refactor: switch preprocessing to use delegation tools

Changes preprocessing to use get_delegation_tools() instead of
get_scoped_tools(). Expert agents now get delegation wrappers
(delegate_to_librarian) while core tools are returned directly.

This reduces Tatlock's cognitive load from 16+ tools to ~3-5.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/core/preprocessing.py

@@ -103,9 +103,11 @@ async def preprocess_request(
     # Format note for Tatlock (includes conversation context)
     steward_note = await format_steward_note(recommendation)
 
-    # Get scoped tools from household registry
+    # Get delegation tools from household registry
+    # Uses agent-as-tool pattern: expert agents get delegation wrappers,
+    # core tools are returned directly
     registry = get_household_registry()
-    scoped_tools = registry.get_scoped_tools(
+    scoped_tools = registry.get_delegation_tools(
         recommendation.recommended_capabilities
     )