diff --git a/src/crewai/agent.py b/src/crewai/agent.py
index e2c6b88f1..08ff2ad70 100644
--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -55,6 +55,9 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
+    """
+
+    _times_executed: int = PrivateAttr(default=0)
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
@@ -186,6 +189,20 @@ class Agent(BaseAgent):
         else:
             task_prompt = self._use_trained_data(task_prompt=task_prompt)
 
+        try:
+            result = self.agent_executor.invoke(
+                {
+                    "input": task_prompt,
+                    "tool_names": self.agent_executor.tools_names,
+                    "tools": self.agent_executor.tools_description,
+                }
+            )["output"]
+        except Exception as e:
+            self._times_executed += 1
+            if self._times_executed > self.max_retry_limit:
+                raise e
+            result = self.execute_task(task, context, tools)
+
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
 
diff --git a/src/crewai/memory/short_term/short_term_memory.py b/src/crewai/memory/short_term/short_term_memory.py
index ec65ad6f6..0824c6737 100644
--- a/src/crewai/memory/short_term/short_term_memory.py
+++ b/src/crewai/memory/short_term/short_term_memory.py
@@ -19,7 +19,7 @@ class ShortTermMemory(Memory):
         super().__init__(storage)
 
     def save(self, item: ShortTermMemoryItem) -> None:
-        super().save(item.data, item.metadata, item.agent)
+        super().save(value=item.data, metadata=item.metadata, agent=item.agent)
 
     def search(self, query: str, score_threshold: float = 0.35):
         return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
diff --git a/src/crewai/task.py b/src/crewai/task.py
index 222ef1e5d..bd7e328b0 100644
--- a/src/crewai/task.py
+++ b/src/crewai/task.py
@@ -356,6 +356,9 @@ class Task(BaseModel):
         return OutputFormat.RAW
 
     def _save_file(self, result: Any) -> None:
+        if self.output_file is None:
+            raise ValueError("output_file is not set.")
+
         directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
 
         if directory and not os.path.exists(directory):
@@ -364,6 +367,7 @@ class Task(BaseModel):
         with open(self.output_file, "w", encoding="utf-8") as file:
             if isinstance(result, dict):
                 import json
+
                 json.dump(result, file, ensure_ascii=False, indent=2)
             else:
                 file.write(str(result))
diff --git a/tests/crew_test.py b/tests/crew_test.py
index 86c4404ed..141ecfb7c 100644
--- a/tests/crew_test.py
+++ b/tests/crew_test.py
@@ -8,7 +8,6 @@ from unittest.mock import MagicMock, patch
 
 import pydantic_core
 import pytest
-
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -572,47 +571,6 @@ def test_api_calls_throttling(capsys):
         moveon.assert_called()
 
 
-# This test is not consistent, some issue is happening on the CI when it comes to Prompt tokens
-#  {'usage_metrics': {'completion_tokens': 34, 'prompt_tokens': 0, 'successful_requests': 2, 'total_tokens': 34}} CI OUTPUT
-#  {'usage_metrics': {'completion_tokens': 34, 'prompt_tokens': 314, 'successful_requests': 2, 'total_tokens': 348}}
-# The issue might be related to the calculate_usage_metrics function
-# @pytest.mark.vcr(filter_headers=["authorization"])
-# def test_crew_full_output():
-#     agent = Agent(
-#         role="test role",
-#         goal="test goal",
-#         backstory="test backstory",
-#         allow_delegation=False,
-#         verbose=True,
-#     )
-
-#     task1 = Task(
-#         description="just say hi!",
-#         expected_output="your greeting",
-#         agent=agent,
-#     )
-#     task2 = Task(
-#         description="just say hello!",
-#         expected_output="your greeting",
-#         agent=agent,
-#     )
-
-#     crew = Crew(agents=[agent], tasks=[task1, task2], full_output=True)
-
-#     result = crew.kickoff()
-
-#     assert result == {
-#         "final_output": "Hello!",
-#         "tasks_outputs": [task1.output, task2.output],
-#         "usage_metrics": {
-#             "total_tokens": 348,
-#             "prompt_tokens": 314,
-#             "completion_tokens": 34,
-#             "successful_requests": 2,
-#         },
-#     }
-
-
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_kickoff_usage_metrics():
     inputs = [