fix: resolve remaining ruff lint and mypy type errors

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

app/api/media.py

@@ -11,6 +11,7 @@ from app.api.errors import ApiException
 from app.db.models import User
 from app.db.session import get_db_session
 from app.services.domains.scholars import application as scholar_service
+from app.services.domains.scholars import uploads as scholar_uploads
 from app.settings import settings
 
 router = APIRouter(tags=["media"])
@@ -41,7 +42,7 @@ async def get_uploaded_scholar_image(
         )
 
     try:
-        image_path = scholar_service.resolve_upload_file_path(
+        image_path = scholar_uploads.resolve_upload_file_path(
             upload_dir=settings.scholar_image_upload_dir,
             relative_path=profile.profile_image_upload_path,
         )

app/api/routers/auth.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import logging
+from typing import NoReturn
 
 from fastapi import APIRouter, Depends, Request
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -61,7 +62,7 @@ def _serialize_user_payload(user: User) -> dict[str, object]:
     }
 
 
-def _raise_invalid_credentials(*, normalized_email: str) -> None:
+def _raise_invalid_credentials(*, normalized_email: str) -> NoReturn:
     structured_log(logger, "info", "api.auth.login_failed", email=normalized_email)
     raise ApiException(
         status_code=401,

app/api/routers/runs.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import asyncio
 import logging
 import re
 from typing import Any
@@ -32,6 +33,7 @@ from app.services.domains.settings import application as user_settings_service
 from app.settings import settings
 
 logger = logging.getLogger(__name__)
+_background_tasks: set[asyncio.Task[Any]] = set()
 
 router = APIRouter(prefix="/runs", tags=["api-runs"])
 ACTIVE_RUN_STATUSES = {RunStatus.RUNNING, RunStatus.RESOLVING}
@@ -656,11 +658,9 @@ async def run_manual(
         await db_session.commit()
 
         # Kick off background execution
-        import asyncio
-
         from app.db.session import get_session_factory
 
-        asyncio.create_task(
+        task = asyncio.create_task(
             ingest_service.execute_run(
                 session_factory=get_session_factory(),
                 run_id=run.id,
@@ -680,6 +680,8 @@ async def run_manual(
                 idempotency_key=idempotency_key,
             )
         )
+        _background_tasks.add(task)
+        task.add_done_callback(_background_tasks.discard)
 
         return success_payload(
             request,

app/api/routers/scholars.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import asyncio
 import logging
+from typing import Any
 
 from fastapi import APIRouter, Depends, File, Query, Request, UploadFile
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -29,6 +30,7 @@ from app.services.domains.portability import application as import_export_servic
 from app.services.domains.scholar import rate_limit as scholar_rate_limit
 from app.services.domains.scholar.source import ScholarSource
 from app.services.domains.scholars import application as scholar_service
+from app.services.domains.scholars import search_hints as scholar_search_hints
 from app.settings import settings
 
 logger = logging.getLogger(__name__)
@@ -110,7 +112,7 @@ def _serialize_scholar(profile) -> dict[str, object]:
     if profile.profile_image_upload_path:
         uploaded_image_url = _uploaded_image_media_path(int(profile.id))
 
-    profile_image_url, profile_image_source = scholar_service.resolve_profile_image(
+    profile_image_url, profile_image_source = scholar_search_hints.resolve_profile_image(
         profile,
         uploaded_image_url=uploaded_image_url,
     )
@@ -180,7 +182,7 @@ async def _hydrate_scholar_metadata_if_needed(
     return profile
 
 
-def _search_kwargs() -> dict[str, object]:
+def _search_kwargs() -> dict[str, Any]:
     return {
         "network_error_retries": settings.ingestion_network_error_retries,
         "retry_backoff_seconds": settings.ingestion_retry_backoff_seconds,
@@ -202,7 +204,7 @@ def _search_response_data(query: str, parsed) -> dict[str, object]:
         "query": query.strip(),
         "state": parsed.state.value,
         "state_reason": parsed.state_reason,
-        "action_hint": scholar_service.scrape_state_hint(
+        "action_hint": scholar_search_hints.scrape_state_hint(
             state=parsed.state,
             state_reason=parsed.state_reason,
         ),

app/security/csrf.py

@@ -54,7 +54,7 @@ class CSRFMiddleware(BaseHTTPMiddleware):
         if request_token is None and self._is_form_payload(request):
             body = await request.body()
             request_token = self._token_from_form_body(request, body)
-            request._receive = self._build_receive(body)  # type: ignore[attr-defined]
+            request._receive = self._build_receive(body)
 
         if not request_token or not compare_digest(str(session_token), str(request_token)):
             structured_log(

app/services/domains/arxiv/rate_limit.py

@@ -68,8 +68,7 @@ async def _run_serialized_fetch(
     source_path: str,
 ) -> tuple[httpx.Response, bool]:
     session_factory = get_session_factory()
-    async with session_factory() as db_session:
-        async with db_session.begin():
+    async with session_factory() as db_session, db_session.begin():
             await _acquire_arxiv_lock(db_session)
             runtime_state = await _load_runtime_state_for_update(db_session)
             wait_seconds = await _wait_for_allowed_slot_or_raise(

app/services/domains/ingestion/application.py

@@ -109,6 +109,9 @@ def _classify_failure_bucket(*, state: str, state_reason: str) -> str:
     return FAILURE_BUCKET_OTHER
 
 
+_background_tasks: set[asyncio.Task[Any]] = set()
+
+
 class ScholarIngestionService:
     def __init__(self, *, source: ScholarSource) -> None:
         self._source = source
@@ -287,8 +290,7 @@ class ScholarIngestionService:
         paged_parse_result: PagedParseResult,
     ) -> None:
         parsed_page = paged_parse_result.parsed_page
-        if parsed_page.state in {ParseState.OK, ParseState.NO_RESULTS}:
-            if any(code.startswith("layout_") for code in parsed_page.warnings):
+        if parsed_page.state in {ParseState.OK, ParseState.NO_RESULTS} and any(code.startswith("layout_") for code in parsed_page.warnings):
             raise RuntimeError(f"Layout warning marked as terminal for scholar_id={scholar_id}.")
         for publication in paged_parse_result.publications:
             if not publication.title.strip():
@@ -1490,7 +1492,7 @@ class ScholarIngestionService:
 
                 # Fire-and-forget enrichment in a separate background task
                 if intended_final_status not in (RunStatus.CANCELED,):
-                    asyncio.create_task(
+                    task = asyncio.create_task(
                         self._background_enrich(
                             session_factory,
                             run_id=run.id,
@@ -1498,6 +1500,8 @@ class ScholarIngestionService:
                             openalex_api_key=getattr(user_settings, "openalex_api_key", None),
                         )
                     )
+                    _background_tasks.add(task)
+                    task.add_done_callback(_background_tasks.discard)
             except Exception as exc:
                 await db_session.rollback()
                 logger.exception("ingestion.background_run_failed", extra={"run_id": run_id, "user_id": user_id})
@@ -2807,7 +2811,7 @@ class ScholarIngestionService:
             publication.venue_text = candidate.venue_text
         if candidate.title_url:
             publication.pub_url = build_publication_url(candidate.title_url)
-        local_doi = first_doi_from_texts(candidate.title_url, candidate.venue_text, candidate.title)
+        first_doi_from_texts(candidate.title_url, candidate.venue_text, candidate.title)
 
     async def _resolve_publication(
         self,

app/services/domains/ingestion/fingerprints.py

@@ -367,10 +367,7 @@ def _publication_identity(pub: PublicationCandidate) -> str:
 
 
 def _is_fuzzy_dup(tokens: set[str], seen: list[set[str]]) -> bool:
-    for existing in seen:
-        if _jaccard(tokens, existing) >= _CANONICAL_DEDUP_THRESHOLD:
-            return True
-    return False
+    return any(_jaccard(tokens, existing) >= _CANONICAL_DEDUP_THRESHOLD for existing in seen)
 
 
 def _build_body_excerpt(body: str, *, max_chars: int = 220) -> str | None:

app/services/domains/ingestion/scheduler.py

@@ -330,9 +330,7 @@ class SchedulerService:
             await session.commit()
         if queue_item is None:
             return False
-        if queue_item.status == QueueItemStatus.DROPPED.value:
-            return False
-        return True
+        return queue_item.status != QueueItemStatus.DROPPED.value
 
     async def _queue_job_has_available_scholar(
         self,

app/services/domains/openalex/matching.py

@@ -93,8 +93,7 @@ def find_best_match(
 
     for original_score, cand in top_scored_candidates:
         tb_score = 0
-        if target_year is not None and cand.publication_year is not None:
-            if abs(target_year - cand.publication_year) <= 1:
+        if target_year is not None and cand.publication_year is not None and abs(target_year - cand.publication_year) <= 1:
                 tb_score += 1
 
         candidate_author_names = [a.display_name for a in cand.authors if a.display_name]

app/services/domains/portability/__init__.py

@@ -1 +1,21 @@
-from app.services.domains.portability.application import *
+from app.services.domains.portability.application import (
+    EXPORT_SCHEMA_VERSION as EXPORT_SCHEMA_VERSION,
+)
+from app.services.domains.portability.application import (
+    MAX_IMPORT_PUBLICATIONS as MAX_IMPORT_PUBLICATIONS,
+)
+from app.services.domains.portability.application import (
+    MAX_IMPORT_SCHOLARS as MAX_IMPORT_SCHOLARS,
+)
+from app.services.domains.portability.application import (
+    ImportedPublicationInput as ImportedPublicationInput,
+)
+from app.services.domains.portability.application import (
+    ImportExportError as ImportExportError,
+)
+from app.services.domains.portability.application import (
+    export_user_data as export_user_data,
+)
+from app.services.domains.portability.application import (
+    import_user_data as import_user_data,
+)

app/services/domains/publication_identifiers/application.py

@@ -188,7 +188,7 @@ async def _discover_crossref_doi(
 
     discovered_doi = await crossref_service.discover_doi_for_publication(item=item)
     normalized_doi = normalize_doi(discovered_doi)
-    if normalized_doi is None:
+    if discovered_doi is None or normalized_doi is None:
         return False
     candidate = _candidate(
         IdentifierKind.DOI,
@@ -216,7 +216,7 @@ async def _discover_arxiv_identifier(
 
     discovered_arxiv = await arxiv_service.discover_arxiv_id_for_publication(item=item)
     normalized_arxiv = normalize_arxiv_id(discovered_arxiv)
-    if normalized_arxiv is None:
+    if discovered_arxiv is None or normalized_arxiv is None:
         return
     candidate = _candidate(
         IdentifierKind.ARXIV,

app/services/domains/publications/__init__.py

@@ -1 +1,84 @@
-from app.services.domains.publications.application import *
+from app.services.domains.publications.application import (
+    MODE_ALL as MODE_ALL,
+)
+from app.services.domains.publications.application import (
+    MODE_LATEST as MODE_LATEST,
+)
+from app.services.domains.publications.application import (
+    MODE_NEW as MODE_NEW,
+)
+from app.services.domains.publications.application import (
+    MODE_UNREAD as MODE_UNREAD,
+)
+from app.services.domains.publications.application import (
+    PublicationListItem as PublicationListItem,
+)
+from app.services.domains.publications.application import (
+    UnreadPublicationItem as UnreadPublicationItem,
+)
+from app.services.domains.publications.application import (
+    count_favorite_for_user as count_favorite_for_user,
+)
+from app.services.domains.publications.application import (
+    count_for_user as count_for_user,
+)
+from app.services.domains.publications.application import (
+    count_latest_for_user as count_latest_for_user,
+)
+from app.services.domains.publications.application import (
+    count_pdf_queue_items as count_pdf_queue_items,
+)
+from app.services.domains.publications.application import (
+    count_unread_for_user as count_unread_for_user,
+)
+from app.services.domains.publications.application import (
+    enqueue_all_missing_pdf_jobs as enqueue_all_missing_pdf_jobs,
+)
+from app.services.domains.publications.application import (
+    enqueue_retry_pdf_job_for_publication_id as enqueue_retry_pdf_job_for_publication_id,
+)
+from app.services.domains.publications.application import (
+    get_latest_run_id_for_user as get_latest_run_id_for_user,
+)
+from app.services.domains.publications.application import (
+    get_publication_item_for_user as get_publication_item_for_user,
+)
+from app.services.domains.publications.application import (
+    hydrate_pdf_enrichment_state as hydrate_pdf_enrichment_state,
+)
+from app.services.domains.publications.application import (
+    list_for_user as list_for_user,
+)
+from app.services.domains.publications.application import (
+    list_pdf_queue_items as list_pdf_queue_items,
+)
+from app.services.domains.publications.application import (
+    list_pdf_queue_page as list_pdf_queue_page,
+)
+from app.services.domains.publications.application import (
+    list_unread_for_user as list_unread_for_user,
+)
+from app.services.domains.publications.application import (
+    mark_all_unread_as_read_for_user as mark_all_unread_as_read_for_user,
+)
+from app.services.domains.publications.application import (
+    mark_selected_as_read_for_user as mark_selected_as_read_for_user,
+)
+from app.services.domains.publications.application import (
+    publications_query as publications_query,
+)
+from app.services.domains.publications.application import (
+    resolve_publication_view_mode as resolve_publication_view_mode,
+)
+from app.services.domains.publications.application import (
+    retry_pdf_for_user as retry_pdf_for_user,
+)
+from app.services.domains.publications.application import (
+    schedule_missing_pdf_enrichment_for_user as schedule_missing_pdf_enrichment_for_user,
+)
+from app.services.domains.publications.application import (
+    schedule_retry_pdf_enrichment_for_row as schedule_retry_pdf_enrichment_for_row,
+)
+from app.services.domains.publications.application import (
+    set_publication_favorite_for_user as set_publication_favorite_for_user,
+)

app/services/domains/publications/pdf_queue.py

@@ -190,12 +190,10 @@ def _can_enqueue_job(
         return False
     if int(job.attempt_count) >= _auto_retry_max_attempts():
         return False
-    if _cooldown_active(
+    return not _cooldown_active(
         last_attempt_at=job.last_attempt_at,
         attempt_count=int(job.attempt_count),
-    ):
-        return False
-    return True
+    )
 
 
 def _event_row(

app/services/domains/publications/pdf_resolution_pipeline.py

@@ -5,7 +5,7 @@ from dataclasses import dataclass
 from typing import Any
 
 from app.logging_utils import structured_log
-from app.services.domains.arxiv.application import ArxivRateLimitError
+from app.services.domains.arxiv.errors import ArxivRateLimitError
 from app.services.domains.arxiv.guards import arxiv_skip_reason_for_item
 from app.services.domains.openalex.client import OpenAlexBudgetExhaustedError
 from app.services.domains.publications.types import PublicationListItem

app/services/domains/publications/queries.py

@@ -19,7 +19,7 @@ from app.services.domains.publications.types import PublicationListItem, UnreadP
 
 def _normalized_citation_count(value: object) -> int:
     try:
-        return int(value or 0)
+        return int(value or 0)  # type: ignore[call-overload]  # intentionally accepts any object
     except (TypeError, ValueError):
         return 0
 

app/services/domains/runs/__init__.py

@@ -1 +1,51 @@
-from app.services.domains.runs.application import *
+from app.services.domains.runs.application import (
+    QUEUE_STATUS_DROPPED as QUEUE_STATUS_DROPPED,
+)
+from app.services.domains.runs.application import (
+    QUEUE_STATUS_QUEUED as QUEUE_STATUS_QUEUED,
+)
+from app.services.domains.runs.application import (
+    QUEUE_STATUS_RETRYING as QUEUE_STATUS_RETRYING,
+)
+from app.services.domains.runs.application import (
+    QueueClearResult as QueueClearResult,
+)
+from app.services.domains.runs.application import (
+    QueueListItem as QueueListItem,
+)
+from app.services.domains.runs.application import (
+    QueueTransitionError as QueueTransitionError,
+)
+from app.services.domains.runs.application import (
+    clear_queue_item_for_user as clear_queue_item_for_user,
+)
+from app.services.domains.runs.application import (
+    drop_queue_item_for_user as drop_queue_item_for_user,
+)
+from app.services.domains.runs.application import (
+    extract_run_summary as extract_run_summary,
+)
+from app.services.domains.runs.application import (
+    get_manual_run_by_idempotency_key as get_manual_run_by_idempotency_key,
+)
+from app.services.domains.runs.application import (
+    get_queue_item_for_user as get_queue_item_for_user,
+)
+from app.services.domains.runs.application import (
+    get_run_for_user as get_run_for_user,
+)
+from app.services.domains.runs.application import (
+    list_queue_items_for_user as list_queue_items_for_user,
+)
+from app.services.domains.runs.application import (
+    list_recent_runs_for_user as list_recent_runs_for_user,
+)
+from app.services.domains.runs.application import (
+    list_runs_for_user as list_runs_for_user,
+)
+from app.services.domains.runs.application import (
+    queue_status_counts_for_user as queue_status_counts_for_user,
+)
+from app.services.domains.runs.application import (
+    retry_queue_item_for_user as retry_queue_item_for_user,
+)

app/services/domains/runs/summary.py

@@ -1,11 +1,11 @@
 from __future__ import annotations
 
-from typing import Any
+from typing import Any, cast
 
 
 def _safe_int(value: object, default: int = 0) -> int:
     try:
-        return int(value)
+        return int(cast(Any, value))
     except (TypeError, ValueError):
         return default
 

app/services/domains/scholar/parser.py

@@ -12,6 +12,15 @@ from app.services.domains.scholar.parser_types import (
     ScholarDomInvariantError,
     ScholarMalformedDataError,
 )
+from app.services.domains.scholar.parser_types import (
+    ParseState as ParseState,
+)
+from app.services.domains.scholar.parser_types import (
+    ScholarParserError as ScholarParserError,
+)
+from app.services.domains.scholar.parser_types import (
+    ScholarSearchCandidate as ScholarSearchCandidate,
+)
 from app.services.domains.scholar.parser_utils import (
     strip_tags,
 )

app/services/domains/scholar/profile_rows.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import re
 from html.parser import HTMLParser
+from typing import Any
 from urllib.parse import parse_qs, urlparse
 
 from app.services.domains.scholar.parser_constants import (
@@ -30,7 +31,7 @@ class ScholarRowParser(HTMLParser):
         self._title_depth = 0
         self._citation_depth = 0
         self._year_depth = 0
-        self._gray_stack: list[dict[str, object]] = []
+        self._gray_stack: list[dict[str, Any]] = []
 
     def handle_starttag(self, tag: str, attrs: list[tuple[str, str | None]]) -> None:
         if self._title_depth > 0:
@@ -252,9 +253,7 @@ def has_show_more_button(html: str) -> bool:
         return False
     if 'aria-disabled="true"' in button_tag or "aria-disabled='true'" in button_tag:
         return False
-    if "gs_dis" in button_tag:
-        return False
-    return True
+    return "gs_dis" not in button_tag
 
 
 def has_operation_error_banner(html: str) -> bool:

app/services/domains/scholars/application.py

@@ -6,6 +6,7 @@ import os
 import random
 from dataclasses import replace
 from datetime import UTC, datetime, timedelta
+from typing import Any
 from uuid import uuid4
 
 from sqlalchemy import delete, func, select, text
@@ -182,11 +183,11 @@ def _deserialize_candidate_payload(value: object) -> dict[str, object] | None:
     }
 
 
-def _deserialize_candidates(payload: dict[str, object]) -> list[dict[str, object]]:
+def _deserialize_candidates(payload: dict[str, object]) -> list[dict[str, Any]]:
     candidates_payload = payload.get("candidates")
     if not isinstance(candidates_payload, list):
         return []
-    normalized: list[dict[str, object]] = []
+    normalized: list[dict[str, Any]] = []
     for value in candidates_payload:
         candidate = _deserialize_candidate_payload(value)
         if candidate is not None:
@@ -790,7 +791,7 @@ async def _perform_live_author_search(
     cache_ttl_seconds: int,
     cache_max_entries: int,
 ) -> tuple[ParsedAuthorSearchPage, bool]:
-    runtime_state_updated = await _wait_for_author_search_throttle(
+    await _wait_for_author_search_throttle(
         runtime_state=runtime_state,
         normalized_query=normalized_query,
         now_utc=datetime.now(UTC),

app/services/domains/settings/application.py

@@ -4,6 +4,7 @@ from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import UserSetting
+from app.settings import settings as app_settings
 
 
 class UserSettingsServiceError(ValueError):
@@ -103,9 +104,6 @@ def parse_nav_visible_pages(value: object) -> list[str]:
     return deduped
 
 
-from app.settings import settings as app_settings
-
-
 async def get_or_create_settings(
     db_session: AsyncSession,
     *,

app/services/domains/unpaywall/application.py

@@ -65,8 +65,9 @@ def _extract_explicit_doi(text: str | None) -> str | None:
 
 def _publication_doi(item: PublicationListItem | UnreadPublicationItem) -> str | None:
     stored = None
-    if getattr(item, "display_identifier", None) and item.display_identifier.kind == "doi":
-        stored = normalize_doi(item.display_identifier.value)
+    di = getattr(item, "display_identifier", None)
+    if di is not None and di.kind == "doi":
+        stored = normalize_doi(di.value)
 
     explicit_doi = _extract_explicit_doi(item.pub_url) or _extract_explicit_doi(item.venue_text)
     if explicit_doi:

tests/unit/test_user_settings.py

@@ -22,7 +22,7 @@ def test_parse_run_interval_minutes_accepts_valid_value() -> None:
 def test_parse_run_interval_minutes_rejects_below_minimum() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Check interval must be at least 15 minutes.",
+        match=r"Check interval must be at least 15 minutes.",
     ):
         parse_run_interval_minutes("14")
 
@@ -34,7 +34,7 @@ def test_parse_request_delay_seconds_accepts_valid_value() -> None:
 def test_parse_request_delay_seconds_rejects_below_minimum() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Request delay must be at least 2 seconds.",
+        match=r"Request delay must be at least 2 seconds.",
     ):
         parse_request_delay_seconds("1")
 
@@ -42,7 +42,7 @@ def test_parse_request_delay_seconds_rejects_below_minimum() -> None:
 def test_parse_run_interval_minutes_rejects_below_configured_minimum() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Check interval must be at least 30 minutes.",
+        match=r"Check interval must be at least 30 minutes.",
     ):
         parse_run_interval_minutes("29", minimum=30)
 
@@ -50,7 +50,7 @@ def test_parse_run_interval_minutes_rejects_below_configured_minimum() -> None:
 def test_parse_request_delay_seconds_rejects_below_configured_minimum() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Request delay must be at least 8 seconds.",
+        match=r"Request delay must be at least 8 seconds.",
     ):
         parse_request_delay_seconds("7", minimum=8)
 
@@ -82,7 +82,7 @@ def test_parse_nav_visible_pages_accepts_valid_pages() -> None:
 def test_parse_nav_visible_pages_rejects_missing_required_pages() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Dashboard, Scholars, and Settings must remain visible.",
+        match=r"Dashboard, Scholars, and Settings must remain visible.",
     ):
         parse_nav_visible_pages(["dashboard", "publications"])
 
@@ -90,6 +90,6 @@ def test_parse_nav_visible_pages_rejects_missing_required_pages() -> None:
 def test_parse_nav_visible_pages_rejects_unknown_page() -> None:
     with pytest.raises(
         UserSettingsServiceError,
-        match="Unsupported navigation page id: reports",
+        match=r"Unsupported navigation page id: reports",
     ):
-        parse_nav_visible_pages(DEFAULT_NAV_VISIBLE_PAGES + ["reports"])
+        parse_nav_visible_pages([*DEFAULT_NAV_VISIBLE_PAGES, "reports"])