Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Python aicode-complexitycode-healthcode-intelligencecode-qualitydead-codedeveloper-toolsdocumentationgit-analyticsmcpopen-sourcepythonrefactoringstatic-analysistechnical-debt
fix(server): count stale pages without loading content (#2257)
ASVLCII26f9bf73d856
diff --git a/packages/server/src/repowise/server/scheduler.py b/packages/server/src/repowise/server/scheduler.pyindex bb8d415a6..17832d8c5 100644--- a/packages/server/src/repowise/server/scheduler.py+++ b/packages/server/src/repowise/server/scheduler.py@@ -1,7 +1,7 @@"""APScheduler background jobs for repowise server.Two recurring jobs:-1. Staleness checker — finds stale wiki pages and queues regeneration.+1. Staleness checker — reports stale wiki pages without regenerating them.2. Polling fallback — catches missed webhooks by comparing HEAD commits."""@@ -73,7 +73,7 @@ def setup_scheduler(async def check_staleness() -> None:"""Find stale pages and log them for regeneration."""- from sqlalchemy import select+ from sqlalchemy import func, selectfrom repowise.core.persistence.database import get_sessionfrom repowise.core.persistence.models import Page, Repository@@ -85,19 +85,21 @@ def setup_scheduler(for repo in repos:stale_result = await session.execute(- select(Page).where(+ select(func.count())+ .select_from(Page)+ .where(Page.repository_id == repo.id,Page.freshness_status.in_(["stale", "expired"]),))- stale = stale_result.scalars().all()- if stale:+ stale_count = stale_result.scalar()+ if stale_count:logger.info("staleness_check",extra={"repo_id": repo.id,"repo_name": repo.name,- "stale_count": len(stale),+ "stale_count": stale_count,},)except Exception:diff --git a/tests/unit/server/test_scheduler.py b/tests/unit/server/test_scheduler.pyindex 76ea32cd2..676099e50 100644--- a/tests/unit/server/test_scheduler.py+++ b/tests/unit/server/test_scheduler.py@@ -4,17 +4,74 @@ from __future__ import annotationsimport asyncioimport json+import logging+from datetime import UTC, datetimefrom types import SimpleNamespacefrom unittest.mock import AsyncMock, patch-from sqlalchemy import select+from sqlalchemy import event, selectfrom repowise.core.persistence import crudfrom repowise.core.persistence.database import get_session-from repowise.core.persistence.models import GenerationJob+from repowise.core.persistence.models import GenerationJob, Pagefrom repowise.server.scheduler import _inspect_repository, setup_scheduler+async def test_staleness_checker_counts_in_sql(+ session_factory, test_engine, tmp_path, caplog+) -> None:+ """Report only stale/expired pages per repo without selecting their content."""+ async with get_session(session_factory) as session:+ first = await crud.upsert_repository(+ session, name="first", local_path=str(tmp_path / "first")+ )+ second = await crud.upsert_repository(+ session, name="second", local_path=str(tmp_path / "second")+ )+ for repo, statuses in ((first, ("stale", "expired", "fresh")), (second, ("stale",))):+ for index, status in enumerate(statuses):+ session.add(+ Page(+ id=f"file_page:{repo.name}:{index}",+ repository_id=repo.id,+ page_type="file_page",+ title=f"Page {index}",+ content="long rendered markdown " * 100,+ target_path=f"{repo.name}/{index}",+ source_hash="hash",+ model_name="test",+ provider_name="test",+ freshness_status=status,+ created_at=datetime.now(UTC),+ updated_at=datetime.now(UTC),+ )+ )+ await session.commit()++ statements: list[str] = []++ def capture_sql(_connection, _cursor, statement, _parameters, _context, _executemany) -> None:+ if "wiki_pages" in statement:+ statements.append(statement)++ scheduler = setup_scheduler(session_factory)+ staleness_job = next(job for job in scheduler.get_jobs() if job.id == "staleness_check")+ event.listen(test_engine.sync_engine, "before_cursor_execute", capture_sql)+ try:+ with caplog.at_level(logging.INFO, logger="repowise.server.scheduler"):+ await staleness_job.func()+ finally:+ event.remove(test_engine.sync_engine, "before_cursor_execute", capture_sql)++ assert len(statements) == 2+ assert all(+ "count(" in statement.lower() and "wiki_pages.content" not in statement+ for statement in statements+ )+ records = [record for record in caplog.records if record.msg == "staleness_check"]+ assert {record.repo_name: record.stale_count for record in records} == {"first": 2, "second": 1}++async def test_polling_fallback_launches_persisted_job(session_factory, tmp_path) -> None:"""A diverged repository should launch the sync job that was persisted."""repo_path = tmp_path / "repo"