Merge branch 'main' into fix-knowledgestorage-default-instantiation

src/crewai/crew.py

@@ -873,22 +873,10 @@ class Crew(BaseModel):
                 tools = self._inject_delegation_tools(tools, self.manager_agent, self.agents)
         return tools
 
-    def _get_context(self, task: Task, task_outputs: List[TaskOutput]) -> str:
-        """Get context for task execution.
-        
-        Determines whether to use the task's explicit context or aggregate outputs from previous tasks.
-        When task.context is an empty list, it will use the task_outputs instead.
-        
-        Args:
-            task: The task to get context for
-            task_outputs: List of previous task outputs
-            
-        Returns:
-            String containing the aggregated context
-        """
+    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
             aggregate_raw_outputs_from_tasks(task.context)
-            if task.context and len(task.context) > 0
+            if task.context
             else aggregate_raw_outputs_from_task_outputs(task_outputs)
         )
         return context

src/crewai/knowledge/knowledge.py

@@ -14,13 +14,13 @@ class Knowledge(BaseModel):
     Knowledge is a collection of sources and setup for the vector store to save and query relevant context.
     Args:
         sources: List[BaseKnowledgeSource] = Field(default_factory=list)
-        storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+        storage: Optional[KnowledgeStorage] = Field(default=None)
         embedder_config: Optional[Dict[str, Any]] = None
     """
 
     sources: List[BaseKnowledgeSource] = Field(default_factory=list)
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     embedder_config: Optional[Dict[str, Any]] = None
     collection_name: Optional[str] = None
 

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -22,7 +22,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         default_factory=list, description="The path to the file"
     )
     content: Dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     safe_file_paths: List[Path] = Field(default_factory=list)
 
     @field_validator("file_path", "file_paths", mode="before")
@@ -62,7 +62,10 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _save_documents(self):
         """Save the documents to the storage."""
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")
 
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""

src/crewai/knowledge/source/base_knowledge_source.py

@@ -16,7 +16,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
     chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
+    storage: Optional[KnowledgeStorage] = Field(default=None)
     metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
     collection_name: Optional[str] = Field(default=None)
 
@@ -46,4 +46,7 @@ class BaseKnowledgeSource(BaseModel, ABC):
         Save the documents to the storage.
         This method should be called after the chunks and embeddings are generated.
         """
-        self.storage.save(self.chunks)
+        if self.storage:
+            self.storage.save(self.chunks)
+        else:
+            raise ValueError("No storage found to save documents.")

tests/context_empty_list_test.py

@@ -1,85 +0,0 @@
-"""Test that context=[] is respected and doesn't include previous task outputs."""
-from unittest import mock
-
-import pytest
-
-from crewai import Agent, Crew, Process, Task
-from crewai.tasks.task_output import OutputFormat, TaskOutput
-from crewai.utilities.formatter import (
-    aggregate_raw_outputs_from_task_outputs,
-    aggregate_raw_outputs_from_tasks,
-)
-
-
-def test_context_empty_list():
-    """Test that context=[] is respected and doesn't include previous task outputs.
-    
-    This test verifies that when a task has context=[], the _get_context method
-    correctly uses task_outputs instead of an empty context list.
-    
-    Returns:
-        None
-        
-    Raises:
-        AssertionError: If the context handling doesn't work as expected
-    """
-    
-    
-    researcher = Agent(
-        role='Researcher',
-        goal='Research thoroughly',
-        backstory='You are an expert researcher'
-    )
-    
-    task_with_empty_context = Task(
-        description='Task with empty context',
-        expected_output='Output',
-        agent=researcher,
-        context=[]  # Explicitly set context to empty list
-    )
-    
-    task_outputs = [
-        TaskOutput(
-            description="Previous task output",
-            raw="Previous task result",
-            agent="Researcher",
-            json_dict=None,
-            output_format=OutputFormat.RAW,
-            pydantic=None,
-            summary="Previous task result",
-        )
-    ]
-    
-    crew = Crew(
-        agents=[researcher],
-        tasks=[task_with_empty_context],
-        process=Process.sequential,
-        verbose=False
-    )
-    
-    with mock.patch('crewai.agent.Agent.execute_task') as mock_execute:
-        mock_execute.return_value = "Mocked execution result"
-        
-        context = crew._get_context(task_with_empty_context, task_outputs)
-        
-        # So it should return the aggregated task_outputs
-        expected_context = aggregate_raw_outputs_from_task_outputs(task_outputs)
-        
-        assert context == expected_context
-        
-        assert not (task_with_empty_context.context and len(task_with_empty_context.context) > 0)
-        
-        other_task = Task(
-            description='Other task',
-            expected_output='Output',
-            agent=researcher
-        )
-        
-        task_with_context = Task(
-            description='Task with context',
-            expected_output='Output',
-            agent=researcher,
-            context=[other_task]  # Non-empty context
-        )
-        
-        assert task_with_context.context and len(task_with_context.context) > 0