feat(tier4): Integrate patch generation into GUI workflow

- Add patch_callback parameter throughout the tool execution chain
- Add _render_patch_modal() to gui_2.py with colored diff display
- Add patch modal state variables to App.__init__
- Add request_patch_from_tier4() to trigger patch generation
- Add run_tier4_patch_callback() to ai_client.py
- Update shell_runner to accept and execute patch_callback
- Diff colors: green for additions, red for deletions, cyan for headers
- 36 tests passing

src/app_controller.py

@@ -907,7 +907,8 @@ class AppController:
     stream=True,
     stream_callback=lambda text: self._on_ai_stream(text),
     pre_tool_callback=self._confirm_and_run,
-    qa_callback=ai_client.run_tier4_analysis
+    qa_callback=ai_client.run_tier4_analysis,
+    patch_callback=ai_client.run_tier4_patch_callback
    )
    self.event_queue.put("response", {"text": resp, "status": "done", "role": "AI"})
   except ai_client.ProviderError as e:
@@ -988,14 +989,14 @@ class AppController:
      "ts": project_manager.now_ts()
     })
 
- def _confirm_and_run(self, script: str, base_dir: str, qa_callback: Optional[Callable[[str], str]] = None) -> Optional[str]:
+ def _confirm_and_run(self, script: str, base_dir: str, qa_callback: Optional[Callable[[str], str]] = None, patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> Optional[str]:
   sys.stderr.write(f"[DEBUG] _confirm_and_run called. test_hooks={self.test_hooks_enabled}, manual_approve={getattr(self, 'ui_manual_approve', False)}\n")
   sys.stderr.flush()
   if self.test_hooks_enabled and not getattr(self, "ui_manual_approve", False):
    sys.stderr.write("[DEBUG] Auto-approving script.\n")
    sys.stderr.flush()
    self._set_status("running powershell...")
-   output = shell_runner.run_powershell(script, base_dir, qa_callback=qa_callback)
+   output = shell_runner.run_powershell(script, base_dir, qa_callback=qa_callback, patch_callback=patch_callback)
    self._append_tool_log(script, output)
    self._set_status("powershell done, awaiting AI...")
    return output
@@ -1033,7 +1034,7 @@ class AppController:
    self._append_tool_log(final_script, "REJECTED by user")
    return None
   self._set_status("running powershell...")
-  output = shell_runner.run_powershell(final_script, base_dir, qa_callback=qa_callback)
+  output = shell_runner.run_powershell(final_script, base_dir, qa_callback=qa_callback, patch_callback=patch_callback)
   self._append_tool_log(final_script, output)
   self._set_status("powershell done, awaiting AI...")
   return output