feat: H-CITE + H-RET + H-DATA-LIFE — evidence references in ask_knowledge, knowledge retention ARQ cron job (daily 05:00), re-extraction hook on wiki.article.updated

app/core/worker.py

@@ -445,6 +445,53 @@ async def cleanup_trash_job(ctx: dict[str, Any]) -> None:
 register_job("cleanup_trash", cleanup_trash_job)
 
 
+# ── Knowledge retention cleanup job ─────────────────────────────────────────
+
+async def cleanup_knowledge_job(ctx: dict[str, Any]) -> None:
+    """Delete old knowledge extractions (rejected or auto_created) older than 90 days.
+
+    Runs daily. Keeps approved extractions indefinitely.
+    Iterates per-tenant for RLS compliance.
+    """
+    from sqlalchemy import text as sa_text, delete as sa_delete
+    from datetime import datetime, timedelta
+
+    from app.core.db import get_worker_session_factory
+    from app.plugins.builtins.knowledge.models import KnowledgeExtraction
+
+    factory = get_worker_session_factory()
+    async with factory() as db:
+        try:
+            tenant_result = await db.execute(sa_text("SELECT id FROM tenants"))
+            tenant_ids = [row[0] for row in tenant_result]
+
+            cutoff = datetime.utcnow() - timedelta(days=90)
+            total_deleted = 0
+            for tenant_id in tenant_ids:
+                await db.execute(
+                    sa_text("SELECT set_config('app.current_tenant_id', :tid, true)"),
+                    {"tid": str(tenant_id)},
+                )
+                # Delete rejected and auto_created extractions older than 90 days
+                result = await db.execute(
+                    sa_delete(KnowledgeExtraction).where(
+                        KnowledgeExtraction.status.in_(["rejected", "auto_created"]),
+                        KnowledgeExtraction.created_at < cutoff,
+                    )
+                )
+                total_deleted += result.rowcount
+                await db.commit()
+
+            if total_deleted:
+                logger.info("Knowledge retention: cleaned up %d old extractions", total_deleted)
+        except Exception:
+            logger.error("Knowledge retention cleanup failed", exc_info=True)
+            await db.rollback()
+
+
+register_job("cleanup_knowledge", cleanup_knowledge_job)
+
+
 class WorkerSettings:
     """ARQ worker settings."""
     functions = get_all_jobs()
@@ -484,6 +531,11 @@ class WorkerSettings:
             _wrap_cron_with_lock("cleanup_trash", cleanup_trash_job, ttl_seconds=300),
             hour=4, minute=0,
         ),
+        # Knowledge retention cleanup — daily at 05:00 (90 days, keeps approved)
+        cron(
+            _wrap_cron_with_lock("cleanup_knowledge", cleanup_knowledge_job, ttl_seconds=300),
+            hour=5, minute=0,
+        ),
         # Scheduled backup — daily at 02:00 (guarded by distributed lock)
         cron(
             _wrap_cron_with_lock("run_backup", get_job("run_backup"), ttl_seconds=600),