fix(security): scope every HybridRAG leg and ingestion path to the caller's tenant

A live /query/hybrid probe as user=llm_tester returned jpmschweitzer
pages. Audit of all legs (vector, graph, web-persistence, volatile,
documents) plus enrichment/persistence found and fixed these unscoped
paths:

- vector_service.update_from_page and graph_service.update_from_page now
  refuse pages outside users/{user}/ - previously any tenant could
  ingest any wiki page (incl. another tenant's) into its own collection
  and graph labels, which is how foreign content entered the vector leg.
- ingestion_service.ingest_all_pages clamps path_prefix to the caller's
  namespace (segment-exact, sanitized comparison) and defaults to
  users/{user}; /ingest/all returns 400 on cross-tenant prefixes.
- hybrid_rag_service._persist_search_for_librarian linked SearchQuery
  nodes to unscoped (d:Document {page_id}); now matches only
  User_{Tenant}_Document nodes.
- graph_service: _get_entity_mention_count, entity-stub mention/related
  queries, generate_entity_stubs, find/purge_orphan_entities matched
  unscoped Document nodes; cleanup_broken_relationships matched all
  tenants' SearchQuery nodes; _entity_has_wiki_page listed all wiki
  pages. All are now tenant-label / namespace scoped.
- volatile_service collection names now use the sanitized user id.
- is_path_in_user_namespace enforces a path-segment boundary
  (users/llm_tester2 is not llm_tester's namespace) and treats
  hyphen/underscore tenant spellings as the same sanitized tenant.
- New offline unit tests per leg (mocked clients) assert the
  tenant-scoped collection/label/path is used and cross-tenant access
  is refused.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

src/services/graph_service.py

@@ -12,7 +12,7 @@ import logging
 
 from src.clients.neo4j_client import Neo4jClient
 from src.clients.wikijs_client import WikiJSClient
-from src.core.multi_tenancy import get_neo4j_user_label
+from src.core.multi_tenancy import get_neo4j_user_label, is_path_in_user_namespace
 from src.models.graph import (
     GraphNode, GraphRelationship, GraphNodeDetail,
     CypherQueryResponse, GraphUpdateSummary, EntityMention,
@@ -424,6 +424,14 @@ class GraphService:
             if not page:
                 raise ValueError(f"Page {page_id} not found")
 
+            # TENANT ISOLATION: only pages inside the user's own wiki
+            # namespace may be written into that user's graph labels.
+            if not is_path_in_user_namespace(page.get("path", ""), user):
+                raise ValueError(
+                    f"Page {page_id} (path: {page.get('path')!r}) is outside "
+                    f"user '{user}' namespace - refusing cross-tenant ingestion"
+                )
+
             # PROTECTION: Skip entity extraction on auto-generated entity stub pages
             tags = page.get("tags", [])
             if "entity-stub" in tags or "auto-generated" in tags:
@@ -675,10 +683,11 @@ class GraphService:
         """
         from src.core.multi_tenancy import get_neo4j_user_base_label
         user_base_label = get_neo4j_user_base_label(user)
+        user_doc_label = get_neo4j_user_label(user)
 
         query = f"""
         MATCH (e:{user_base_label}:{entity_type} {{name: $name}})
-        MATCH (d:Document)-[:MENTIONS]->(e)
+        MATCH (d:{user_doc_label}:Document)-[:MENTIONS]->(e)
         RETURN count(distinct d) as mention_count
         """
 
@@ -714,8 +723,8 @@ class GraphService:
         entity_path = f"{user_namespace}/entities/{entity_type.lower()}/{entity_name.lower().replace(' ', '-')}"
 
         try:
-            # Search for page by path
-            pages = await self.wiki.list_pages(limit=1000)
+            # Search for page by path (scoped to the user's namespace)
+            pages = await self.wiki.list_pages(path_prefix=user_namespace, limit=1000)
             # list_pages returns a list directly, not a dict
             for page in pages:
                 if page.get("path", "") == entity_path:
@@ -822,11 +831,12 @@ Feel free to expand it with more details!
         try:
             from src.core.multi_tenancy import get_neo4j_user_base_label
             user_base_label = get_neo4j_user_base_label(user)
+            user_doc_label = get_neo4j_user_label(user)
 
-            # Get mentioning documents
+            # Get mentioning documents (scoped to this tenant's documents)
             mention_query = f"""
             MATCH (e:{user_base_label}:{entity_type} {{name: $name}})
-            MATCH (d:Document)-[:MENTIONS]->(e)
+            MATCH (d:{user_doc_label}:Document)-[:MENTIONS]->(e)
             RETURN d.title as title, d.path as path, d.page_id as page_id
             """
 
@@ -844,7 +854,7 @@ Feel free to expand it with more details!
             # Only match entity nodes (not Document nodes)
             related_query = f"""
             MATCH (e1:{user_base_label}:{entity_type} {{name: $name}})
-            MATCH (d:Document)-[:MENTIONS]->(e1)
+            MATCH (d:{user_doc_label}:Document)-[:MENTIONS]->(e1)
             MATCH (d)-[:MENTIONS]->(e2:{user_base_label})
             WHERE e2 <> e1 AND NOT (e2:Document)
             RETURN DISTINCT e2.name as name, labels(e2) as labels,
@@ -934,15 +944,16 @@ Feel free to expand it with more details!
 
         from src.core.multi_tenancy import get_neo4j_user_base_label
         user_base_label = get_neo4j_user_base_label(user)
+        user_doc_label = get_neo4j_user_label(user)
         pages_created = []
         pages_skipped = []
 
         try:
-            # Query for entities with sufficient mentions
+            # Query for entities with sufficient mentions (tenant-scoped)
             for entity_type in entity_types:
                 query = f"""
                 MATCH (e:{user_base_label}:{entity_type})
-                MATCH (d:Document)-[:MENTIONS]->(e)
+                MATCH (d:{user_doc_label}:Document)-[:MENTIONS]->(e)
                 WITH e, count(distinct d) as mention_count
                 WHERE mention_count >= $min_mentions
                 RETURN e.name as name, mention_count
@@ -1427,12 +1438,13 @@ Feel free to expand it with more details!
         from src.core.multi_tenancy import get_neo4j_user_base_label
 
         user_base_label = get_neo4j_user_base_label(user)
+        user_doc_label = get_neo4j_user_label(user)
 
         query = f"""
         MATCH (e:{user_base_label})
         WHERE NOT e:Document
         AND NOT e:DocumentCollection
-        AND NOT EXISTS {{ (d:Document)-[:MENTIONS]->(e) }}
+        AND NOT EXISTS {{ (d:{user_doc_label}:Document)-[:MENTIONS]->(e) }}
         RETURN elementId(e) as id, e.name as name, labels(e) as labels
         """
 
@@ -1475,12 +1487,13 @@ Feel free to expand it with more details!
         from src.core.multi_tenancy import get_neo4j_user_base_label
 
         user_base_label = get_neo4j_user_base_label(user)
+        user_doc_label = get_neo4j_user_label(user)
 
         query = f"""
         MATCH (e:{user_base_label})
         WHERE NOT e:Document
         AND NOT e:DocumentCollection
-        AND NOT EXISTS {{ (d:Document)-[:MENTIONS]->(e) }}
+        AND NOT EXISTS {{ (d:{user_doc_label}:Document)-[:MENTIONS]->(e) }}
         DETACH DELETE e
         RETURN count(e) as purged_count
         """
@@ -1608,9 +1621,13 @@ Feel free to expand it with more details!
         Returns:
             Number of relationships cleaned
         """
-        query = """
-        MATCH (sq:SearchQuery)-[r:FOUND]->(d)
-        WHERE NOT EXISTS { (d) }
+        from src.core.multi_tenancy import get_neo4j_user_base_label
+
+        user_base_label = get_neo4j_user_base_label(user)
+
+        query = f"""
+        MATCH (sq:{user_base_label}_SearchQuery:SearchQuery)-[r:FOUND]->(d)
+        WHERE NOT EXISTS {{ (d) }}
         DELETE r
         RETURN count(r) as cleaned_count
         """