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>

docs/docs/contributing/index.mdx

@@ -158,7 +158,7 @@ under the LICENSE file in the root directory of this source tree.
 
 Some tips about common tasks you work on while contributing to Llama Stack:
 
-### Using `llama stack build`
+### Installing dependencies of distributions
 
 Building a stack image will use the production version of the `llama-stack` and `llama-stack-client` packages. If you are developing with a llama-stack repository checked out and need your code to be reflected in the stack image, set `LLAMA_STACK_DIR` and `LLAMA_STACK_CLIENT_DIR` to the appropriate checked out directories when running any of the `llama` CLI commands.
 
@@ -168,7 +168,7 @@ cd work/
 git clone https://github.com/meta-llama/llama-stack.git
 git clone https://github.com/meta-llama/llama-stack-client-python.git
 cd llama-stack
-LLAMA_STACK_DIR=$(pwd) LLAMA_STACK_CLIENT_DIR=../llama-stack-client-python llama stack build --distro <...>
+llama stack build --distro <...>
 ```
 
 ### Updating distribution configurations

docs/docs/distributions/self_hosted_distro/starter.md

@@ -169,7 +169,11 @@ docker run \
 Ensure you have configured the starter distribution using the environment variables explained above.
 
 ```bash
-uv run --with llama-stack llama stack build --distro starter --image-type venv --run
+# Install dependencies for the starter distribution
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+uv run --with llama-stack llama stack run starter
 ```
 
 ## Example Usage

docs/docs/getting_started/detailed_tutorial.mdx

@@ -58,15 +58,19 @@ Llama Stack is a server that exposes multiple APIs, you connect with it using th
 
 <Tabs>
 <TabItem value="venv" label="Using venv">
-You can use Python to build and run the Llama Stack server, which is useful for testing and development.
+You can use Python to install dependencies and run the Llama Stack server, which is useful for testing and development.
 
 Llama Stack uses a [YAML configuration file](../distributions/configuration) to specify the stack setup,
 which defines the providers and their settings. The generated configuration serves as a starting point that you can [customize for your specific needs](../distributions/customizing_run_yaml).
-Now let's build and run the Llama Stack config for Ollama.
+Now let's install dependencies and run the Llama Stack config for Ollama.
 We use `starter` as template. By default all providers are disabled, this requires enable ollama by passing environment variables.
 
 ```bash
-llama stack build --distro starter --image-type venv --run
+# Install dependencies for the starter distribution
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+llama stack run starter
 ```
 </TabItem>
 <TabItem value="container" label="Using a Container">

docs/docs/getting_started/quickstart.mdx

@@ -24,10 +24,13 @@ ollama run llama3.2:3b --keepalive 60m
 
 #### Step 2: Run the Llama Stack server
 
-We will use `uv` to run the Llama Stack server.
+We will use `uv` to install dependencies and run the Llama Stack server.
 ```bash
-OLLAMA_URL=http://localhost:11434 \
-  uv run --with llama-stack llama stack build --distro starter --image-type venv --run
+# Install dependencies for the starter distribution
+uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install
+
+# Run the server
+OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter
 ```
 #### Step 3: Run the demo
 Now open up a new terminal and copy the following script into a file named `demo_script.py`.