M25: expose provenance-aware knowledge statistics

docs/09-ragcore-integration.md

@@ -14,7 +14,24 @@ These values are configurable.
 
 ## Source documents
 
-The ten Markdown files under `knowledge/procedures/` are authoritative PoC sources. Keep their IDs, versions and effective dates as metadata.
+The versioned Markdown files under `knowledge/procedures/` (currently eleven per supported
+language) are the authoritative sources. Keep their IDs, versions and effective dates as
+metadata.
+
+## Index statistics and provenance
+
+`GET /api/v1/knowledge/status` keeps three different measurements separate:
+
+- `source_document_count`: authoritative procedure files available to Fleet Ops for the requested language;
+- `reported_synced_document_count`, `reported_failed_document_count` and `last_sync_at`: the latest persisted result reported by the central n8n synchronization workflow;
+- `document_count`: documents independently verified as indexed by the active provider.
+
+The current RAGcore contract deliberately has no corpus-size or space-browse endpoint. For
+the RAGcore provider, `document_count` therefore remains `null`; a successful upload report
+is never relabelled as proof that indexing and publishing completed. The deterministic demo
+provider can verify its in-memory corpus and reports `statistics_state=verified`. RAGcore
+reports `sync_reported` only when a persisted workflow callback exists, otherwise
+`not_reported`.
 
 ## Required adapter interface