decomposer: generate deliverable files for Define the normalized ingestion contract and pluggable source-connector interface for SCM, CMS, and other content sources.; Implement a GitHub SCM connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of Markdown, plain-text, and source files with webhook and revision metadata.; Implement a SharePoint CMS connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of PDF, DOCX, and HTML files with webhook and revision metadata.; Implement ingestion orchestration and triggers; Normalize, govern, and publish ingested content to the shared knowledge store.; Add deployment/configuration, tests, and documentation for the ingestion agent.; Validate end-to-end ingestion and downstream content availability.

kab_ingestion/governance.py

@@ -0,0 +1,14 @@
+from __future__ import annotations
+from datetime import datetime, timedelta, timezone
+
+class GovernedPublisher:
+    def __init__(self, store, audit, retention_days=30): self.store, self.audit, self.retention_days = store, audit, retention_days
+    def publish(self, batch):
+        if any(d.tenant_id != batch.tenant_id for d in batch.documents): raise PermissionError('tenant mismatch')
+        self.store.upsert(batch.documents)
+        self.audit.append({'tenant_id': batch.tenant_id, 'run_id': batch.run_id, 'action': 'publish', 'count': len(batch.documents), 'at': datetime.now(timezone.utc).isoformat()})
+    def purge_expired_tombstones(self, docs):
+        cutoff = datetime.now(timezone.utc) - timedelta(days=self.retention_days)
+        ids = [d.document_id for d in docs if d.deleted and d.updated_at < cutoff]
+        if ids: self.store.delete(ids, docs[0].tenant_id)
+        return ids