test(rag): add Phase 4 stress test for large codebase verification

conductor/tracks/rag_support_20260308/plan.md

@@ -42,5 +42,5 @@
 - [x] Task: Implement support for external RAG APIs/MCP servers. f57e2fe
     - [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
-- [ ] Task: Perform a final end-to-end verification with a large codebase.
+- [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)

tests/mock_gcli.bat

@@ -0,0 +1,2 @@
+@echo off
+python %~dp0mock_gemini_cli.py %*

tests/test_rag_phase4_stress.py

@@ -0,0 +1,139 @@
+import pytest
+import time
+import sys
+import os
+import shutil
+import tempfile
+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_rag_large_codebase_verification_sim(live_gui):
+ client = api_hook_client.ApiHookClient()
+ assert client.wait_for_server(timeout=15), "Hook server did not start"
+ 
+ # 1. Setup mock large project data
+ # Create 50 dummy files to test parallel indexing and incrementality
+ workspace_dir = Path("tests/artifacts/live_gui_workspace")
+ workspace_dir.mkdir(parents=True, exist_ok=True)
+ 
+ file_names = [f"file_{i}.txt" for i in range(50)]
+ for name in file_names:
+  (workspace_dir / name).write_text(f"This is the content of {name}. It contains unique tokens to verify RAG.")
+
+ try:
+  # 2. Configure project through Hook API
+  client.set_value('files', file_names)
+  client.set_value('rag_enabled', True)
+  client.set_value('rag_source', 'chroma')
+  client.set_value('rag_emb_provider', 'local')
+  
+  # 3. Trigger Initial Indexing
+  print("[SIM] Triggering initial indexing of 50 files...")
+  start = time.time()
+  client.click('btn_rebuild_rag_index')
+  
+  # Wait for ready
+  success = False
+  for _ in range(100):
+   status = client.get_value('rag_status')
+   if status == 'ready':
+    success = True
+    break
+   time.sleep(0.5)
+  
+  duration_initial = time.time() - start
+  assert success, f"Initial indexing timed out. Final status: {status}"
+  print(f"[SIM] Initial indexing took {duration_initial:.2f}s")
+  
+  # 4. Trigger Incremental Indexing (no changes)
+  print("[SIM] Triggering incremental indexing (no changes)...")
+  start = time.time()
+  client.click('btn_rebuild_rag_index')
+  
+  success = False
+  for _ in range(50):
+   status = client.get_value('rag_status')
+   if status == 'ready':
+    success = True
+    break
+   time.sleep(0.2)
+  
+  duration_incremental = time.time() - start
+  assert success, "Incremental indexing timed out"
+  print(f"[SIM] Incremental indexing took {duration_incremental:.2f}s")
+  # Incremental should be significantly faster
+  assert duration_incremental < duration_initial, f"Incremental ({duration_incremental:.2f}s) not faster than initial ({duration_initial:.2f}s)"
+  
+  # 5. Modify one file and re-index
+  print("[SIM] Modifying one file and re-indexing...")
+  (workspace_dir / "file_25.txt").write_text("MODIFIED CONTENT FOR FILE 25. SEARCH FOR THIS.")
+  
+  client.click('btn_rebuild_rag_index')
+  time.sleep(2) # Wait for it to finish
+  
+  # 6. Verify retrieval of modified content
+  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")))
+  client.set_value('auto_add_history', True)
+  client.set_value('ai_input', "What is the modified content?")
+  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"
+  
+  # Verify retrieved context in discussion
+  session = client.get_session()
+  entries = session.get('session', {}).get('entries', [])
+  
+  found_mod = False
+  for entry in entries:
+   if entry.get('role') == 'User' and 'MODIFIED CONTENT FOR FILE 25' in entry.get('content', ''):
+    found_mod = True
+    break
+  
+  assert found_mod, "Modified context not found in discussion"
+  print("[SIM] Modified content retrieval SUCCESS.")
+
+  # 7. Delete files and verify cleanup
+  print("[SIM] Deleting files and verifying cleanup...")
+  files_to_keep = file_names[:10]
+  client.set_value('files', files_to_keep)
+  client.click('btn_rebuild_rag_index')
+  time.sleep(2)
+  
+  # How to verify cleanup? RAGEngine.get_all_indexed_paths is not exposed yet.
+  # But we can verify by searching for a deleted file's content.
+  client.set_value('ai_input', "What is in file_49.txt?")
+  client.click('btn_gen_send')
+  time.sleep(5)
+  
+  session = client.get_session()
+  entries = session.get('session', {}).get('entries', [])
+  
+  # Last User message should NOT contain context from file_49
+  last_user = next(e for e in reversed(entries) if e.get('role') == 'User')
+  content = last_user.get('content', '')
+  
+  # Check if "Source: file_49.txt" exists in the context block
+  # (which is prepended to the user input)
+  has_stale_context = "Source: file_49.txt" in content
+  assert not has_stale_context, f"Cleanup failed: stale file context found in: {content[:100]}..."
+  
+  print("[SIM] Large codebase verification PASSED.")
+  
+ except Exception as e:
+  print(f"[SIM] Error in stress test: {e}")
+  raise