refactor(phase5): Comprehensive stabilisation pass. De-duplicated App/Controller state, hardened session reset, and updated integration tests with deterministic polling.

src/app_controller.py

@@ -261,6 +261,9 @@ class AppController:
   self.ui_gemini_cli_path: str = "gemini"
   self.ui_word_wrap: bool = True
   self.ui_auto_add_history: bool = False
+  self.ui_separate_message_panel: bool = False
+  self.ui_separate_response_panel: bool = False
+  self.ui_separate_tool_calls_panel: bool = False
   self.ui_active_tool_preset: str | None = None
   self.ui_global_system_prompt: str = ""
   self.ui_base_system_prompt: str = ""
@@ -560,6 +563,11 @@ class AppController:
  def thinking_indicator(self) -> bool:
   return self.ai_status in ("sending...", "streaming...")
 
+ @property
+ def summary_cache(self) -> Any:
+  from src import summarize
+  return summarize._summary_cache
+
  @property
  def rag_enabled(self) -> bool:
   return self.rag_config.enabled if self.rag_config else False
@@ -673,6 +681,7 @@ class AppController:
    'btn_reset_base_prompt': self._cb_reset_base_prompt,
    'btn_show_base_prompt_diff': self._cb_show_base_prompt_diff,
    'btn_rebuild_rag_index': self._rebuild_rag_index,
+   'btn_clear_summary_cache': self._handle_clear_summary_cache,
   }
   self._predefined_callbacks: dict[str, Callable[..., Any]] = {
    '_test_callback_func_write_to_file': self._test_callback_func_write_to_file,
@@ -1013,8 +1022,6 @@ class AppController:
       self.mma_streams[stream_id] = ""
      self.mma_streams[stream_id] += f"[BEAD UPDATE] {bead_id} -> status: {status}\n"
    except Exception as e:
-    sys.stderr.write(f"[DEBUG] Error executing GUI task: {e}\n{traceback.format_exc()}\n")
-    sys.stderr.flush()
     print(f"Error executing GUI task: {e}")
 
  def _process_pending_history_adds(self) -> None:
@@ -1107,6 +1114,9 @@ class AppController:
   self.ui_separate_tier2 = False
   self.ui_separate_tier3 = False
   self.ui_separate_tier4 = False
+  self.ui_separate_message_panel = False
+  self.ui_separate_response_panel = False
+  self.ui_separate_tool_calls_panel = False
   self.ui_separate_external_tools = False
   self.config = models.load_config()
   path_info = paths.get_full_path_info()
@@ -1124,6 +1134,9 @@ class AppController:
   self.project_paths = list(projects_cfg.get("paths", []))
   self.active_project_path = projects_cfg.get("active", "")
   self._load_active_project()
+  if not self.project or not isinstance(self.project, dict) or "project" not in self.project:
+   name = Path(self.active_project_path).stem if self.active_project_path else "unnamed"
+   self.project = project_manager.default_project(name)
   self.workspace_manager = workspace_manager.WorkspaceManager(project_root=Path(self.active_project_path).parent if self.active_project_path else None)
   self.workspace_profiles = self.workspace_manager.load_all_profiles()
   # Deserialize FileItems in files.paths
@@ -1203,6 +1216,9 @@ class AppController:
   self.ui_project_preset_name = proj_meta.get("active_preset")
   
   gui_cfg = self.config.get("gui", {})
+  self.ui_separate_message_panel = gui_cfg.get('separate_message_panel', False)
+  self.ui_separate_response_panel = gui_cfg.get('separate_response_panel', False)
+  self.ui_separate_tool_calls_panel = gui_cfg.get('separate_tool_calls_panel', False)
   self.ui_auto_switch_layout = gui_cfg.get("auto_switch_layout", False)
   self.ui_tier_layout_bindings = gui_cfg.get("tier_layout_bindings", {"Tier 1": "", "Tier 2": "", "Tier 3": "", "Tier 4": ""})
   from src import bg_shader
@@ -1531,7 +1547,6 @@ class AppController:
      try:
       self.all_available_models[p] = ai_client.list_models(p)
      except Exception as e:
-      sys.stderr.write(f"[DEBUG] Error fetching models for {p}: {e}\n")
       self.all_available_models[p] = []
     
     models_list = self.all_available_models.get(provider, [])
@@ -2275,6 +2290,10 @@ class AppController:
   summarize._summary_cache.clear()
   self._push_mma_state_update()
 
+ def _handle_clear_summary_cache(self, user_data: Any = None) -> None:
+  self.summary_cache.clear()
+  self.ai_status = 'summary cache cleared'
+
  def _cb_show_base_prompt_diff(self, user_data=None) -> None:
   """
     [C: src/gui_2.py:App._render_system_prompts_panel]
@@ -2425,7 +2444,6 @@ class AppController:
   """
     [C: src/gui_2.py:App._render_system_prompts_panel]
   """
-  print(f"[DEBUG] _apply_preset: name={name}, scope={scope}")
   if name == "None":
    if scope == "global":
     self.ui_global_preset_name = ""
@@ -2434,7 +2452,6 @@ class AppController:
    return
   preset = self.presets.get(name)
   if not preset:
-   print(f"[DEBUG] _apply_preset: preset {name} not found in {list(self.presets.keys())}")
    return
   if scope == "global":
    self.ui_global_system_prompt = preset.system_prompt
@@ -2447,7 +2464,6 @@ class AppController:
   """
     [C: src/gui_2.py:App._render_preset_manager_content]
   """
-  print(f"[DEBUG] _cb_save_preset: name={name}, scope={scope}")
   if not name or not name.strip():
    raise ValueError("Preset name cannot be empty or whitespace.")
   preset = models.Preset(
@@ -2456,7 +2472,6 @@ class AppController:
   )
   self.preset_manager.save_preset(preset, scope)
   self.presets = self.preset_manager.load_all()
-  print(f"[DEBUG] _cb_save_preset: saved {name}, total presets now {len(self.presets)}")
 
  def _cb_delete_preset(self, name, scope):
   """
@@ -2746,6 +2761,14 @@ class AppController:
   self.ui_ai_input = ""
   self.ui_manual_approve = False
   self.ui_auto_add_history = False
+  self.active_track = None
+  self.active_tier = None
+  self.mma_status = 'idle'
+  self.proposed_tracks = []
+  self.active_tickets = []
+  self.engines.clear()
+  self.mma_streams.clear()
+  self._worker_status.clear()
   self._current_provider = "gemini"
   self._current_model = "gemini-2.5-flash-lite"
   ai_client.set_provider(self._current_provider, self._current_model)
@@ -2755,6 +2778,17 @@ class AppController:
    self._api_event_queue.clear()
   with self._pending_gui_tasks_lock:
    self._pending_gui_tasks.clear()
+  self.ui_use_default_base_prompt = True
+  self.ui_global_system_prompt = ''
+  self.ui_base_system_prompt = ''
+  self.ui_project_system_prompt = ''
+  self.ui_project_main_context = ''
+  self.ui_active_persona = ''
+  self.ui_active_tool_preset = None
+  self.ui_active_bias_profile = None
+  self.temperature = 0.0
+  self.top_p = 1.0
+  self.max_tokens = 8192
 
  def _handle_md_only(self) -> None:
   """
@@ -2789,8 +2823,6 @@ class AppController:
    """
       [C: tests/test_symbol_parsing.py:test_handle_generate_send_appends_definitions, tests/test_symbol_parsing.py:test_handle_generate_send_no_symbols]
    """
-   sys.stderr.write("[DEBUG] _handle_generate_send worker started\n")
-   sys.stderr.flush()
    try:
     md, path, file_items, stable_md, disc_text = self._do_generate()
     self._last_stable_md = stable_md
@@ -2819,8 +2851,6 @@ class AppController:
       user_msg += f'\n\n[Definition: {symbol} from {file_path} (line {line})]\n```python\n{definition}\n```'
 
     base_dir = self.active_project_root
-    sys.stderr.write(f"[DEBUG] _do_generate success. Prompt: {user_msg[:50]}...\n")
-    sys.stderr.flush()
     # Prepare event payload
     event_payload = events.UserRequestEvent(
      prompt=user_msg,
@@ -2831,11 +2861,7 @@ class AppController:
     )
     # Push to async queue
     self.event_queue.put("user_request", event_payload)
-    sys.stderr.write("[DEBUG] Enqueued user_request event\n")
-    sys.stderr.flush()
    except Exception as e:
-    sys.stderr.write(f"[DEBUG] _do_generate ERROR: {e}\n{traceback.format_exc()}\n")
-    sys.stderr.flush()
     self.ai_status = f"generate error: {e}"
   threading.Thread(target=worker, daemon=True).start()
 
@@ -3035,13 +3061,9 @@ class AppController:
     [C: src/gui_2.py:App._render_mma_dashboard, tests/test_mma_orchestration_gui.py:test_cb_plan_epic_launches_thread]
   """
   def _bg_task() -> None:
-   sys.stderr.write("[DEBUG] _cb_plan_epic _bg_task started\n")
-   sys.stderr.flush()
    try:
     self.ai_status = "Planning Epic (Tier 1)..."
     history = orchestrator_pm.get_track_history_summary()
-    sys.stderr.write(f"[DEBUG] History summary length: {len(history)}\n")
-    sys.stderr.flush()
     proj = project_manager.load_project(self.active_project_path)
     flat = project_manager.flat_config(self.project)
     file_items = aggregate.build_file_items(Path(self.active_project_root), flat.get("files", {}).get("paths", []))
@@ -3086,16 +3108,13 @@ class AppController:
   self._show_track_proposal_modal = False
 
   def _bg_task() -> None:
-   sys.stderr.write("[DEBUG] _cb_accept_tracks _bg_task started\n")
    # Generate skeletons once
    self.ai_status = "Phase 2: Generating skeletons for all tracks..."
-   sys.stderr.write("[DEBUG] Creating ASTParser...\n")
    parser = ASTParser(language="python")
    generated_skeletons = ""
    try:
    # Use a local copy of files to avoid concurrent modification issues
     files_to_scan = list(self.files)
-    sys.stderr.write(f"[DEBUG] Scanning {len(files_to_scan)} files for skeletons...\n")
     for i, file_path in enumerate(files_to_scan):
      try:
       self.ai_status = f"Phase 2: Scanning files ({i+1}/{len(files_to_scan)})..."
@@ -3105,19 +3124,16 @@ class AppController:
         code = f.read()
         generated_skeletons += f"\nFile: {file_path}\n{parser.get_skeleton(code)}\n"
      except Exception as e:
-      sys.stderr.write(f"[DEBUG] Error parsing skeleton for {file_path}: {e}\n")
+      pass
    except Exception as e:
-    sys.stderr.write(f"[DEBUG] Error in scan loop: {e}\n")
     self.ai_status = f"Error generating skeletons: {e}"
     return # Exit if skeleton generation fails
-   sys.stderr.write("[DEBUG] Skeleton generation complete. Starting tracks...\n")
    # Now loop through tracks and call _start_track_logic with generated skeletons
    total_tracks = len(self.proposed_tracks)
    for i, track_data in enumerate(self.proposed_tracks):
     title = track_data.get("title") or track_data.get("goal", "Untitled Track")
     self.ai_status = f"Processing track {i+1} of {total_tracks}: '{title}'..."
     self._start_track_logic(track_data, skeletons_str=generated_skeletons) # Pass skeletons
-   sys.stderr.write("[DEBUG] All tracks started. Refreshing...\n")
    with self._pending_gui_tasks_lock:
     self._pending_gui_tasks.append({'action': 'refresh_from_project'}) # Ensure UI refresh after tracks are started
    self.ai_status = f"All {total_tracks} tracks accepted and execution started."
@@ -3135,7 +3151,6 @@ class AppController:
     self._cb_load_track(track_id)
    if self.active_track and self.active_track.id == track_id:
    # Use the active track object directly to start execution
-    print(f"[DEBUG] _cb_start_track: track_id={self.active_track.id}, desc={self.active_track.description}")
     self.mma_status = "running"
     engine = multi_agent_conductor.ConductorEngine(self.active_track, self.event_queue, auto_queue=not self.mma_step_mode)
     self.engines[self.active_track.id] = engine
@@ -3145,7 +3160,6 @@ class AppController:
     self.ai_status = f"Track '{self.active_track.description}' started."
    elif self.active_track and self.active_track.id != track_id:
    # load_track failed but active_track is still wrong - reload explicitly
-    print(f"[DEBUG] _cb_start_track: load failed, trying reload track_id={track_id}")
     self._cb_load_track(track_id)
     if self.active_track and self.active_track.id == track_id:
      self.mma_status = "running"