diff --git a/src/app_controller.py b/src/app_controller.py
index 1062b81e..d618a464 100644
--- a/src/app_controller.py
+++ b/src/app_controller.py
@@ -275,45 +275,37 @@ def _api_generate(controller: 'AppController', req: GenerateRequest) -> dict[str
       "ts": project_manager.now_ts()
       })
       
-   try:
-    with controller._disc_entries_lock:
-     has_ai_response = any(e.get("role") == "AI" for e in controller.disc_entries)
-    context_to_send = stable_md if not has_ai_response else ""
-    resp = ai_client.send(context_to_send, user_msg, base_dir, controller.last_file_items, disc_text, rag_engine=None)
-    
-    if req.auto_add_history:
-     with controller._pending_history_adds_lock:
-      controller._pending_history_adds.append({
-       "role": "AI",
-       "content": resp,
-       "collapsed": True,
-       "ts": project_manager.now_ts()
-       })
-    
-    controller._recalculate_session_usage()
-    duration = time.time() - start_time
-    return {
-     "text": resp,
-     "metadata": {
-      "provider": controller.current_provider,
-      "model": controller.current_model,
-      "duration_sec": round(duration, 3),
-      "timestamp": project_manager.now_ts()
-     },
-     "usage": controller.session_usage
-    }
-   except ai_client.ProviderError as e:
-    raise HTTPException(status_code=500, detail=e.ui_message())
-   except Exception as e:
-    raise HTTPException(status_code=500, detail=str(e))
+   result = ai_client.send_result(context_to_send, user_msg, base_dir, controller.last_file_items, disc_text, rag_engine=None)
+   if not result.ok:
+    err = result.errors[0]
+    raise HTTPException(status_code=502, detail=err.ui_message())
+   resp = result.data
+
+   if req.auto_add_history:
+    with controller._pending_history_adds_lock:
+     controller._pending_history_adds.append({
+      "role": "AI",
+      "content": resp,
+      "collapsed": True,
+      "ts": project_manager.now_ts()
+      })
+
+   controller._recalculate_session_usage()
+   duration = time.time() - start_time
+   return {
+    "text": resp,
+    "metadata": {
+     "provider": controller.current_provider,
+     "model": controller.current_model,
+     "duration_sec": round(duration, 3),
+     "timestamp": project_manager.now_ts()
+    },
+    "usage": controller.session_usage
+   }
   except Exception as e:
    import traceback
    traceback.print_exc()
    raise HTTPException(status_code=500, detail=str(e))
-  except ai_client.ProviderError as e:
-   raise HTTPException(status_code=502, detail=f"AI Provider Error: {e.ui_message()}")
-  except Exception as e:
-   raise HTTPException(status_code=500, detail=f"In-flight AI request failure: {e}")
 
 async def _api_stream(controller: 'AppController', req: GenerateRequest) -> Any:
  """
@@ -3673,6 +3665,8 @@ class AppController:
   ai_client.set_model_params(self.temperature, self.max_tokens, self.history_trunc_limit, self.top_p)
   ai_client.set_agent_tools(self.ui_agent_tools)  # Force update adapter path right before send to bypass potential duplication issues
   self._update_gcli_adapter(self.ui_gemini_cli_path)
+  # FR2 / Bug #1: per conductor/code_styleguides/error_handling.md section 3.1 (AND over OR),
+  # we check result.ok instead of catching a ProviderError exception.
   result = ai_client.send_result(
    event.stable_md,
    user_msg,