fix(rag): Resolve RAG test failures and race conditions

- Fixed circular import in chromadb by using lazy imports in 
ag_engine.py.
- Moved RAG engine initialization to background threads in AppController to avoid blocking UI.
- Added _rag_engine_lock to prevent race conditions during engine re-initialization.
- Updated Gemini embedding model to gemini-embedding-001 (available) from 	ext-embedding-004 (not found).
- Fixed _rebuild_rag_index to use fresh 
ag_engine instance from self in every iteration.
- Optimized 	est_rag_phase4_final_verify.py and 	est_rag_phase4_stress.py to wait for RAG sync before continuing.
- Added dummy embedding fallback in LocalEmbeddingProvider if sentence-transformers fails to load.

src/app_controller.py

@@ -1,4 +1,3 @@
-import chromadb
 import copy
 import inspect
 import json
@@ -750,6 +749,7 @@ class AppController:
   self._pending_gui_tasks_lock: threading.Lock = threading.Lock()
   self._pending_dialog_lock: threading.Lock = threading.Lock()
   self._api_event_queue_lock: threading.Lock = threading.Lock()
+  self._rag_engine_lock: threading.Lock = threading.Lock()
 
   # --- Internal State ---
   self._ai_status: str = "idle"
@@ -1186,6 +1186,31 @@ class AppController:
   from src import summarize
   return summarize._summary_cache
 
+ @property
+ def rag_enabled(self) -> bool:
+  return self.rag_config.enabled if self.rag_config else False
+ def _sync_rag_engine(self):
+  """
+  Re-initializes the RAG engine in a background thread to avoid blocking the UI.
+  """
+  self._set_rag_status("initializing...")
+  def _task():
+   try:
+    from src import rag_engine
+    engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
+    with self._rag_engine_lock:
+     self.rag_engine = engine
+    self._set_rag_status("ready")
+    # If the engine is empty and we have files, trigger indexing
+    if self.rag_engine and self.rag_engine.is_empty() and self.files:
+     self._rebuild_rag_index()
+   except Exception as e:
+    self._set_rag_status(f"error: {e}")
+    sys.stderr.write(f"[DEBUG RAG] Failed to sync engine: {e}\n")
+    sys.stderr.flush()
+  
+  threading.Thread(target=_task, daemon=True).start()
+
  @property
  def rag_enabled(self) -> bool:
   return self.rag_config.enabled if self.rag_config else False
@@ -1193,8 +1218,7 @@ class AppController:
  def rag_enabled(self, value: bool) -> None:
   if self.rag_config:
    self.rag_config.enabled = value
-   from src import rag_engine
-   self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
+   self._sync_rag_engine()
 
  @property
  def rag_source(self) -> str:
@@ -1203,8 +1227,7 @@ class AppController:
  def rag_source(self, value: str) -> None:
   if self.rag_config:
    self.rag_config.vector_store.provider = value
-   from src import rag_engine
-   if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
+   self._sync_rag_engine()
 
  @property
  def rag_emb_provider(self) -> str:
@@ -1213,8 +1236,7 @@ class AppController:
  def rag_emb_provider(self, value: str) -> None:
   if self.rag_config:
    self.rag_config.embedding_provider = value
-   from src import rag_engine
-   if self.rag_engine: self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
+   self._sync_rag_engine()
 
  @property
  def rag_chunk_size(self) -> int:
@@ -1351,9 +1373,11 @@ class AppController:
     # 1. Incremental indexing of current files in parallel
     with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:
      futures = []
+     def do_index(p):
+      if self.rag_engine: self.rag_engine.index_file(p)
      for f in self.files:
       path = f.path if hasattr(f, "path") else str(f)
-      futures.append(executor.submit(self.rag_engine.index_file, path))
+      futures.append(executor.submit(do_index, path))
      concurrent.futures.wait(futures)
 
     # 2. Cleanup stale entries (files no longer tracked)
@@ -1596,12 +1620,7 @@ class AppController:
 
   self.rag_engine = None
   if self.rag_config.enabled:
-   def _init_rag_engine():
-    from src import rag_engine
-    self.rag_engine = rag_engine.RAGEngine(self.rag_config, self.active_project_root)
-    if self.rag_engine.is_empty():
-     self._rebuild_rag_index()
-   threading.Thread(target=_init_rag_engine, daemon=True).start()
+   self._sync_rag_engine()
 
   from src.personas import PersonaManager
   self.persona_manager = PersonaManager(Path(self.active_project_path).parent if self.active_project_path else None)