Add Default Value for vLLM Env Vars

[Jdubrick]

What does this PR do?:

• Adds default value of empty string for vLLM envs to prevent error if missing

Which issue(s) this PR fixes:

N/A

PR acceptance criteria:

Testing and documentation do not need to be complete in order for this PR to be approved. We just need to ensure tracking issues are opened and linked to this PR, if they are not in the PR scope due to various constraints.

• Tested and Verified

• Documentation (READMEs, Product Docs, Blogs, Education Modules, etc.)

How to test changes / Special notes to the reviewer:

[michael-valdron]

@Jdubrick Might of missed something but I'm still getting the error with blank variables:

INFO     2025-11-28 22:07:15,672 llama_stack.core.utils.config_resolution:45 config_resolution: Using file path: run.yaml                             
INFO     2025-11-28 22:07:15,675 llama_stack.cli.stack.run:129 server: Using run configuration: /app-root/run.yaml                                    
Traceback (most recent call last):
  File "/app-root/.venv/bin/llama", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/llama.py", line 53, in main
    parser.run(args)
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/llama.py", line 47, in run
    args.func(args)
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/stack/run.py", line 137, in _run_stack_run_cmd
    config = parse_and_maybe_upgrade_config(config_dict)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/core/configure.py", line 180, in parse_and_maybe_upgrade_config
    processed_config_dict = replace_env_vars(config_dict)
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/core/stack.py", line 150, in replace_env_vars
    raise EnvVarError(e.var_name, e.path) from None
llama_stack.core.stack.EnvVarError: Environment variable 'VLLM_URL' not set or empty at providers.inference[0].config.url. Use ${env.VLLM_URL:=default_value} to provide a default value, ${env.VLLM_URL:+value_if_set} to make the field conditional, or ensure the environment variable is set.

[michael-valdron]

@Jdubrick Might of missed something but I'm still getting the error with blank variables:

INFO     2025-11-28 22:07:15,672 llama_stack.core.utils.config_resolution:45 config_resolution: Using file path: run.yaml                             
INFO     2025-11-28 22:07:15,675 llama_stack.cli.stack.run:129 server: Using run configuration: /app-root/run.yaml                                    
Traceback (most recent call last):
  File "/app-root/.venv/bin/llama", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/llama.py", line 53, in main
    parser.run(args)
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/llama.py", line 47, in run
    args.func(args)
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/cli/stack/run.py", line 137, in _run_stack_run_cmd
    config = parse_and_maybe_upgrade_config(config_dict)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/core/configure.py", line 180, in parse_and_maybe_upgrade_config
    processed_config_dict = replace_env_vars(config_dict)
                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app-root/.venv/lib64/python3.12/site-packages/llama_stack/core/stack.py", line 150, in replace_env_vars
    raise EnvVarError(e.var_name, e.path) from None
llama_stack.core.stack.EnvVarError: Environment variable 'VLLM_URL' not set or empty at providers.inference[0].config.url. Use ${env.VLLM_URL:=default_value} to provide a default value, ${env.VLLM_URL:+value_if_set} to make the field conditional, or ensure the environment variable is set.

Re-ran this with a new build, confirmed it works. lgtm ✔️

Must of ran it with quay.io/redhat-ai-dev/llama-stack last time 🤦