Make code lookup mandatory in between investigation steps for better results

tests/test_collaboration.py

@@ -95,10 +95,13 @@ class TestDynamicContextRequests:
 
         # Parse the response - new debug tool returns structured JSON
         response_data = json.loads(result[0].text)
-        assert response_data["status"] == "investigation_in_progress"
+        # Debug tool now returns "pause_for_investigation" to force actual investigation
+        assert response_data["status"] == "pause_for_investigation"
         assert response_data["step_number"] == 1
         assert response_data["next_step_required"] is True
         assert response_data["investigation_status"]["current_confidence"] == "high"
+        assert response_data["investigation_required"] is True
+        assert "required_actions" in response_data
 
     @pytest.mark.asyncio
     @patch("tools.base.BaseTool.get_model_provider")

tests/test_debug.py

@@ -133,13 +133,16 @@ class TestDebugTool:
 
         parsed_response = json.loads(result[0].text)
 
-        assert parsed_response["status"] == "investigation_in_progress"
+        # Debug tool now returns "pause_for_investigation" for ongoing steps
+        assert parsed_response["status"] == "pause_for_investigation"
         assert parsed_response["step_number"] == 1
         assert parsed_response["total_steps"] == 5
         assert parsed_response["next_step_required"] is True
         assert parsed_response["continuation_id"] == "debug-uuid-123"
         assert parsed_response["investigation_status"]["files_checked"] == 1
         assert parsed_response["investigation_status"]["relevant_files"] == 1
+        assert parsed_response["investigation_required"] is True
+        assert "required_actions" in parsed_response
 
     @pytest.mark.asyncio
     async def test_execute_subsequent_investigation_step(self):
@@ -317,6 +320,7 @@ class TestDebugTool:
             result = await tool.execute(arguments)
 
         # Should return a list with TextContent
+        # Debug tool now returns "pause_for_investigation" for ongoing steps
         assert len(result) == 1
         response_text = result[0].text
 
@@ -325,7 +329,7 @@ class TestDebugTool:
 
         parsed_response = json.loads(response_text)
 
-        assert parsed_response["status"] == "investigation_in_progress"
+        assert parsed_response["status"] == "pause_for_investigation"
         # After backtracking from step 2, history should have step 1 plus the new step
         assert len(tool.investigation_history) == 2  # Step 1 + new step 3
         assert tool.investigation_history[0]["step_number"] == 1
@@ -502,6 +506,7 @@ class TestDebugToolIntegration:
                 result = await self.tool.execute(arguments)
 
         # Verify response structure
+        # Debug tool now returns "pause_for_investigation" for ongoing steps
         assert len(result) == 1
         response_text = result[0].text
 
@@ -510,7 +515,7 @@ class TestDebugToolIntegration:
 
         parsed_response = json.loads(response_text)
 
-        assert parsed_response["status"] == "investigation_in_progress"
+        assert parsed_response["status"] == "pause_for_investigation"
         assert parsed_response["step_number"] == 1
         assert parsed_response["continuation_id"] == "debug-flow-uuid"
 

tests/test_debug_certain_confidence.py

@@ -45,8 +45,10 @@ class TestDebugCertainConfidence:
 
         # Verify step 1 response
         response1 = json.loads(result1[0].text)
-        assert response1["status"] == "investigation_in_progress"
+        assert response1["status"] == "pause_for_investigation"
         assert response1["step_number"] == 1
+        assert response1["investigation_required"] is True
+        assert "required_actions" in response1
         continuation_id = response1["continuation_id"]
 
         # Step 2: Final step with certain confidence (simple import fix)

tests/test_debug_comprehensive_workflow.py

@@ -43,7 +43,7 @@ class TestDebugComprehensiveWorkflow:
         # Verify step 1 response
         assert len(result1) == 1
         response1 = json.loads(result1[0].text)
-        assert response1["status"] == "investigation_in_progress"
+        assert response1["status"] == "pause_for_investigation"
         assert response1["step_number"] == 1
         assert response1["continuation_id"] == "debug-workflow-uuid"
 
@@ -56,7 +56,8 @@ class TestDebugComprehensiveWorkflow:
             if args and len(args) >= 3:
                 assert args[0] == "debug-workflow-uuid"
                 assert args[1] == "assistant"
-                assert json.loads(args[2])["status"] == "investigation_in_progress"
+                # Debug tool now returns "pause_for_investigation" for ongoing steps
+                assert json.loads(args[2])["status"] == "pause_for_investigation"
 
         # Step 2: Continue investigation with findings
         with patch("utils.conversation_memory.add_turn") as mock_add_turn:
@@ -78,7 +79,8 @@ class TestDebugComprehensiveWorkflow:
 
         # Verify step 2 response
         response2 = json.loads(result2[0].text)
-        assert response2["status"] == "investigation_in_progress"
+        # Debug tool now returns "pause_for_investigation" for ongoing steps
+        assert response2["status"] == "pause_for_investigation"
         assert response2["step_number"] == 2
         assert response2["investigation_status"]["files_checked"] == 2
         assert response2["investigation_status"]["relevant_methods"] == 2
@@ -268,9 +270,12 @@ class TestDebugComprehensiveWorkflow:
                 states.append(json.loads(result[0].text))
 
         # Verify initial state
-        assert states[0]["status"] == "investigation_in_progress"
+        # Debug tool now returns "pause_for_investigation" for ongoing steps
+        assert states[0]["status"] == "pause_for_investigation"
         assert states[0]["step_number"] == 1
         assert states[0]["next_step_required"] is True
+        assert states[0]["investigation_required"] is True
+        assert "required_actions" in states[0]
 
         # Final state (triggers expert analysis)
         mock_expert_response = {"status": "analysis_complete", "summary": "Test complete"}

tests/test_debug_continuation.py

@@ -39,8 +39,10 @@ class TestDebugContinuation:
 
         assert len(result) == 1
         response = json.loads(result[0].text)
-        assert response["status"] == "investigation_in_progress"
+        assert response["status"] == "pause_for_investigation"
         assert response["continuation_id"] == "debug-test-uuid-123"
+        assert response["investigation_required"] is True
+        assert "required_actions" in response
 
     def test_debug_conversation_formatting(self):
         """Test that debug tool's structured output is properly formatted in conversation history."""