8df0d))
+* **docs:** grammar improvements ([6f57b13](https://github.com/llamastack/llama-stack-client-python/commit/6f57b1363367de7ed5035fd1d6ba1a071eee67ba))
+* **docs:** remove reference to rye shell ([bcf315a](https://github.com/llamastack/llama-stack-client-python/commit/bcf315ae00c458f89dfa3684bcc7abdb732b6c5f))
+* **docs:** remove unnecessary param examples ([60ec829](https://github.com/llamastack/llama-stack-client-python/commit/60ec829e809156217cf2f911b3cac6b23a06baad))
+* **internal:** avoid errors for isinstance checks on proxies ([758a188](https://github.com/llamastack/llama-stack-client-python/commit/758a188dbfaa284a13b70816689c99917a05d16c))
+* **internal:** codegen related update ([ab9f05c](https://github.com/llamastack/llama-stack-client-python/commit/ab9f05cc1da5b21afceacdf9c8eb54b6e59eed01))
+* **internal:** update conftest.py ([218e172](https://github.com/llamastack/llama-stack-client-python/commit/218e172c16014dad41a7c189c5620077955d6bdf))
+* **readme:** update badges ([9b63e1b](https://github.com/llamastack/llama-stack-client-python/commit/9b63e1b7dbbbd7556d046a2a4224a8385bbea24c))
+* **tests:** add tests for httpx client instantiation & proxies ([b27b11b](https://github.com/llamastack/llama-stack-client-python/commit/b27b11bbe0a9c5778b757733c11828d9603307ea))
+* **tests:** run tests in parallel ([1287a3c](https://github.com/llamastack/llama-stack-client-python/commit/1287a3c11f668d916c8c7af534a48523e2e69140))
+* **tests:** skip some failing tests on the latest python versions ([73b5705](https://github.com/llamastack/llama-stack-client-python/commit/73b57051c48d2ec42b844a288ffc9b5e3bbe6f2b))
+* update SDK settings ([e54ba91](https://github.com/llamastack/llama-stack-client-python/commit/e54ba9163792ab80362a189acb825bcd00e5384b))
+
+
+### Documentation
+
+* **client:** fix httpx.Timeout documentation reference ([497f2a1](https://github.com/llamastack/llama-stack-client-python/commit/497f2a198140f73525a880497bf1c51b5749c1f3))
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
index 8e5d5903..e4d657d0 100644
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -17,8 +17,7 @@ $ rye sync --all-features
 You can then run scripts using `rye run python script.py` or by activating the virtual environment:
 
 ```sh
-$ rye shell
-# or manually activate - https://docs.python.org/3/library/venv.html#how-venvs-work
+# Activate the virtual environment - https://docs.python.org/3/library/venv.html#how-venvs-work
 $ source .venv/bin/activate
 
 # now you can omit the `rye run` prefix
@@ -63,7 +62,7 @@ If you’d like to use the repository from source, you can either install from g
 To install via git:
 
 ```sh
-$ pip install git+ssh://git@github.com/stainless-sdks/llama-stack-client-python.git
+$ pip install git+ssh://git@github.com/llamastack/llama-stack-client-python.git
 ```
 
 Alternatively, you can build from source and install the wheel file:
@@ -121,7 +120,7 @@ the changes aren't made through the automated pipeline, you may want to make rel
 
 ### Publish with a GitHub workflow
 
-You can release to package managers by using [the `Publish PyPI` GitHub action](https://www.github.com/stainless-sdks/llama-stack-client-python/actions/workflows/publish-pypi.yml). This requires a setup organization or repository secret to be set up.
+You can release to package managers by using [the `Publish PyPI` GitHub action](https://www.github.com/llamastack/llama-stack-client-python/actions/workflows/publish-pypi.yml). This requires a setup organization or repository secret to be set up.
 
 ### Publish manually
 
diff --git a/README.md b/README.md
index 745c0719..70a15cc6 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Llama Stack Client Python API library
 
-[![PyPI version](https://img.shields.io/pypi/v/llama_stack_client.svg)](https://pypi.org/project/llama_stack_client/)
+[![PyPI version](<https://img.shields.io/pypi/v/llama_stack_client.svg?label=pypi%20(stable)>)](https://pypi.org/project/llama_stack_client/)
 
 The Llama Stack Client Python library provides convenient access to the Llama Stack Client REST API from any Python 3.8+
 application. The library includes type definitions for all request params and response fields,
@@ -15,12 +15,12 @@ The full API of this library can be found in [api.md](api.md).
 ## Installation
 
 ```sh
-# install from this staging repo
-pip install git+ssh://git@github.com/stainless-sdks/llama-stack-client-python.git
+# install from the production repo
+pip install git+ssh://git@github.com/llamastack/llama-stack-client-python.git
 ```
 
 > [!NOTE]
-> Once this package is [published to PyPI](https://app.stainless.com/docs/guides/publish), this will become: `pip install --pre llama_stack_client`
+> Once this package is [published to PyPI](https://www.stainless.com/docs/guides/publish), this will become: `pip install --pre llama_stack_client`
 
 ## Usage
 
@@ -71,6 +71,42 @@ asyncio.run(main())
 
 Functionality between the synchronous and asynchronous clients is otherwise identical.
 
+### With aiohttp
+
+By default, the async client uses `httpx` for HTTP requests. However, for improved concurrency performance you may also use `aiohttp` as the HTTP backend.
+
+You can enable this by installing `aiohttp`:
+
+```sh
+# install from the production repo
+pip install 'llama_stack_client[aiohttp] @ git+ssh://git@github.com/llamastack/llama-stack-client-python.git'
+```
+
+Then you can enable it by instantiating the client with `http_client=DefaultAioHttpClient()`:
+
+```python
+import os
+import asyncio
+from llama_stack_client import DefaultAioHttpClient
+from llama_stack_client import AsyncLlamaStackClient
+
+
+async def main() -> None:
+    async with AsyncLlamaStackClient(
+        api_key=os.environ.get(
+            "LLAMA_STACK_CLIENT_API_KEY"
+        ),  # This is the default and can be omitted
+        http_client=DefaultAioHttpClient(),
+    ) as client:
+        await client.datasetio.append_rows(
+            dataset_id="REPLACE_ME",
+            rows=[{"foo": True}],
+        )
+
+
+asyncio.run(main())
+```
+
 ## Using types
 
 Nested request parameters are [TypedDicts](https://docs.python.org/3/library/typing.html#typing.TypedDict). Responses are [Pydantic models](https://docs.pydantic.dev) which also provide helper methods for things like:
@@ -99,7 +135,7 @@ response = client.inference.batch_chat_completion(
         ]
     ],
     model_id="model_id",
-    logprobs={"top_k": 0},
+    logprobs={},
 )
 print(response.logprobs)
 ```
@@ -175,7 +211,7 @@ client.with_options(max_retries=5).datasetio.append_rows(
 ### Timeouts
 
 By default requests time out after 1 minute. You can configure this with a `timeout` option,
-which accepts a float or an [`httpx.Timeout`](https://www.python-httpx.org/advanced/#fine-tuning-the-configuration) object:
+which accepts a float or an [`httpx.Timeout`](https://www.python-httpx.org/advanced/timeouts/#fine-tuning-the-configuration) object:
 
 ```python
 from llama_stack_client import LlamaStackClient
@@ -248,9 +284,9 @@ datasetio = response.parse()  # get the object that `datasetio.append_rows()` wo
 print(datasetio)
 ```
 
-These methods return an [`APIResponse`](https://github.com/stainless-sdks/llama-stack-client-python/tree/main/src/llama_stack_client/_response.py) object.
+These methods return an [`APIResponse`](https://github.com/llamastack/llama-stack-client-python/tree/main/src/llama_stack_client/_response.py) object.
 
-The async client returns an [`AsyncAPIResponse`](https://github.com/stainless-sdks/llama-stack-client-python/tree/main/src/llama_stack_client/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
+The async client returns an [`AsyncAPIResponse`](https://github.com/llamastack/llama-stack-client-python/tree/main/src/llama_stack_client/_response.py) with the same structure, the only difference being `await`able methods for reading the response content.
 
 #### `.with_streaming_response`
 
@@ -357,7 +393,7 @@ This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) con
 
 We take backwards-compatibility seriously and work hard to ensure you can rely on a smooth upgrade experience.
 
-We are keen for your feedback; please open an [issue](https://www.github.com/stainless-sdks/llama-stack-client-python/issues) with questions, bugs, or suggestions.
+We are keen for your feedback; please open an [issue](https://www.github.com/llamastack/llama-stack-client-python/issues) with questions, bugs, or suggestions.
 
 ### Determining the installed version
 
diff --git a/SECURITY.md b/SECURITY.md
index 5bbcc8f1..52ce19c1 100644
--- a/SECURITY.md
+++ b/SECURITY.md
@@ -16,7 +16,7 @@ before making any information public.
 ## Reporting Non-SDK Related Security Issues
 
 If you encounter security issues that are not directly related to SDKs but pertain to the services
-or products provided by Llama Stack Client please follow the respective company's security reporting guidelines.
+or products provided by Llama Stack Client, please follow the respective company's security reporting guidelines.
 
 ---
 
diff --git a/bin/check-release-environment b/bin/check-release-environment
new file mode 100644
index 00000000..b845b0f4
--- /dev/null
+++ b/bin/check-release-environment
@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+
+errors=()
+
+if [ -z "${PYPI_TOKEN}" ]; then
+  errors+=("The PYPI_TOKEN secret has not been set. Please set it in either this repository's secrets or your organization secrets.")
+fi
+
+lenErrors=${#errors[@]}
+
+if [[ lenErrors -gt 0 ]]; then
+  echo -e "Found the following errors in the release environment:\n"
+
+  for error in "${errors[@]}"; do
+    echo -e "- $error\n"
+  done
+
+  exit 1
+fi
+
+echo "The environment is ready to push releases!"
diff --git a/pyproject.toml b/pyproject.toml
index 34dbaa46..dc25fd75 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "llama_stack_client"
-version = "0.0.1-alpha.0"
+version = "0.1.0-alpha.1"
 description = "The official Python library for the llama-stack-client API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -34,9 +34,11 @@ classifiers = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/stainless-sdks/llama-stack-client-python"
-Repository = "https://github.com/stainless-sdks/llama-stack-client-python"
+Homepage = "https://github.com/llamastack/llama-stack-client-python"
+Repository = "https://github.com/llamastack/llama-stack-client-python"
 
+[project.optional-dependencies]
+aiohttp = ["aiohttp", "httpx_aiohttp>=0.1.6"]
 
 [tool.rye]
 managed = true
@@ -54,6 +56,7 @@ dev-dependencies = [
     "importlib-metadata>=6.7.0",
     "rich>=13.7.1",
     "nest_asyncio==1.6.0",
+    "pytest-xdist>=3.6.1",
 ]
 
 [tool.rye.scripts]
@@ -121,11 +124,11 @@ path = "README.md"
 [[tool.hatch.metadata.hooks.fancy-pypi-readme.substitutions]]
 # replace relative links with absolute links
 pattern = '\[(.+?)\]\(((?!https?://)\S+?)\)'
-replacement = '[\1](https://github.com/stainless-sdks/llama-stack-client-python/tree/main/\g<2>)'
+replacement = '[\1](https://github.com/llamastack/llama-stack-client-python/tree/main/\g<2>)'
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
-addopts = "--tb=short"
+addopts = "--tb=short -n auto"
 xfail_strict = true
 asyncio_mode = "auto"
 asyncio_default_fixture_loop_scope = "session"
diff --git a/release-please-config.json b/release-please-config.json
new file mode 100644
index 00000000..3602e961
--- /dev/null
+++ b/release-please-config.json
@@ -0,0 +1,66 @@
+{
+  "packages": {
+    ".": {}
+  },
+  "$schema": "https://raw.githubusercontent.com/stainless-api/release-please/main/schemas/config.json",
+  "include-v-in-tag": true,
+  "include-component-in-tag": false,
+  "versioning": "prerelease",
+  "prerelease": true,
+  "bump-minor-pre-major": true,
+  "bump-patch-for-minor-pre-major": false,
+  "pull-request-header": "Automated Release PR",
+  "pull-request-title-pattern": "release: ${version}",
+  "changelog-sections": [
+    {
+      "type": "feat",
+      "section": "Features"
+    },
+    {
+      "type": "fix",
+      "section": "Bug Fixes"
+    },
+    {
+      "type": "perf",
+      "section": "Performance Improvements"
+    },
+    {
+      "type": "revert",
+      "section": "Reverts"
+    },
+    {
+      "type": "chore",
+      "section": "Chores"
+    },
+    {
+      "type": "docs",
+      "section": "Documentation"
+    },
+    {
+      "type": "style",
+      "section": "Styles"
+    },
+    {
+      "type": "refactor",
+      "section": "Refactors"
+    },
+    {
+      "type": "test",
+      "section": "Tests",
+      "hidden": true
+    },
+    {
+      "type": "build",
+      "section": "Build System"
+    },
+    {
+      "type": "ci",
+      "section": "Continuous Integration",
+      "hidden": true
+    }
+  ],
+  "release-type": "python",
+  "extra-files": [
+    "src/llama_stack_client/_version.py"
+  ]
+}
\ No newline at end of file
diff --git a/requirements-dev.lock b/requirements-dev.lock
index 8c2e8e4d..869ac57f 100644
--- a/requirements-dev.lock
+++ b/requirements-dev.lock
@@ -10,6 +10,13 @@
 #   universal: false
 
 -e file:.
+aiohappyeyeballs==2.6.1
+    # via aiohttp
+aiohttp==3.12.8
+    # via httpx-aiohttp
+    # via llama-stack-client
+aiosignal==1.3.2
+    # via aiohttp
 annotated-types==0.6.0
     # via pydantic
 anyio==4.4.0
@@ -17,6 +24,10 @@ anyio==4.4.0
     # via llama-stack-client
 argcomplete==3.1.2
     # via nox
+async-timeout==5.0.1
+    # via aiohttp
+attrs==25.3.0
+    # via aiohttp
 certifi==2023.7.22
     # via httpcore
     # via httpx
@@ -30,18 +41,27 @@ distro==1.8.0
 exceptiongroup==1.2.2
     # via anyio
     # via pytest
+execnet==2.1.1
+    # via pytest-xdist
 filelock==3.12.4
     # via virtualenv
+frozenlist==1.6.2
+    # via aiohttp
+    # via aiosignal
 h11==0.14.0
     # via httpcore
 httpcore==1.0.2
     # via httpx
 httpx==0.28.1
+    # via httpx-aiohttp
     # via llama-stack-client
     # via respx
+httpx-aiohttp==0.1.6
+    # via llama-stack-client
 idna==3.4
     # via anyio
     # via httpx
+    # via yarl
 importlib-metadata==7.0.0
 iniconfig==2.0.0
     # via pytest
@@ -49,6 +69,9 @@ markdown-it-py==3.0.0
     # via rich
 mdurl==0.1.2
     # via markdown-it-py
+multidict==6.4.4
+    # via aiohttp
+    # via yarl
 mypy==1.14.1
 mypy-extensions==1.0.0
     # via mypy
@@ -63,6 +86,9 @@ platformdirs==3.11.0
     # via virtualenv
 pluggy==1.5.0
     # via pytest
+propcache==0.3.1
+    # via aiohttp
+    # via yarl
 pydantic==2.10.3
     # via llama-stack-client
 pydantic-core==2.27.1
@@ -72,7 +98,9 @@ pygments==2.18.0
 pyright==1.1.399
 pytest==8.3.3
     # via pytest-asyncio
+    # via pytest-xdist
 pytest-asyncio==0.24.0
+pytest-xdist==3.7.0
 python-dateutil==2.8.2
     # via time-machine
 pytz==2023.3.post1
@@ -94,11 +122,14 @@ tomli==2.0.2
 typing-extensions==4.12.2
     # via anyio
     # via llama-stack-client
+    # via multidict
     # via mypy
     # via pydantic
     # via pydantic-core
     # via pyright
 virtualenv==20.24.5
     # via nox
+yarl==1.20.0
+    # via aiohttp
 zipp==3.17.0
     # via importlib-metadata
diff --git a/requirements.lock b/requirements.lock
index d2711460..ac621298 100644
--- a/requirements.lock
+++ b/requirements.lock
@@ -10,11 +10,22 @@
 #   universal: false
 
 -e file:.
+aiohappyeyeballs==2.6.1
+    # via aiohttp
+aiohttp==3.12.8
+    # via httpx-aiohttp
+    # via llama-stack-client
+aiosignal==1.3.2
+    # via aiohttp
 annotated-types==0.6.0
     # via pydantic
 anyio==4.4.0
     # via httpx
     # via llama-stack-client
+async-timeout==5.0.1
+    # via aiohttp
+attrs==25.3.0
+    # via aiohttp
 certifi==2023.7.22
     # via httpcore
     # via httpx
@@ -22,15 +33,28 @@ distro==1.8.0
     # via llama-stack-client
 exceptiongroup==1.2.2
     # via anyio
+frozenlist==1.6.2
+    # via aiohttp
+    # via aiosignal
 h11==0.14.0
     # via httpcore
 httpcore==1.0.2
     # via httpx
 httpx==0.28.1
+    # via httpx-aiohttp
+    # via llama-stack-client
+httpx-aiohttp==0.1.6
     # via llama-stack-client
 idna==3.4
     # via anyio
     # via httpx
+    # via yarl
+multidict==6.4.4
+    # via aiohttp
+    # via yarl
+propcache==0.3.1
+    # via aiohttp
+    # via yarl
 pydantic==2.10.3
     # via llama-stack-client
 pydantic-core==2.27.1
@@ -41,5 +65,8 @@ sniffio==1.3.0
 typing-extensions==4.12.2
     # via anyio
     # via llama-stack-client
+    # via multidict
     # via pydantic
     # via pydantic-core
+yarl==1.20.0
+    # via aiohttp
diff --git a/scripts/utils/upload-artifact.sh b/scripts/utils/upload-artifact.sh
new file mode 100755
index 00000000..f6c7413b
--- /dev/null
+++ b/scripts/utils/upload-artifact.sh
@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+set -exuo pipefail
+
+RESPONSE=$(curl -X POST "$URL" \
+  -H "Authorization: Bearer $AUTH" \
+  -H "Content-Type: application/json")
+
+SIGNED_URL=$(echo "$RESPONSE" | jq -r '.url')
+
+if [[ "$SIGNED_URL" == "null" ]]; then
+  echo -e "\033[31mFailed to get signed URL.\033[0m"
+  exit 1
+fi
+
+UPLOAD_RESPONSE=$(tar -cz . | curl -v -X PUT \
+  -H "Content-Type: application/gzip" \
+  --data-binary @- "$SIGNED_URL" 2>&1)
+
+if echo "$UPLOAD_RESPONSE" | grep -q "HTTP/[0-9.]* 200"; then
+  echo -e "\033[32mUploaded build to Stainless storage.\033[0m"
+  echo -e "\033[32mInstallation: pip install --pre 'https://pkg.stainless.com/s/llama-stack-client-python/$SHA'\033[0m"
+else
+  echo -e "\033[31mFailed to upload artifact.\033[0m"
+  exit 1
+fi
diff --git a/src/llama_stack_client/__init__.py b/src/llama_stack_client/__init__.py
index 30e6e9cb..3c952a95 100644
--- a/src/llama_stack_client/__init__.py
+++ b/src/llama_stack_client/__init__.py
@@ -1,5 +1,7 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
+import typing as _t
+
 from . import types
 from ._types import NOT_GIVEN, Omit, NoneType, NotGiven, Transport, ProxiesTypes
 from ._utils import file_from_path
@@ -34,7 +36,7 @@
     UnprocessableEntityError,
     APIResponseValidationError,
 )
-from ._base_client import DefaultHttpxClient, DefaultAsyncHttpxClient
+from ._base_client import DefaultHttpxClient, DefaultAioHttpClient, DefaultAsyncHttpxClient
 from ._utils._logs import setup_logging as _setup_logging
 
 __all__ = [
@@ -76,8 +78,12 @@
     "DEFAULT_CONNECTION_LIMITS",
     "DefaultHttpxClient",
     "DefaultAsyncHttpxClient",
+    "DefaultAioHttpClient",
 ]
 
+if not _t.TYPE_CHECKING:
+    from ._utils._resources_proxy import resources as resources
+
 _setup_logging()
 
 # Update the __module__ attribute for exported symbols so that
diff --git a/src/llama_stack_client/_base_client.py b/src/llama_stack_client/_base_client.py
index a0c4ea5b..a0bbc468 100644
--- a/src/llama_stack_client/_base_client.py
+++ b/src/llama_stack_client/_base_client.py
@@ -960,6 +960,9 @@ def request(
             if self.custom_auth is not None:
                 kwargs["auth"] = self.custom_auth
 
+            if options.follow_redirects is not None:
+                kwargs["follow_redirects"] = options.follow_redirects
+
             log.debug("Sending HTTP Request: %s %s", request.method, request.url)
 
             response = None
@@ -1068,7 +1071,14 @@ def _process_response(
     ) -> ResponseT:
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, APIResponse):
                 raise TypeError(f"API Response types must subclass {APIResponse}; Received {origin}")
 
@@ -1279,6 +1289,24 @@ def __init__(self, **kwargs: Any) -> None:
         super().__init__(**kwargs)
 
 
+try:
+    import httpx_aiohttp
+except ImportError:
+
+    class _DefaultAioHttpClient(httpx.AsyncClient):
+        def __init__(self, **_kwargs: Any) -> None:
+            raise RuntimeError("To use the aiohttp client you must have installed the package with the `aiohttp` extra")
+else:
+
+    class _DefaultAioHttpClient(httpx_aiohttp.HttpxAiohttpClient):  # type: ignore
+        def __init__(self, **kwargs: Any) -> None:
+            kwargs.setdefault("timeout", DEFAULT_TIMEOUT)
+            kwargs.setdefault("limits", DEFAULT_CONNECTION_LIMITS)
+            kwargs.setdefault("follow_redirects", True)
+
+            super().__init__(**kwargs)
+
+
 if TYPE_CHECKING:
     DefaultAsyncHttpxClient = httpx.AsyncClient
     """An alias to `httpx.AsyncClient` that provides the same defaults that this SDK
@@ -1287,8 +1315,12 @@ def __init__(self, **kwargs: Any) -> None:
     This is useful because overriding the `http_client` with your own instance of
     `httpx.AsyncClient` will result in httpx's defaults being used, not ours.
     """
+
+    DefaultAioHttpClient = httpx.AsyncClient
+    """An alias to `httpx.AsyncClient` that changes the default HTTP transport to `aiohttp`."""
 else:
     DefaultAsyncHttpxClient = _DefaultAsyncHttpxClient
+    DefaultAioHttpClient = _DefaultAioHttpClient
 
 
 class AsyncHttpxClientWrapper(DefaultAsyncHttpxClient):
@@ -1460,6 +1492,9 @@ async def request(
             if self.custom_auth is not None:
                 kwargs["auth"] = self.custom_auth
 
+            if options.follow_redirects is not None:
+                kwargs["follow_redirects"] = options.follow_redirects
+
             log.debug("Sending HTTP Request: %s %s", request.method, request.url)
 
             response = None
@@ -1568,7 +1603,14 @@ async def _process_response(
     ) -> ResponseT:
         origin = get_origin(cast_to) or cast_to
 
-        if inspect.isclass(origin) and issubclass(origin, BaseAPIResponse):
+        if (
+            inspect.isclass(origin)
+            and issubclass(origin, BaseAPIResponse)
+            # we only want to actually return the custom BaseAPIResponse class if we're
+            # returning the raw response, or if we're not streaming SSE, as if we're streaming
+            # SSE then `cast_to` doesn't actively reflect the type we need to parse into
+            and (not stream or bool(response.request.headers.get(RAW_RESPONSE_HEADER)))
+        ):
             if not issubclass(origin, AsyncAPIResponse):
                 raise TypeError(f"API Response types must subclass {AsyncAPIResponse}; Received {origin}")
 
diff --git a/src/llama_stack_client/_models.py b/src/llama_stack_client/_models.py
index 798956f1..4f214980 100644
--- a/src/llama_stack_client/_models.py
+++ b/src/llama_stack_client/_models.py
@@ -737,6 +737,7 @@ class FinalRequestOptionsInput(TypedDict, total=False):
     idempotency_key: str
     json_data: Body
     extra_json: AnyMapping
+    follow_redirects: bool
 
 
 @final
@@ -750,6 +751,7 @@ class FinalRequestOptions(pydantic.BaseModel):
     files: Union[HttpxRequestFiles, None] = None
     idempotency_key: Union[str, None] = None
     post_parser: Union[Callable[[Any], Any], NotGiven] = NotGiven()
+    follow_redirects: Union[bool, None] = None
 
     # It should be noted that we cannot use `json` here as that would override
     # a BaseModel method in an incompatible fashion.
diff --git a/src/llama_stack_client/_types.py b/src/llama_stack_client/_types.py
index ed5b188d..63631322 100644
--- a/src/llama_stack_client/_types.py
+++ b/src/llama_stack_client/_types.py
@@ -100,6 +100,7 @@ class RequestOptions(TypedDict, total=False):
     params: Query
     extra_json: AnyMapping
     idempotency_key: str
+    follow_redirects: bool
 
 
 # Sentinel class used until PEP 0661 is accepted
@@ -215,3 +216,4 @@ class _GenericAlias(Protocol):
 
 class HttpxSendArgs(TypedDict, total=False):
     auth: httpx.Auth
+    follow_redirects: bool
diff --git a/src/llama_stack_client/_utils/_proxy.py b/src/llama_stack_client/_utils/_proxy.py
index ffd883e9..0f239a33 100644
--- a/src/llama_stack_client/_utils/_proxy.py
+++ b/src/llama_stack_client/_utils/_proxy.py
@@ -46,7 +46,10 @@ def __dir__(self) -> Iterable[str]:
     @property  # type: ignore
     @override
     def __class__(self) -> type:  # pyright: ignore
-        proxied = self.__get_proxied__()
+        try:
+            proxied = self.__get_proxied__()
+        except Exception:
+            return type(self)
         if issubclass(type(proxied), LazyProxy):
             return type(proxied)
         return proxied.__class__
diff --git a/src/llama_stack_client/_utils/_resources_proxy.py b/src/llama_stack_client/_utils/_resources_proxy.py
new file mode 100644
index 00000000..bf0a876a
--- /dev/null
+++ b/src/llama_stack_client/_utils/_resources_proxy.py
@@ -0,0 +1,24 @@
+from __future__ import annotations
+
+from typing import Any
+from typing_extensions import override
+
+from ._proxy import LazyProxy
+
+
+class ResourcesProxy(LazyProxy[Any]):
+    """A proxy for the `llama_stack_client.resources` module.
+
+    This is used so that we can lazily import `llama_stack_client.resources` only when
+    needed *and* so that users can just import `llama_stack_client` and reference `llama_stack_client.resources`
+    """
+
+    @override
+    def __load__(self) -> Any:
+        import importlib
+
+        mod = importlib.import_module("llama_stack_client.resources")
+        return mod
+
+
+resources = ResourcesProxy().__as_proxied__()
diff --git a/src/llama_stack_client/_version.py b/src/llama_stack_client/_version.py
index d4078242..3cd34bab 100644
--- a/src/llama_stack_client/_version.py
+++ b/src/llama_stack_client/_version.py
@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "llama_stack_client"
-__version__ = "0.0.1-alpha.0"
+__version__ = "0.1.0-alpha.1"  # x-release-please-version
diff --git a/src/llama_stack_client/resources/agents/agents.py b/src/llama_stack_client/resources/agents/agents.py
index ccc28bd5..cae1d400 100644
--- a/src/llama_stack_client/resources/agents/agents.py
+++ b/src/llama_stack_client/resources/agents/agents.py
@@ -44,7 +44,7 @@ def with_raw_response(self) -> AgentsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AgentsResourceWithRawResponse(self)
 
@@ -53,7 +53,7 @@ def with_streaming_response(self) -> AgentsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AgentsResourceWithStreamingResponse(self)
 
@@ -222,7 +222,7 @@ def with_raw_response(self) -> AsyncAgentsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncAgentsResourceWithRawResponse(self)
 
@@ -231,7 +231,7 @@ def with_streaming_response(self) -> AsyncAgentsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncAgentsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/agents/session/session.py b/src/llama_stack_client/resources/agents/session/session.py
index a88ccc2d..5298db2a 100644
--- a/src/llama_stack_client/resources/agents/session/session.py
+++ b/src/llama_stack_client/resources/agents/session/session.py
@@ -43,7 +43,7 @@ def with_raw_response(self) -> SessionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return SessionResourceWithRawResponse(self)
 
@@ -52,7 +52,7 @@ def with_streaming_response(self) -> SessionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return SessionResourceWithStreamingResponse(self)
 
@@ -185,7 +185,7 @@ def with_raw_response(self) -> AsyncSessionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncSessionResourceWithRawResponse(self)
 
@@ -194,7 +194,7 @@ def with_streaming_response(self) -> AsyncSessionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncSessionResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/agents/session/turn/step.py b/src/llama_stack_client/resources/agents/session/turn/step.py
index 18ba0cfd..cfbe35d9 100644
--- a/src/llama_stack_client/resources/agents/session/turn/step.py
+++ b/src/llama_stack_client/resources/agents/session/turn/step.py
@@ -26,7 +26,7 @@ def with_raw_response(self) -> StepResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return StepResourceWithRawResponse(self)
 
@@ -35,7 +35,7 @@ def with_streaming_response(self) -> StepResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return StepResourceWithStreamingResponse(self)
 
@@ -89,7 +89,7 @@ def with_raw_response(self) -> AsyncStepResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncStepResourceWithRawResponse(self)
 
@@ -98,7 +98,7 @@ def with_streaming_response(self) -> AsyncStepResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncStepResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/agents/session/turn/turn.py b/src/llama_stack_client/resources/agents/session/turn/turn.py
index d2423ba6..7649a060 100644
--- a/src/llama_stack_client/resources/agents/session/turn/turn.py
+++ b/src/llama_stack_client/resources/agents/session/turn/turn.py
@@ -45,7 +45,7 @@ def with_raw_response(self) -> TurnResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return TurnResourceWithRawResponse(self)
 
@@ -54,7 +54,7 @@ def with_streaming_response(self) -> TurnResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return TurnResourceWithStreamingResponse(self)
 
@@ -229,7 +229,7 @@ def with_raw_response(self) -> AsyncTurnResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncTurnResourceWithRawResponse(self)
 
@@ -238,7 +238,7 @@ def with_streaming_response(self) -> AsyncTurnResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncTurnResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/datasetio.py b/src/llama_stack_client/resources/datasetio.py
index 204c53e9..4117dfc4 100644
--- a/src/llama_stack_client/resources/datasetio.py
+++ b/src/llama_stack_client/resources/datasetio.py
@@ -30,7 +30,7 @@ def with_raw_response(self) -> DatasetioResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return DatasetioResourceWithRawResponse(self)
 
@@ -39,7 +39,7 @@ def with_streaming_response(self) -> DatasetioResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return DatasetioResourceWithStreamingResponse(self)
 
@@ -143,7 +143,7 @@ def with_raw_response(self) -> AsyncDatasetioResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncDatasetioResourceWithRawResponse(self)
 
@@ -152,7 +152,7 @@ def with_streaming_response(self) -> AsyncDatasetioResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncDatasetioResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/datasets.py b/src/llama_stack_client/resources/datasets.py
index 53440a24..826d7bb4 100644
--- a/src/llama_stack_client/resources/datasets.py
+++ b/src/llama_stack_client/resources/datasets.py
@@ -33,7 +33,7 @@ def with_raw_response(self) -> DatasetsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return DatasetsResourceWithRawResponse(self)
 
@@ -42,7 +42,7 @@ def with_streaming_response(self) -> DatasetsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return DatasetsResourceWithStreamingResponse(self)
 
@@ -204,7 +204,7 @@ def with_raw_response(self) -> AsyncDatasetsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncDatasetsResourceWithRawResponse(self)
 
@@ -213,7 +213,7 @@ def with_streaming_response(self) -> AsyncDatasetsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncDatasetsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/eval/benchmarks/benchmarks.py b/src/llama_stack_client/resources/eval/benchmarks/benchmarks.py
index 965137e1..b753f95a 100644
--- a/src/llama_stack_client/resources/eval/benchmarks/benchmarks.py
+++ b/src/llama_stack_client/resources/eval/benchmarks/benchmarks.py
@@ -45,7 +45,7 @@ def with_raw_response(self) -> BenchmarksResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return BenchmarksResourceWithRawResponse(self)
 
@@ -54,7 +54,7 @@ def with_streaming_response(self) -> BenchmarksResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return BenchmarksResourceWithStreamingResponse(self)
 
@@ -215,7 +215,7 @@ def with_raw_response(self) -> AsyncBenchmarksResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncBenchmarksResourceWithRawResponse(self)
 
@@ -224,7 +224,7 @@ def with_streaming_response(self) -> AsyncBenchmarksResourceWithStreamingRespons
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncBenchmarksResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/eval/benchmarks/jobs.py b/src/llama_stack_client/resources/eval/benchmarks/jobs.py
index eb5118e1..24edd80a 100644
--- a/src/llama_stack_client/resources/eval/benchmarks/jobs.py
+++ b/src/llama_stack_client/resources/eval/benchmarks/jobs.py
@@ -30,7 +30,7 @@ def with_raw_response(self) -> JobsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return JobsResourceWithRawResponse(self)
 
@@ -39,7 +39,7 @@ def with_streaming_response(self) -> JobsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return JobsResourceWithStreamingResponse(self)
 
@@ -197,7 +197,7 @@ def with_raw_response(self) -> AsyncJobsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncJobsResourceWithRawResponse(self)
 
@@ -206,7 +206,7 @@ def with_streaming_response(self) -> AsyncJobsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncJobsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/eval/eval.py b/src/llama_stack_client/resources/eval/eval.py
index d441e624..fb847c17 100644
--- a/src/llama_stack_client/resources/eval/eval.py
+++ b/src/llama_stack_client/resources/eval/eval.py
@@ -27,7 +27,7 @@ def with_raw_response(self) -> EvalResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return EvalResourceWithRawResponse(self)
 
@@ -36,7 +36,7 @@ def with_streaming_response(self) -> EvalResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return EvalResourceWithStreamingResponse(self)
 
@@ -52,7 +52,7 @@ def with_raw_response(self) -> AsyncEvalResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncEvalResourceWithRawResponse(self)
 
@@ -61,7 +61,7 @@ def with_streaming_response(self) -> AsyncEvalResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncEvalResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/files/files.py b/src/llama_stack_client/resources/files/files.py
index 1bda9e18..9ff01adb 100644
--- a/src/llama_stack_client/resources/files/files.py
+++ b/src/llama_stack_client/resources/files/files.py
@@ -43,7 +43,7 @@ def with_raw_response(self) -> FilesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return FilesResourceWithRawResponse(self)
 
@@ -52,7 +52,7 @@ def with_streaming_response(self) -> FilesResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return FilesResourceWithStreamingResponse(self)
 
@@ -260,7 +260,7 @@ def with_raw_response(self) -> AsyncFilesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncFilesResourceWithRawResponse(self)
 
@@ -269,7 +269,7 @@ def with_streaming_response(self) -> AsyncFilesResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncFilesResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/files/session.py b/src/llama_stack_client/resources/files/session.py
index 0fea6271..632aa5d2 100644
--- a/src/llama_stack_client/resources/files/session.py
+++ b/src/llama_stack_client/resources/files/session.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> SessionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return SessionResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> SessionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return SessionResourceWithStreamingResponse(self)
 
@@ -122,7 +122,7 @@ def with_raw_response(self) -> AsyncSessionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncSessionResourceWithRawResponse(self)
 
@@ -131,7 +131,7 @@ def with_streaming_response(self) -> AsyncSessionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncSessionResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/health.py b/src/llama_stack_client/resources/health.py
index 4d40dbc2..1c4cdecd 100644
--- a/src/llama_stack_client/resources/health.py
+++ b/src/llama_stack_client/resources/health.py
@@ -26,7 +26,7 @@ def with_raw_response(self) -> HealthResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return HealthResourceWithRawResponse(self)
 
@@ -35,7 +35,7 @@ def with_streaming_response(self) -> HealthResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return HealthResourceWithStreamingResponse(self)
 
@@ -65,7 +65,7 @@ def with_raw_response(self) -> AsyncHealthResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncHealthResourceWithRawResponse(self)
 
@@ -74,7 +74,7 @@ def with_streaming_response(self) -> AsyncHealthResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncHealthResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/inference.py b/src/llama_stack_client/resources/inference.py
index 932e202f..cd81d83b 100644
--- a/src/llama_stack_client/resources/inference.py
+++ b/src/llama_stack_client/resources/inference.py
@@ -48,7 +48,7 @@ def with_raw_response(self) -> InferenceResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return InferenceResourceWithRawResponse(self)
 
@@ -57,7 +57,7 @@ def with_streaming_response(self) -> InferenceResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return InferenceResourceWithStreamingResponse(self)
 
@@ -380,7 +380,7 @@ def with_raw_response(self) -> AsyncInferenceResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncInferenceResourceWithRawResponse(self)
 
@@ -389,7 +389,7 @@ def with_streaming_response(self) -> AsyncInferenceResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncInferenceResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/inspect.py b/src/llama_stack_client/resources/inspect.py
index 10a83b06..72f7b374 100644
--- a/src/llama_stack_client/resources/inspect.py
+++ b/src/llama_stack_client/resources/inspect.py
@@ -26,7 +26,7 @@ def with_raw_response(self) -> InspectResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return InspectResourceWithRawResponse(self)
 
@@ -35,7 +35,7 @@ def with_streaming_response(self) -> InspectResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return InspectResourceWithStreamingResponse(self)
 
@@ -65,7 +65,7 @@ def with_raw_response(self) -> AsyncInspectResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncInspectResourceWithRawResponse(self)
 
@@ -74,7 +74,7 @@ def with_streaming_response(self) -> AsyncInspectResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncInspectResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/models.py b/src/llama_stack_client/resources/models.py
index 55ddb52a..86862a7b 100644
--- a/src/llama_stack_client/resources/models.py
+++ b/src/llama_stack_client/resources/models.py
@@ -32,7 +32,7 @@ def with_raw_response(self) -> ModelsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ModelsResourceWithRawResponse(self)
 
@@ -41,7 +41,7 @@ def with_streaming_response(self) -> ModelsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ModelsResourceWithStreamingResponse(self)
 
@@ -177,7 +177,7 @@ def with_raw_response(self) -> AsyncModelsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncModelsResourceWithRawResponse(self)
 
@@ -186,7 +186,7 @@ def with_streaming_response(self) -> AsyncModelsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncModelsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/openai/openai.py b/src/llama_stack_client/resources/openai/openai.py
index f794e84c..e1900239 100644
--- a/src/llama_stack_client/resources/openai/openai.py
+++ b/src/llama_stack_client/resources/openai/openai.py
@@ -27,7 +27,7 @@ def with_raw_response(self) -> OpenAIResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return OpenAIResourceWithRawResponse(self)
 
@@ -36,7 +36,7 @@ def with_streaming_response(self) -> OpenAIResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return OpenAIResourceWithStreamingResponse(self)
 
@@ -52,7 +52,7 @@ def with_raw_response(self) -> AsyncOpenAIResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncOpenAIResourceWithRawResponse(self)
 
@@ -61,7 +61,7 @@ def with_streaming_response(self) -> AsyncOpenAIResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncOpenAIResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/openai/v1/chat.py b/src/llama_stack_client/resources/openai/v1/chat.py
index c94cfd53..00332b34 100644
--- a/src/llama_stack_client/resources/openai/v1/chat.py
+++ b/src/llama_stack_client/resources/openai/v1/chat.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> ChatResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ChatResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> ChatResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ChatResourceWithStreamingResponse(self)
 
@@ -188,7 +188,7 @@ def with_raw_response(self) -> AsyncChatResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncChatResourceWithRawResponse(self)
 
@@ -197,7 +197,7 @@ def with_streaming_response(self) -> AsyncChatResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncChatResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/openai/v1/responses.py b/src/llama_stack_client/resources/openai/v1/responses.py
index a51a0154..052e1ed1 100644
--- a/src/llama_stack_client/resources/openai/v1/responses.py
+++ b/src/llama_stack_client/resources/openai/v1/responses.py
@@ -30,7 +30,7 @@ def with_raw_response(self) -> ResponsesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ResponsesResourceWithRawResponse(self)
 
@@ -39,7 +39,7 @@ def with_streaming_response(self) -> ResponsesResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ResponsesResourceWithStreamingResponse(self)
 
@@ -141,7 +141,7 @@ def with_raw_response(self) -> AsyncResponsesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncResponsesResourceWithRawResponse(self)
 
@@ -150,7 +150,7 @@ def with_streaming_response(self) -> AsyncResponsesResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncResponsesResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/openai/v1/v1.py b/src/llama_stack_client/resources/openai/v1/v1.py
index cabf4c9d..30af7bad 100644
--- a/src/llama_stack_client/resources/openai/v1/v1.py
+++ b/src/llama_stack_client/resources/openai/v1/v1.py
@@ -55,7 +55,7 @@ def with_raw_response(self) -> V1ResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return V1ResourceWithRawResponse(self)
 
@@ -64,7 +64,7 @@ def with_streaming_response(self) -> V1ResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return V1ResourceWithStreamingResponse(self)
 
@@ -211,7 +211,7 @@ def with_raw_response(self) -> AsyncV1ResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncV1ResourceWithRawResponse(self)
 
@@ -220,7 +220,7 @@ def with_streaming_response(self) -> AsyncV1ResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncV1ResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/post_training/job.py b/src/llama_stack_client/resources/post_training/job.py
index 945d02f5..76ff806e 100644
--- a/src/llama_stack_client/resources/post_training/job.py
+++ b/src/llama_stack_client/resources/post_training/job.py
@@ -29,7 +29,7 @@ def with_raw_response(self) -> JobResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return JobResourceWithRawResponse(self)
 
@@ -38,7 +38,7 @@ def with_streaming_response(self) -> JobResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return JobResourceWithStreamingResponse(self)
 
@@ -147,7 +147,7 @@ def with_raw_response(self) -> AsyncJobResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncJobResourceWithRawResponse(self)
 
@@ -156,7 +156,7 @@ def with_streaming_response(self) -> AsyncJobResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncJobResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/post_training/post_training.py b/src/llama_stack_client/resources/post_training/post_training.py
index 91612810..1a43a68c 100644
--- a/src/llama_stack_client/resources/post_training/post_training.py
+++ b/src/llama_stack_client/resources/post_training/post_training.py
@@ -47,7 +47,7 @@ def with_raw_response(self) -> PostTrainingResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return PostTrainingResourceWithRawResponse(self)
 
@@ -56,7 +56,7 @@ def with_streaming_response(self) -> PostTrainingResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return PostTrainingResourceWithStreamingResponse(self)
 
@@ -182,7 +182,7 @@ def with_raw_response(self) -> AsyncPostTrainingResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncPostTrainingResourceWithRawResponse(self)
 
@@ -191,7 +191,7 @@ def with_streaming_response(self) -> AsyncPostTrainingResourceWithStreamingRespo
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncPostTrainingResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/providers.py b/src/llama_stack_client/resources/providers.py
index 5936d6b0..96feebcb 100644
--- a/src/llama_stack_client/resources/providers.py
+++ b/src/llama_stack_client/resources/providers.py
@@ -27,7 +27,7 @@ def with_raw_response(self) -> ProvidersResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ProvidersResourceWithRawResponse(self)
 
@@ -36,7 +36,7 @@ def with_streaming_response(self) -> ProvidersResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ProvidersResourceWithStreamingResponse(self)
 
@@ -97,7 +97,7 @@ def with_raw_response(self) -> AsyncProvidersResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncProvidersResourceWithRawResponse(self)
 
@@ -106,7 +106,7 @@ def with_streaming_response(self) -> AsyncProvidersResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncProvidersResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/safety.py b/src/llama_stack_client/resources/safety.py
index 77df2f6d..c6ed1ad9 100644
--- a/src/llama_stack_client/resources/safety.py
+++ b/src/llama_stack_client/resources/safety.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> SafetyResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return SafetyResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> SafetyResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return SafetyResourceWithStreamingResponse(self)
 
@@ -91,7 +91,7 @@ def with_raw_response(self) -> AsyncSafetyResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncSafetyResourceWithRawResponse(self)
 
@@ -100,7 +100,7 @@ def with_streaming_response(self) -> AsyncSafetyResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncSafetyResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/scoring.py b/src/llama_stack_client/resources/scoring.py
index 2e7fea47..ee345778 100644
--- a/src/llama_stack_client/resources/scoring.py
+++ b/src/llama_stack_client/resources/scoring.py
@@ -32,7 +32,7 @@ def with_raw_response(self) -> ScoringResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ScoringResourceWithRawResponse(self)
 
@@ -41,7 +41,7 @@ def with_streaming_response(self) -> ScoringResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ScoringResourceWithStreamingResponse(self)
 
@@ -135,7 +135,7 @@ def with_raw_response(self) -> AsyncScoringResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncScoringResourceWithRawResponse(self)
 
@@ -144,7 +144,7 @@ def with_streaming_response(self) -> AsyncScoringResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncScoringResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/scoring_functions.py b/src/llama_stack_client/resources/scoring_functions.py
index 3acacab1..e6e910b0 100644
--- a/src/llama_stack_client/resources/scoring_functions.py
+++ b/src/llama_stack_client/resources/scoring_functions.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> ScoringFunctionsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ScoringFunctionsResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> ScoringFunctionsResourceWithStreamingRespon
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ScoringFunctionsResourceWithStreamingResponse(self)
 
@@ -147,7 +147,7 @@ def with_raw_response(self) -> AsyncScoringFunctionsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncScoringFunctionsResourceWithRawResponse(self)
 
@@ -156,7 +156,7 @@ def with_streaming_response(self) -> AsyncScoringFunctionsResourceWithStreamingR
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncScoringFunctionsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/shields.py b/src/llama_stack_client/resources/shields.py
index 5c116691..2f75a8a9 100644
--- a/src/llama_stack_client/resources/shields.py
+++ b/src/llama_stack_client/resources/shields.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> ShieldsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ShieldsResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> ShieldsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ShieldsResourceWithStreamingResponse(self)
 
@@ -142,7 +142,7 @@ def with_raw_response(self) -> AsyncShieldsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncShieldsResourceWithRawResponse(self)
 
@@ -151,7 +151,7 @@ def with_streaming_response(self) -> AsyncShieldsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncShieldsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/synthetic_data_generation.py b/src/llama_stack_client/resources/synthetic_data_generation.py
index 07109275..b05627f9 100644
--- a/src/llama_stack_client/resources/synthetic_data_generation.py
+++ b/src/llama_stack_client/resources/synthetic_data_generation.py
@@ -32,7 +32,7 @@ def with_raw_response(self) -> SyntheticDataGenerationResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return SyntheticDataGenerationResourceWithRawResponse(self)
 
@@ -41,7 +41,7 @@ def with_streaming_response(self) -> SyntheticDataGenerationResourceWithStreamin
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return SyntheticDataGenerationResourceWithStreamingResponse(self)
 
@@ -94,7 +94,7 @@ def with_raw_response(self) -> AsyncSyntheticDataGenerationResourceWithRawRespon
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncSyntheticDataGenerationResourceWithRawResponse(self)
 
@@ -103,7 +103,7 @@ def with_streaming_response(self) -> AsyncSyntheticDataGenerationResourceWithStr
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncSyntheticDataGenerationResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/telemetry/spans.py b/src/llama_stack_client/resources/telemetry/spans.py
index 5b84f666..9f6bb681 100644
--- a/src/llama_stack_client/resources/telemetry/spans.py
+++ b/src/llama_stack_client/resources/telemetry/spans.py
@@ -32,7 +32,7 @@ def with_raw_response(self) -> SpansResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return SpansResourceWithRawResponse(self)
 
@@ -41,7 +41,7 @@ def with_streaming_response(self) -> SpansResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return SpansResourceWithStreamingResponse(self)
 
@@ -174,7 +174,7 @@ def with_raw_response(self) -> AsyncSpansResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncSpansResourceWithRawResponse(self)
 
@@ -183,7 +183,7 @@ def with_streaming_response(self) -> AsyncSpansResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncSpansResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/telemetry/telemetry.py b/src/llama_stack_client/resources/telemetry/telemetry.py
index 1dc60da3..018b6b96 100644
--- a/src/llama_stack_client/resources/telemetry/telemetry.py
+++ b/src/llama_stack_client/resources/telemetry/telemetry.py
@@ -51,7 +51,7 @@ def with_raw_response(self) -> TelemetryResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return TelemetryResourceWithRawResponse(self)
 
@@ -60,7 +60,7 @@ def with_streaming_response(self) -> TelemetryResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return TelemetryResourceWithStreamingResponse(self)
 
@@ -118,7 +118,7 @@ def with_raw_response(self) -> AsyncTelemetryResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncTelemetryResourceWithRawResponse(self)
 
@@ -127,7 +127,7 @@ def with_streaming_response(self) -> AsyncTelemetryResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncTelemetryResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/telemetry/traces.py b/src/llama_stack_client/resources/telemetry/traces.py
index 17c26ba3..af5d7885 100644
--- a/src/llama_stack_client/resources/telemetry/traces.py
+++ b/src/llama_stack_client/resources/telemetry/traces.py
@@ -33,7 +33,7 @@ def with_raw_response(self) -> TracesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return TracesResourceWithRawResponse(self)
 
@@ -42,7 +42,7 @@ def with_streaming_response(self) -> TracesResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return TracesResourceWithStreamingResponse(self)
 
@@ -160,7 +160,7 @@ def with_raw_response(self) -> AsyncTracesResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncTracesResourceWithRawResponse(self)
 
@@ -169,7 +169,7 @@ def with_streaming_response(self) -> AsyncTracesResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncTracesResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/tool_runtime/rag_tool.py b/src/llama_stack_client/resources/tool_runtime/rag_tool.py
index 347972ac..b9f9a0f0 100644
--- a/src/llama_stack_client/resources/tool_runtime/rag_tool.py
+++ b/src/llama_stack_client/resources/tool_runtime/rag_tool.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> RagToolResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return RagToolResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> RagToolResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return RagToolResourceWithStreamingResponse(self)
 
@@ -137,7 +137,7 @@ def with_raw_response(self) -> AsyncRagToolResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncRagToolResourceWithRawResponse(self)
 
@@ -146,7 +146,7 @@ def with_streaming_response(self) -> AsyncRagToolResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncRagToolResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/tool_runtime/tool_runtime.py b/src/llama_stack_client/resources/tool_runtime/tool_runtime.py
index 9d5afe82..92af76ef 100644
--- a/src/llama_stack_client/resources/tool_runtime/tool_runtime.py
+++ b/src/llama_stack_client/resources/tool_runtime/tool_runtime.py
@@ -44,7 +44,7 @@ def with_raw_response(self) -> ToolRuntimeResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ToolRuntimeResourceWithRawResponse(self)
 
@@ -53,7 +53,7 @@ def with_streaming_response(self) -> ToolRuntimeResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ToolRuntimeResourceWithStreamingResponse(self)
 
@@ -148,7 +148,7 @@ def with_raw_response(self) -> AsyncToolRuntimeResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncToolRuntimeResourceWithRawResponse(self)
 
@@ -157,7 +157,7 @@ def with_streaming_response(self) -> AsyncToolRuntimeResourceWithStreamingRespon
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncToolRuntimeResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/toolgroups.py b/src/llama_stack_client/resources/toolgroups.py
index 4fb15858..a34c5f14 100644
--- a/src/llama_stack_client/resources/toolgroups.py
+++ b/src/llama_stack_client/resources/toolgroups.py
@@ -32,7 +32,7 @@ def with_raw_response(self) -> ToolgroupsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ToolgroupsResourceWithRawResponse(self)
 
@@ -41,7 +41,7 @@ def with_streaming_response(self) -> ToolgroupsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ToolgroupsResourceWithStreamingResponse(self)
 
@@ -181,7 +181,7 @@ def with_raw_response(self) -> AsyncToolgroupsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncToolgroupsResourceWithRawResponse(self)
 
@@ -190,7 +190,7 @@ def with_streaming_response(self) -> AsyncToolgroupsResourceWithStreamingRespons
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncToolgroupsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/tools.py b/src/llama_stack_client/resources/tools.py
index 9c161451..9cc02e12 100644
--- a/src/llama_stack_client/resources/tools.py
+++ b/src/llama_stack_client/resources/tools.py
@@ -29,7 +29,7 @@ def with_raw_response(self) -> ToolsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return ToolsResourceWithRawResponse(self)
 
@@ -38,7 +38,7 @@ def with_streaming_response(self) -> ToolsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return ToolsResourceWithStreamingResponse(self)
 
@@ -116,7 +116,7 @@ def with_raw_response(self) -> AsyncToolsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncToolsResourceWithRawResponse(self)
 
@@ -125,7 +125,7 @@ def with_streaming_response(self) -> AsyncToolsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncToolsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/vector_dbs.py b/src/llama_stack_client/resources/vector_dbs.py
index 008102a4..dfc683a9 100644
--- a/src/llama_stack_client/resources/vector_dbs.py
+++ b/src/llama_stack_client/resources/vector_dbs.py
@@ -29,7 +29,7 @@ def with_raw_response(self) -> VectorDBsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return VectorDBsResourceWithRawResponse(self)
 
@@ -38,7 +38,7 @@ def with_streaming_response(self) -> VectorDBsResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return VectorDBsResourceWithStreamingResponse(self)
 
@@ -174,7 +174,7 @@ def with_raw_response(self) -> AsyncVectorDBsResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncVectorDBsResourceWithRawResponse(self)
 
@@ -183,7 +183,7 @@ def with_streaming_response(self) -> AsyncVectorDBsResourceWithStreamingResponse
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncVectorDBsResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/vector_io.py b/src/llama_stack_client/resources/vector_io.py
index cb3f5768..1bf62bc3 100644
--- a/src/llama_stack_client/resources/vector_io.py
+++ b/src/llama_stack_client/resources/vector_io.py
@@ -31,7 +31,7 @@ def with_raw_response(self) -> VectorIoResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return VectorIoResourceWithRawResponse(self)
 
@@ -40,7 +40,7 @@ def with_streaming_response(self) -> VectorIoResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return VectorIoResourceWithStreamingResponse(self)
 
@@ -133,7 +133,7 @@ def with_raw_response(self) -> AsyncVectorIoResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncVectorIoResourceWithRawResponse(self)
 
@@ -142,7 +142,7 @@ def with_streaming_response(self) -> AsyncVectorIoResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncVectorIoResourceWithStreamingResponse(self)
 
diff --git a/src/llama_stack_client/resources/version.py b/src/llama_stack_client/resources/version.py
index 70234826..391b5ed2 100644
--- a/src/llama_stack_client/resources/version.py
+++ b/src/llama_stack_client/resources/version.py
@@ -26,7 +26,7 @@ def with_raw_response(self) -> VersionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return VersionResourceWithRawResponse(self)
 
@@ -35,7 +35,7 @@ def with_streaming_response(self) -> VersionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return VersionResourceWithStreamingResponse(self)
 
@@ -65,7 +65,7 @@ def with_raw_response(self) -> AsyncVersionResourceWithRawResponse:
         This property can be used as a prefix for any HTTP method call to return
         the raw response object instead of the parsed content.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#accessing-raw-response-data-eg-headers
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#accessing-raw-response-data-eg-headers
         """
         return AsyncVersionResourceWithRawResponse(self)
 
@@ -74,7 +74,7 @@ def with_streaming_response(self) -> AsyncVersionResourceWithStreamingResponse:
         """
         An alternative to `.with_raw_response` that doesn't eagerly read the response body.
 
-        For more information, see https://www.github.com/stainless-sdks/llama-stack-client-python#with_streaming_response
+        For more information, see https://www.github.com/llamastack/llama-stack-client-python#with_streaming_response
         """
         return AsyncVersionResourceWithStreamingResponse(self)
 
diff --git a/tests/api_resources/agents/session/test_turn.py b/tests/api_resources/agents/session/test_turn.py
index 6c89efc6..4f56eee8 100644
--- a/tests/api_resources/agents/session/test_turn.py
+++ b/tests/api_resources/agents/session/test_turn.py
@@ -319,7 +319,9 @@ def test_path_params_resume(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncTurn:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/agents/session/turn/test_step.py b/tests/api_resources/agents/session/turn/test_step.py
index 7ef9e200..b847f4c3 100644
--- a/tests/api_resources/agents/session/turn/test_step.py
+++ b/tests/api_resources/agents/session/turn/test_step.py
@@ -97,7 +97,9 @@ def test_path_params_retrieve(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncStep:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/agents/test_session.py b/tests/api_resources/agents/test_session.py
index 7efd0b41..79b6673e 100644
--- a/tests/api_resources/agents/test_session.py
+++ b/tests/api_resources/agents/test_session.py
@@ -180,7 +180,9 @@ def test_path_params_delete(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncSession:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/eval/benchmarks/test_jobs.py b/tests/api_resources/eval/benchmarks/test_jobs.py
index 984cd704..41c7302e 100644
--- a/tests/api_resources/eval/benchmarks/test_jobs.py
+++ b/tests/api_resources/eval/benchmarks/test_jobs.py
@@ -312,7 +312,9 @@ def test_path_params_run(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncJobs:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/eval/test_benchmarks.py b/tests/api_resources/eval/test_benchmarks.py
index 6cefaf46..338c31ad 100644
--- a/tests/api_resources/eval/test_benchmarks.py
+++ b/tests/api_resources/eval/test_benchmarks.py
@@ -292,7 +292,9 @@ def test_path_params_evaluate(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncBenchmarks:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/files/test_session.py b/tests/api_resources/files/test_session.py
index 3951efff..618e7e2a 100644
--- a/tests/api_resources/files/test_session.py
+++ b/tests/api_resources/files/test_session.py
@@ -107,7 +107,9 @@ def test_path_params_upload_content(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncSession:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/openai/test_v1.py b/tests/api_resources/openai/test_v1.py
index 3df65f6e..2b7b722e 100644
--- a/tests/api_resources/openai/test_v1.py
+++ b/tests/api_resources/openai/test_v1.py
@@ -113,7 +113,9 @@ def test_streaming_response_list_models(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncV1:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/openai/v1/test_chat.py b/tests/api_resources/openai/v1/test_chat.py
index b3cb940a..3baa1df8 100644
--- a/tests/api_resources/openai/v1/test_chat.py
+++ b/tests/api_resources/openai/v1/test_chat.py
@@ -107,7 +107,9 @@ def test_streaming_response_generate_completion(self, client: LlamaStackClient)
 
 
 class TestAsyncChat:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/openai/v1/test_responses.py b/tests/api_resources/openai/v1/test_responses.py
index 5ae4d001..72a7cd1d 100644
--- a/tests/api_resources/openai/v1/test_responses.py
+++ b/tests/api_resources/openai/v1/test_responses.py
@@ -117,7 +117,9 @@ def test_path_params_retrieve(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncResponses:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/post_training/test_job.py b/tests/api_resources/post_training/test_job.py
index 4fb2dccb..5b9ea28e 100644
--- a/tests/api_resources/post_training/test_job.py
+++ b/tests/api_resources/post_training/test_job.py
@@ -124,7 +124,9 @@ def test_streaming_response_retrieve_status(self, client: LlamaStackClient) -> N
 
 
 class TestAsyncJob:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/telemetry/test_spans.py b/tests/api_resources/telemetry/test_spans.py
index 84a70ef1..5982a183 100644
--- a/tests/api_resources/telemetry/test_spans.py
+++ b/tests/api_resources/telemetry/test_spans.py
@@ -220,7 +220,9 @@ def test_streaming_response_export(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncSpans:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/telemetry/test_traces.py b/tests/api_resources/telemetry/test_traces.py
index ec95822f..7406a801 100644
--- a/tests/api_resources/telemetry/test_traces.py
+++ b/tests/api_resources/telemetry/test_traces.py
@@ -158,7 +158,9 @@ def test_path_params_retrieve_trace(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncTraces:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_agents.py b/tests/api_resources/test_agents.py
index a6b1e33e..db65ed56 100644
--- a/tests/api_resources/test_agents.py
+++ b/tests/api_resources/test_agents.py
@@ -271,7 +271,9 @@ def test_path_params_list_sessions(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncAgents:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_datasetio.py b/tests/api_resources/test_datasetio.py
index 4f38eb3b..9130b380 100644
--- a/tests/api_resources/test_datasetio.py
+++ b/tests/api_resources/test_datasetio.py
@@ -119,7 +119,9 @@ def test_path_params_iterate_rows(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncDatasetio:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_datasets.py b/tests/api_resources/test_datasets.py
index 668f3e0b..30df5161 100644
--- a/tests/api_resources/test_datasets.py
+++ b/tests/api_resources/test_datasets.py
@@ -191,7 +191,9 @@ def test_path_params_delete(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncDatasets:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_files.py b/tests/api_resources/test_files.py
index 6ea7652f..e28e3353 100644
--- a/tests/api_resources/test_files.py
+++ b/tests/api_resources/test_files.py
@@ -247,7 +247,9 @@ def test_path_params_list_in_bucket(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncFiles:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_health.py b/tests/api_resources/test_health.py
index 16175743..cd820405 100644
--- a/tests/api_resources/test_health.py
+++ b/tests/api_resources/test_health.py
@@ -47,7 +47,9 @@ def test_streaming_response_check(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncHealth:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_inference.py b/tests/api_resources/test_inference.py
index 47ea2b95..bcd63c8b 100644
--- a/tests/api_resources/test_inference.py
+++ b/tests/api_resources/test_inference.py
@@ -394,7 +394,9 @@ def test_streaming_response_embeddings(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncInference:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_inspect.py b/tests/api_resources/test_inspect.py
index e4b7f30f..6e5d8669 100644
--- a/tests/api_resources/test_inspect.py
+++ b/tests/api_resources/test_inspect.py
@@ -47,7 +47,9 @@ def test_streaming_response_list_routes(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncInspect:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_models.py b/tests/api_resources/test_models.py
index 2017423d..d2476ca4 100644
--- a/tests/api_resources/test_models.py
+++ b/tests/api_resources/test_models.py
@@ -177,7 +177,9 @@ def test_path_params_delete(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncModels:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_post_training.py b/tests/api_resources/test_post_training.py
index 0692c60a..c6441dc9 100644
--- a/tests/api_resources/test_post_training.py
+++ b/tests/api_resources/test_post_training.py
@@ -276,7 +276,9 @@ def test_streaming_response_optimize_preferences(self, client: LlamaStackClient)
 
 
 class TestAsyncPostTraining:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_providers.py b/tests/api_resources/test_providers.py
index fb9c92ba..8870e4de 100644
--- a/tests/api_resources/test_providers.py
+++ b/tests/api_resources/test_providers.py
@@ -89,7 +89,9 @@ def test_streaming_response_list(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncProviders:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_safety.py b/tests/api_resources/test_safety.py
index 568733d6..49e9edfb 100644
--- a/tests/api_resources/test_safety.py
+++ b/tests/api_resources/test_safety.py
@@ -74,7 +74,9 @@ def test_streaming_response_run_shield(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncSafety:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_scoring.py b/tests/api_resources/test_scoring.py
index 1e36d526..122dddab 100644
--- a/tests/api_resources/test_scoring.py
+++ b/tests/api_resources/test_scoring.py
@@ -141,7 +141,9 @@ def test_streaming_response_score_batch(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncScoring:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_scoring_functions.py b/tests/api_resources/test_scoring_functions.py
index 38aa98bf..82628084 100644
--- a/tests/api_resources/test_scoring_functions.py
+++ b/tests/api_resources/test_scoring_functions.py
@@ -151,7 +151,9 @@ def test_streaming_response_list(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncScoringFunctions:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_shields.py b/tests/api_resources/test_shields.py
index b352a607..7b5ae969 100644
--- a/tests/api_resources/test_shields.py
+++ b/tests/api_resources/test_shields.py
@@ -134,7 +134,9 @@ def test_streaming_response_list(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncShields:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_synthetic_data_generation.py b/tests/api_resources/test_synthetic_data_generation.py
index 13374ac1..fc9c0398 100644
--- a/tests/api_resources/test_synthetic_data_generation.py
+++ b/tests/api_resources/test_synthetic_data_generation.py
@@ -87,7 +87,9 @@ def test_streaming_response_generate(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncSyntheticDataGeneration:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_telemetry.py b/tests/api_resources/test_telemetry.py
index 688a7724..3d8abd29 100644
--- a/tests/api_resources/test_telemetry.py
+++ b/tests/api_resources/test_telemetry.py
@@ -93,7 +93,9 @@ def test_streaming_response_create_event(self, client: LlamaStackClient) -> None
 
 
 class TestAsyncTelemetry:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_tool_runtime.py b/tests/api_resources/test_tool_runtime.py
index b66a378f..7bccfafe 100644
--- a/tests/api_resources/test_tool_runtime.py
+++ b/tests/api_resources/test_tool_runtime.py
@@ -96,7 +96,9 @@ def test_streaming_response_list_tools(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncToolRuntime:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_toolgroups.py b/tests/api_resources/test_toolgroups.py
index ffb342f0..11f9e3ac 100644
--- a/tests/api_resources/test_toolgroups.py
+++ b/tests/api_resources/test_toolgroups.py
@@ -179,7 +179,9 @@ def test_path_params_unregister(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncToolgroups:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_tools.py b/tests/api_resources/test_tools.py
index ce9e3f10..e6d8408e 100644
--- a/tests/api_resources/test_tools.py
+++ b/tests/api_resources/test_tools.py
@@ -97,7 +97,9 @@ def test_streaming_response_list(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncTools:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_vector_dbs.py b/tests/api_resources/test_vector_dbs.py
index 5b7ddd2c..dfad4a3a 100644
--- a/tests/api_resources/test_vector_dbs.py
+++ b/tests/api_resources/test_vector_dbs.py
@@ -180,7 +180,9 @@ def test_path_params_delete(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncVectorDBs:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_vector_io.py b/tests/api_resources/test_vector_io.py
index 4c3f0a8b..d06a3664 100644
--- a/tests/api_resources/test_vector_io.py
+++ b/tests/api_resources/test_vector_io.py
@@ -135,7 +135,9 @@ def test_streaming_response_query(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncVectorIo:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/test_version.py b/tests/api_resources/test_version.py
index fcd975e8..3863855f 100644
--- a/tests/api_resources/test_version.py
+++ b/tests/api_resources/test_version.py
@@ -47,7 +47,9 @@ def test_streaming_response_retrieve(self, client: LlamaStackClient) -> None:
 
 
 class TestAsyncVersion:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/api_resources/tool_runtime/test_rag_tool.py b/tests/api_resources/tool_runtime/test_rag_tool.py
index 6c1eda4e..2599886a 100644
--- a/tests/api_resources/tool_runtime/test_rag_tool.py
+++ b/tests/api_resources/tool_runtime/test_rag_tool.py
@@ -133,7 +133,9 @@ def test_streaming_response_query_context(self, client: LlamaStackClient) -> Non
 
 
 class TestAsyncRagTool:
-    parametrize = pytest.mark.parametrize("async_client", [False, True], indirect=True, ids=["loose", "strict"])
+    parametrize = pytest.mark.parametrize(
+        "async_client", [False, True, {"http_client": "aiohttp"}], indirect=True, ids=["loose", "strict", "aiohttp"]
+    )
 
     @pytest.mark.skip()
     @parametrize
diff --git a/tests/conftest.py b/tests/conftest.py
index d40bf410..054ff89e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,13 +1,17 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
 from __future__ import annotations
 
 import os
 import logging
 from typing import TYPE_CHECKING, Iterator, AsyncIterator
 
+import httpx
 import pytest
 from pytest_asyncio import is_async_test
 
-from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient
+from llama_stack_client import LlamaStackClient, DefaultAioHttpClient, AsyncLlamaStackClient
+from llama_stack_client._utils import is_dict
 
 if TYPE_CHECKING:
     from _pytest.fixtures import FixtureRequest  # pyright: ignore[reportPrivateImportUsage]
@@ -25,6 +29,19 @@ def pytest_collection_modifyitems(items: list[pytest.Function]) -> None:
     for async_test in pytest_asyncio_tests:
         async_test.add_marker(session_scope_marker, append=False)
 
+    # We skip tests that use both the aiohttp client and respx_mock as respx_mock
+    # doesn't support custom transports.
+    for item in items:
+        if "async_client" not in item.fixturenames or "respx_mock" not in item.fixturenames:
+            continue
+
+        if not hasattr(item, "callspec"):
+            continue
+
+        async_client_param = item.callspec.params.get("async_client")
+        if is_dict(async_client_param) and async_client_param.get("http_client") == "aiohttp":
+            item.add_marker(pytest.mark.skip(reason="aiohttp client is not compatible with respx_mock"))
+
 
 base_url = os.environ.get("TEST_API_BASE_URL", "http://127.0.0.1:4010")
 
@@ -43,9 +60,25 @@ def client(request: FixtureRequest) -> Iterator[LlamaStackClient]:
 
 @pytest.fixture(scope="session")
 async def async_client(request: FixtureRequest) -> AsyncIterator[AsyncLlamaStackClient]:
-    strict = getattr(request, "param", True)
-    if not isinstance(strict, bool):
-        raise TypeError(f"Unexpected fixture parameter type {type(strict)}, expected {bool}")
-
-    async with AsyncLlamaStackClient(base_url=base_url, api_key=api_key, _strict_response_validation=strict) as client:
+    param = getattr(request, "param", True)
+
+    # defaults
+    strict = True
+    http_client: None | httpx.AsyncClient = None
+
+    if isinstance(param, bool):
+        strict = param
+    elif is_dict(param):
+        strict = param.get("strict", True)
+        assert isinstance(strict, bool)
+
+        http_client_type = param.get("http_client", "httpx")
+        if http_client_type == "aiohttp":
+            http_client = DefaultAioHttpClient()
+    else:
+        raise TypeError(f"Unexpected fixture parameter type {type(param)}, expected bool or dict")
+
+    async with AsyncLlamaStackClient(
+        base_url=base_url, api_key=api_key, _strict_response_validation=strict, http_client=http_client
+    ) as client:
         yield client
diff --git a/tests/test_client.py b/tests/test_client.py
index a2ddcb62..c7901e7e 100644
--- a/tests/test_client.py
+++ b/tests/test_client.py
@@ -23,17 +23,16 @@
 
 from llama_stack_client import LlamaStackClient, AsyncLlamaStackClient, APIResponseValidationError
 from llama_stack_client._types import Omit
-from llama_stack_client._utils import maybe_transform
 from llama_stack_client._models import BaseModel, FinalRequestOptions
-from llama_stack_client._constants import RAW_RESPONSE_HEADER
 from llama_stack_client._exceptions import APIStatusError, APITimeoutError, APIResponseValidationError
 from llama_stack_client._base_client import (
     DEFAULT_TIMEOUT,
     HTTPX_DEFAULT_TIMEOUT,
     BaseClient,
+    DefaultHttpxClient,
+    DefaultAsyncHttpxClient,
     make_request_options,
 )
-from llama_stack_client.types.datasetio_append_rows_params import DatasetioAppendRowsParams
 
 from .utils import update_env
 
@@ -192,6 +191,7 @@ def test_copy_signature(self) -> None:
             copy_param = copy_signature.parameters.get(name)
             assert copy_param is not None, f"copy() signature is missing the {name} param"
 
+    @pytest.mark.skipif(sys.version_info >= (3, 10), reason="fails because of a memory leak that started from 3.12")
     def test_copy_build_request(self) -> None:
         options = FinalRequestOptions(method="get", url="/foo")
 
@@ -732,34 +732,27 @@ def test_parse_retry_after_header(self, remaining_retries: int, retry_after: str
 
     @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout)
     @pytest.mark.respx(base_url=base_url)
-    def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) -> None:
+    def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter, client: LlamaStackClient) -> None:
         respx_mock.post("/v1/datasetio/append-rows/dataset_id").mock(
             side_effect=httpx.TimeoutException("Test timeout error")
         )
 
         with pytest.raises(APITimeoutError):
-            self.client.post(
-                "/v1/datasetio/append-rows/dataset_id",
-                body=cast(object, maybe_transform(dict(rows=[{"foo": True}]), DatasetioAppendRowsParams)),
-                cast_to=httpx.Response,
-                options={"headers": {RAW_RESPONSE_HEADER: "stream"}},
-            )
+            client.datasetio.with_streaming_response.append_rows(
+                dataset_id="dataset_id", rows=[{"foo": True}]
+            ).__enter__()
 
         assert _get_open_connections(self.client) == 0
 
     @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout)
     @pytest.mark.respx(base_url=base_url)
-    def test_retrying_status_errors_doesnt_leak(self, respx_mock: MockRouter) -> None:
+    def test_retrying_status_errors_doesnt_leak(self, respx_mock: MockRouter, client: LlamaStackClient) -> None:
         respx_mock.post("/v1/datasetio/append-rows/dataset_id").mock(return_value=httpx.Response(500))
 
         with pytest.raises(APIStatusError):
-            self.client.post(
-                "/v1/datasetio/append-rows/dataset_id",
-                body=cast(object, maybe_transform(dict(rows=[{"foo": True}]), DatasetioAppendRowsParams)),
-                cast_to=httpx.Response,
-                options={"headers": {RAW_RESPONSE_HEADER: "stream"}},
-            )
-
+            client.datasetio.with_streaming_response.append_rows(
+                dataset_id="dataset_id", rows=[{"foo": True}]
+            ).__enter__()
         assert _get_open_connections(self.client) == 0
 
     @pytest.mark.parametrize("failures_before_success", [0, 2, 4])
@@ -843,6 +836,55 @@ def retry_handler(_request: httpx.Request) -> httpx.Response:
 
         assert response.http_request.headers.get("x-stainless-retry-count") == "42"
 
+    def test_proxy_environment_variables(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        # Test that the proxy environment variables are set correctly
+        monkeypatch.setenv("HTTPS_PROXY", "https://example.org")
+
+        client = DefaultHttpxClient()
+
+        mounts = tuple(client._mounts.items())
+        assert len(mounts) == 1
+        assert mounts[0][0].pattern == "https://"
+
+    @pytest.mark.filterwarnings("ignore:.*deprecated.*:DeprecationWarning")
+    def test_default_client_creation(self) -> None:
+        # Ensure that the client can be initialized without any exceptions
+        DefaultHttpxClient(
+            verify=True,
+            cert=None,
+            trust_env=True,
+            http1=True,
+            http2=False,
+            limits=httpx.Limits(max_connections=100, max_keepalive_connections=20),
+        )
+
+    @pytest.mark.respx(base_url=base_url)
+    def test_follow_redirects(self, respx_mock: MockRouter) -> None:
+        # Test that the default follow_redirects=True allows following redirects
+        respx_mock.post("/redirect").mock(
+            return_value=httpx.Response(302, headers={"Location": f"{base_url}/redirected"})
+        )
+        respx_mock.get("/redirected").mock(return_value=httpx.Response(200, json={"status": "ok"}))
+
+        response = self.client.post("/redirect", body={"key": "value"}, cast_to=httpx.Response)
+        assert response.status_code == 200
+        assert response.json() == {"status": "ok"}
+
+    @pytest.mark.respx(base_url=base_url)
+    def test_follow_redirects_disabled(self, respx_mock: MockRouter) -> None:
+        # Test that follow_redirects=False prevents following redirects
+        respx_mock.post("/redirect").mock(
+            return_value=httpx.Response(302, headers={"Location": f"{base_url}/redirected"})
+        )
+
+        with pytest.raises(APIStatusError) as exc_info:
+            self.client.post(
+                "/redirect", body={"key": "value"}, options={"follow_redirects": False}, cast_to=httpx.Response
+            )
+
+        assert exc_info.value.response.status_code == 302
+        assert exc_info.value.response.headers["Location"] == f"{base_url}/redirected"
+
 
 class TestAsyncLlamaStackClient:
     client = AsyncLlamaStackClient(base_url=base_url, api_key=api_key, _strict_response_validation=True)
@@ -979,6 +1021,7 @@ def test_copy_signature(self) -> None:
             copy_param = copy_signature.parameters.get(name)
             assert copy_param is not None, f"copy() signature is missing the {name} param"
 
+    @pytest.mark.skipif(sys.version_info >= (3, 10), reason="fails because of a memory leak that started from 3.12")
     def test_copy_build_request(self) -> None:
         options = FinalRequestOptions(method="get", url="/foo")
 
@@ -1523,34 +1566,31 @@ async def test_parse_retry_after_header(self, remaining_retries: int, retry_afte
 
     @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout)
     @pytest.mark.respx(base_url=base_url)
-    async def test_retrying_timeout_errors_doesnt_leak(self, respx_mock: MockRouter) -> None:
+    async def test_retrying_timeout_errors_doesnt_leak(
+        self, respx_mock: MockRouter, async_client: AsyncLlamaStackClient
+    ) -> None:
         respx_mock.post("/v1/datasetio/append-rows/dataset_id").mock(
             side_effect=httpx.TimeoutException("Test timeout error")
         )
 
         with pytest.raises(APITimeoutError):
-            await self.client.post(
-                "/v1/datasetio/append-rows/dataset_id",
-                body=cast(object, maybe_transform(dict(rows=[{"foo": True}]), DatasetioAppendRowsParams)),
-                cast_to=httpx.Response,
-                options={"headers": {RAW_RESPONSE_HEADER: "stream"}},
-            )
+            await async_client.datasetio.with_streaming_response.append_rows(
+                dataset_id="dataset_id", rows=[{"foo": True}]
+            ).__aenter__()
 
         assert _get_open_connections(self.client) == 0
 
     @mock.patch("llama_stack_client._base_client.BaseClient._calculate_retry_timeout", _low_retry_timeout)
     @pytest.mark.respx(base_url=base_url)
-    async def test_retrying_status_errors_doesnt_leak(self, respx_mock: MockRouter) -> None:
+    async def test_retrying_status_errors_doesnt_leak(
+        self, respx_mock: MockRouter, async_client: AsyncLlamaStackClient
+    ) -> None:
         respx_mock.post("/v1/datasetio/append-rows/dataset_id").mock(return_value=httpx.Response(500))
 
         with pytest.raises(APIStatusError):
-            await self.client.post(
-                "/v1/datasetio/append-rows/dataset_id",
-                body=cast(object, maybe_transform(dict(rows=[{"foo": True}]), DatasetioAppendRowsParams)),
-                cast_to=httpx.Response,
-                options={"headers": {RAW_RESPONSE_HEADER: "stream"}},
-            )
-
+            await async_client.datasetio.with_streaming_response.append_rows(
+                dataset_id="dataset_id", rows=[{"foo": True}]
+            ).__aenter__()
         assert _get_open_connections(self.client) == 0
 
     @pytest.mark.parametrize("failures_before_success", [0, 2, 4])
@@ -1681,3 +1721,52 @@ async def test_main() -> None:
                     raise AssertionError("calling get_platform using asyncify resulted in a hung process")
 
                 time.sleep(0.1)
+
+    async def test_proxy_environment_variables(self, monkeypatch: pytest.MonkeyPatch) -> None:
+        # Test that the proxy environment variables are set correctly
+        monkeypatch.setenv("HTTPS_PROXY", "https://example.org")
+
+        client = DefaultAsyncHttpxClient()
+
+        mounts = tuple(client._mounts.items())
+        assert len(mounts) == 1
+        assert mounts[0][0].pattern == "https://"
+
+    @pytest.mark.filterwarnings("ignore:.*deprecated.*:DeprecationWarning")
+    async def test_default_client_creation(self) -> None:
+        # Ensure that the client can be initialized without any exceptions
+        DefaultAsyncHttpxClient(
+            verify=True,
+            cert=None,
+            trust_env=True,
+            http1=True,
+            http2=False,
+            limits=httpx.Limits(max_connections=100, max_keepalive_connections=20),
+        )
+
+    @pytest.mark.respx(base_url=base_url)
+    async def test_follow_redirects(self, respx_mock: MockRouter) -> None:
+        # Test that the default follow_redirects=True allows following redirects
+        respx_mock.post("/redirect").mock(
+            return_value=httpx.Response(302, headers={"Location": f"{base_url}/redirected"})
+        )
+        respx_mock.get("/redirected").mock(return_value=httpx.Response(200, json={"status": "ok"}))
+
+        response = await self.client.post("/redirect", body={"key": "value"}, cast_to=httpx.Response)
+        assert response.status_code == 200
+        assert response.json() == {"status": "ok"}
+
+    @pytest.mark.respx(base_url=base_url)
+    async def test_follow_redirects_disabled(self, respx_mock: MockRouter) -> None:
+        # Test that follow_redirects=False prevents following redirects
+        respx_mock.post("/redirect").mock(
+            return_value=httpx.Response(302, headers={"Location": f"{base_url}/redirected"})
+        )
+
+        with pytest.raises(APIStatusError) as exc_info:
+            await self.client.post(
+                "/redirect", body={"key": "value"}, options={"follow_redirects": False}, cast_to=httpx.Response
+            )
+
+        assert exc_info.value.response.status_code == 302
+        assert exc_info.value.response.headers["Location"] == f"{base_url}/redirected"
diff --git a/tests/test_utils/test_proxy.py b/tests/test_utils/test_proxy.py
index 9cefe4ea..76a29efd 100644
--- a/tests/test_utils/test_proxy.py
+++ b/tests/test_utils/test_proxy.py
@@ -21,3 +21,14 @@ def test_recursive_proxy() -> None:
     assert dir(proxy) == []
     assert type(proxy).__name__ == "RecursiveLazyProxy"
     assert type(operator.attrgetter("name.foo.bar.baz")(proxy)).__name__ == "RecursiveLazyProxy"
+
+
+def test_isinstance_does_not_error() -> None:
+    class AlwaysErrorProxy(LazyProxy[Any]):
+        @override
+        def __load__(self) -> Any:
+            raise RuntimeError("Mocking missing dependency")
+
+    proxy = AlwaysErrorProxy()
+    assert not isinstance(proxy, dict)
+    assert isinstance(proxy, LazyProxy)