test: Add knowledge effectiveness test

- Add test to verify knowledge is effectively used in agent execution
- Test checks that knowledge from agent is correctly used in response
- Verifies fix for issue #2269

Co-Authored-By: Joe Moura <joao@crewai.com>

tests/knowledge/test_knowledge_utils.py

@@ -36,4 +36,32 @@ def test_extract_knowledge_context_with_missing_context():
     """Test extracting knowledge context with missing context."""
     snippets = [{"score": 0.9}, {"context": "Valid context"}]
     result = extract_knowledge_context(snippets)
-    assert result == "Additional Information: Valid context"
+    assert result == "Important Context (You MUST use this information to complete your task accurately and effectively):\nValid context\n\nMake sure to incorporate the above context into your response."
+
+
+def test_knowledge_effectiveness():
+    """Test that knowledge is effectively used in agent execution."""
+    from crewai import Agent, Task, Crew
+    from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+
+    content = "The capital of France is Paris. The Eiffel Tower is located in Paris."
+    string_source = StringKnowledgeSource(content=content)
+    
+    agent = Agent(
+        role="Geography Expert",
+        goal="Answer questions about geography accurately",
+        backstory="You are an expert in geography",
+        knowledge_sources=[string_source],
+    )
+    
+    task = Task(
+        description="What is the capital of France?",
+        expected_output="The capital of France",
+        agent=agent,
+    )
+    
+    crew = Crew(agents=[agent], tasks=[task])
+    result = crew.kickoff()
+    
+    assert "paris" in result.raw.lower()
+    assert "capital" in result.raw.lower()