mlx-stack 0.3.3__tar.gz → 0.3.4__tar.gz

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/.github/workflows/ci.yml

@@ -49,3 +49,31 @@ jobs:
         with:
           name: coverage-report
           path: coverage.xml
+
+  catalog-validation:
+    name: Catalog Validation
+    runs-on: macos-latest
+    needs: ci
+    strategy:
+      matrix:
+        python-version: ["3.13"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Install Python ${{ matrix.python-version }}
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install dependencies
+        run: make install
+
+      - name: Validate catalog entries
+        run: make test-catalog

mlx_stack-0.3.4/.github/workflows/integration-nightly.yml

@@ -0,0 +1,58 @@
+name: Nightly Integration
+
+on:
+  schedule:
+    - cron: "0 6 * * *"  # 6 AM UTC daily
+  workflow_dispatch:
+    inputs:
+      model:
+        description: "Specific model ID to test (blank = all non-gated models that fit in memory)"
+        required: false
+
+concurrency:
+  group: nightly-integration
+  cancel-in-progress: true
+
+jobs:
+  smoke:
+    name: Model Smoke Tests
+    runs-on: macos-latest
+    timeout-minutes: 120
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Install Python 3.13
+        run: uv python install 3.13
+
+      - name: Install project dependencies
+        run: make install
+
+      - name: Install vllm-mlx
+        run: uv tool install vllm-mlx==0.2.6
+
+      - name: Run smoke tests
+        run: |
+          MODEL_FILTER="${{ github.event.inputs.model }}"
+          if [ -n "$MODEL_FILTER" ]; then
+            uv run pytest -m smoke -k "$MODEL_FILTER" -v --tb=long
+          else
+            uv run pytest -m smoke -v --tb=long
+          fi
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+      - name: Upload compatibility matrix
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: compatibility-matrix
+          path: ~/.mlx-stack-test-cache/reports/

mlx_stack-0.3.4/.github/workflows/integration-prerelease.yml

@@ -0,0 +1,53 @@
+name: Pre-Release Integration
+
+on:
+  release:
+    types: [created]
+  workflow_dispatch:
+
+concurrency:
+  group: prerelease-integration
+  cancel-in-progress: true
+
+jobs:
+  stack-integration:
+    name: Full Stack Integration
+    runs-on: macos-latest
+    timeout-minutes: 60
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v6
+        with:
+          fetch-depth: 0
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v7
+        with:
+          enable-cache: true
+
+      - name: Install Python 3.13
+        run: uv python install 3.13
+
+      - name: Install project dependencies
+        run: uv sync --dev
+
+      - name: Install openai for harness tests
+        run: uv pip install openai>=1.0
+
+      - name: Install vllm-mlx and litellm
+        run: |
+          uv tool install vllm-mlx==0.2.6
+          uv tool install "litellm[proxy]==1.83.0"
+
+      - name: Run stack integration tests
+        run: uv run pytest -m "integration or harness" -v --tb=long
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+
+      - name: Upload test results
+        uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: integration-results
+          path: ~/.mlx-stack-test-cache/reports/

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/.gitignore

@@ -34,3 +34,4 @@ htmlcov/
 
 # Ruff
 .ruff_cache/
+REQUIREMENTS.md

mlx_stack-0.3.4/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "0.3.4"
+}

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/CHANGELOG.md

@@ -4,6 +4,13 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.4](https://github.com/weklund/mlx-stack/compare/v0.3.3...v0.3.4) (2026-04-03)
+
+
+### Features
+
+* 4-tier integration testing framework ([#16](https://github.com/weklund/mlx-stack/issues/16)) ([e3dcf9a](https://github.com/weklund/mlx-stack/commit/e3dcf9ae4eaa55ee8ca522819d3dc16846d3e1ea))
+
 ## [0.3.3](https://github.com/weklund/mlx-stack/compare/v0.3.2...v0.3.3) (2026-04-02)
 
 

mlx_stack-0.3.4/Makefile

@@ -0,0 +1,36 @@
+.PHONY: install lint typecheck test check test-catalog test-smoke test-integration test-harness
+
+## Install dev dependencies
+install:
+	uv sync --dev
+
+## Lint source and tests
+lint:
+	uv run ruff check src/ tests/
+
+## Run type checker across the full project
+typecheck:
+	uv run python -m pyright
+
+## Run tests with coverage
+test:
+	uv run pytest --cov=src/mlx_stack -x -q --tb=short
+
+## Run all checks (same as CI)
+check: lint typecheck test
+
+## Run catalog validation (requires network, no models)
+test-catalog:
+	uv run pytest -m catalog_validation -v --tb=short
+
+## Run per-model smoke tests (requires macOS + vllm-mlx)
+test-smoke:
+	uv run pytest -m smoke -v --tb=long
+
+## Run full stack integration tests (requires macOS + vllm-mlx + litellm)
+test-integration:
+	uv run pytest -m integration -v --tb=long
+
+## Run harness compatibility tests (requires above + openai)
+test-harness:
+	uv run pytest -m harness -v --tb=long

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlx-stack
-Version: 0.3.3
+Version: 0.3.4
 Summary: CLI control plane for local LLM infrastructure on Apple Silicon
 Project-URL: Homepage, https://github.com/weklund/mlx-stack
 Project-URL: Repository, https://github.com/weklund/mlx-stack

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/pyproject.toml

@@ -53,9 +53,12 @@ packages = ["src/mlx_stack"]
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 pythonpath = ["src"]
-addopts = "-x -q --tb=short -m 'not integration'"
+addopts = "-x -q --tb=short -m 'not integration and not smoke and not catalog_validation and not harness'"
 markers = [
     "integration: real system integration tests (launchctl, etc.)",
+    "smoke: per-model smoke tests requiring model download and inference",
+    "catalog_validation: catalog data integrity checks (requires network, no models)",
+    "harness: external tool compatibility tests (OpenAI client, streaming)",
 ]
 
 [tool.ruff]

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/src/mlx_stack/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.3.3'
-__version_tuple__ = version_tuple = (0, 3, 3)
+__version__ = version = '0.3.4'
+__version_tuple__ = version_tuple = (0, 3, 4)
 
 __commit_id__ = commit_id = None

{mlx_stack-0.3.3 → mlx_stack-0.3.4}/src/mlx_stack/cli/main.py

@@ -25,6 +25,7 @@ from mlx_stack.cli.models import models as models_command
 from mlx_stack.cli.profile import profile as profile_command
 from mlx_stack.cli.pull import pull as pull_command
 from mlx_stack.cli.recommend import recommend as recommend_command
+from mlx_stack.cli.setup import setup as setup_command
 from mlx_stack.cli.status import status as status_command
 from mlx_stack.cli.up import up as up_command
 from mlx_stack.cli.watch import watch as watch_command
@@ -73,6 +74,7 @@ class RichGroup(click.Group):
             }
 
             command_categories = {
+                "setup": "Setup & Configuration",
                 "profile": "Setup & Configuration",
                 "config": "Setup & Configuration",
                 "init": "Setup & Configuration",
@@ -165,6 +167,7 @@ def cli(ctx: click.Context) -> None:
 # These will be replaced by real implementations in subsequent features.
 
 
+cli.add_command(setup_command, "setup")
 cli.add_command(profile_command, "profile")
 cli.add_command(recommend_command, "recommend")
 cli.add_command(init_command, "init")