refactor(server): replace print statements with logger (#1250)

# What does this PR do?

- Introduced logging in `StackRun` to replace print-based messages
- Improved error handling for config file loading and parsing
- Replaced `cprint` with `logger.error` for consistent error messaging
- Ensured logging is used in `server.py` for startup, shutdown, and
runtime messages
- Added missing exception handling for invalid providers

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

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

llama_stack/cli/stack/run.py

@@ -5,6 +5,7 @@
 # the root directory of this source tree.
 
 import argparse
+import logging
 import os
 from pathlib import Path
 
@@ -12,6 +13,8 @@ from llama_stack.cli.subcommand import Subcommand
 
 REPO_ROOT = Path(__file__).parent.parent.parent.parent
 
+logger = logging.getLogger(__name__)
+
 
 class StackRun(Subcommand):
     def __init__(self, subparsers: argparse._SubParsersAction):
@@ -70,12 +73,10 @@ class StackRun(Subcommand):
             type=str,
             help="Image Type used during the build. This can be either conda or container or venv.",
             choices=["conda", "container", "venv"],
-            default="conda",
         )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
         import yaml
-        from termcolor import cprint
 
         from llama_stack.distribution.build import ImageType
         from llama_stack.distribution.configure import parse_and_maybe_upgrade_config
@@ -85,10 +86,6 @@ class StackRun(Subcommand):
         )
         from llama_stack.distribution.utils.exec import formulate_run_args, run_with_pty
 
-        if not args.config:
-            self.parser.error("Must specify a config file to run")
-            return
-
         config_file = Path(args.config)
         has_yaml_suffix = args.config.endswith(".yaml")
         template_name = None
@@ -115,11 +112,23 @@ class StackRun(Subcommand):
             self.parser.error(
                 f"File {str(config_file)} does not exist.\n\nPlease run `llama stack build` to generate (and optionally edit) a run.yaml file"
             )
-            return
 
-        print(f"Using run configuration: {config_file}")
+        if not config_file.is_file():
+            self.parser.error(
+                f"Config file must be a valid file path, '{config_file}’ is not a file: type={type(config_file)}"
+            )
+
+        logger.info(f"Using run configuration: {config_file}")
+
+        try:
             config_dict = yaml.safe_load(config_file.read_text())
+        except yaml.parser.ParserError as e:
+            self.parser.error(f"failed to load config file '{config_file}':\n {e}")
+
+        try:
             config = parse_and_maybe_upgrade_config(config_dict)
+        except AttributeError as e:
+            self.parser.error(f"failed to parse config file '{config_file}':\n {e}")
 
         run_args = formulate_run_args(args.image_type, args.image_name, config, template_name)
 
@@ -129,18 +138,10 @@ class StackRun(Subcommand):
 
         for env_var in args.env:
             if "=" not in env_var:
-                cprint(
+                self.parser.error(f"Environment variable '{env_var}' must be in KEY=VALUE format")
-                    f"Environment variable '{env_var}' must be in KEY=VALUE format",
-                    color="red",
-                )
-                return
             key, value = env_var.split("=", 1)  # split on first = only
             if not key:
-                cprint(
+                self.parser.error(f"Environment variable '{env_var}' has empty key")
-                    f"Environment variable '{env_var}' has empty key",
-                    color="red",
-                )
-                return
             run_args.extend(["--env", f"{key}={value}"])
 
         if args.tls_keyfile and args.tls_certfile:

llama_stack/distribution/server/server.py

@@ -142,7 +142,7 @@ def handle_signal(app, signum, _) -> None:
         not block the current execution.
     """
     signame = signal.Signals(signum).name
-    print(f"Received signal {signame} ({signum}). Exiting gracefully...")
+    logger.info(f"Received signal {signame} ({signum}). Exiting gracefully...")
 
     async def shutdown():
         try:
@@ -184,9 +184,9 @@ def handle_signal(app, signum, _) -> None:
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
-    print("Starting up")
+    logger.info("Starting up")
     yield
-    print("Shutting down")
+    logger.info("Shutting down")
     for impl in app.__llama_stack_impls__.values():
         await impl.shutdown()
 
@@ -352,10 +352,10 @@ def main():
         for env_pair in args.env:
             try:
                 key, value = validate_env_pair(env_pair)
-                print(f"Setting CLI environment variable {key} => {value}")
+                logger.info(f"Setting CLI environment variable {key} => {value}")
                 os.environ[key] = value
             except ValueError as e:
-                print(f"Error: {str(e)}")
+                logger.error(f"Error: {str(e)}")
                 sys.exit(1)
 
     if args.yaml_config:
@@ -363,12 +363,12 @@ def main():
         config_file = Path(args.yaml_config)
         if not config_file.exists():
             raise ValueError(f"Config file {config_file} does not exist")
-        print(f"Using config file: {config_file}")
+        logger.info(f"Using config file: {config_file}")
     elif args.template:
         config_file = Path(REPO_ROOT) / "llama_stack" / "templates" / args.template / "run.yaml"
         if not config_file.exists():
             raise ValueError(f"Template {args.template} does not exist")
-        print(f"Using template {args.template} config file: {config_file}")
+        logger.info(f"Using template {args.template} config file: {config_file}")
     else:
         raise ValueError("Either --yaml-config or --template must be provided")
 
@@ -376,9 +376,9 @@ def main():
         config = replace_env_vars(yaml.safe_load(fp))
         config = StackRunConfig(**config)
 
-    print("Run configuration:")
+    logger.info("Run configuration:")
     safe_config = redact_sensitive_fields(config.model_dump())
-    print(yaml.dump(safe_config, indent=2))
+    logger.info(yaml.dump(safe_config, indent=2))
 
     app = FastAPI(lifespan=lifespan)
     app.add_middleware(TracingMiddleware)
@@ -387,7 +387,8 @@ def main():
 
     try:
         impls = asyncio.run(construct_stack(config))
-    except InvalidProviderError:
+    except InvalidProviderError as e:
+        logger.error(f"Error: {str(e)}")
         sys.exit(1)
 
     if Api.telemetry in impls:
@@ -432,7 +433,7 @@ def main():
                     )
                 )
 
-        cprint(f"Serving API {api_str}", "white", attrs=["bold"])
+        logger.info(f"Serving API {api_str}")
         for endpoint in endpoints:
             cprint(f" {endpoint.method.upper()} {endpoint.route}", "white")
 
@@ -462,10 +463,10 @@ def main():
             "ssl_keyfile": keyfile,
             "ssl_certfile": certfile,
         }
-        print(f"HTTPS enabled with certificates:\n  Key: {keyfile}\n  Cert: {certfile}")
+        logger.info(f"HTTPS enabled with certificates:\n  Key: {keyfile}\n  Cert: {certfile}")
 
     listen_host = ["::", "0.0.0.0"] if not args.disable_ipv6 else "0.0.0.0"
-    print(f"Listening on {listen_host}:{port}")
+    logger.info(f"Listening on {listen_host}:{port}")
 
     uvicorn_config = {
         "app": app,