[CICD] Github workflow for publishing Docker images (#764)

# What does this PR do?

- Add Github workflow for publishing docker images. 
- Manual Inputs
- We can use a (1) TestPyPi version / (2) build via released PyPi
version

**Notes**
- Keep this workflow manually triggered as we don't want to publish
nightly docker images

**Additional Changes**
- Resolve issue with running llama stack build in non-terminal device
```
  File "/home/runner/.local/lib/python3.12/site-packages/llama_stack/distribution/utils/exec.py", line 25, in run_with_pty
    old_settings = termios.tcgetattr(sys.stdin)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
termios.error: (25, 'Inappropriate ioctl for device')
```
- Modified build_container.sh to work in non-terminal environment


## Test Plan

- Triggered workflow:
3562217878
<img width="1076" alt="image"
src="https://github.com/user-attachments/assets/f1b5cef6-05ab-49c7-b405-53abc9264734"
/>


- Tested published docker image
<img width="702" alt="image"
src="https://github.com/user-attachments/assets/e7135189-65c8-45d8-86f9-9f3be70e380b"
/>


- /tools API endpoints are served so that docker is correctly using the
TestPyPi package
<img width="296" alt="image"
src="https://github.com/user-attachments/assets/bbcaa7fe-c0a4-4d22-b600-90e3c254bbfd"
/>

- Published tagged images:
https://hub.docker.com/repositories/llamastack
<img width="947" alt="image"
src="https://github.com/user-attachments/assets/2a0a0494-4d45-4643-bc29-72154ecc54a5"
/>


## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/distribution/build.py

@@ -6,6 +6,7 @@
 
 import importlib.resources
 import logging
+import sys
 from enum import Enum
 
 from pathlib import Path
@@ -20,7 +21,7 @@ from llama_stack.distribution.distribution import get_provider_registry
 
 from llama_stack.distribution.utils.config_dirs import BUILDS_BASE_DIR
 
-from llama_stack.distribution.utils.exec import run_with_pty
+from llama_stack.distribution.utils.exec import run_command, run_with_pty
 from llama_stack.providers.datatypes import Api
 
 log = logging.getLogger(__name__)
@@ -102,7 +103,10 @@ def print_pip_install_help(providers: Dict[str, List[Provider]]):
     print()
 
 
-def build_image(build_config: BuildConfig, build_file_path: Path):
+def build_image(
+    build_config: BuildConfig,
+    build_file_path: Path,
+):
     docker_image = build_config.distribution_spec.docker_image or "python:3.10-slim"
 
     normal_deps, special_deps = get_provider_dependencies(
@@ -144,7 +148,12 @@ def build_image(build_config: BuildConfig, build_file_path: Path):
     if special_deps:
         args.append("#".join(special_deps))
 
-    return_code = run_with_pty(args)
+    is_terminal = sys.stdin.isatty()
+    if is_terminal:
+        return_code = run_with_pty(args)
+    else:
+        return_code = run_command(args)
+
     if return_code != 0:
         log.error(
             f"Failed to build target {build_config.name} with return code {return_code}",

llama_stack/distribution/build_container.sh

@@ -54,7 +54,7 @@ add_to_docker() {
 
 # Update and install UBI9 components if UBI9 base image is used
 if [[ $docker_base == *"registry.access.redhat.com/ubi9"* ]]; then
-  add_to_docker <<EOF
+  add_to_docker << EOF
 FROM $docker_base
 WORKDIR /app
 
@@ -64,7 +64,7 @@ RUN microdnf -y update && microdnf install -y iputils net-tools wget \
 
 EOF
 else
-  add_to_docker <<EOF
+  add_to_docker << EOF
 FROM $docker_base
 WORKDIR /app
 
@@ -82,13 +82,17 @@ fi
 # Add pip dependencies first since llama-stack is what will change most often
 # so we can reuse layers.
 if [ -n "$pip_dependencies" ]; then
-  add_to_docker "RUN pip install --no-cache $pip_dependencies"
+  add_to_docker << EOF
+RUN pip install --no-cache $pip_dependencies
+EOF
 fi
 
 if [ -n "$special_pip_deps" ]; then
   IFS='#' read -ra parts <<<"$special_pip_deps"
   for part in "${parts[@]}"; do
-    add_to_docker "RUN pip install --no-cache $part"
+    add_to_docker <<EOF
+RUN pip install --no-cache $part
+EOF
   done
 fi
 
@@ -104,14 +108,19 @@ if [ -n "$LLAMA_STACK_DIR" ]; then
   # Install in editable format. We will mount the source code into the container
   # so that changes will be reflected in the container without having to do a
   # rebuild. This is just for development convenience.
-  add_to_docker "RUN pip install --no-cache -e $stack_mount"
+  add_to_docker << EOF
+RUN pip install --no-cache -e $stack_mount
+EOF
 else
   if [ -n "$TEST_PYPI_VERSION" ]; then
     # these packages are damaged in test-pypi, so install them first
-    add_to_docker "RUN pip install fastapi libcst"
-    add_to_docker <<EOF
+    add_to_docker << EOF
+RUN pip install fastapi libcst
+EOF
+    add_to_docker << EOF
 RUN pip install --no-cache --extra-index-url https://test.pypi.org/simple/ \
   llama-models==$TEST_PYPI_VERSION llama-stack-client==$TEST_PYPI_VERSION llama-stack==$TEST_PYPI_VERSION
+
 EOF
   else
     if [ -n "$PYPI_VERSION" ]; then
@@ -119,7 +128,9 @@ EOF
     else
       SPEC_VERSION="llama-stack"
     fi
-    add_to_docker "RUN pip install --no-cache $SPEC_VERSION"
+    add_to_docker << EOF
+RUN pip install --no-cache $SPEC_VERSION
+EOF
   fi
 fi
 
@@ -129,14 +140,14 @@ if [ -n "$LLAMA_MODELS_DIR" ]; then
     exit 1
   fi
 
-  add_to_docker <<EOF
+  add_to_docker << EOF
 RUN pip uninstall -y llama-models
 RUN pip install --no-cache $models_mount
 
 EOF
 fi
 
-add_to_docker <<EOF
+add_to_docker << EOF
 
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway

llama_stack/distribution/utils/exec.py

@@ -98,9 +98,11 @@ def run_with_pty(command):
 
 
 def run_command(command):
-    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-    output, error = process.communicate()
-    if process.returncode != 0:
-        log.error(f"Error: {error.decode('utf-8')}")
-        sys.exit(1)
-    return output.decode("utf-8")
+    try:
+        result = subprocess.run(command, capture_output=True, text=True, check=True)
+        print("Script Output\n", result.stdout)
+        return result.returncode
+    except subprocess.CalledProcessError as e:
+        print("Error running script:", e)
+        print("Error output:", e.stderr)
+        return e.returncode