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.

tests/mock_gemini_cli.py

@@ -7,6 +7,10 @@ def main() -> None:
  sys.stderr.write(f"DEBUG: GEMINI_CLI_HOOK_CONTEXT: {os.environ.get('GEMINI_CLI_HOOK_CONTEXT')}\n")
  sys.stderr.flush()
 
+ if "--list-models" in sys.argv:
+  print(json.dumps(["mock-model-1", "mock-model-2", "mock-model-3"]), flush=True)
+  return
+
  mock_mode = os.environ.get("MOCK_MODE", "success")
  if mock_mode == "malformed_json":
   print("{broken_json: ", flush=True)
@@ -21,7 +25,11 @@ def main() -> None:
 
  # Read prompt from stdin
  try:
+  sys.stderr.write("DEBUG: mock_gemini_cli reading from stdin...\n")
+  sys.stderr.flush()
   prompt = sys.stdin.read()
+  sys.stderr.write(f"DEBUG: mock_gemini_cli read {len(prompt)} chars from stdin.\n")
+  sys.stderr.flush()
   with open("mock_debug_prompt.txt", "a") as f:
    f.write(f"--- MOCK INVOKED ---\nARGS: {sys.argv}\nPROMPT:\n{prompt}\n------------------\n")
  except EOFError: