Add a pre-commit for distro_codegen but it does not work yet

.pre-commit-config.yaml

@@ -57,3 +57,17 @@ repos:
 #   hooks:
 #     - id: markdown-link-check
 #       args: ['--quiet']
+
+# -   repo: local
+#     hooks:
+#       - id: distro-codegen
+#         name: Distribution Template Codegen
+#         additional_dependencies:
+#           - rich
+#           - pydantic
+#         entry: python -m llama_stack.scripts.distro_codegen
+#         language: python
+#         pass_filenames: false
+#         require_serial: true
+#         files: ^llama_stack/templates/.*$
+#         stages: [manual]

docs/source/getting_started/distributions/self_hosted_distro/meta-reference-gpu.md

@@ -13,6 +13,15 @@ The `llamastack/distribution-meta-reference-gpu` distribution consists of the fo
 
 Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.
 
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
+- `INFERENCE_MODEL`: Inference model loaded into the Meta Reference server (default: `meta-llama/Llama-3.2-3B-Instruct`)
+- `INFERENCE_CHECKPOINT_DIR`: Directory containing the Meta Reference model checkpoint (default: `null`)
+- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)
+- `SAFETY_CHECKPOINT_DIR`: Directory containing the Llama-Guard model checkpoint (default: `null`)
 
 
 ## Prerequisite: Downloading Models

docs/source/getting_started/distributions/self_hosted_distro/ollama.md

@@ -11,7 +11,15 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
 | telemetry | `inline::meta-reference` |
 
 
-You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.
+You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
+- `OLLAMA_URL`: URL of the Ollama server (default: `http://127.0.0.1:11434`)
+- `INFERENCE_MODEL`: Inference model loaded into the Ollama server (default: `meta-llama/Llama-3.2-3B-Instruct`)
+- `SAFETY_MODEL`: Safety model loaded into the Ollama server (default: `meta-llama/Llama-Guard-3-1B`)
+
 
 ## Setting up Ollama server
 

docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md

@@ -13,6 +13,16 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
 
 You can use this distribution if you have GPUs and want to run an independent vLLM server container for running inference.
 
+### Environment Variables
+
+The following environment variables can be configured:
+
+- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
+- `INFERENCE_MODEL`: Inference model loaded into the vLLM server (default: `meta-llama/Llama-3.2-3B-Instruct`)
+- `VLLM_URL`: URL of the vLLM server with the main inference model (default: `http://host.docker.internal:5100}/v1`)
+- `MAX_TOKENS`: Maximum number of tokens for generation (default: `4096`)
+- `SAFETY_VLLM_URL`: URL of the vLLM server with the safety model (default: `http://host.docker.internal:5101/v1`)
+- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)
 
 
 ## Setting up vLLM server

llama_stack/scripts/distro_codegen.py

@@ -6,6 +6,8 @@
 
 import concurrent.futures
 import importlib
+import subprocess
+import sys
 from functools import partial
 from pathlib import Path
 from typing import Iterator
@@ -55,6 +57,16 @@ def process_template(template_dir: Path, progress) -> None:
         raise e
 
 
+def check_for_changes() -> bool:
+    """Check if there are any uncommitted changes."""
+    result = subprocess.run(
+        ["git", "diff", "--exit-code"],
+        cwd=REPO_ROOT,
+        capture_output=True,
+    )
+    return result.returncode != 0
+
+
 def main():
     templates_dir = REPO_ROOT / "llama_stack" / "templates"
 
@@ -76,6 +88,15 @@ def main():
             list(executor.map(process_func, template_dirs))
             progress.update(task, advance=len(template_dirs))
 
+    if check_for_changes():
+        print(
+            "Distribution template changes detected. Please commit the changes.",
+            file=sys.stderr,
+        )
+        sys.exit(1)
+
+    sys.exit(0)
+
 
 if __name__ == "__main__":
     main()

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -75,7 +75,7 @@ def get_distribution_template() -> DistributionTemplate:
                 default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
             ),
         },
-        docker_compose_env_vars={
+        run_config_env_vars={
             "LLAMASTACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",

llama_stack/templates/ollama/ollama.py

@@ -63,7 +63,7 @@ def get_distribution_template() -> DistributionTemplate:
                 default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
             ),
         },
-        docker_compose_env_vars={
+        run_config_env_vars={
             "LLAMASTACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",

llama_stack/templates/remote-vllm/vllm.py

@@ -71,7 +71,7 @@ def get_distribution_template() -> DistributionTemplate:
                 default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
             ),
         },
-        docker_compose_env_vars={
+        run_config_env_vars={
             "LLAMASTACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",