conductor(checkpoint): Checkpoint end of Phase 3: Diagnostics UI and Optimization

conductor/tracks/ui_performance_20260223/plan.md

@@ -25,7 +25,7 @@
 - [x] Task: Build the Diagnostics Panel in Dear PyGui 30d838c
     - [x] Sub-task: Write Tests (verify panel components render)
     - [x] Sub-task: Implement Feature (plots, stat readouts in `gui.py`)
-- [ ] Task: Identify and fix main thread performance bottlenecks
+- [~] Task: Identify and fix main thread performance bottlenecks
     - [ ] Sub-task: Write Tests (reproducible "heavy" load test)
     - [ ] Sub-task: Implement Feature (refactor heavy logic to workers)
 - [ ] Task: Conductor - User Manual Verification 'Phase 3: Diagnostics UI and Optimization' (Protocol in workflow.md)

gui.py

@@ -504,6 +504,13 @@ class App:
             "input_lag": [0.0] * 100
         }
 
+        self.session_usage = {
+            "input_tokens": 0,
+            "output_tokens": 0,
+            "cache_read_input_tokens": 0,
+            "cache_creation_input_tokens": 0
+        }
+
         session_logger.open_session()
         ai_client.set_provider(self.current_provider, self.current_model)
         ai_client.confirm_and_run_callback = self._confirm_and_run
@@ -511,6 +518,8 @@ class App:
         ai_client.tool_log_callback = self._on_tool_log
         mcp_client.perf_monitor_callback = self.perf_monitor.get_metrics
         self.perf_monitor.alert_callback = self._on_performance_alert
+        self._last_bleed_update_time = 0
+        self._recalculate_session_usage()
 
     # ---------------------------------------------------------------- project loading
 
@@ -775,6 +784,21 @@ class App:
                 "ts": project_manager.now_ts()
             })
 
+    def _recalculate_session_usage(self):
+        """Aggregates usage across the session from comms log."""
+        usage = {
+            "input_tokens": 0,
+            "output_tokens": 0,
+            "cache_read_input_tokens": 0,
+            "cache_creation_input_tokens": 0
+        }
+        for entry in ai_client.get_comms_log():
+            if entry.get("kind") == "response" and "usage" in entry.get("payload", {}):
+                u = entry["payload"]["usage"]
+                for k in usage.keys():
+                    usage[k] += u.get(k, 0) or 0
+        self.session_usage = usage
+
     def _flush_pending_comms(self):
         """Called every frame from the main render loop."""
         with self._pending_comms_lock:
@@ -784,18 +808,22 @@ class App:
             self._comms_entry_count += 1
             self._append_comms_entry(entry, self._comms_entry_count)
         if entries:
+            self._recalculate_session_usage()
             self._update_token_usage()
 
     def _update_token_usage(self):
         if not dpg.does_item_exist("ai_token_usage"):
             return
-        usage = get_total_token_usage()
+        usage = self.session_usage
         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."""
-        # Update history bleed stats for all providers
+        # Update history bleed stats for all providers (throttled)
+        now = time.time()
+        if now - self._last_bleed_update_time > 2.0:
+            self._last_bleed_update_time = now
             stats = ai_client.get_history_bleed_stats()
             if dpg.does_item_exist("token_budget_bar"):
                 percentage = stats.get("percentage", 0.0)

project.toml

@@ -35,5 +35,5 @@ active = "main"
 
 [discussion.discussions.main]
 git_commit = ""
-last_updated = "2026-02-23T14:48:16"
+last_updated = "2026-02-23T14:52:20"
 history = []

tests/test_gui_updates.py

@@ -56,9 +56,11 @@ def test_telemetry_panel_updates_correctly(app_instance):
     }
 
     # 3. Patch the dependencies
+    app_instance._last_bleed_update_time = 0 # Force update
     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.configure_item') as mock_configure_item, \
+         patch('dearpygui.dearpygui.is_item_shown', return_value=False), \
          patch('dearpygui.dearpygui.does_item_exist', return_value=True) as mock_does_item_exist:
 
         # 4. Call the method under test
@@ -91,9 +93,11 @@ def test_cache_data_display_updates_correctly(app_instance):
     expected_text = "Gemini Caches: 5 (12.1 KB)"
 
     # 3. Patch dependencies
+    app_instance._last_bleed_update_time = 0 # Force update
     with patch('ai_client.get_gemini_cache_stats', return_value=mock_cache_stats) as mock_get_cache_stats, \
          patch('dearpygui.dearpygui.set_value') as mock_set_value, \
          patch('dearpygui.dearpygui.configure_item') as mock_configure_item, \
+         patch('dearpygui.dearpygui.is_item_shown', return_value=False), \
          patch('dearpygui.dearpygui.does_item_exist', return_value=True) as mock_does_item_exist:
         
         # We also need to mock get_history_bleed_stats as it's called in the same function