refactor(build): rework CLI commands and build process (1/2) (#2974)

# What does this PR do?

This PR does a few things outlined in #2878 namely:
1. adds `llama stack list-deps` a command which simply takes the build
logic and instead of executing one of the `build_...` scripts, it
displays all of the providers' dependencies using the `module` and `uv`.
2. deprecated `llama stack build` in favor of `llama stack list-deps`
3. updates all tests to use `list-deps` alongside `build`.

PR 2/2 will migrate `llama stack run`'s default behavior to be `llama
stack build --run` and use the new `list-deps` command under the hood
before running the server.

examples of `llama stack list-deps starter`

```
llama stack list-deps starter --format json
{
  "name": "starter",
  "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.",
  "apis": [
    {
      "api": "inference",
      "provider": "remote::cerebras"
    },
    {
      "api": "inference",
      "provider": "remote::ollama"
    },
    {
      "api": "inference",
      "provider": "remote::vllm"
    },
    {
      "api": "inference",
      "provider": "remote::tgi"
    },
    {
      "api": "inference",
      "provider": "remote::fireworks"
    },
    {
      "api": "inference",
      "provider": "remote::together"
    },
    {
      "api": "inference",
      "provider": "remote::bedrock"
    },
    {
      "api": "inference",
      "provider": "remote::nvidia"
    },
    {
      "api": "inference",
      "provider": "remote::openai"
    },
    {
      "api": "inference",
      "provider": "remote::anthropic"
    },
    {
      "api": "inference",
      "provider": "remote::gemini"
    },
    {
      "api": "inference",
      "provider": "remote::vertexai"
    },
    {
      "api": "inference",
      "provider": "remote::groq"
    },
    {
      "api": "inference",
      "provider": "remote::sambanova"
    },
    {
      "api": "inference",
      "provider": "remote::azure"
    },
    {
      "api": "inference",
      "provider": "inline::sentence-transformers"
    },
    {
      "api": "vector_io",
      "provider": "inline::faiss"
    },
    {
      "api": "vector_io",
      "provider": "inline::sqlite-vec"
    },
    {
      "api": "vector_io",
      "provider": "inline::milvus"
    },
    {
      "api": "vector_io",
      "provider": "remote::chromadb"
    },
    {
      "api": "vector_io",
      "provider": "remote::pgvector"
    },
    {
      "api": "files",
      "provider": "inline::localfs"
    },
    {
      "api": "safety",
      "provider": "inline::llama-guard"
    },
    {
      "api": "safety",
      "provider": "inline::code-scanner"
    },
    {
      "api": "agents",
      "provider": "inline::meta-reference"
    },
    {
      "api": "telemetry",
      "provider": "inline::meta-reference"
    },
    {
      "api": "post_training",
      "provider": "inline::torchtune-cpu"
    },
    {
      "api": "eval",
      "provider": "inline::meta-reference"
    },
    {
      "api": "datasetio",
      "provider": "remote::huggingface"
    },
    {
      "api": "datasetio",
      "provider": "inline::localfs"
    },
    {
      "api": "scoring",
      "provider": "inline::basic"
    },
    {
      "api": "scoring",
      "provider": "inline::llm-as-judge"
    },
    {
      "api": "scoring",
      "provider": "inline::braintrust"
    },
    {
      "api": "tool_runtime",
      "provider": "remote::brave-search"
    },
    {
      "api": "tool_runtime",
      "provider": "remote::tavily-search"
    },
    {
      "api": "tool_runtime",
      "provider": "inline::rag-runtime"
    },
    {
      "api": "tool_runtime",
      "provider": "remote::model-context-protocol"
    },
    {
      "api": "batches",
      "provider": "inline::reference"
    }
  ],
  "pip_dependencies": [
    "pandas",
    "opentelemetry-exporter-otlp-proto-http",
    "matplotlib",
    "opentelemetry-sdk",
    "sentence-transformers",
    "datasets",
    "pymilvus[milvus-lite]>=2.4.10",
    "codeshield",
    "scipy",
    "torchvision",
    "tree_sitter",
    "h11>=0.16.0",
    "aiohttp",
    "pymongo",
    "tqdm",
    "pythainlp",
    "pillow",
    "torch",
    "emoji",
    "grpcio>=1.67.1,<1.71.0",
    "fireworks-ai",
    "langdetect",
    "psycopg2-binary",
    "asyncpg",
    "redis",
    "together",
    "torchao>=0.12.0",
    "openai",
    "sentencepiece",
    "aiosqlite",
    "google-cloud-aiplatform",
    "faiss-cpu",
    "numpy",
    "sqlite-vec",
    "nltk",
    "scikit-learn",
    "mcp>=1.8.1",
    "transformers",
    "boto3",
    "huggingface_hub",
    "ollama",
    "autoevals",
    "sqlalchemy[asyncio]",
    "torchtune>=0.5.0",
    "chromadb-client",
    "pypdf",
    "requests",
    "anthropic",
    "chardet",
    "aiosqlite",
    "fastapi",
    "fire",
    "httpx",
    "uvicorn",
    "opentelemetry-sdk",
    "opentelemetry-exporter-otlp-proto-http"
  ]
}
```

<img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM"
src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721"
/>

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>

.github/actions/setup-test-environment/action.yml

@@ -57,7 +57,7 @@ runs:
         echo "Building Llama Stack"
 
         LLAMA_STACK_DIR=. \
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run --no-sync llama stack list-deps ci-tests | xargs -L1 uv pip install
 
     - name: Configure git for commits
       shell: bash

.github/workflows/README.md

@@ -14,6 +14,7 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
 | Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
 | Pre-commit Bot | [precommit-trigger.yml](precommit-trigger.yml) | Pre-commit bot for PR |
 | Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |
+| Test llama stack list-deps | [providers-list-deps.yml](providers-list-deps.yml) | Test llama stack list-deps |
 | Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |
 | Integration Tests (Record) | [record-integration-tests.yml](record-integration-tests.yml) | Run the integration test suite from tests/integration |
 | Check semantic PR titles | [semantic-pr.yml](semantic-pr.yml) | Ensure that PR titles follow the conventional commit spec |

.github/workflows/integration-vector-io-tests.yml

@@ -144,7 +144,7 @@ jobs:
 
       - name: Build Llama Stack
         run: |
-          uv run --no-sync llama stack build --template ci-tests --image-type venv
+          uv run --no-sync llama stack list-deps ci-tests | xargs -L1 uv pip install
 
       - name: Check Storage and Memory Available Before Tests
         if: ${{ always() }}

.github/workflows/providers-list-deps.yml

@@ -0,0 +1,105 @@
+name: Test llama stack list-deps
+
+run-name: Test llama stack list-deps
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'llama_stack/cli/stack/list_deps.py'
+      - 'llama_stack/cli/stack/_list_deps.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-list-deps.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+  pull_request:
+    paths:
+      - 'llama_stack/cli/stack/list_deps.py'
+      - 'llama_stack/cli/stack/_list_deps.py'
+      - 'llama_stack/core/build.*'
+      - 'llama_stack/core/*.sh'
+      - '.github/workflows/providers-list-deps.yml'
+      - 'llama_stack/templates/**'
+      - 'pyproject.toml'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  generate-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      distros: ${{ steps.set-matrix.outputs.distros }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Generate Distribution List
+        id: set-matrix
+        run: |
+          distros=$(ls llama_stack/distributions/*/*build.yaml | awk -F'/' '{print $(NF-1)}' | jq -R -s -c 'split("\n")[:-1]')
+          echo "distros=$distros" >> "$GITHUB_OUTPUT"
+
+  list-deps:
+    needs: generate-matrix
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        distro: ${{ fromJson(needs.generate-matrix.outputs.distros) }}
+        image-type: [venv, container]
+      fail-fast: false # We want to run all jobs even if some fail
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Print dependencies
+        run: |
+          uv run llama stack list-deps ${{ matrix.distro }}
+
+      - name: Install Distro using llama stack list-deps
+        run: |
+          # USE_COPY_NOT_MOUNT is set to true since mounting is not supported by docker buildx, we use COPY instead
+          # LLAMA_STACK_DIR is set to the current directory so we are building from the source
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack list-deps ${{ matrix.distro }} | xargs -L1 uv pip install
+
+      - name: Print dependencies in the image
+        if: matrix.image-type == 'venv'
+        run: |
+          uv pip list
+
+  show-single-provider:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: Show a single provider
+        run: |
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack list-deps --providers inference=remote::ollama
+
+  list-deps-from-config:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Install dependencies
+        uses: ./.github/actions/setup-runner
+
+      - name: list-des from Config
+        env:
+          USE_COPY_NOT_MOUNT: "true"
+          LLAMA_STACK_DIR: "."
+        run: |
+          uv run llama stack list-deps llama_stack/distributions/ci-tests/build.yaml

.github/workflows/test-external.yml

@@ -44,11 +44,14 @@ jobs:
 
       - name: Print distro dependencies
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml --print-deps-only
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack list-deps tests/external/build.yaml
 
       - name: Build distro from config file
         run: |
-          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run --no-sync llama stack build --config tests/external/build.yaml
+          uv venv ci-test
+          source ci-test/bin/activate
+          uv pip install -e .
+          LLAMA_STACK_LOGGING=all=CRITICAL llama stack list-deps tests/external/build.yaml | xargs -L1 uv pip install
 
       - name: Start Llama Stack server in background
         if: ${{ matrix.image-type }} == 'venv'