feat: expose messages to TaskOutput and LiteAgentOutputs (#3880)

* feat: add messages to task and agent outputs

- Introduced a new  field in  and  to capture messages from the last task execution.
- Updated the  class to store the last messages and provide a property for easy access.
- Enhanced the  and  classes to include messages in their outputs.
- Added tests to ensure that messages are correctly included in task outputs and agent outputs during execution.

* using typing_extensions for 3.10 compatability

* feat: add last_messages attribute to agent for improved task tracking

- Introduced a new `last_messages` attribute in the agent class to store messages from the last task execution.
- Updated the `Crew` class to handle the new messages attribute in task outputs.
- Enhanced existing tests to ensure that the `last_messages` attribute is correctly initialized and utilized across various guardrail scenarios.

* fix: add messages field to TaskOutput in tests for consistency

- Updated multiple test cases to include the new `messages` field in the `TaskOutput` instances.
- Ensured that all relevant tests reflect the latest changes in the TaskOutput structure, maintaining consistency across the test suite.
- This change aligns with the recent addition of the `last_messages` attribute in the agent class for improved task tracking.

* feat: preserve messages in task outputs during replay

- Added functionality to the Crew class to store and retrieve messages in task outputs.
- Enhanced the replay mechanism to ensure that messages from stored task outputs are preserved and accessible.
- Introduced a new test case to verify that messages are correctly stored and replayed, ensuring consistency in task execution and output handling.
- This change improves the overall tracking and context retention of task interactions within the CrewAI framework.

* fix original test, prev was debugging

lib/crewai/src/crewai/agent/core.py

@@ -119,6 +119,7 @@ class Agent(BaseAgent):
 
     _times_executed: int = PrivateAttr(default=0)
     _mcp_clients: list[Any] = PrivateAttr(default_factory=list)
+    _last_messages: list[LLMMessage] = PrivateAttr(default_factory=list)
     max_execution_time: int | None = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
@@ -538,6 +539,12 @@ class Agent(BaseAgent):
             event=AgentExecutionCompletedEvent(agent=self, task=task, output=result),
         )
 
+        self._last_messages = (
+            self.agent_executor.messages.copy()
+            if self.agent_executor and hasattr(self.agent_executor, "messages")
+            else []
+        )
+
         self._cleanup_mcp_clients()
 
         return result
@@ -1341,6 +1348,15 @@ class Agent(BaseAgent):
     def set_fingerprint(self, fingerprint: Fingerprint) -> None:
         self.security_config.fingerprint = fingerprint
 
+    @property
+    def last_messages(self) -> list[LLMMessage]:
+        """Get messages from the last task execution.
+
+        Returns:
+            List of LLM messages from the most recent task execution.
+        """
+        return self._last_messages
+
     def _get_knowledge_search_query(self, task_prompt: str, task: Task) -> str | None:
         """Generate a search query for the knowledge base based on the task description."""
         crewai_event_bus.emit(

lib/crewai/src/crewai/crew.py

@@ -809,6 +809,7 @@ class Crew(FlowTrackable, BaseModel):
                 "json_dict": output.json_dict,
                 "output_format": output.output_format,
                 "agent": output.agent,
+                "messages": output.messages,
             },
             "task_index": task_index,
             "inputs": inputs,
@@ -1236,6 +1237,7 @@ class Crew(FlowTrackable, BaseModel):
                 pydantic=stored_output["pydantic"],
                 json_dict=stored_output["json_dict"],
                 output_format=stored_output["output_format"],
+                messages=stored_output.get("messages", []),
             )
             self.tasks[i].output = task_output
 

lib/crewai/src/crewai/lite_agent.py

@@ -358,6 +358,7 @@ class LiteAgent(FlowTrackable, BaseModel):
             pydantic=formatted_result,
             agent_role=self.role,
             usage_metrics=usage_metrics.model_dump() if usage_metrics else None,
+            messages=self._messages,
         )
 
         # Process guardrail if set

lib/crewai/src/crewai/lite_agent_output.py

@@ -6,6 +6,8 @@ from typing import Any
 
 from pydantic import BaseModel, Field
 
+from crewai.utilities.types import LLMMessage
+
 
 class LiteAgentOutput(BaseModel):
     """Class that represents the result of a LiteAgent execution."""
@@ -20,6 +22,7 @@ class LiteAgentOutput(BaseModel):
     usage_metrics: dict[str, Any] | None = Field(
         description="Token usage metrics for this execution", default=None
     )
+    messages: list[LLMMessage] = Field(description="Messages of the agent", default=[])
 
     def to_dict(self) -> dict[str, Any]:
         """Convert pydantic_output to a dictionary."""

lib/crewai/src/crewai/task.py

@@ -539,6 +539,7 @@ class Task(BaseModel):
                 json_dict=json_output,
                 agent=agent.role,
                 output_format=self._get_output_format(),
+                messages=agent.last_messages,
             )
 
             if self._guardrails:
@@ -949,6 +950,7 @@ Follow these guidelines:
                 json_dict=json_output,
                 agent=agent.role,
                 output_format=self._get_output_format(),
+                messages=agent.last_messages,
             )
 
         return task_output

lib/crewai/src/crewai/tasks/task_output.py

@@ -6,6 +6,7 @@ from typing import Any
 from pydantic import BaseModel, Field, model_validator
 
 from crewai.tasks.output_format import OutputFormat
+from crewai.utilities.types import LLMMessage
 
 
 class TaskOutput(BaseModel):
@@ -40,6 +41,7 @@ class TaskOutput(BaseModel):
     output_format: OutputFormat = Field(
         description="Output format of the task", default=OutputFormat.RAW
     )
+    messages: list[LLMMessage] = Field(description="Messages of the task", default=[])
 
     @model_validator(mode="after")
     def set_summary(self):

lib/crewai/src/crewai/utilities/types.py

@@ -1,6 +1,8 @@
 """Types for CrewAI utilities."""
 
-from typing import Any, Literal, TypedDict
+from typing import Any, Literal
+
+from typing_extensions import TypedDict
 
 
 class LLMMessage(TypedDict):