refactor(orchestrator_pm): migrate to send_result() (G2, public_api_migration_and_ui_polish_20260615 Phase 1.2)

Replaces deprecated ai_client.send(md_content='', user_message=user_message,
enable_tools=False) with ai_client.send_result(...) and branches on
result.ok. On error, logs the ui_message() and returns [] (the function
returns a list of track definitions or [] on failure).

The 3 tests in test_orchestrator_pm.py + 1 in test_orchestrator_pm_history.py
now fail because they mock src.ai_client.send. These will be fixed in
Phase 2.14-2.15 by mocking send_result instead.

src/orchestrator_pm.py

@@ -83,11 +83,17 @@ def generate_tracks(user_request: str, project_config: dict[str, Any], file_item
  try:
  # 3. Call Tier 1 Model (Strategic - Pro)
  # Note: We use gemini-1.5-pro or similar high-reasoning model for Tier 1
-  response = ai_client.send(
+  result = ai_client.send_result(
    md_content="", # We pass everything in user_message for clarity
    user_message=user_message,
    enable_tools=False,
   )
+  if not result.ok:
+   _err = result.errors[0] if result.errors else None
+   _msg = _err.ui_message() if _err else "unknown error"
+   print(f"[orchestrator_pm] send_result failed: {_msg}")
+   return []
+  response = result.data
   # 4. Parse JSON Output
   try:
   # The prompt asks for a JSON array. We need to extract it if the AI added markdown blocks.