Usage metrics fixed

examples/lite_agent_example.py

@@ -111,6 +111,8 @@ async def main():
         print(
             "\nNote: Structured output was not generated. The LLM may need more explicit instructions to format the response as JSON."
         )
+    print("Usage metrics:")
+    print(result.usage_metrics)
 
     # # Example 3: Multi-turn conversation
     # print("\n=== Example 3: Multi-turn Conversation ===")

src/crewai/lite_agent.py

@@ -278,7 +278,11 @@ class LiteAgent(BaseModel):
 
         Returns:
             LiteAgentOutput: The result of the agent execution.
+
+        Raises:
+            Exception: If agent execution fails
         """
+        try:
             # Reset state for this run
             self._iterations = 0
             self.tools_results = []
@@ -305,9 +309,34 @@ class LiteAgent(BaseModel):
                 ),
             )
 
-        try:
             # Execute the agent using invoke loop
-            result = await self._invoke()
+            agent_finish = await self._invoke()
+
+            formatted_result: Optional[BaseModel] = None
+            if self.response_format:
+                try:
+                    # Cast to BaseModel to ensure type safety
+                    result = self.response_format.model_validate_json(
+                        agent_finish.output
+                    )
+                    if isinstance(result, BaseModel):
+                        formatted_result = result
+                except Exception as e:
+                    self._printer.print(
+                        content=f"Failed to parse output into response format: {str(e)}",
+                        color="yellow",
+                    )
+
+            # Calculate token usage metrics
+            usage_metrics = self._token_process.get_summary()
+
+            return LiteAgentOutput(
+                raw=agent_finish.output,
+                pydantic=formatted_result,
+                agent_role=self.role,
+                usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
+            )
+
         except AssertionError:
             self._printer.print(
                 content="Agent failed to reach a final answer. This is likely a bug - please report it.",
@@ -319,20 +348,8 @@ class LiteAgent(BaseModel):
             if e.__class__.__module__.startswith("litellm"):
                 # Do not retry on litellm errors
                 raise e
-            else:
             raise e
 
-        formatted_result: Optional[BaseModel] = None
-        if self.response_format:
-            formatted_result = self.response_format.model_validate_json(result.output)
-
-        return LiteAgentOutput(
-            raw=result.output,
-            pydantic=formatted_result,
-            agent_role=self.role,
-            usage_metrics=None,  # TODO: Add usage metrics
-        )
-
     async def _invoke(self) -> AgentFinish:
         """
         Run the agent's thought process until it reaches a conclusion or max iterations.