feat: include run.yaml in the container image (#2005)

As part of the build process, we now include the generated run.yaml
(based of the provided build configuration file) into the container. We
updated the entrypoint to use this run configuration as well.

Given this simple distribution configuration:

```
# build.yaml
version: '2'
distribution_spec:
  description: Use (an external) Ollama server for running LLM inference
  providers:
    inference:
    - remote::ollama
    vector_io:
    - inline::faiss
    safety:
    - inline::llama-guard
    agents:
    - inline::meta-reference
    telemetry:
    - inline::meta-reference
    eval:
    - inline::meta-reference
    datasetio:
    - remote::huggingface
    - inline::localfs
    scoring:
    - inline::basic
    - inline::llm-as-judge
    - inline::braintrust
    tool_runtime:
    - remote::brave-search
    - remote::tavily-search
    - inline::code-interpreter
    - inline::rag-runtime
    - remote::model-context-protocol
    - remote::wolfram-alpha
  container_image: "registry.access.redhat.com/ubi9"
image_type: container
image_name: test
```

Build it:
```
llama stack build --config build.yaml
```

Run it:

```
podman run --rm \
         -p 8321:8321 \
         -e OLLAMA_URL=http://host.containers.internal:11434 \
         --name llama-stack-server \
         localhost/leseb-test:0.2.2
```

Signed-off-by: Sébastien Han <seb@redhat.com>

.github/workflows/providers-build.yml

@@ -107,3 +107,41 @@ jobs:
       - name: Build a single provider
         run: |
           USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --image-type venv --image-name test --providers inference=remote::ollama
+
+  build-custom-container-distribution:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+
+      - name: Set up Python
+        uses: actions/setup-python@8d9ed9ac5c53483de85588cdf95a591a75ab9f55 # v5.5.0
+        with:
+          python-version: '3.10'
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@0c5e2b8115b80b4c7c5ddf6ffdd634974642d182 # v5.4.1
+        with:
+          python-version: "3.10"
+
+      - name: Install LlamaStack
+        run: |
+          uv venv
+          source .venv/bin/activate
+          uv pip install -e .
+
+      - name: Build a single provider
+        run: |
+          yq -i '.image_type = "container"' llama_stack/templates/dev/build.yaml
+          yq -i '.image_name = "test"' llama_stack/templates/dev/build.yaml
+          USE_COPY_NOT_MOUNT=true LLAMA_STACK_DIR=. uv run llama stack build --config llama_stack/templates/dev/build.yaml
+
+      - name: Inspect the container image entrypoint
+        run: |
+          IMAGE_ID=$(docker images --format "{{.Repository}}:{{.Tag}}" | head -n 1)
+          entrypoint=$(docker inspect --format '{{ .Config.Entrypoint }}' $IMAGE_ID)
+          echo "Entrypoint: $entrypoint"
+          if [ "$entrypoint" != "[python -m llama_stack.distribution.server.server --config /app/run.yaml]" ]; then
+            echo "Entrypoint is not correct"
+            exit 1
+          fi