fix(gui): Resolve AppController state regressions

src/app_controller.py

@@ -233,6 +233,8 @@ class AppController:
   self.ui_auto_add_history: bool = False
   self.ui_active_tool_preset: str | None = None
   self.ui_global_system_prompt: str = ""
+  self.ui_global_tool_instructions: str = ""
+  self.ui_project_context_marker: str = ""
   self.ui_agent_tools: Dict[str, bool] = {}
   self.available_models: List[str] = []
   self.all_available_models: Dict[str, List[str]] = {} # provider -> list of models
@@ -913,6 +915,8 @@ class AppController:
   self.ui_word_wrap = proj_meta.get("word_wrap", True)
   self.ui_auto_add_history = disc_sec.get("auto_add", False)
   self.ui_global_system_prompt = self.config.get("ai", {}).get("system_prompt", "")
+  self.ui_global_tool_instructions = self.config.get("ai", {}).get("tool_instructions", "")
+  self.ui_project_context_marker = proj_meta.get("context_marker", "")
   
   self.preset_manager = presets.PresetManager(Path(self.active_project_path).parent if self.active_project_path else None)
   self.presets = self.preset_manager.load_all()
@@ -1404,9 +1408,10 @@ class AppController:
   self.ai_response = ""
   csp = filter(bool, [self.ui_global_system_prompt.strip(), self.ui_project_system_prompt.strip()])
   ai_client.set_custom_system_prompt("\n\n".join(csp))
+  ai_client.set_global_tool_instructions(self.ui_global_tool_instructions)
+  ai_client.set_project_context_marker(self.ui_project_context_marker)
   ai_client.set_model_params(self.temperature, self.max_tokens, self.history_trunc_limit, self.top_p)
-  ai_client.set_agent_tools(self.ui_agent_tools)
-  # Force update adapter path right before send to bypass potential duplication issues
+  ai_client.set_agent_tools(self.ui_agent_tools)  # Force update adapter path right before send to bypass potential duplication issues
   self._update_gcli_adapter(self.ui_gemini_cli_path)
   sys.stderr.write(f"[DEBUG] Calling ai_client.send with provider={ai_client.get_provider()}, model={self.current_model}, gcli_path={self.ui_gemini_cli_path}\n")
   sys.stderr.flush()
@@ -1465,11 +1470,11 @@ class AppController:
   
   if kind == "response" and "usage" in payload:
    u = payload["usage"]
-   inp = u.get("input_tokens", u.get("prompt_tokens", 0))
-   out = u.get("output_tokens", u.get("completion_tokens", 0))
-   cache_read = u.get("cache_read_input_tokens", 0)
-   cache_create = u.get("cache_creation_input_tokens", 0)
-   total = u.get("total_tokens", 0)
+   inp = u.get("input_tokens") or u.get("prompt_tokens") or 0
+   out = u.get("output_tokens") or u.get("completion_tokens") or 0
+   cache_read = u.get("cache_read_input_tokens") or 0
+   cache_create = u.get("cache_creation_input_tokens") or 0
+   total = u.get("total_tokens") or 0
 
    # Store normalized usage back in payload for history rendering
    u["input_tokens"] = inp
@@ -1481,8 +1486,8 @@ class AppController:
    self.session_usage["cache_read_input_tokens"] += cache_read
    self.session_usage["cache_creation_input_tokens"] += cache_create
    self.session_usage["total_tokens"] += total
-   input_t = u.get("input_tokens", 0)
-   output_t = u.get("output_tokens", 0)
+   input_t = u.get("input_tokens") or 0
+   output_t = u.get("output_tokens") or 0
    model = payload.get("model", "unknown")
    self._token_history.append({
     "time": time.time(),
@@ -1823,6 +1828,8 @@ class AppController:
     base_dir = self.active_project_root
     csp = filter(bool, [self.ui_global_system_prompt.strip(), self.ui_project_system_prompt.strip()])
     ai_client.set_custom_system_prompt("\n\n".join(csp))
+    ai_client.set_global_tool_instructions(self.ui_global_tool_instructions)
+    ai_client.set_project_context_marker(self.ui_project_context_marker)
     temp = req.temperature if req.temperature is not None else self.temperature
     top_p = req.top_p if req.top_p is not None else self.top_p
     tokens = req.max_tokens if req.max_tokens is not None else self.max_tokens