ci: add ruff linting and mypy type checking

Add ruff and mypy to dev dependencies with configuration in pyproject.toml.
Add a lint CI job that runs ruff check, ruff format --check, and mypy.
Auto-fix import sorting and formatting across the codebase. Exclude
alembic/versions from linting (auto-generated migrations). Ignore B008
(FastAPI Depends pattern) and RUF001 (unicode in user-facing strings).

21 ruff lint errors and 50 mypy errors remain for manual review.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/services/domains/dbops/__init__.py

@@ -1,8 +1,8 @@
 from app.services.domains.dbops.application import run_publication_link_repair
+from app.services.domains.dbops.integrity import collect_integrity_report
 from app.services.domains.dbops.near_duplicate_repair import (
     run_publication_near_duplicate_repair,
 )
-from app.services.domains.dbops.integrity import collect_integrity_report
 from app.services.domains.dbops.query import list_repair_jobs
 
 __all__ = [

app/services/domains/dbops/application.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any
 
 from sqlalchemy import delete, exists, func, select, update
@@ -8,7 +8,6 @@ from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import DataRepairJob, IngestionQueueItem, Publication, ScholarProfile, ScholarPublication
 
-
 REPAIR_STATUS_PLANNED = "planned"
 REPAIR_STATUS_RUNNING = "running"
 REPAIR_STATUS_COMPLETED = "completed"
@@ -18,7 +17,7 @@ SCOPE_MODE_ALL_USERS = "all_users"
 
 
 def _utcnow() -> datetime:
-    return datetime.now(timezone.utc)
+    return datetime.now(UTC)
 
 
 def _normalize_scope_mode(scope_mode: str) -> str:
@@ -105,11 +104,7 @@ async def _count_orphan_publications(db_session: AsyncSession) -> int:
     stmt = (
         select(func.count())
         .select_from(Publication)
-        .where(
-            ~exists(
-                select(1).where(ScholarPublication.publication_id == Publication.id)
-            )
-        )
+        .where(~exists(select(1).where(ScholarPublication.publication_id == Publication.id)))
     )
     result = await db_session.execute(stmt)
     return int(result.scalar_one() or 0)
@@ -158,9 +153,7 @@ def _job_summary(
 
 async def _delete_links_for_targets(db_session: AsyncSession, *, target_scholar_profile_ids: list[int]) -> int:
     result = await db_session.execute(
-        delete(ScholarPublication).where(
-            ScholarPublication.scholar_profile_id.in_(target_scholar_profile_ids)
-        )
+        delete(ScholarPublication).where(ScholarPublication.scholar_profile_id.in_(target_scholar_profile_ids))
     )
     return int(result.rowcount or 0)
 
@@ -171,9 +164,7 @@ async def _delete_queue_for_targets(
     user_id: int | None,
     target_scholar_profile_ids: list[int],
 ) -> int:
-    stmt = delete(IngestionQueueItem).where(
-        IngestionQueueItem.scholar_profile_id.in_(target_scholar_profile_ids)
-    )
+    stmt = delete(IngestionQueueItem).where(IngestionQueueItem.scholar_profile_id.in_(target_scholar_profile_ids))
     if user_id is not None:
         stmt = stmt.where(IngestionQueueItem.user_id == user_id)
     result = await db_session.execute(stmt)
@@ -203,9 +194,7 @@ async def _reset_scholar_tracking_state(
 
 async def _delete_orphan_publications(db_session: AsyncSession) -> int:
     result = await db_session.execute(
-        delete(Publication).where(
-            ~exists(select(1).where(ScholarPublication.publication_id == Publication.id))
-        )
+        delete(Publication).where(~exists(select(1).where(ScholarPublication.publication_id == Publication.id)))
     )
     return int(result.rowcount or 0)
 

app/services/domains/dbops/integrity.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any
 
 from sqlalchemy import func, select, text
@@ -168,7 +168,7 @@ async def collect_integrity_report(db_session: AsyncSession) -> dict[str, Any]:
 
     return {
         "status": _status_from_issues(failures=failures, warnings=warnings),
-        "checked_at": datetime.now(timezone.utc).isoformat(),
+        "checked_at": datetime.now(UTC).isoformat(),
         "failures": failures,
         "warnings": warnings,
         "checks": checks,

app/services/domains/dbops/near_duplicate_repair.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import Any
 
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -17,7 +17,7 @@ NEAR_DUP_DEFAULT_MAX_CLUSTERS = 25
 
 
 def _utcnow() -> datetime:
-    return datetime.now(timezone.utc)
+    return datetime.now(UTC)
 
 
 def _normalized_cluster_keys(values: list[str] | None) -> list[str]:

app/services/domains/dbops/query.py

@@ -16,7 +16,5 @@ async def list_repair_jobs(
     limit: int = 50,
 ) -> list[DataRepairJob]:
     bounded = _bounded_limit(limit)
-    result = await db_session.execute(
-        select(DataRepairJob).order_by(DataRepairJob.created_at.desc()).limit(bounded)
-    )
+    result = await db_session.execute(select(DataRepairJob).order_by(DataRepairJob.created_at.desc()).limit(bounded))
     return list(result.scalars())