Refactor: Move backend files to backend/ directory and split .gitignore

backend/tests/test_workflow_e2e.py

@@ -0,0 +1,139 @@
+import pytest
+import yaml
+from unittest.mock import MagicMock, patch
+from langchain_core.messages import AIMessage
+from ea_chatbot.graph.workflow import app
+from ea_chatbot.graph.nodes.query_analyzer import QueryAnalysis
+from ea_chatbot.schemas import TaskPlanResponse, TaskPlanContext, CodeGenerationResponse
+
+@pytest.fixture
+def mock_llms():
+    with patch("ea_chatbot.graph.nodes.query_analyzer.get_llm_model") as mock_qa_llm, \
+         patch("ea_chatbot.graph.nodes.planner.get_llm_model") as mock_planner_llm, \
+         patch("ea_chatbot.graph.nodes.coder.get_llm_model") as mock_coder_llm, \
+         patch("ea_chatbot.graph.nodes.summarizer.get_llm_model") as mock_summarizer_llm, \
+         patch("ea_chatbot.graph.nodes.researcher.get_llm_model") as mock_researcher_llm, \
+                      patch("ea_chatbot.graph.nodes.summarize_conversation.get_llm_model") as mock_summary_llm, \
+                      patch("ea_chatbot.utils.database_inspection.get_data_summary") as mock_get_summary:        
+        mock_get_summary.return_value = "Data summary"
+        
+        # Mock summary LLM to return a simple response
+        mock_summary_instance = MagicMock()
+        mock_summary_llm.return_value = mock_summary_instance
+        mock_summary_instance.invoke.return_value = AIMessage(content="Turn summary")
+
+        yield {
+            "qa": mock_qa_llm,
+            "planner": mock_planner_llm,
+            "coder": mock_coder_llm,
+            "summarizer": mock_summarizer_llm,
+            "researcher": mock_researcher_llm,
+            "summary": mock_summary_llm
+        }
+
+def test_workflow_data_analysis_flow(mock_llms):
+    """Test full flow: QueryAnalyzer -> Planner -> Coder -> Executor -> Summarizer."""
+    
+    # 1. Mock Query Analyzer (routes to plan)
+    mock_qa_instance = MagicMock()
+    mock_llms["qa"].return_value = mock_qa_instance
+    mock_qa_instance.with_structured_output.return_value.invoke.return_value = QueryAnalysis(
+        data_required=["2024 results"], 
+        unknowns=[], 
+        ambiguities=[],
+        conditions=[], 
+        next_action="plan"
+    )
+    
+    # 2. Mock Planner
+    mock_planner_instance = MagicMock()
+    mock_llms["planner"].return_value = mock_planner_instance
+    mock_planner_instance.with_structured_output.return_value.invoke.return_value = TaskPlanResponse(
+        goal="Get results",
+        reflection="Reflect",
+        context=TaskPlanContext(initial_context="Ctx", assumptions=[], constraints=[]),
+        steps=["Step 1"]
+    )
+    
+    # 3. Mock Coder
+    mock_coder_instance = MagicMock()
+    mock_llms["coder"].return_value = mock_coder_instance
+    mock_coder_instance.with_structured_output.return_value.invoke.return_value = CodeGenerationResponse(
+        code="print('Execution Success')",
+        explanation="Explain"
+    )
+    
+    # 4. Mock Summarizer
+    mock_summarizer_instance = MagicMock()
+    mock_llms["summarizer"].return_value = mock_summarizer_instance
+    mock_summarizer_instance.invoke.return_value = AIMessage(content="Final Summary: Success")
+    
+    # Initial state
+    initial_state = {
+        "messages": [],
+        "question": "Show me 2024 results",
+        "analysis": None,
+        "next_action": "",
+        "plan": None,
+        "code": None,
+        "error": None,
+        "plots": [],
+        "dfs": {}
+    }
+    
+    # Run the graph
+    result = app.invoke(initial_state, config={"recursion_limit": 15})
+    
+    assert result["next_action"] == "plan"
+    assert "Execution Success" in result["code_output"]
+    assert "Final Summary: Success" in result["messages"][-1].content
+
+def test_workflow_research_flow(mock_llms):
+    """Test flow: QueryAnalyzer -> Researcher -> Summarizer."""
+    
+    # 1. Mock Query Analyzer (routes to research)
+    mock_qa_instance = MagicMock()
+    mock_llms["qa"].return_value = mock_qa_instance
+    mock_qa_instance.with_structured_output.return_value.invoke.return_value = QueryAnalysis(
+        data_required=[], 
+        unknowns=[], 
+        ambiguities=[],
+        conditions=[], 
+        next_action="research"
+    )
+    
+    # 2. Mock Researcher
+    mock_researcher_instance = MagicMock()
+    mock_llms["researcher"].return_value = mock_researcher_instance
+    # Researcher node uses bind_tools if it's ChatOpenAI/ChatGoogleGenerativeAI
+    # Since it's a MagicMock, it will fallback to using the base instance
+    mock_researcher_instance.invoke.return_value = AIMessage(content="Research Results")
+    
+    # Also mock bind_tools just in case we ever use spec
+    mock_llm_with_tools = MagicMock()
+    mock_researcher_instance.bind_tools.return_value = mock_llm_with_tools
+    mock_llm_with_tools.invoke.return_value = AIMessage(content="Research Results")
+    
+    # 3. Mock Summarizer (not used in this flow, but kept for completeness)
+    mock_summarizer_instance = MagicMock()
+    mock_llms["summarizer"].return_value = mock_summarizer_instance
+    mock_summarizer_instance.invoke.return_value = AIMessage(content="Final Summary: Research Success")
+    
+    # Initial state
+    initial_state = {
+        "messages": [],
+        "question": "Who is the governor of Florida?",
+        "analysis": None,
+        "next_action": "",
+        "plan": None,
+        "code": None,
+        "error": None,
+        "plots": [],
+        "dfs": {}
+    }
+    
+    # Run the graph
+    result = app.invoke(initial_state, config={"recursion_limit": 10})
+    
+    assert result["next_action"] == "research"
+    assert "Research Results" in result["messages"][-1].content