Supporting no-code Guardrail creation (#2636)

* feat: support to define a guardrail task no-code

* feat: add auto-discovery for Guardrail code execution mode

* feat: handle malformed or invalid response from CodeInterpreterTool

* feat: allow to set unsafe_mode from Guardrail task

* feat: renaming GuardrailTask to TaskGuardrail

* feat: ensure guardrail is callable while initializing Task

* feat: remove Docker availability check from TaskGuardrail

The CodeInterpreterTool already ensures compliance with this requirement.

* refactor: replace if/raise with assert

For this use case `assert` is more appropriate choice

* test: remove useless or duplicated test

* fix: attempt to fix type-checker

* feat: support to define a task guardrail using YAML config

* refactor: simplify TaskGuardrail to use LLM for validation, no code generation

* docs: update TaskGuardrail doc strings

* refactor: drop task paramenter from TaskGuardrail

This parameter was used to get the model from the `task.agent` which is a quite bit redudant since we could propagate the llm directly

src/crewai/tasks/task_guardrail.py

@@ -0,0 +1,92 @@
+from typing import Any, Optional, Tuple
+
+from pydantic import BaseModel, Field
+
+from crewai.agent import Agent, LiteAgentOutput
+from crewai.llm import LLM
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+
+
+class TaskGuardrailResult(BaseModel):
+    valid: bool = Field(
+        description="Whether the task output complies with the guardrail"
+    )
+    feedback: str | None = Field(
+        description="A feedback about the task output if it is not valid",
+        default=None,
+    )
+
+
+class TaskGuardrail:
+    """It validates the output of another task using an LLM.
+
+    This class is used to validate the output from a Task based on specified criteria.
+    It uses an LLM to validate the output and provides a feedback if the output is not valid.
+
+    Args:
+        description (str): The description of the validation criteria.
+        llm (LLM, optional): The language model to use for code generation.
+    """
+
+    def __init__(
+        self,
+        description: str,
+        llm: LLM,
+    ):
+        self.description = description
+
+        self.llm: LLM = llm
+
+    def _validate_output(self, task_output: TaskOutput) -> LiteAgentOutput:
+        agent = Agent(
+            role="Guardrail Agent",
+            goal="Validate the output of the task",
+            backstory="You are a expert at validating the output of a task. By providing effective feedback if the output is not valid.",
+            llm=self.llm,
+        )
+
+        query = f"""
+        Ensure the following task result complies with the given guardrail.
+
+        Task result:
+        {task_output.raw}
+
+        Guardrail:
+        {self.description}
+        
+        Your task:
+        - Confirm if the Task result complies with the guardrail.
+        - If not, provide clear feedback explaining what is wrong (e.g., by how much it violates the rule, or what specific part fails).
+        - Focus only on identifying issues — do not propose corrections.
+        - If the Task result complies with the guardrail, saying that is valid
+        """
+
+        result = agent.kickoff(query, response_format=TaskGuardrailResult)
+
+        return result
+
+    def __call__(self, task_output: TaskOutput) -> Tuple[bool, Any]:
+        """Validates the output of a task based on specified criteria.
+
+        Args:
+            task_output (TaskOutput): The output to be validated.
+
+        Returns:
+            Tuple[bool, Any]: A tuple containing:
+                - bool: True if validation passed, False otherwise
+                - Any: The validation result or error message
+        """
+
+        try:
+            result = self._validate_output(task_output)
+            assert isinstance(
+                result.pydantic, TaskGuardrailResult
+            ), "The guardrail result is not a valid pydantic model"
+
+            if result.pydantic.valid:
+                return True, task_output.raw
+            else:
+                return False, result.pydantic.feedback
+        except Exception as e:
+            return False, f"Error while validating the task output: {str(e)}"