Merge branch 'main' into joaomdmoura/multimodal-crew

tests/flow_test.py

@@ -263,3 +263,62 @@ def test_flow_with_custom_state():
     flow = StateFlow()
     flow.kickoff()
     assert flow.counter == 2
+
+
+def test_router_with_multiple_conditions():
+    """Test a router that triggers when any of multiple steps complete (OR condition),
+    and another router that triggers only after all specified steps complete (AND condition).
+    """
+
+    execution_order = []
+
+    class ComplexRouterFlow(Flow):
+        @start()
+        def step_a(self):
+            execution_order.append("step_a")
+
+        @start()
+        def step_b(self):
+            execution_order.append("step_b")
+
+        @router(or_("step_a", "step_b"))
+        def router_or(self):
+            execution_order.append("router_or")
+            return "next_step_or"
+
+        @listen("next_step_or")
+        def handle_next_step_or_event(self):
+            execution_order.append("handle_next_step_or_event")
+
+        @listen(handle_next_step_or_event)
+        def branch_2_step(self):
+            execution_order.append("branch_2_step")
+
+        @router(and_(handle_next_step_or_event, branch_2_step))
+        def router_and(self):
+            execution_order.append("router_and")
+            return "final_step"
+
+        @listen("final_step")
+        def log_final_step(self):
+            execution_order.append("log_final_step")
+
+    flow = ComplexRouterFlow()
+    flow.kickoff()
+
+    assert "step_a" in execution_order
+    assert "step_b" in execution_order
+    assert "router_or" in execution_order
+    assert "handle_next_step_or_event" in execution_order
+    assert "branch_2_step" in execution_order
+    assert "router_and" in execution_order
+    assert "log_final_step" in execution_order
+
+    # Check that the AND router triggered after both relevant steps:
+    assert execution_order.index("router_and") > execution_order.index(
+        "handle_next_step_or_event"
+    )
+    assert execution_order.index("router_and") > execution_order.index("branch_2_step")
+
+    # final_step should run after router_and
+    assert execution_order.index("log_final_step") > execution_order.index("router_and")

tests/knowledge/knowledge_test.py

@@ -1,10 +1,12 @@
 """Test Knowledge creation and querying functionality."""
 
 from pathlib import Path
+from typing import List, Union
 from unittest.mock import patch
 
 import pytest
 
+from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
 from crewai.knowledge.source.csv_knowledge_source import CSVKnowledgeSource
 from crewai.knowledge.source.excel_knowledge_source import ExcelKnowledgeSource
 from crewai.knowledge.source.json_knowledge_source import JSONKnowledgeSource
@@ -200,7 +202,7 @@ def test_single_short_file(mock_vector_db, tmpdir):
         f.write(content)
 
     file_source = TextFileKnowledgeSource(
-        file_path=file_path, metadata={"preference": "personal"}
+        file_paths=[file_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [file_source]
     mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
@@ -242,7 +244,7 @@ def test_single_2k_character_file(mock_vector_db, tmpdir):
         f.write(content)
 
     file_source = TextFileKnowledgeSource(
-        file_path=file_path, metadata={"preference": "personal"}
+        file_paths=[file_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [file_source]
     mock_vector_db.query.return_value = [{"context": content, "score": 0.9}]
@@ -279,7 +281,7 @@ def test_multiple_short_files(mock_vector_db, tmpdir):
         file_paths.append((file_path, item["metadata"]))
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata=metadata)
+        TextFileKnowledgeSource(file_paths=[path], metadata=metadata)
         for path, metadata in file_paths
     ]
     mock_vector_db.sources = file_sources
@@ -352,7 +354,7 @@ def test_multiple_2k_character_files(mock_vector_db, tmpdir):
         file_paths.append(file_path)
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        TextFileKnowledgeSource(file_paths=[path], metadata={"preference": "personal"})
         for path in file_paths
     ]
     mock_vector_db.sources = file_sources
@@ -399,7 +401,7 @@ def test_hybrid_string_and_files(mock_vector_db, tmpdir):
         file_paths.append(file_path)
 
     file_sources = [
-        TextFileKnowledgeSource(file_path=path, metadata={"preference": "personal"})
+        TextFileKnowledgeSource(file_paths=[path], metadata={"preference": "personal"})
         for path in file_paths
     ]
 
@@ -424,7 +426,7 @@ def test_pdf_knowledge_source(mock_vector_db):
 
     # Create a PDFKnowledgeSource
     pdf_source = PDFKnowledgeSource(
-        file_path=pdf_path, metadata={"preference": "personal"}
+        file_paths=[pdf_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [pdf_source]
     mock_vector_db.query.return_value = [
@@ -461,7 +463,7 @@ def test_csv_knowledge_source(mock_vector_db, tmpdir):
 
     # Create a CSVKnowledgeSource
     csv_source = CSVKnowledgeSource(
-        file_path=csv_path, metadata={"preference": "personal"}
+        file_paths=[csv_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [csv_source]
     mock_vector_db.query.return_value = [
@@ -496,7 +498,7 @@ def test_json_knowledge_source(mock_vector_db, tmpdir):
 
     # Create a JSONKnowledgeSource
     json_source = JSONKnowledgeSource(
-        file_path=json_path, metadata={"preference": "personal"}
+        file_paths=[json_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [json_source]
     mock_vector_db.query.return_value = [
@@ -529,7 +531,7 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
 
     # Create an ExcelKnowledgeSource
     excel_source = ExcelKnowledgeSource(
-        file_path=excel_path, metadata={"preference": "personal"}
+        file_paths=[excel_path], metadata={"preference": "personal"}
     )
     mock_vector_db.sources = [excel_source]
     mock_vector_db.query.return_value = [
@@ -543,3 +545,42 @@ def test_excel_knowledge_source(mock_vector_db, tmpdir):
     # Assert that the correct information is retrieved
     assert any("30" in result["context"] for result in results)
     mock_vector_db.query.assert_called_once()
+
+
+def test_docling_source(mock_vector_db):
+    docling_source = CrewDoclingSource(
+        file_paths=[
+            "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
+        ],
+    )
+    mock_vector_db.sources = [docling_source]
+    mock_vector_db.query.return_value = [
+        {
+            "context": "Reward hacking is a technique used to improve the performance of reinforcement learning agents.",
+            "score": 0.9,
+        }
+    ]
+    # Perform a query
+    query = "What is reward hacking?"
+    results = mock_vector_db.query(query)
+    assert any("reward hacking" in result["context"].lower() for result in results)
+    mock_vector_db.query.assert_called_once()
+
+
+def test_multiple_docling_sources():
+    urls: List[Union[Path, str]] = [
+        "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
+        "https://lilianweng.github.io/posts/2024-07-07-hallucination/",
+    ]
+    docling_source = CrewDoclingSource(file_paths=urls)
+
+    assert docling_source.file_paths == urls
+    assert docling_source.content is not None
+
+
+def test_docling_source_with_local_file():
+    current_dir = Path(__file__).parent
+    pdf_path = current_dir / "crewai_quickstart.pdf"
+    docling_source = CrewDoclingSource(file_paths=[pdf_path])
+    assert docling_source.file_paths == [pdf_path]
+    assert docling_source.content is not None

tests/task_test.py

@@ -736,6 +736,48 @@ def test_interpolate_inputs():
     assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
 
 
+def test_interpolate_only():
+    """Test the interpolate_only method for various scenarios including JSON structure preservation."""
+    task = Task(
+        description="Unused in this test",
+        expected_output="Unused in this test"
+    )
+    
+    # Test JSON structure preservation
+    json_string = '{"info": "Look at {placeholder}", "nested": {"val": "{nestedVal}"}}'
+    result = task.interpolate_only(
+        input_string=json_string,
+        inputs={"placeholder": "the data", "nestedVal": "something else"}
+    )
+    assert '"info": "Look at the data"' in result
+    assert '"val": "something else"' in result
+    assert "{placeholder}" not in result
+    assert "{nestedVal}" not in result
+    
+    # Test normal string interpolation
+    normal_string = "Hello {name}, welcome to {place}!"
+    result = task.interpolate_only(
+        input_string=normal_string,
+        inputs={"name": "John", "place": "CrewAI"}
+    )
+    assert result == "Hello John, welcome to CrewAI!"
+    
+    # Test empty string
+    result = task.interpolate_only(
+        input_string="",
+        inputs={"unused": "value"}
+    )
+    assert result == ""
+    
+    # Test string with no placeholders
+    no_placeholders = "Hello, this is a test"
+    result = task.interpolate_only(
+        input_string=no_placeholders,
+        inputs={"unused": "value"}
+    )
+    assert result == no_placeholders
+
+
 def test_task_output_str_with_pydantic():
     from crewai.tasks.output_format import OutputFormat
 

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)