justinzeus/scholarr
1
0
Fork 0
Code Issues 1 Pull requests 18 Projects Releases Packages Wiki Activity Actions

ci: add ruff linting and mypy type checking

Browse source 
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>
This commit is contained in:
Justin Visser 2026-02-26 22:11:41 +01:00
parent 399276ea69
commit bf04c77aa9
137 changed files with 3066 additions and 1900 deletions
Download patch file Download diff file Expand all files Collapse all files

1
app/api/__init__.py
View file

@ -1,2 +1 @@
from __future__ import annotations

1
app/api/errors.py
View file

@ -82,4 +82,3 @@ def register_api_exception_handlers(app: FastAPI) -> None:
message="Request validation failed.",
details=exc.errors(),
)

1
app/api/routers/__init__.py
View file

@ -1,2 +1 @@
from __future__ import annotations

32
app/api/routers/admin.py
View file

@ -86,7 +86,14 @@ async def create_user(
message=str(exc),
) from exc
structured_log(logger, "info", "api.admin.user_created", admin_user_id=int(admin_user.id), target_user_id=int(created_user.id), target_is_admin=bool(created_user.is_admin))
structured_log(
logger,
"info",
"api.admin.user_created",
admin_user_id=int(admin_user.id),
target_user_id=int(created_user.id),
target_is_admin=bool(created_user.is_admin),
)
return success_payload(
request,
data=_serialize_user(created_user),
@ -111,11 +118,7 @@ async def set_user_active(
code="user_not_found",
message="User not found.",
)
if (
int(target_user.id) == int(admin_user.id)
and bool(target_user.is_active)
and not bool(payload.is_active)
):
if int(target_user.id) == int(admin_user.id) and bool(target_user.is_active) and not bool(payload.is_active):
raise ApiException(
status_code=400,
code="cannot_deactivate_self",
@ -126,7 +129,14 @@ async def set_user_active(
user=target_user,
is_active=bool(payload.is_active),
)
structured_log(logger, "info", "api.admin.user_active_updated", admin_user_id=int(admin_user.id), target_user_id=int(updated_user.id), is_active=bool(updated_user.is_active))
structured_log(
logger,
"info",
"api.admin.user_active_updated",
admin_user_id=int(admin_user.id),
target_user_id=int(updated_user.id),
is_active=bool(updated_user.is_active),
)
return success_payload(
request,
data=_serialize_user(updated_user),
@ -166,7 +176,13 @@ async def reset_user_password(
user=target_user,
password_hash=auth_service.hash_password(validated_password),
)
structured_log(logger, "info", "api.admin.user_password_reset", admin_user_id=int(admin_user.id), target_user_id=int(target_user.id))
structured_log(
logger,
"info",
"api.admin.user_password_reset",
admin_user_id=int(admin_user.id),
target_user_id=int(target_user.id),
)
return success_payload(
request,
data={"message": f"Password reset: {target_user.email}"},

82
app/api/routers/admin_dbops.py
View file

@ -10,14 +10,14 @@ from app.api.errors import ApiException
from app.api.responses import success_payload
from app.api.schemas import (
AdminDbIntegrityEnvelope,
AdminPdfQueueBulkEnqueueEnvelope,
AdminPdfQueueRequeueEnvelope,
AdminPdfQueueEnvelope,
AdminDbRepairJobsEnvelope,
AdminRepairPublicationNearDuplicatesEnvelope,
AdminRepairPublicationNearDuplicatesRequest,
AdminPdfQueueBulkEnqueueEnvelope,
AdminPdfQueueEnvelope,
AdminPdfQueueRequeueEnvelope,
AdminRepairPublicationLinksEnvelope,
AdminRepairPublicationLinksRequest,
AdminRepairPublicationNearDuplicatesEnvelope,
AdminRepairPublicationNearDuplicatesRequest,
)
from app.db.models import DataRepairJob, User
from app.db.session import get_db_session
@ -25,8 +25,8 @@ from app.logging_utils import structured_log
from app.services.domains.dbops import (
collect_integrity_report,
list_repair_jobs,
run_publication_near_duplicate_repair,
run_publication_link_repair,
run_publication_near_duplicate_repair,
)
from app.services.domains.publications import application as publication_service
@ -136,7 +136,15 @@ async def get_integrity_report(
admin_user: User = Depends(get_api_admin_user),
):
report = await collect_integrity_report(db_session)
structured_log(logger, "info", "api.admin.db.integrity_checked", admin_user_id=int(admin_user.id), status=report.get("status"), failure_count=len(report.get("failures", [])), warning_count=len(report.get("warnings", [])))
structured_log(
logger,
"info",
"api.admin.db.integrity_checked",
admin_user_id=int(admin_user.id),
status=report.get("status"),
failure_count=len(report.get("failures", [])),
warning_count=len(report.get("warnings", [])),
)
return success_payload(request, data=report)
@ -151,7 +159,14 @@ async def get_repair_jobs(
admin_user: User = Depends(get_api_admin_user),
):
jobs = await list_repair_jobs(db_session, limit=limit)
structured_log(logger, "info", "api.admin.db.repair_jobs_listed", admin_user_id=int(admin_user.id), limit=int(limit), job_count=len(jobs))
structured_log(
logger,
"info",
"api.admin.db.repair_jobs_listed",
admin_user_id=int(admin_user.id),
limit=int(limit),
job_count=len(jobs),
)
return success_payload(
request,
data={"jobs": [_serialize_repair_job(job) for job in jobs]},
@ -186,7 +201,9 @@ async def get_pdf_queue(
status=normalized_status,
)
structured_log(
logger, "info", "api.admin.db.pdf_queue_listed",
logger,
"info",
"api.admin.db.pdf_queue_listed",
admin_user_id=int(admin_user.id),
page=int(resolved_page),
page_size=int(resolved_limit),
@ -232,7 +249,14 @@ async def requeue_pdf_lookup(
message="Publication not found.",
)
status, message = _requeue_response_state(queued=result.queued)
structured_log(logger, "info", "api.admin.db.pdf_requeued", admin_user_id=int(admin_user.id), publication_id=int(publication_id), queued=bool(result.queued))
structured_log(
logger,
"info",
"api.admin.db.pdf_requeued",
admin_user_id=int(admin_user.id),
publication_id=int(publication_id),
queued=bool(result.queued),
)
return success_payload(
request,
data={
@ -260,7 +284,15 @@ async def requeue_all_missing_pdfs(
request_email=admin_user.email,
limit=limit,
)
structured_log(logger, "info", "api.admin.db.pdf_queue_requeue_all", admin_user_id=int(admin_user.id), limit=int(limit), requested_count=int(result.requested_count), queued_count=int(result.queued_count))
structured_log(
logger,
"info",
"api.admin.db.pdf_queue_requeue_all",
admin_user_id=int(admin_user.id),
limit=int(limit),
requested_count=int(result.requested_count),
queued_count=int(result.queued_count),
)
return success_payload(
request,
data={
@ -301,7 +333,9 @@ async def trigger_publication_link_repair(
message=str(exc),
) from exc
structured_log(
logger, "info", "api.admin.db.publication_link_repair_triggered",
logger,
"info",
"api.admin.db.publication_link_repair_triggered",
admin_user_id=int(admin_user.id),
scope_mode=payload.scope_mode,
target_user_id=int(payload.user_id) if payload.user_id is not None else None,
@ -340,7 +374,16 @@ async def trigger_publication_near_duplicate_repair(
code="invalid_near_duplicate_repair_request",
message=str(exc),
) from exc
structured_log(logger, "info", "api.admin.db.dedup_repair_triggered", admin_user_id=int(admin_user.id), dry_run=bool(payload.dry_run), selected_cluster_count=len(payload.selected_cluster_keys), job_id=int(result["job_id"]), status=result["status"])
structured_log(
logger,
"info",
"api.admin.db.dedup_repair_triggered",
admin_user_id=int(admin_user.id),
dry_run=bool(payload.dry_run),
selected_cluster_count=len(payload.selected_cluster_keys),
job_id=int(result["job_id"]),
status=result["status"],
)
return success_payload(request, data=result)
@ -381,12 +424,17 @@ async def drop_all_publications(
await db_session.execute(delete(PublicationPdfJobEvent))
await db_session.execute(delete(PublicationPdfJob))
await db_session.execute(delete(Publication))
await db_session.execute(
update(ScholarProfile).values(baseline_completed=False)
)
await db_session.execute(update(ScholarProfile).values(baseline_completed=False))
await db_session.commit()
structured_log(logger, "warning", "api.admin.db.all_publications_dropped", admin_user_id=int(admin_user.id), admin_email=admin_user.email, deleted_count=int(total_publications))
structured_log(
logger,
"warning",
"api.admin.db.all_publications_dropped",
admin_user_id=int(admin_user.id),
admin_email=admin_user.email,
deleted_count=int(total_publications),
)
return success_payload(
request,
data={

20
app/api/routers/auth.py
View file

@ -5,8 +5,8 @@ import logging
from fastapi import APIRouter, Depends, Request
from sqlalchemy.ext.asyncio import AsyncSession
from app.api.errors import ApiException
from app.api.deps import get_api_current_user
from app.api.errors import ApiException
from app.api.responses import success_payload
from app.api.schemas import (
AuthMeEnvelope,
@ -16,14 +16,14 @@ from app.api.schemas import (
LoginRequest,
MessageEnvelope,
)
from app.auth.deps import get_auth_service, get_login_rate_limiter
from app.logging_utils import structured_log
from app.auth.rate_limit import SlidingWindowRateLimiter
from app.auth import runtime as auth_runtime
from app.auth.deps import get_auth_service, get_login_rate_limiter
from app.auth.rate_limit import SlidingWindowRateLimiter
from app.auth.service import AuthService
from app.auth.session import set_session_user
from app.db.models import User
from app.db.session import get_db_session
from app.logging_utils import structured_log
from app.security.csrf import ensure_csrf_token
from app.services.domains.users import application as user_service
@ -37,7 +37,13 @@ def _login_limiter_key_and_email(request: Request, payload: LoginRequest) -> tup
def _raise_rate_limited(normalized_email: str, retry_after_seconds: int) -> None:
structured_log(logger, "warning", "api.auth.login_rate_limited", email=normalized_email, retry_after_seconds=retry_after_seconds)
structured_log(
logger,
"warning",
"api.auth.login_rate_limited",
email=normalized_email,
retry_after_seconds=retry_after_seconds,
)
raise ApiException(
status_code=429,
code="rate_limited",
@ -200,7 +206,9 @@ async def logout(
):
current_user = await auth_runtime.get_authenticated_user(request, db_session)
auth_runtime.invalidate_session(request)
structured_log(logger, "info", "api.auth.logout", user_id=int(current_user.id) if current_user is not None else None)
structured_log(
logger, "info", "api.auth.logout", user_id=int(current_user.id) if current_user is not None else None
)
return success_payload(
request,
data={

42
app/api/routers/publications.py
View file

@ -1,7 +1,7 @@
from __future__ import annotations
from datetime import datetime, timezone
import logging
from datetime import UTC, datetime
from typing import Literal
from fastapi import APIRouter, Depends, Path, Query, Request
@ -183,7 +183,7 @@ def _resolve_publications_snapshot(
snapshot: str | None,
) -> tuple[datetime, str]:
if snapshot is None:
now_utc = datetime.now(timezone.utc)
now_utc = datetime.now(UTC)
return now_utc, now_utc.isoformat()
try:
parsed = datetime.fromisoformat(snapshot)
@ -194,8 +194,8 @@ def _resolve_publications_snapshot(
message="Invalid publications snapshot cursor.",
) from exc
if parsed.tzinfo is None:
parsed = parsed.replace(tzinfo=timezone.utc)
normalized = parsed.astimezone(timezone.utc)
parsed = parsed.replace(tzinfo=UTC)
normalized = parsed.astimezone(UTC)
return normalized, normalized.isoformat()
@ -420,7 +420,9 @@ async def mark_all_publications_read(
db_session,
user_id=current_user.id,
)
structured_log(logger, "info", "api.publications.mark_all_read", user_id=current_user.id, updated_count=updated_count)
structured_log(
logger, "info", "api.publications.mark_all_read", user_id=current_user.id, updated_count=updated_count
)
return success_payload(
request,
data={
@ -440,18 +442,20 @@ async def mark_selected_publications_read(
db_session: AsyncSession = Depends(get_db_session),
current_user: User = Depends(get_api_current_user),
):
selection_pairs = sorted(
{
(int(item.scholar_profile_id), int(item.publication_id))
for item in payload.selections
}
)
selection_pairs = sorted({(int(item.scholar_profile_id), int(item.publication_id)) for item in payload.selections})
updated_count = await publication_service.mark_selected_as_read_for_user(
db_session,
user_id=current_user.id,
selections=selection_pairs,
)
structured_log(logger, "info", "api.publications.mark_selected_read", user_id=current_user.id, requested_count=len(selection_pairs), updated_count=updated_count)
structured_log(
logger,
"info",
"api.publications.mark_selected_read",
user_id=current_user.id,
requested_count=len(selection_pairs),
updated_count=updated_count,
)
return success_payload(
request,
data={
@ -486,7 +490,9 @@ async def retry_publication_pdf(
pdf_status=current.pdf_status,
)
structured_log(
logger, "info", "api.publications.retry_pdf",
logger,
"info",
"api.publications.retry_pdf",
user_id=current_user.id,
scholar_profile_id=payload.scholar_profile_id,
publication_id=publication_id,
@ -523,7 +529,15 @@ async def toggle_publication_favorite(
publication_id=publication_id,
is_favorite=payload.is_favorite,
)
structured_log(logger, "info", "api.publications.favorite", user_id=current_user.id, scholar_profile_id=payload.scholar_profile_id, publication_id=publication_id, is_favorite=bool(payload.is_favorite))
structured_log(
logger,
"info",
"api.publications.favorite",
user_id=current_user.id,
scholar_profile_id=payload.scholar_profile_id,
publication_id=publication_id,
is_favorite=bool(payload.is_favorite),
)
return success_payload(
request,
data={

84
app/api/routers/runs.py
View file

@ -5,13 +5,14 @@ import re
from typing import Any
from fastapi import APIRouter, Depends, Query, Request
from fastapi.responses import StreamingResponse
from sqlalchemy.exc import IntegrityError
from sqlalchemy.ext.asyncio import AsyncSession
from app.api.deps import get_api_current_user
from app.api.errors import ApiException
from app.api.responses import success_payload
from fastapi.responses import StreamingResponse
from app.api.runtime_deps import get_ingestion_service
from app.api.schemas import (
ManualRunEnvelope,
QueueClearEnvelope,
@ -29,7 +30,6 @@ from app.services.domains.runs import application as run_service
from app.services.domains.runs.events import event_generator
from app.services.domains.settings import application as user_settings_service
from app.settings import settings
from app.api.runtime_deps import get_ingestion_service
logger = logging.getLogger(__name__)
@ -77,10 +77,7 @@ def _normalize_idempotency_key(raw_value: str | None) -> str | None:
raise ApiException(
status_code=400,
code="invalid_idempotency_key",
message=(
"Invalid Idempotency-Key. Use 8-128 characters from: "
"A-Z a-z 0-9 . _ : -"
),
message=("Invalid Idempotency-Key. Use 8-128 characters from: A-Z a-z 0-9 . _ : -"),
)
return candidate
@ -130,11 +127,7 @@ def _normalize_attempt_log(value: Any) -> list[dict[str, Any]]:
"cstart": _int_value(item.get("cstart"), 0),
"state": _str_value(item.get("state")),
"state_reason": _str_value(item.get("state_reason")),
"status_code": (
_int_value(item.get("status_code"))
if item.get("status_code") is not None
else None
),
"status_code": (_int_value(item.get("status_code")) if item.get("status_code") is not None else None),
"fetch_error": _str_value(item.get("fetch_error")),
}
)
@ -155,19 +148,12 @@ def _normalize_page_logs(value: Any) -> list[dict[str, Any]]:
"cstart": _int_value(item.get("cstart"), 0),
"state": _str_value(item.get("state")) or "unknown",
"state_reason": _str_value(item.get("state_reason")),
"status_code": (
_int_value(item.get("status_code"))
if item.get("status_code") is not None
else None
),
"status_code": (_int_value(item.get("status_code")) if item.get("status_code") is not None else None),
"publication_count": _int_value(item.get("publication_count"), 0),
"attempt_count": _int_value(item.get("attempt_count"), 0),
"has_show_more_button": _bool_value(item.get("has_show_more_button"), False),
"articles_range": _str_value(item.get("articles_range")),
"warning_codes": [
str(code)
for code in (warning_codes if isinstance(warning_codes, list) else [])
],
"warning_codes": [str(code) for code in (warning_codes if isinstance(warning_codes, list) else [])],
}
)
return normalized
@ -179,19 +165,11 @@ def _normalize_debug(value: Any) -> dict[str, Any] | None:
marker_counts = value.get("marker_counts_nonzero")
warning_codes = value.get("warning_codes")
return {
"status_code": (
_int_value(value.get("status_code"))
if value.get("status_code") is not None
else None
),
"status_code": (_int_value(value.get("status_code")) if value.get("status_code") is not None else None),
"final_url": _str_value(value.get("final_url")),
"fetch_error": _str_value(value.get("fetch_error")),
"body_sha256": _str_value(value.get("body_sha256")),
"body_length": (
_int_value(value.get("body_length"))
if value.get("body_length") is not None
else None
),
"body_length": (_int_value(value.get("body_length")) if value.get("body_length") is not None else None),
"has_show_more_button": (
_bool_value(value.get("has_show_more_button"), False)
if value.get("has_show_more_button") is not None
@ -199,10 +177,7 @@ def _normalize_debug(value: Any) -> dict[str, Any] | None:
),
"articles_range": _str_value(value.get("articles_range")),
"state_reason": _str_value(value.get("state_reason")),
"warning_codes": [
str(code)
for code in (warning_codes if isinstance(warning_codes, list) else [])
],
"warning_codes": [str(code) for code in (warning_codes if isinstance(warning_codes, list) else [])],
"marker_counts_nonzero": {
str(key): _int_value(count, 0)
for key, count in (marker_counts.items() if isinstance(marker_counts, dict) else [])
@ -241,9 +216,7 @@ def _normalize_scholar_result(value: Any) -> dict[str, Any]:
"publication_count": _int_value(value.get("publication_count"), 0),
"start_cstart": _int_value(value.get("start_cstart"), 0),
"continuation_cstart": (
_int_value(value.get("continuation_cstart"))
if value.get("continuation_cstart") is not None
else None
_int_value(value.get("continuation_cstart")) if value.get("continuation_cstart") is not None else None
),
"continuation_enqueued": _bool_value(value.get("continuation_enqueued"), False),
"continuation_cleared": _bool_value(value.get("continuation_cleared"), False),
@ -289,7 +262,9 @@ async def _load_safety_state(
await db_session.commit()
await db_session.refresh(user_settings)
structured_log(
logger, "info", "api.runs.safety_cooldown_cleared",
logger,
"info",
"api.runs.safety_cooldown_cleared",
user_id=user_id,
reason=previous_safety_state.get("cooldown_reason"),
cooldown_until=previous_safety_state.get("cooldown_until"),
@ -299,7 +274,9 @@ async def _load_safety_state(
def _raise_manual_runs_disabled(*, user_id: int, safety_state: dict[str, Any]) -> None:
structured_log(
logger, "warning", "api.runs.manual_blocked_policy",
logger,
"warning",
"api.runs.manual_blocked_policy",
user_id=user_id,
policy={"manual_run_allowed": False},
safety_state=safety_state,
@ -463,7 +440,9 @@ async def _execute_manual_run(
def _raise_manual_blocked_safety(*, exc, user_id: int) -> None:
structured_log(
logger, "info", "api.runs.manual_blocked_safety",
logger,
"info",
"api.runs.manual_blocked_safety",
user_id=user_id,
reason=exc.safety_state.get("cooldown_reason"),
cooldown_until=exc.safety_state.get("cooldown_until"),
@ -613,12 +592,12 @@ async def cancel_run(
scholar_results = error_log.get("scholar_results")
if not isinstance(scholar_results, list):
scholar_results = []
safety_state = await _load_safety_state(
db_session,
user_id=current_user.id,
)
return success_payload(
request,
data={
@ -657,7 +636,7 @@ async def run_manual(
try:
user_settings = await user_settings_service.get_or_create_settings(db_session, user_id=current_user.id)
# Initialize run (creates the record and performs safety checks)
run, scholars, start_cstart_map = await ingest_service.initialize_run(
db_session,
@ -673,13 +652,14 @@ async def run_manual(
alert_network_failure_threshold=settings.ingestion_alert_network_failure_threshold,
alert_retry_scheduled_threshold=settings.ingestion_alert_retry_scheduled_threshold,
)
await db_session.commit()
# Kick off background execution
from app.db.session import get_session_factory
import asyncio
from app.db.session import get_session_factory
asyncio.create_task(
ingest_service.execute_run(
session_factory=get_session_factory(),
@ -700,7 +680,7 @@ async def run_manual(
idempotency_key=idempotency_key,
)
)
return success_payload(
request,
data={
@ -714,7 +694,7 @@ async def run_manual(
"reused_existing_run": False,
"idempotency_key": idempotency_key,
"safety_state": await _load_safety_state(db_session, user_id=current_user.id),
}
},
)
except ingestion_service.RunBlockedBySafetyPolicyError as exc:
await db_session.rollback()
@ -740,7 +720,6 @@ async def run_manual(
_raise_manual_failed(exc=exc, user_id=current_user.id)
@router.get(
"/queue/items",
response_model=QueueListEnvelope,
@ -891,7 +870,4 @@ async def stream_run_events(
code="run_not_found",
message="Run not found.",
)
return StreamingResponse(
event_generator(run_id),
media_type="text/event-stream"
)
return StreamingResponse(event_generator(run_id), media_type="text/event-stream")

70
app/api/routers/scholars.py
View file

@ -27,8 +27,8 @@ from app.logging_utils import structured_log
from app.services.domains.ingestion import queue as ingestion_queue_service
from app.services.domains.portability import application as import_export_service
from app.services.domains.scholar import rate_limit as scholar_rate_limit
from app.services.domains.scholars import application as scholar_service
from app.services.domains.scholar.source import ScholarSource
from app.services.domains.scholars import application as scholar_service
from app.settings import settings
logger = logging.getLogger(__name__)
@ -82,14 +82,18 @@ async def _enqueue_initial_scrape_job_for_scholar(
except Exception:
await db_session.rollback()
structured_log(
logger, "warning", "api.scholars.initial_scrape_enqueue_failed",
logger,
"warning",
"api.scholars.initial_scrape_enqueue_failed",
user_id=user_id,
scholar_profile_id=profile.id,
)
return False
structured_log(
logger, "info", "api.scholars.initial_scrape_enqueued",
logger,
"info",
"api.scholars.initial_scrape_enqueued",
user_id=user_id,
scholar_profile_id=profile.id,
reason=INITIAL_SCHOLAR_SCRAPE_QUEUE_REASON,
@ -120,9 +124,7 @@ def _serialize_scholar(profile) -> dict[str, object]:
"is_enabled": bool(profile.is_enabled),
"baseline_completed": bool(profile.baseline_completed),
"last_run_dt": profile.last_run_dt,
"last_run_status": (
profile.last_run_status.value if profile.last_run_status is not None else None
),
"last_run_status": (profile.last_run_status.value if profile.last_run_status is not None else None),
}
@ -139,7 +141,9 @@ async def _hydrate_scholar_metadata_if_needed(
should_skip, remaining_seconds = _is_create_hydration_rate_limited()
if should_skip:
structured_log(
logger, "info", "api.scholars.create_metadata_hydration_skipped",
logger,
"info",
"api.scholars.create_metadata_hydration_skipped",
reason="scholar_request_throttle_active",
user_id=user_id,
scholar_profile_id=profile.id,
@ -158,14 +162,18 @@ async def _hydrate_scholar_metadata_if_needed(
)
except TimeoutError:
structured_log(
logger, "info", "api.scholars.create_metadata_hydration_skipped",
logger,
"info",
"api.scholars.create_metadata_hydration_skipped",
reason="create_timeout",
user_id=user_id,
scholar_profile_id=profile.id,
)
except Exception:
structured_log(
logger, "warning", "api.scholars.create_metadata_hydration_failed",
logger,
"warning",
"api.scholars.create_metadata_hydration_failed",
user_id=user_id,
scholar_profile_id=profile.id,
)
@ -185,9 +193,7 @@ def _search_kwargs() -> dict[str, object]:
"cooldown_block_threshold": settings.scholar_name_search_cooldown_block_threshold,
"cooldown_seconds": settings.scholar_name_search_cooldown_seconds,
"retry_alert_threshold": settings.scholar_name_search_alert_retry_count_threshold,
"cooldown_rejection_alert_threshold": (
settings.scholar_name_search_alert_cooldown_rejections_threshold
),
"cooldown_rejection_alert_threshold": (settings.scholar_name_search_alert_cooldown_rejections_threshold),
}
@ -299,8 +305,7 @@ async def import_scholars_and_publications(
status_code=400,
code="invalid_import_schema_version",
message=(
"Import schema version is not supported. "
f"Expected {import_export_service.EXPORT_SCHEMA_VERSION}."
f"Import schema version is not supported. Expected {import_export_service.EXPORT_SCHEMA_VERSION}."
),
)
try:
@ -393,7 +398,15 @@ async def search_scholars(
message=str(exc),
) from exc
structured_log(logger, "info", "api.scholars.search.completed", user_id=current_user.id, query=query.strip(), candidate_count=len(parsed.candidates), state=parsed.state.value)
structured_log(
logger,
"info",
"api.scholars.search.completed",
user_id=current_user.id,
query=query.strip(),
candidate_count=len(parsed.candidates),
state=parsed.state.value,
)
return success_payload(
request,
data=_search_response_data(query, parsed),
@ -422,7 +435,14 @@ async def toggle_scholar(
message="Scholar not found.",
)
updated = await scholar_service.toggle_scholar_enabled(db_session, profile=profile)
structured_log(logger, "info", "api.scholars.toggled", user_id=current_user.id, scholar_profile_id=updated.id, is_enabled=updated.is_enabled)
structured_log(
logger,
"info",
"api.scholars.toggled",
user_id=current_user.id,
scholar_profile_id=updated.id,
is_enabled=updated.is_enabled,
)
return success_payload(
request,
data=_serialize_scholar(updated),
@ -455,7 +475,9 @@ async def delete_scholar(
profile=profile,
upload_dir=settings.scholar_image_upload_dir,
)
structured_log(logger, "info", "api.scholars.deleted", user_id=current_user.id, scholar_profile_id=scholar_profile_id)
structured_log(
logger, "info", "api.scholars.deleted", user_id=current_user.id, scholar_profile_id=scholar_profile_id
)
return success_payload(
request,
data={"message": "Scholar deleted."},
@ -499,7 +521,9 @@ async def update_scholar_image_url(
message=str(exc),
) from exc
structured_log(logger, "info", "api.scholars.image_url_updated", user_id=current_user.id, scholar_profile_id=updated.id)
structured_log(
logger, "info", "api.scholars.image_url_updated", user_id=current_user.id, scholar_profile_id=updated.id
)
return success_payload(
request,
data=_serialize_scholar(updated),
@ -541,7 +565,15 @@ async def upload_scholar_image(
) from exc
image_size = len(image_bytes)
structured_log(logger, "info", "api.scholars.image_uploaded", user_id=current_user.id, scholar_profile_id=updated.id, content_type=image.content_type, size_bytes=image_size)
structured_log(
logger,
"info",
"api.scholars.image_uploaded",
user_id=current_user.id,
scholar_profile_id=updated.id,
content_type=image.content_type,
size_bytes=image_size,
)
return success_payload(
request,
data=_serialize_scholar(updated),

8
app/api/routers/settings.py
View file

@ -85,7 +85,9 @@ async def _clear_expired_cooldown_with_log(
await db_session.commit()
await db_session.refresh(user_settings)
structured_log(
logger, "info", "api.settings.safety_cooldown_cleared",
logger,
"info",
"api.settings.safety_cooldown_cleared",
user_id=user_id,
reason=previous_safety_state.get("cooldown_reason"),
cooldown_until=previous_safety_state.get("cooldown_until"),
@ -164,7 +166,9 @@ async def update_settings(
user_settings=updated,
)
structured_log(
logger, "info", "api.settings.updated",
logger,
"info",
"api.settings.updated",
user_id=current_user.id,
auto_run_enabled=updated.auto_run_enabled,
run_interval_minutes=updated.run_interval_minutes,

14
app/api/schemas.py
View file

@ -671,7 +671,7 @@ class AdminRepairPublicationLinksRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
@model_validator(mode="after")
def validate_scope(self) -> "AdminRepairPublicationLinksRequest":
def validate_scope(self) -> AdminRepairPublicationLinksRequest:
if self.scope_mode == "single_user" and self.user_id is None:
raise ValueError("user_id is required when scope_mode=single_user.")
if self.scope_mode == "all_users" and self.user_id is not None:
@ -680,10 +680,7 @@ class AdminRepairPublicationLinksRequest(BaseModel):
expected = "REPAIR ALL USERS"
provided = (self.confirmation_text or "").strip()
if provided != expected:
raise ValueError(
"confirmation_text must equal 'REPAIR ALL USERS' "
"when applying a repair to all users."
)
raise ValueError("confirmation_text must equal 'REPAIR ALL USERS' when applying a repair to all users.")
return self
@ -735,7 +732,7 @@ class AdminRepairPublicationNearDuplicatesRequest(BaseModel):
model_config = ConfigDict(extra="forbid")
@model_validator(mode="after")
def validate_apply_mode(self) -> "AdminRepairPublicationNearDuplicatesRequest":
def validate_apply_mode(self) -> AdminRepairPublicationNearDuplicatesRequest:
if self.dry_run:
return self
if not self.selected_cluster_keys:
@ -744,8 +741,7 @@ class AdminRepairPublicationNearDuplicatesRequest(BaseModel):
provided = (self.confirmation_text or "").strip()
if provided != expected:
raise ValueError(
"confirmation_text must equal 'MERGE SELECTED DUPLICATES' "
"when applying near-duplicate merges."
"confirmation_text must equal 'MERGE SELECTED DUPLICATES' when applying near-duplicate merges."
)
return self
@ -787,7 +783,7 @@ class SettingsData(BaseModel):
nav_visible_pages: list[str]
policy: SettingsPolicyData
safety_state: ScrapeSafetyStateData
openalex_api_key: str | None = None
crossref_api_token: str | None = None
crossref_api_mailto: str | None = None