Merge branch 'main' into feat/docling

tests/cassettes/test_agent_function_calling_llm.yaml

@@ -26237,7 +26237,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}], "model": "gpt-4o"}'
     headers:
@@ -26590,7 +26590,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -26941,7 +26941,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27292,7 +27292,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -27647,7 +27647,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28005,7 +28005,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28364,7 +28364,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -28718,7 +28718,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29082,7 +29082,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29441,7 +29441,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -29802,7 +29802,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30170,7 +30170,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30533,7 +30533,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -30907,7 +30907,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31273,7 +31273,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -31644,7 +31644,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the
@@ -32015,7 +32015,7 @@ interactions:
       answer."}, {"role": "user", "content": "I did it wrong. Invalid Format: I missed
       the ''Action:'' after ''Thought:''. I will do right next, and don''t use a tool
       I have already used.\n\nIf you don''t need to use any more tools, you must give
-      your best complete final answer, make sure it satisfy the expect criteria, use
+      your best complete final answer, make sure it satisfies the expected criteria, use
       the EXACT format below:\n\nThought: I now can give a great answer\nFinal Answer:
       my best complete final answer to the task.\n\n"}, {"role": "user", "content":
       "I did it wrong. Tried to both perform Action and give a Final Answer at the

tests/cassettes/test_agent_powered_by_new_o_model_family_that_allows_skipping_tool.yaml

@@ -247,7 +247,7 @@ interactions:
       {"role": "user", "content": "I did it wrong. Invalid Format: I missed the ''Action:''
       after ''Thought:''. I will do right next, and don''t use a tool I have already
       used.\n\nIf you don''t need to use any more tools, you must give your best complete
-      final answer, make sure it satisfy the expect criteria, use the EXACT format
+      final answer, make sure it satisfies the expected criteria, use the EXACT format
       below:\n\nThought: I now can give a great answer\nFinal Answer: my best complete
       final answer to the task.\n\n"}], "model": "o1-preview"}'
     headers:

tests/test_task_guardrails.py

@@ -0,0 +1,134 @@
+"""Tests for task guardrails functionality."""
+
+from unittest.mock import Mock
+
+import pytest
+
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+
+
+def test_task_without_guardrail():
+    """Test that tasks work normally without guardrails (backward compatibility)."""
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "test result"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output"
+    )
+
+    result = task.execute_sync(agent=agent)
+    assert isinstance(result, TaskOutput)
+    assert result.raw == "test result"
+
+
+def test_task_with_successful_guardrail():
+    """Test that successful guardrail validation passes transformed result."""
+    def guardrail(result: TaskOutput):
+        return (True, result.raw.upper())
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "test result"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail
+    )
+
+    result = task.execute_sync(agent=agent)
+    assert isinstance(result, TaskOutput)
+    assert result.raw == "TEST RESULT"
+
+
+def test_task_with_failing_guardrail():
+    """Test that failing guardrail triggers retry with error context."""
+    def guardrail(result: TaskOutput):
+        return (False, "Invalid format")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.side_effect = [
+        "bad result",
+        "good result"
+    ]
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=1
+    )
+
+    # First execution fails guardrail, second succeeds
+    agent.execute_task.side_effect = ["bad result", "good result"]
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert "Task failed guardrail validation" in str(exc_info.value)
+    assert task.retry_count == 1
+
+
+def test_task_with_guardrail_retries():
+    """Test that guardrail respects max_retries configuration."""
+    def guardrail(result: TaskOutput):
+        return (False, "Invalid format")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.execute_task.return_value = "bad result"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=2
+    )
+
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert task.retry_count == 2
+    assert "Task failed guardrail validation after 2 retries" in str(exc_info.value)
+    assert "Invalid format" in str(exc_info.value)
+
+
+def test_guardrail_error_in_context():
+    """Test that guardrail error is passed in context for retry."""
+    def guardrail(result: TaskOutput):
+        return (False, "Expected JSON, got string")
+
+    agent = Mock()
+    agent.role = "test_agent"
+    agent.crew = None
+
+    task = Task(
+        description="Test task",
+        expected_output="Output",
+        guardrail=guardrail,
+        max_retries=1
+    )
+
+    # Mock execute_task to succeed on second attempt
+    first_call = True
+    def execute_task(task, context, tools):
+        nonlocal first_call
+        if first_call:
+            first_call = False
+            return "invalid"
+        return '{"valid": "json"}'
+
+    agent.execute_task.side_effect = execute_task
+
+    with pytest.raises(Exception) as exc_info:
+        task.execute_sync(agent=agent)
+
+    assert "Task failed guardrail validation" in str(exc_info.value)
+    assert "Expected JSON, got string" in str(exc_info.value)