conductor(checkpoint): Final checkpoint for RAG Support track - Phase 4 complete

conductor/tracks/rag_support_20260308/plan.md

@@ -43,4 +43,5 @@
     - [x] Create a bridge in `src/rag_engine.py` to call external RAG tools via the MCP interface. f57e2fe
 - [x] Task: Optimize indexing performance for large projects (e.g., incremental updates, parallel chunking). f57e2fe
 - [x] Task: Perform a final end-to-end verification with a large codebase. f57e2fe
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Refinement & Advanced RAG' (Protocol in workflow.md)
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Refinement & Advanced RAG' (Protocol in workflow.md) f57e2fe
+

src/ai_client.py

@@ -2250,7 +2250,7 @@ def send(
  monitor = performance_monitor.get_monitor()
  if monitor.enabled: monitor.start_component("ai_client.send")
 
- if rag_engine and getattr(rag_engine.config, "enabled", False):
+ if rag_engine and getattr(rag_engine.config, "enabled", False) and "## Retrieved Context" not in user_message:
   chunks = rag_engine.search(user_message)
   if chunks:
    context_block = "## Retrieved Context\n\n"

src/app_controller.py

@@ -534,6 +534,7 @@ class AppController:
   if self.rag_config:
    self.rag_config.embedding_provider = value
    if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
+   if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
 
  @property
  def rag_chunk_size(self) -> int:

src/models.py

@@ -598,10 +598,12 @@ class MCPConfiguration:
 
 @dataclass
 class VectorStoreConfig:
- provider: str # 'chroma', 'qdrant', 'mock'
+ provider: str # 'chroma', 'qdrant', 'mock', 'mcp'
  url: Optional[str] = None
  api_key: Optional[str] = None
  collection_name: str = 'manual_slop'
+ mcp_server: Optional[str] = None
+ mcp_tool: Optional[str] = None
 
  def to_dict(self) -> Dict[str, Any]:
   return {
@@ -609,6 +611,8 @@ class VectorStoreConfig:
    "url": self.url,
    "api_key": self.api_key,
    "collection_name": self.collection_name,
+   "mcp_server": self.mcp_server,
+   "mcp_tool": self.mcp_tool,
   }
 
  @classmethod
@@ -618,6 +622,8 @@ class VectorStoreConfig:
    url=data.get("url"),
    api_key=data.get("api_key"),
    collection_name=data.get("collection_name", "manual_slop"),
+   mcp_server=data.get("mcp_server"),
+   mcp_tool=data.get("mcp_tool"),
   )
 
 @dataclass

tests/test_rag_phase4_final_verify.py

@@ -0,0 +1,94 @@
+import pytest
+import time
+import sys
+import os
+import json
+import shutil
+from pathlib import Path
+
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..")))
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "src")))
+
+from src import api_hook_client
+
+@pytest.mark.integration
+def test_phase4_final_verify(live_gui):
+ client = api_hook_client.ApiHookClient()
+ assert client.wait_for_server(timeout=15), "Hook server did not start"
+ 
+ # 1. Setup mock project data
+ workspace_dir = Path("tests/artifacts/live_gui_workspace")
+ workspace_dir.mkdir(parents=True, exist_ok=True)
+ 
+ # Create dummy files
+ (workspace_dir / "final_test_1.txt").write_text("Manual Slop RAG is great.")
+ (workspace_dir / "final_test_2.py").write_text("def test_func():\n return 'Manual Slop RAG result'")
+ 
+ try:
+  # 2. Configure project through Hook API
+  client.set_value('files', ['final_test_1.txt', 'final_test_2.py'])
+  client.set_value('rag_enabled', True)
+  client.set_value('rag_source', 'chroma')
+  client.set_value('rag_emb_provider', 'local')
+  client.set_value('auto_add_history', True)
+  client.set_value('current_provider', 'gemini_cli')
+  client.set_value('gcli_path', os.path.abspath(os.path.join(os.path.dirname(__file__), "mock_gcli.bat")))
+  
+  # 3. Trigger Initial Indexing
+  print("[VERIFY] Triggering indexing...")
+  client.click('btn_rebuild_rag_index')
+  
+  # Wait for ready
+  success = False
+  for _ in range(50):
+   status = client.get_value('rag_status')
+   if status == 'ready':
+    success = True
+    break
+   time.sleep(0.5)
+  assert success, f"Indexing failed. Status: {status}"
+  
+  # 4. Verify Retrieval and Visualization
+  print("[VERIFY] Triggering retrieval turn...")
+  client.set_value('ai_input', "What makes RAG great?")
+  client.click('btn_gen_send')
+  
+  # Wait for completion
+  success = False
+  for _ in range(50):
+   state = client.get_gui_state()
+   if state.get('ai_status') == 'done':
+    success = True
+    break
+   time.sleep(0.5)
+  assert success, "AI request timed out"
+  
+  # 5. Verify discussion history has the context
+  session = client.get_session()
+  entries = session.get('session', {}).get('entries', [])
+  
+  found_rag = False
+  for entry in entries:
+   if entry.get('role') == 'User' and '## Retrieved Context' in entry.get('content', ''):
+    found_rag = True
+    print(f"[VERIFY] Found RAG context: {entry.get('content')[:100]}...")
+    assert "Manual Slop RAG is great" in entry.get('content')
+    break
+  assert found_rag, "RAG context not found in history"
+
+  # 6. Verify Incremental Indexing (no changes)
+  print("[VERIFY] Verifying incrementality...")
+  start = time.time()
+  client.click('btn_rebuild_rag_index')
+  for _ in range(50):
+   if client.get_value('rag_status') == 'ready': break
+   time.sleep(0.1)
+  duration = time.time() - start
+  print(f"[VERIFY] Incremental indexing took {duration:.2f}s")
+  assert duration < 1.0, "Incremental indexing too slow (expected < 1s for 2 files)"
+
+  print("[VERIFY] Phase 4 final verification COMPLETED successfully.")
+  
+ except Exception as e:
+  print(f"[VERIFY] ERROR in final verification: {e}")
+  raise