feat(E): Unified Search — 24 Tasks complete

- SPIKE-E: FTS+Vector+Permission benchmark on 10k records (all <30ms)
- E-PROV: supports_fts/vector/rag/graph capability flags on all providers
- E-FTS/VEC: All 11 providers refactored to BaseSearchProvider with permission filtering
- E-PERM: Over-fetch strategy for vector+permission (15x faster than ANY() filter)
- E-FUSE: rrf_fusion_multi() for N-way RRF over FTS+Vector+RAG+Graph
- E-LLM: Query understanding cleaned up to use central llm_complete()
- E-CHUNK: Document chunking module + document_chunks table with HNSW index
- E-EMB: Chunk embedding ARQ jobs (index_file_chunks, reindex_chunks)
- E-RAG: RAG retrieval via FileSearchProvider.search_rag()
- E-GRAPH: GraphRAG BFS traversal via GraphRAGSearchProvider.search_graph()
- E-IX-EVT: Auto-indexing via outbox events + delete/cleanup handlers
- E-IX-RE: Batch reindex with progress tracking + reindex_all job
- E-DATA-LIFE: Lifecycle module (remove/rebuild/restore/correct) + API endpoints
- E-K-MEM: AgentMemorySearchProvider
- E-P-AI: AIChatSearchProvider
- E-P-WF: WorkflowSearchProvider
- E-P-COMM: ConversationSearchProvider verified (already on BaseSearchProvider)
- E-API: Filter params (date_from/to, tags, sort) + /facets endpoint
- E-TOOL: unified_search AI tool registered in ToolRegistry
- E-MCP: Search tool in MCP server with normal RBAC/tenant checks
- E-UI-CMD: CommandPalette (Cmd+K) with debounced search + recent searches
- E-UI-FAC: SearchFacets, SearchResultCard, SavedSearches components
- E-TEST: 40 new tests in test_unified_search_phase_e.py (105 total green)
- E-DOC: api-documentation.md, plugin-development-guide.md, test-strategy.md updated

105 tests passing, TypeScript clean.

app/plugins/builtins/unified_search/base_provider.py

@@ -25,6 +25,12 @@ class BaseSearchProvider:
     The base class handles loading visible IDs and passing them to the subclass.
     """
 
+    # Capability flags — override in subclass
+    supports_fts: bool = True
+    supports_vector: bool = True
+    supports_rag: bool = False
+    supports_graph: bool = False
+
     entity_type: str = ""  # Override in subclass
 
     async def search_fts(
@@ -54,7 +60,12 @@ class BaseSearchProvider:
         user_id: uuid.UUID | None = None,
         is_system_admin: bool = False,
     ) -> list[dict[str, Any]]:
-        """Semantic vector search with visibility filter."""
+        """Semantic vector search with visibility filter.
+
+        Uses over-fetch strategy: fetch limit*3 from HNSW without permission
+        filter, then post-filter in Python. This avoids the 15x performance
+        hit of `id = ANY($uuid[])` on HNSW results found in SPIKE-E.
+        """
         # Set HNSW ef_search parameter for this transaction
         await db.execute(text(f"SET LOCAL hnsw.ef_search = {settings.hnsw_ef_search}"))
         if is_system_admin or not user_id:
@@ -63,7 +74,12 @@ class BaseSearchProvider:
         visible_ids = await self._get_visible_ids(db, tenant_id, user_id)
         if not visible_ids:
             return []
-        return await self._search_vector_filtered(db, embedding, tenant_id, limit, visible_ids)
+
+        # Over-fetch 3x the limit, then post-filter in Python
+        over_fetch_limit = limit * 3
+        results = await self._search_vector_filtered(db, embedding, tenant_id, over_fetch_limit, None)
+        filtered = [r for r in results if r.get("id") in visible_ids]
+        return filtered[:limit]
 
     async def _get_visible_ids(
         self, db: AsyncSession, tenant_id: uuid.UUID, user_id: uuid.UUID