fix: enforce stricter ASCII rules lint rules in Ruff (#2062)

# What does this PR do?

- Added new Ruff lint rules to detect ambiguous or non-ASCII characters:
- Added per-file ignores where Unicode usage is still required.
- Fixed whatever had to be fixed

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

llama_stack/cli/stack/run.py

@@ -119,7 +119,7 @@ class StackRun(Subcommand):
 
         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)}"
+                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}")

llama_stack/distribution/build.py

@@ -47,14 +47,13 @@ def get_provider_dependencies(
         providers = config.distribution_spec.providers
     deps = []
     registry = get_provider_registry(config)
-
     for api_str, provider_or_providers in providers.items():
         providers_for_api = registry[Api(api_str)]
 
         providers = provider_or_providers if isinstance(provider_or_providers, list) else [provider_or_providers]
 
         for provider in providers:
-            # Providers from BuildConfig and RunConfig are subtly different – not great
+            # Providers from BuildConfig and RunConfig are subtly different - not great
             provider_type = provider if isinstance(provider, str) else provider.provider_type
 
             if provider_type not in providers_for_api:

pyproject.toml

@@ -144,15 +144,25 @@ exclude = [
 
 [tool.ruff.lint]
 select = [
-    "B",   # flake8-bugbear
+    "B",       # flake8-bugbear
-    "B9",  # flake8-bugbear subset
+    "B9",      # flake8-bugbear subset
-    "C",   # comprehensions
+    "C",       # comprehensions
-    "E",   # pycodestyle
+    "E",       # pycodestyle
-    "F",   # Pyflakes
+    "F",       # Pyflakes
-    "N",   # Naming
+    "N",       # Naming
-    "W",   # Warnings
+    "W",       # Warnings
-    "DTZ", # datetime rules
+    "DTZ",     # datetime rules
-    "I",   # isort (imports order)
+    "I",       # isort (imports order)
+    "RUF001",  # Checks for ambiguous Unicode characters in strings
+    "RUF002",  # Checks for ambiguous Unicode characters in docstrings
+    "RUF003",  # Checks for ambiguous Unicode characters in comments
+    "PLC2401", # Checks for the use of non-ASCII characters in variable names
+    "PLC2403", # Checks for the use of non-ASCII characters in import statements
+    "PLE2510", # Checks for strings that contain the control character BS.
+    "PLE2512", # Checks for strings that contain the raw control character SUB.
+    "PLE2513", # Checks for strings that contain the raw control character ESC.
+    "PLE2514", # Checks for strings that contain the raw control character NUL (0 byte).
+    "PLE2515", # Checks for strings that contain the zero width space character.
 ]
 ignore = [
     # The following ignores are desired by the project maintainers.
@@ -165,10 +175,18 @@ ignore = [
     # These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later.
     "C901", # Complexity of the function is too high
 ]
+unfixable = [
+    "PLE2515",
+] # Do not fix this automatically since ruff will replace the zero-width space with \u200b - let's do it manually
 
 # Ignore the following errors for the following files
 [tool.ruff.lint.per-file-ignores]
 "tests/**/*.py" = ["DTZ"] # Ignore datetime rules for tests
+"llama_stack/providers/inline/scoring/basic/utils/ifeval_utils.py" = ["RUF001"]
+"llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py" = [
+    "RUF001",
+    "PLE2515",
+]
 
 [tool.mypy]
 mypy_path = ["llama_stack"]