fix: resolve all mypy type errors across service modules

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

app/services/arxiv/client.py

@@ -232,7 +232,7 @@ async def _request_arxiv_feed(
         timeout_value = _timeout_seconds(timeout_seconds)
         headers = {"User-Agent": f"scholar-scraper/1.0 (mailto:{_contact_email(request_email)})"}
         async with httpx.AsyncClient(timeout=timeout_value, follow_redirects=True, headers=headers) as client:
-            return await client.get(_ARXIV_API_URL, params=params)
+            return await client.get(_ARXIV_API_URL, params=params)  # type: ignore[arg-type]
 
     return await run_with_global_arxiv_limit(
         fetch=_fetch,

app/services/dbops/application.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 from datetime import UTC, datetime
 from typing import Any
 
-from sqlalchemy import delete, exists, func, select, update
+from sqlalchemy import CursorResult, delete, exists, func, select, update
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import DataRepairJob, IngestionQueueItem, Publication, ScholarProfile, ScholarPublication
@@ -152,7 +152,7 @@ def _job_summary(
 
 
 async def _delete_links_for_targets(db_session: AsyncSession, *, target_scholar_profile_ids: list[int]) -> int:
-    result = await db_session.execute(
+    result: CursorResult[Any] = await db_session.execute(  # type: ignore[assignment]
         delete(ScholarPublication).where(ScholarPublication.scholar_profile_id.in_(target_scholar_profile_ids))
     )
     return int(result.rowcount or 0)
@@ -167,7 +167,7 @@ async def _delete_queue_for_targets(
     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)
+    result: CursorResult[Any] = await db_session.execute(stmt)  # type: ignore[assignment]
     return int(result.rowcount or 0)
 
 
@@ -180,7 +180,7 @@ async def _reset_scholar_tracking_state(
     stmt = update(ScholarProfile).where(ScholarProfile.id.in_(target_scholar_profile_ids))
     if user_id is not None:
         stmt = stmt.where(ScholarProfile.user_id == user_id)
-    result = await db_session.execute(
+    result: CursorResult[Any] = await db_session.execute(  # type: ignore[assignment]
         stmt.values(
             baseline_completed=False,
             last_initial_page_fingerprint_sha256=None,
@@ -193,7 +193,7 @@ async def _reset_scholar_tracking_state(
 
 
 async def _delete_orphan_publications(db_session: AsyncSession) -> int:
-    result = await db_session.execute(
+    result: CursorResult[Any] = await db_session.execute(  # type: ignore[assignment]
         delete(Publication).where(~exists(select(1).where(ScholarPublication.publication_id == Publication.id)))
     )
     return int(result.rowcount or 0)

app/services/ingestion/scheduler.py

@@ -4,6 +4,7 @@ import asyncio
 import logging
 from dataclasses import dataclass
 from datetime import UTC, datetime, timedelta
+from typing import Any
 
 from sqlalchemy import select
 
@@ -158,7 +159,7 @@ class SchedulerService:
                 continue
             await self._run_candidate(candidate)
 
-    async def _load_candidate_rows(self) -> list[tuple]:
+    async def _load_candidate_rows(self) -> list[Any]:
         session_factory = get_session_factory()
         async with session_factory() as session:
             result = await session.execute(
@@ -173,10 +174,10 @@ class SchedulerService:
                 .where(User.is_active.is_(True), UserSetting.auto_run_enabled.is_(True))
                 .order_by(UserSetting.user_id.asc())
             )
-            return result.all()
+            return list(result.all())
 
     @staticmethod
-    def _candidate_from_row(row: tuple, *, now_utc: datetime) -> _AutoRunCandidate | None:
+    def _candidate_from_row(row: Any, *, now_utc: datetime) -> _AutoRunCandidate | None:
         user_id, run_interval_minutes, request_delay_seconds, cooldown_until, cooldown_reason = row
         if cooldown_until is not None and cooldown_until.tzinfo is None:
             cooldown_until = cooldown_until.replace(tzinfo=UTC)

app/services/ingestion/scholar_processing.py

@@ -547,7 +547,7 @@ async def run_scholar_iteration(
     queue_delay_seconds: int,
 ) -> RunProgress:
     progress = RunProgress()
-    scholar_kwargs = {
+    scholar_kwargs: dict[str, Any] = {
         "request_delay_seconds": request_delay_seconds,
         "network_error_retries": network_error_retries,
         "retry_backoff_seconds": retry_backoff_seconds,

app/services/portability/exporting.py

@@ -23,7 +23,7 @@ def _serialize_export_scholar(profile: ScholarProfile) -> dict[str, Any]:
     }
 
 
-def _serialize_export_publication(row: tuple[Any, ...]) -> dict[str, Any]:
+def _serialize_export_publication(row: Any) -> dict[str, Any]:
     (
         scholar_id,
         cluster_id,

app/services/publications/pdf_queue_queries.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass
 from datetime import UTC, datetime, timedelta
+from typing import Any
 
 from sqlalchemy import Select, and_, func, literal, or_, select, union_all
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -43,7 +44,7 @@ def _retry_item_label(display_name: str | None, scholar_id: str | None) -> str:
 def _retry_item_from_publication(
     publication: Publication,
     *,
-    link_row: tuple | None,
+    link_row: Any | None,
 ) -> PublicationListItem:
     if link_row is None:
         scholar_profile_id = 0
@@ -270,7 +271,7 @@ class PdfQueueListItem:
     display_identifier: DisplayIdentifier | None = None
 
 
-def _queue_item_from_row(row: tuple) -> PdfQueueListItem:
+def _queue_item_from_row(row: Any) -> PdfQueueListItem:
     return PdfQueueListItem(
         publication_id=int(row[0]),
         title=str(row[1] or ""),
@@ -292,7 +293,7 @@ def _queue_item_from_row(row: tuple) -> PdfQueueListItem:
 async def _hydrated_queue_items(
     db_session: AsyncSession,
     *,
-    rows: list[tuple],
+    rows: list[Any],
 ) -> list[PdfQueueListItem]:
     items = [_queue_item_from_row(row) for row in rows]
     return await identifier_service.overlay_pdf_queue_items_with_display_identifiers(

app/services/publications/queries.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
 
 from datetime import datetime
+from typing import Any
 
-from sqlalchemy import Select, case, func, select
+from sqlalchemy import Select, case, false as sa_false, func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import (
@@ -124,7 +125,7 @@ def publications_query(
         stmt = stmt.where(ScholarPublication.is_read.is_(False))
     if mode == MODE_LATEST:
         if latest_run_id is None:
-            return stmt.where(False)
+            return stmt.where(sa_false())
         stmt = stmt.where(ScholarPublication.first_seen_run_id == latest_run_id)
     if snapshot_before is not None:
         stmt = stmt.where(ScholarPublication.created_at <= snapshot_before)
@@ -195,7 +196,7 @@ async def get_publication_item_for_user(
 
 
 def publication_list_item_from_row(
-    row: tuple,
+    row: Any,
     *,
     latest_run_id: int | None,
 ) -> PublicationListItem:
@@ -232,7 +233,7 @@ def publication_list_item_from_row(
     )
 
 
-def unread_item_from_row(row: tuple) -> UnreadPublicationItem:
+def unread_item_from_row(row: Any) -> UnreadPublicationItem:
     (
         publication_id,
         scholar_profile_id,

app/services/publications/read_state.py

@@ -1,6 +1,8 @@
 from __future__ import annotations
 
-from sqlalchemy import select, tuple_, update
+from typing import Any
+
+from sqlalchemy import CursorResult, select, tuple_, update
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import ScholarProfile, ScholarPublication
@@ -34,7 +36,7 @@ async def mark_all_unread_as_read_for_user(
         )
         .values(is_read=True)
     )
-    result = await db_session.execute(stmt)
+    result: CursorResult[Any] = await db_session.execute(stmt)  # type: ignore[assignment]
     await db_session.commit()
     return int(result.rowcount or 0)
 
@@ -62,7 +64,7 @@ async def mark_selected_as_read_for_user(
         )
         .values(is_read=True)
     )
-    result = await db_session.execute(stmt)
+    result: CursorResult[Any] = await db_session.execute(stmt)  # type: ignore[assignment]
     await db_session.commit()
     return int(result.rowcount or 0)
 
@@ -85,6 +87,6 @@ async def set_publication_favorite_for_user(
         )
         .values(is_favorite=bool(is_favorite))
     )
-    result = await db_session.execute(stmt)
+    result: CursorResult[Any] = await db_session.execute(stmt)  # type: ignore[assignment]
     await db_session.commit()
     return int(result.rowcount or 0)

app/services/runs/queue_queries.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+from typing import Any
+
 from sqlalchemy import and_, select
 
 from app.db.models import IngestionQueueItem, ScholarProfile
@@ -38,7 +40,7 @@ def queue_item_select(*, user_id: int):
     )
 
 
-def queue_list_item_from_row(row: tuple) -> QueueListItem:
+def queue_list_item_from_row(row: Any) -> QueueListItem:
     (
         item_id,
         scholar_profile_id,

app/services/scholars/author_search_cache.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from datetime import UTC, datetime, timedelta
+from typing import cast
 
 from sqlalchemy import delete, func, select
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -136,14 +137,14 @@ def _deserialize_parsed_author_search_page(payload: object) -> ParsedAuthorSearc
         state_reason=str(payload.get("state_reason", "")).strip() or "unknown",
         candidates=[
             ScholarSearchCandidate(
-                scholar_id=item["scholar_id"],
+                scholar_id=cast(str, item["scholar_id"]),
-                display_name=item["display_name"],
+                display_name=cast(str, item["display_name"]),
-                affiliation=item["affiliation"],
+                affiliation=cast("str | None", item["affiliation"]),
-                email_domain=item["email_domain"],
+                email_domain=cast("str | None", item["email_domain"]),
-                cited_by_count=item["cited_by_count"],
+                cited_by_count=cast("int | None", item["cited_by_count"]),
-                interests=item["interests"],
+                interests=cast("list[str]", item["interests"]),
-                profile_url=item["profile_url"],
+                profile_url=cast(str, item["profile_url"]),
-                profile_image_url=item["profile_image_url"],
+                profile_image_url=cast("str | None", item["profile_image_url"]),
             )
             for item in normalized_candidates
         ],