WIP: Regression hell

tests/conftest.py

@@ -123,7 +123,7 @@ def mock_app() -> Generator[App, None, None]:
    'projects': {'paths': [], 'active': ''},
    'gui': {'show_windows': {}}
   }),
-  patch('src.gui_2.save_config'),
+  patch('src.models.save_config'),
   patch('src.gui_2.project_manager'),
   patch('src.gui_2.session_logger'),
   patch('src.gui_2.immapp.run'),
@@ -155,7 +155,7 @@ def app_instance() -> Generator[App, None, None]:
    'projects': {'paths': [], 'active': ''},
    'gui': {'show_windows': {}}
   }),
-  patch('src.gui_2.save_config'),
+  patch('src.models.save_config'),
   patch('src.gui_2.project_manager'),
   patch('src.gui_2.session_logger'),
   patch('src.gui_2.immapp.run'),

tests/test_conductor_engine_v2.py

@@ -34,10 +34,15 @@ def test_conductor_engine_run_executes_tickets_in_order(monkeypatch: pytest.Monk
  # Mocking lifecycle to mark ticket as complete so dependencies can be resolved
 
   def side_effect(ticket, context, *args, **kwargs):
-   ticket.mark_complete()
+   import threading
+   def do_work():
+    import time
+    time.sleep(0.1)
+    ticket.mark_complete()
+   threading.Thread(target=do_work).start()
    return "Success"
   mock_lifecycle.side_effect = side_effect
-  engine.run()
+  engine.run(max_ticks=20)
   
   vlogger.log_state("T1 Status Final", "todo", ticket1.status)
   vlogger.log_state("T2 Status Final", "todo", ticket2.status)
@@ -108,8 +113,8 @@ def test_run_worker_lifecycle_context_injection(monkeypatch: pytest.MonkeyPatch)
   run_worker_lifecycle(ticket, context, context_files=context_files)
   # Verify ASTParser calls: 
   # First file (primary) should get curated view, others (secondary) get skeleton
-  mock_ast_parser.get_curated_view.assert_called_once_with("def primary(): pass")
-  mock_ast_parser.get_skeleton.assert_called_once_with("def secondary(): pass")
+  mock_ast_parser.get_curated_view.assert_called_once_with("def primary(): pass", path="primary.py")
+  mock_ast_parser.get_skeleton.assert_called_once_with("def secondary(): pass", path="secondary.py")
   # Verify user_message contains the views
   _, kwargs = mock_send.call_args
   user_message = kwargs["user_message"]
@@ -238,10 +243,15 @@ def test_conductor_engine_dynamic_parsing_and_execution(monkeypatch: pytest.Monk
  # Mock run_worker_lifecycle to mark tickets as complete
  with patch("src.multi_agent_conductor.run_worker_lifecycle") as mock_lifecycle:
   def side_effect(ticket, context, *args, **kwargs):
-   ticket.mark_complete()
+   import threading
+   def do_work():
+    import time
+    time.sleep(0.1)
+    ticket.mark_complete()
+   threading.Thread(target=do_work).start()
    return "Success"
   mock_lifecycle.side_effect = side_effect
-  engine.run()
+  engine.run(max_ticks=20)
   assert mock_lifecycle.call_count == 3
   # Verify dependency order: T1 must be called before T2
   calls = [call[0][0].id for call in mock_lifecycle.call_args_list]

tests/test_deepseek_provider.py

@@ -111,3 +111,55 @@ def test_deepseek_streaming(mock_post: MagicMock) -> None:
   
   result = ai_client.send(md_content="Context", user_message="Stream test", base_dir=".", stream=True)
   assert result == "Hello World"
+
+@patch("requests.post")
+def test_deepseek_payload_verification(mock_post: MagicMock) -> None:
+ """
+    Verifies that the correct JSON payload (tools, history, params) is sent to DeepSeek.
+    """
+ ai_client.set_provider("deepseek", "deepseek-chat")
+ ai_client.reset_session()
+ with patch("src.ai_client._load_credentials", return_value={"deepseek": {"api_key": "test-key"}}):
+  mock_response = MagicMock()
+  mock_response.status_code = 200
+  mock_response.json.return_value = {
+   "choices": [{"message": {"content": "OK"}, "finish_reason": "stop"}]
+  }
+  mock_post.return_value = mock_response
+  
+  ai_client.send(md_content="Context", user_message="Message 1", base_dir=".", discussion_history="History")
+  
+  args, kwargs = mock_post.call_args
+  payload = kwargs["json"]
+  
+  assert payload["model"] == "deepseek-chat"
+  assert "tools" in payload
+  assert len(payload["messages"]) == 2 # system + user
+  assert "[DISCUSSION HISTORY]\n\nHistory" in payload["messages"][1]["content"]
+  assert "temperature" in payload
+  assert "max_tokens" in payload
+
+@patch("requests.post")
+def test_deepseek_reasoner_payload_verification(mock_post: MagicMock) -> None:
+ """
+    Verifies that deepseek-reasoner payload excludes tools and temperature.
+    """
+ ai_client.set_provider("deepseek", "deepseek-reasoner")
+ ai_client.reset_session()
+ with patch("src.ai_client._load_credentials", return_value={"deepseek": {"api_key": "test-key"}}):
+  mock_response = MagicMock()
+  mock_response.status_code = 200
+  mock_response.json.return_value = {
+   "choices": [{"message": {"content": "OK"}, "finish_reason": "stop"}]
+  }
+  mock_post.return_value = mock_response
+  
+  ai_client.send(md_content="Context", user_message="Message 1", base_dir=".")
+  
+  args, kwargs = mock_post.call_args
+  payload = kwargs["json"]
+  
+  assert payload["model"] == "deepseek-reasoner"
+  assert "tools" not in payload
+  assert "temperature" not in payload
+  assert "max_tokens" not in payload

tests/test_gui2_layout.py

@@ -19,11 +19,12 @@ def test_gui2_hubs_exist_in_show_windows(app_instance: App) -> None:
 def test_gui2_old_windows_removed_from_show_windows(app_instance: App) -> None:
  """
     Verifies that the old fragmented windows are removed from show_windows.
+    Note: Message, Response, and Tool Calls are kept as they are now optional standalone windows.
     """
  old_windows = [
   "Projects", "Files", "Screenshots",
   "Provider", "System Prompts",
-  "Message", "Response", "Tool Calls", "Comms History"
+  "Comms History"
  ]
  for old_win in old_windows:
   assert old_win not in app_instance.show_windows, f"Old window '{old_win}' should have been removed from show_windows"

tests/test_log_management_ui.py

@@ -77,7 +77,11 @@ def test_render_log_management_logic(app_instance: App) -> None:
  patch("src.gui_2.imgui.table_headers_row"), \
  patch("src.gui_2.imgui.table_next_row"), \
  patch("src.gui_2.imgui.table_next_column"), \
+ patch("src.gui_2.imgui.same_line"), \
+ patch("src.gui_2.imgui.text_colored"), \
+ patch("src.gui_2.imgui.separator"), \
  patch("src.gui_2.imgui.button"):
+
   mock_reg = MockRegistry.return_value
   mock_reg.data = {
    "session_1": {

tests/test_visual_mma.py

@@ -39,11 +39,18 @@ def test_visual_mma_components(live_gui):
  client.push_event("mma_state_update", payload)
  print("  - MMA state update pushed.")
 
- # Use ApiHookClient.wait_for_event if we had a specific event to wait for,
- # but here we just want to verify state.
- time.sleep(1) # Small sleep for UI to catch up with event queue
+ # Poll for state update
+ success = False
+ for _ in range(50): # 10 seconds total
+  if client.get_value("mma_active_tier") == "Tier 3":
+   success = True
+   break
+  time.sleep(0.2)
+
+ assert success, f"State did not update to Tier 3. Current: {client.get_value('mma_active_tier')}"
 
  # 3. Trigger HITL modal
+
  print("Pushing 'mma_step_approval' event to trigger HITL modal...")
  approval_payload = {
   "ticket_id": "TICKET-002",