Issue LIF-Initiative#853: Apply ruff formatting and lint auto-fixes (LIF-Initiative#855)

##### Description of Change

Applies `ruff check --fix` and `ruff format` across the codebase to
resolve accumulated formatting drift and lint auto-fixable issues.

- **Problem:** Multiple files had accumulated formatting inconsistencies
and auto-fixable lint issues (unused imports, trailing whitespace,
missing blank lines, single-line vs multi-line expressions).
- **Solution:** Ran `ruff check --fix` and `ruff format` against the
full codebase.
- **Side effects:** None — purely cosmetic/style changes with no logic
modifications.

33 files reformatted across components, bases, tests, integration tests,
scripts, and orchestrators.

##### Related Issues

Closes LIF-Initiative#853

##### Type of Change

- [x] Code refactoring

##### Project Area(s) Affected

- [x] bases/
- [x] components/
- [x] orchestrators/
- [x] Testing

---

##### Checklist

- [x] code passes linting checks (`uv run ruff check`)
- [x] code passes formatting checks (`uv run ruff format`)

##### Testing

- No logic changes — formatting only.

##### Additional Notes

9 remaining lint warnings (E721, F823) are not auto-fixable and are
pre-existing. They require manual review and are out of scope for this
PR.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Author: bjagg

bases/lif/semantic_search_mcp_server/core.py

@@ -24,10 +24,7 @@
 from lif.lif_schema_config import DEFAULT_ATTRIBUTE_KEYS, LIFSchemaConfig
 from lif.logging import get_logger
 from lif.schema_state_manager import SchemaStateManager
-from lif.semantic_search_service.core import (
-    run_mutation,
-    run_semantic_search,
-)
+from lif.semantic_search_service.core import run_mutation, run_semantic_search
 
 logger = get_logger(__name__)
 
@@ -119,9 +116,7 @@ async def schema_refresh(request: Request) -> JSONResponse:
 
 
 @mcp.tool(
-    name="lif_query",
-    description="Use this tool to run a LIF data query",
-    annotations={"title": "Execute LIF Query"},
+    name="lif_query", description="Use this tool to run a LIF data query", annotations={"title": "Execute LIF Query"}
 )
 async def lif_query(
     filter: Annotated[Filter, Field(description="Parameters for LIF query")],

cloudformation/cf-env-check.py

@@ -19,12 +19,11 @@
 
 import argparse
 import difflib
-import os
 import re
 import sys
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Iterable, List, Optional, Sequence, Tuple
+from typing import List, Optional, Sequence, Tuple
 
 # -----------------------------
 # Config
@@ -35,9 +34,7 @@
     re.compile(r"arn:aws:[^:]+:[^:]*:[^:]*:"),  # generic ARN noise
 ]
 
-ECR_IMAGE_REF_RE = re.compile(
-    r'([0-9]{12}\.dkr\.ecr\.[a-z0-9-]+\.amazonaws\.com/[A-Za-z0-9._\-/]+):([A-Za-z0-9._-]+)'
-)
+ECR_IMAGE_REF_RE = re.compile(r"([0-9]{12}\.dkr\.ecr\.[a-z0-9-]+\.amazonaws\.com/[A-Za-z0-9._\-/]+):([A-Za-z0-9._-]+)")
 
 # Heuristic: only count a non-env diff as a "warning" if it hits any of these.
 SUSPICIOUS_NONENV_PATTERNS = [
@@ -55,12 +52,14 @@
 # Data types
 # -----------------------------
 
+
 @dataclass(frozen=True)
 class Pair:
     key: str
     dev: Path
     demo: Path
 
+
 @dataclass
 class CheckResult:
     key: str
@@ -74,17 +73,21 @@ class CheckResult:
     docker_warnings: List[str]
     cross_env_warnings: List[str]
 
+
 # -----------------------------
 # Helpers
 # -----------------------------
 
+
 def read_text(path: Path) -> str:
     return path.read_text(encoding="utf-8", errors="replace")
 
+
 def split_lines_keepends(s: str) -> List[str]:
     # difflib wants lists of lines *with* newline endings to preserve formatting
     return s.splitlines(keepends=True)
 
+
 def canonicalize_env(s: str) -> str:
     """
     Normalize common dev/demo markers -> __ENV__ so only unexpected diffs remain.
@@ -107,20 +110,15 @@ def canonicalize_env(s: str) -> str:
     s = ECR_IMAGE_REF_RE.sub(r"\1:__TAG__", s)
     return s
 
+
 def unified_diff(a_text: str, b_text: str, a_name: str, b_name: str) -> str:
     a_lines = split_lines_keepends(a_text)
     b_lines = split_lines_keepends(b_text)
-    diff_lines = difflib.unified_diff(
-        a_lines,
-        b_lines,
-        fromfile=a_name,
-        tofile=b_name,
-        lineterm="",
-        n=3,
-    )
+    diff_lines = difflib.unified_diff(a_lines, b_lines, fromfile=a_name, tofile=b_name, lineterm="", n=3)
     # difflib.unified_diff already provides lines without trailing newline when lineterm=""
     return "\n".join(diff_lines)
 
+
 def diff_changed_lines(diff_text: str) -> List[str]:
     """
     Return only changed lines from a unified diff:
@@ -132,6 +130,7 @@ def diff_changed_lines(diff_text: str) -> List[str]:
             out.append(line)
     return out
 
+
 def is_suspicious_nonenv(diff_text: str) -> bool:
     changed = diff_changed_lines(diff_text)
     for line in changed:
@@ -140,10 +139,14 @@ def is_suspicious_nonenv(diff_text: str) -> bool:
                 return True
     return False
 
+
 def any_allowlisted(line: str, allowlist: Sequence[re.Pattern]) -> bool:
     return any(p.search(line) for p in allowlist)
 
-def find_cross_env_leftovers(lines: Sequence[str], forbidden_token: str, allowlist: Sequence[re.Pattern]) -> List[Tuple[int, str]]:
+
+def find_cross_env_leftovers(
+    lines: Sequence[str], forbidden_token: str, allowlist: Sequence[re.Pattern]
+) -> List[Tuple[int, str]]:
     """
     Find occurrences of forbidden_token as a whole word in lines that are not allowlisted.
     Returns list of (lineno, line).
@@ -155,6 +158,7 @@ def find_cross_env_leftovers(lines: Sequence[str], forbidden_token: str, allowli
             hits.append((i, line.rstrip("\n")))
     return hits
 
+
 def extract_ecr_images(content: str) -> List[Tuple[str, str]]:
     """
     Return list of (image_repo, tag)
@@ -164,6 +168,7 @@ def extract_ecr_images(content: str) -> List[Tuple[str, str]]:
         hits.append((m.group(1), m.group(2)))
     return hits
 
+
 def check_docker_policy(env: str, filename: str, content: str) -> List[str]:
     """
     env: 'dev' or 'demo'
@@ -176,6 +181,7 @@ def check_docker_policy(env: str, filename: str, content: str) -> List[str]:
             warnings.append(f"{filename}: demo files must NOT use :latest but found :latest ({image}:{tag})")
     return warnings
 
+
 def list_env_files(directory: Path) -> List[Path]:
     out: List[Path] = []
     for p in directory.iterdir():
@@ -185,14 +191,15 @@ def list_env_files(directory: Path) -> List[Path]:
                 out.append(p)
     return out
 
+
 def pair_files(paths: Sequence[Path]) -> Tuple[List[Pair], List[str]]:
     dev_map = {}
     demo_map = {}
     for p in paths:
         if p.name.startswith("dev-"):
-            dev_map[p.name[len("dev-"):]] = p
+            dev_map[p.name[len("dev-") :]] = p
         elif p.name.startswith("demo-"):
-            demo_map[p.name[len("demo-"):]] = p
+            demo_map[p.name[len("demo-") :]] = p
 
     keys = sorted(set(dev_map) | set(demo_map))
     pairs: List[Pair] = []
@@ -208,39 +215,32 @@ def pair_files(paths: Sequence[Path]) -> Tuple[List[Pair], List[str]]:
 
     return pairs, orphans
 
+
 def print_section(title: str) -> None:
     print("\n" + "=" * 60)
     print(title)
     print("=" * 60)
 
+
 # -----------------------------
 # Main check logic
 # -----------------------------
 
+
 def check_pair(pair: Pair, allowlist: Sequence[re.Pattern], show_full_diff: bool) -> CheckResult:
     dev_text = read_text(pair.dev)
     demo_text = read_text(pair.demo)
 
     # Full diff (demo vs dev) to match your usual reading order
-    full = unified_diff(
-        demo_text,
-        dev_text,
-        a_name=pair.demo.name,
-        b_name=pair.dev.name,
-    )
+    full = unified_diff(demo_text, dev_text, a_name=pair.demo.name, b_name=pair.dev.name)
 
     # Normalized diff
     demo_norm = canonicalize_env(demo_text)
     dev_norm = canonicalize_env(dev_text)
-    norm = unified_diff(
-        demo_norm,
-        dev_norm,
-        a_name=pair.demo.name + ".norm",
-        b_name=pair.dev.name + ".norm",
-    )
+    norm = unified_diff(demo_norm, dev_norm, a_name=pair.demo.name + ".norm", b_name=pair.dev.name + ".norm")
 
-    env_only = (full != "" and norm == "")
-    has_nonenv = (norm != "")
+    env_only = full != "" and norm == ""
+    has_nonenv = norm != ""
     suspicious = is_suspicious_nonenv(norm) if has_nonenv else False
 
     # Docker policy warnings
@@ -285,10 +285,15 @@ def check_pair(pair: Pair, allowlist: Sequence[re.Pattern], show_full_diff: bool
         cross_env_warnings=cross_env_warnings,
     )
 
+
 def main(argv: Optional[Sequence[str]] = None) -> int:
     ap = argparse.ArgumentParser(add_help=True)
     ap.add_argument("--dir", default=".", help="Directory to scan for dev-* and demo-* files")
-    ap.add_argument("--no-diff", action="store_true", help="Do not print full diffs; still prints normalized diffs for non-env cases")
+    ap.add_argument(
+        "--no-diff",
+        action="store_true",
+        help="Do not print full diffs; still prints normalized diffs for non-env cases",
+    )
     ap.add_argument("--allow", action="append", default=[], help="Regex allowlist for cross-env leftovers (can repeat)")
     ap.add_argument("--show-env-only", action="store_true", help="Also print env-only full diffs (can be noisy)")
 
@@ -391,5 +396,6 @@ def main(argv: Optional[Sequence[str]] = None) -> int:
         print(" -", w)
     return 2
 
+
 if __name__ == "__main__":
     raise SystemExit(main())

components/lif/api_key_auth/core.py

@@ -48,9 +48,7 @@ class ApiKeyConfig:
     public_path_prefixes: Set[str] = field(default_factory=lambda: {"/docs", "/openapi.json"})
 
     # HTTP methods that require authentication (empty set = no auth required)
-    methods_requiring_auth: Set[str] = field(
-        default_factory=lambda: {"GET", "POST", "PUT", "DELETE", "PATCH"}
-    )
+    methods_requiring_auth: Set[str] = field(default_factory=lambda: {"GET", "POST", "PUT", "DELETE", "PATCH"})
 
     @classmethod
     def from_environment(cls, prefix: str = "API_AUTH") -> "ApiKeyConfig":
@@ -82,18 +80,10 @@ def from_environment(cls, prefix: str = "API_AUTH") -> "ApiKeyConfig":
                 if key and name:
                     api_keys[key] = name
 
-        public_paths = cls._parse_csv_set(
-            os.environ.get(f"{prefix}__PUBLIC_PATHS", "/health,/health-check")
-        )
-        public_prefixes = cls._parse_csv_set(
-            os.environ.get(f"{prefix}__PUBLIC_PATH_PREFIXES", "/docs,/openapi.json")
-        )
+        public_paths = cls._parse_csv_set(os.environ.get(f"{prefix}__PUBLIC_PATHS", "/health,/health-check"))
+        public_prefixes = cls._parse_csv_set(os.environ.get(f"{prefix}__PUBLIC_PATH_PREFIXES", "/docs,/openapi.json"))
 
-        return cls(
-            api_keys=api_keys,
-            public_paths=public_paths,
-            public_path_prefixes=public_prefixes,
-        )
+        return cls(api_keys=api_keys, public_paths=public_paths, public_path_prefixes=public_prefixes)
 
     @staticmethod
     def _parse_csv_set(value: str) -> Set[str]:
@@ -158,9 +148,7 @@ async def dispatch(self, request: Request, call_next):
         if not client_name:
             logger.warning("Request to %s rejected: invalid API key", path)
             return JSONResponse(
-                status_code=401,
-                content={"detail": "Invalid API key."},
-                headers={"WWW-Authenticate": "X-API-Key"},
+                status_code=401, content={"detail": "Invalid API key."}, headers={"WWW-Authenticate": "X-API-Key"}
             )
 
         # Store client info for downstream use (logging, auditing, etc.)

components/lif/datatypes/core.py

@@ -82,9 +82,7 @@ class LIFQueryPersonFilter(BaseModel):
     model_config = ConfigDict(populate_by_name=True)
 
     # Use alias="Person" to accept PascalCase from GraphQL API while keeping lowercase internally
-    person: LIFPersonIdentifiers = Field(
-        ..., alias="Person", description="Person identifier for the query"
-    )
+    person: LIFPersonIdentifiers = Field(..., alias="Person", description="Person identifier for the query")
 
 
 class LIFQueryFilter(RootModel[LIFQueryPersonFilter]):

components/lif/lif_schema_config/__init__.py

@@ -18,10 +18,7 @@
     print(config.graphql_query_name)  # "person"
 """
 
-from lif.lif_schema_config.core import (
-    LIFSchemaConfig,
-    LIFSchemaConfigError,
-)
+from lif.lif_schema_config.core import LIFSchemaConfig, LIFSchemaConfigError
 from lif.lif_schema_config.naming import (
     normalize_identifier_type,
     safe_identifier,
@@ -56,12 +53,7 @@
     list_schema_names,
     resolve_ref,
 )
-from lif.lif_schema_config.type_mappings import (
-    PYTHON_TO_XSD,
-    XSD_TO_PYTHON,
-    python_type_for_xsd,
-    xsd_type_for_python,
-)
+from lif.lif_schema_config.type_mappings import PYTHON_TO_XSD, XSD_TO_PYTHON, python_type_for_xsd, xsd_type_for_python
 
 __all__ = [
     # Core config

components/lif/lif_schema_config/core.py

@@ -89,9 +89,7 @@ class LIFSchemaConfig:
 
     # Root Type Configuration
     root_type_name: str = "Person"
-    additional_root_types: List[str] = field(
-        default_factory=lambda: ["Course", "Organization", "Credential"]
-    )
+    additional_root_types: List[str] = field(default_factory=lambda: ["Course", "Organization", "Credential"])
 
     # Query Planner URLs
     query_planner_base_url: str = "http://localhost:8002"
@@ -170,21 +168,16 @@ def from_environment(cls) -> "LIFSchemaConfig":
             LIFSchemaConfig: Configuration loaded from environment.
         """
         # Parse root types
-        root_type_name = os.getenv("LIF_GRAPHQL_ROOT_TYPE_NAME",
-                                   os.getenv("LIF_GRAPHQL_ROOT_NODE", "Person"))
+        root_type_name = os.getenv("LIF_GRAPHQL_ROOT_TYPE_NAME", os.getenv("LIF_GRAPHQL_ROOT_NODE", "Person"))
 
         # Parse additional root types (these serve as reference data)
         root_nodes_str = os.getenv("LIF_GRAPHQL_ROOT_NODES", "Course,Organization,Credential")
         additional_root_types = [
-            node.strip() for node in root_nodes_str.split(",")
-            if node.strip() and node.strip() != root_type_name
+            node.strip() for node in root_nodes_str.split(",") if node.strip() and node.strip() != root_type_name
         ]
 
         # Support both new and old env var names for top_k
-        top_k = int(os.getenv(
-            "SEMANTIC_SEARCH__TOP_K",
-            os.getenv("TOP_K", "200")
-        ))
+        top_k = int(os.getenv("SEMANTIC_SEARCH__TOP_K", os.getenv("TOP_K", "200")))
 
         return cls(
             # Root types
@@ -198,23 +191,12 @@ def from_environment(cls) -> "LIFSchemaConfig":
             mdr_api_auth_token=os.getenv("LIF_MDR_API_AUTH_TOKEN", "no_auth_token_set"),
             mdr_timeout_seconds=int(os.getenv("MDR_TIMEOUT_SECONDS", "30")),
             openapi_data_model_id=os.getenv("OPENAPI_DATA_MODEL_ID"),
-            openapi_json_filename=os.getenv(
-                "OPENAPI_JSON_FILENAME",
-                "openapi_constrained_with_interactions.json"
-            ),
-            use_openapi_from_file=os.getenv(
-                "USE_OPENAPI_DATA_MODEL_FROM_FILE", "false"
-            ).lower() == "true",
+            openapi_json_filename=os.getenv("OPENAPI_JSON_FILENAME", "openapi_constrained_with_interactions.json"),
+            use_openapi_from_file=os.getenv("USE_OPENAPI_DATA_MODEL_FROM_FILE", "false").lower() == "true",
             # Semantic search
-            semantic_search_model_name=os.getenv(
-                "SEMANTIC_SEARCH__MODEL_NAME",
-                "all-MiniLM-L6-v2"
-            ),
+            semantic_search_model_name=os.getenv("SEMANTIC_SEARCH__MODEL_NAME", "all-MiniLM-L6-v2"),
             semantic_search_top_k=top_k,
-            semantic_search_timeout=int(os.getenv(
-                "SEMANTIC_SEARCH__GRAPHQL_TIMEOUT__READ",
-                "300"
-            )),
+            semantic_search_timeout=int(os.getenv("SEMANTIC_SEARCH__GRAPHQL_TIMEOUT__READ", "300")),
         )
 
     # Computed properties for convenience