feat(gui): Implement token budget visualizer

This change adds a progress bar and label to the Provider panel to display the current history token usage against the provider's limit. The UI is updated in real-time.

gui.py

@@ -769,6 +769,17 @@ class App:
         total = usage["input_tokens"] + usage["output_tokens"]
         dpg.set_value("ai_token_usage", f"Tokens: {total} (In: {usage['input_tokens']} Out: {usage['output_tokens']})")
 
+    def _update_telemetry_panel(self):
+        """Updates the token budget visualizer in the Provider panel."""
+        stats = ai_client.get_history_bleed_stats()
+        if dpg.does_item_exist("token_budget_bar"):
+            percentage = stats.get("percentage", 0.0)
+            dpg.set_value("token_budget_bar", percentage / 100.0 if percentage else 0.0)
+        if dpg.does_item_exist("token_budget_label"):
+            current = stats.get("current", 0)
+            limit = stats.get("limit", 0)
+            dpg.set_value("token_budget_label", f"{current:,} / {limit:,}")
+
     def _append_comms_entry(self, entry: dict, idx: int):
         if not dpg.does_item_exist("comms_scroll"):
             return
@@ -1870,6 +1881,11 @@ class App:
                 callback=self.cb_model_changed,
             )
             dpg.add_separator()
+            dpg.add_text("Telemetry")
+            dpg.add_text("History Token Budget:", color=_LABEL_COLOR)
+            dpg.add_progress_bar(tag="token_budget_bar", default_value=0.0, width=-1)
+            dpg.add_text("0 / 0", tag="token_budget_label")
+            dpg.add_separator()
             dpg.add_text("Parameters")
             dpg.add_input_float(tag="ai_temperature", label="Temperature", default_value=self.temperature, min_value=0.0, max_value=2.0)
             dpg.add_input_int(tag="ai_max_tokens", label="Max Tokens (Output)", default_value=self.max_tokens, step=1024)
@@ -2207,6 +2223,7 @@ class App:
 
             # Flush any comms entries queued from background threads
             self._flush_pending_comms()
+            self._update_telemetry_panel()
 
             dpg.render_dearpygui_frame()
 

tests/test_gui_updates.py

@@ -0,0 +1,73 @@
+import pytest
+from unittest.mock import patch, MagicMock
+import importlib.util
+import sys
+import dearpygui.dearpygui as dpg
+
+# Load gui.py as a module for testing
+spec = importlib.util.spec_from_file_location("gui", "gui.py")
+gui = importlib.util.module_from_spec(spec)
+sys.modules["gui"] = gui
+spec.loader.exec_module(gui)
+from gui import App
+
+@pytest.fixture
+def app_instance():
+    """
+    Fixture to create an instance of the App class for testing.
+    It creates a real DPG context but mocks functions that would
+    render a window or block execution.
+    """
+    dpg.create_context()
+    
+    # Patch only the functions that would show a window or block,
+    # and the App methods that rebuild UI on init.
+    with patch('dearpygui.dearpygui.create_viewport'), \
+         patch('dearpygui.dearpygui.setup_dearpygui'), \
+         patch('dearpygui.dearpygui.show_viewport'), \
+         patch('dearpygui.dearpygui.start_dearpygui'), \
+         patch('gui.load_config', return_value={}), \
+         patch.object(App, '_rebuild_files_list'), \
+         patch.object(App, '_rebuild_shots_list'), \
+         patch.object(App, '_rebuild_disc_list'), \
+         patch.object(App, '_rebuild_disc_roles_list'), \
+         patch.object(App, '_rebuild_discussion_selector'), \
+         patch.object(App, '_refresh_project_widgets'):
+        
+        app = App()
+        yield app
+    
+    dpg.destroy_context()
+
+def test_telemetry_panel_updates_correctly(app_instance):
+    """
+    Tests that the _update_telemetry_panel method correctly updates
+    DPG widgets based on the stats from ai_client.
+    """
+    # 1. Define the mock stats to be returned by ai_client
+    mock_stats = {
+        "provider": "anthropic",
+        "limit": 180000,
+        "current": 135000,
+        "percentage": 75.0,
+    }
+
+    # 2. Patch the dependencies
+    with patch('ai_client.get_history_bleed_stats', return_value=mock_stats) as mock_get_stats, \
+         patch('dearpygui.dearpygui.set_value') as mock_set_value, \
+         patch('dearpygui.dearpygui.does_item_exist', return_value=True) as mock_does_item_exist:
+
+        # 3. Call the method under test
+        app_instance._update_telemetry_panel()
+
+        # 4. Assert the results
+        mock_get_stats.assert_called_once()
+        
+        # Check that the code verified the existence of the widgets
+        mock_does_item_exist.assert_any_call("token_budget_bar")
+        mock_does_item_exist.assert_any_call("token_budget_label")
+
+        # Check that the widgets were updated with the correct values
+        mock_set_value.assert_any_call("token_budget_bar", 0.75)
+        # Note: My implementation formats numbers with commas
+        mock_set_value.assert_any_call("token_budget_label", "135,000 / 180,000")