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/plugins/builtins/knowledge/services.py

@@ -109,22 +109,48 @@ async def ask_knowledge(
     # Search wiki articles for context
     from app.plugins.builtins.unified_search.provider_registry import get_search_registry
     registry = get_search_registry()
-    wiki_provider = registry.get("wiki_article")
+    evidence: list[dict[str, Any]] = []
     context_parts = []
+    wiki_provider = registry.get("wiki_article")
     if wiki_provider:
         results = await wiki_provider._search_fts_filtered(
             db=db, tsquery=question, tenant_id=tenant_id, limit=5, visible_ids=None
         )
         for r in results:
-            context_parts.append(f"Title: {r.get('title', '')}\nContent: {r.get('content', '')[:500]}")
+            snippet = (r.get("content", "") or "")[:300]
+            title = r.get("title", "")
+            context_parts.append(f"Title: {title}\nContent: {snippet}")
+            evidence.append({
+                "id": str(r.get("id", "")),
+                "source_type": "wiki_article",
+                "source_id": str(r.get("id", "")),
+                "title": title,
+                "snippet": snippet,
+                "score": float(r.get("rank", 0.0)),
+                "url": f"/wiki?article={r.get('slug', '')}",
+            })
     # Search graph_rag for relationships
     graph_provider = registry.get("graph_relationship")
     if graph_provider:
-        results = await graph_provider._search_fts_filtered(
-            db=db, tsquery=question, tenant_id=tenant_id, limit=5, visible_ids=None
-        )
-        for r in results:
-            context_parts.append(f"Relationship: {r.get('source_type')} -> {r.get('relationship_type')} -> {r.get('target_type')}")
+        try:
+            results = await graph_provider._search_fts_filtered(
+                db=db, tsquery=question, tenant_id=tenant_id, limit=5, visible_ids=None
+            )
+            for r in results:
+                title = f"{r.get('source_type', '')} → {r.get('relationship_type', '')} → {r.get('target_type', '')}"
+                snippet = str(r.get("meta", ""))
+                context_parts.append(f"Relationship: {title}")
+                evidence.append({
+                    "id": str(r.get("id", "")),
+                    "source_type": "graph_relationship",
+                    "source_id": str(r.get("id", "")),
+                    "title": title,
+                    "snippet": snippet,
+                    "score": float(r.get("rank", 0.0)),
+                    "url": None,
+                })
+        except Exception:
+            logger.warning("GraphRAG search failed in ask_knowledge", exc_info=True)
     context = "\n\n".join(context_parts) if context_parts else "No knowledge base content found."
     messages = [
         {"role": "system", "content": f"You are a knowledge assistant. Answer based on this context:\n\n{context}"},
@@ -136,7 +162,8 @@ async def ask_knowledge(
     )
     return {
         "answer": response.get("content", ""),
-        "evidence": context_parts[:3],
+        "evidence": evidence,
+        "sources_used": list(set(e["source_type"] for e in evidence)),
         "cost_usd": response.get("cost_usd", 0.0),
     }