feat(mma): complete Phase 6 and finalize Comprehensive GUI UX track

- Implement Live Worker Streaming: wire ai_client.comms_log_callback to Tier 3 streams
- Add Parallel DAG Execution using asyncio.gather for non-dependent tickets
- Implement Automatic Retry with Model Escalation (Flash-Lite -> Flash -> Pro)
- Add Tier Model Configuration UI to MMA Dashboard with project TOML persistence
- Fix FPS reporting in PerformanceMonitor to prevent transient 0.0 values
- Update Ticket model with retry_count and dictionary-like access
- Stabilize Gemini CLI integration tests and handle script approval events in simulations
- Finalize and verify all 6 phases of the implementation plan

tests/test_gemini_cli_integration.py

@@ -1,4 +1,4 @@
-from typing import Any
+from typing import Any
 import pytest
 import time
 import os
@@ -95,14 +95,19 @@ def test_gemini_cli_rejection_and_history(live_gui: Any) -> None:
  while time.time() - start_time < timeout:
   for ev in client.get_events():
    etype = ev.get("type")
-   eid = ev.get("request_id")
-   print(f"[TEST] Received event: {etype}")
+   eid = ev.get("request_id") or ev.get("action_id")
+   print(f"[TEST] Received event: {etype} (ID: {eid})")
    if etype == "ask_received":
     print(f"[TEST] Denying request {eid}")
     requests.post("http://127.0.0.1:8999/api/ask/respond",
      json={"request_id": eid, "response": {"approved": False}})
     denied = True
     break
+   elif etype == "script_confirmation_required":
+    print(f"[TEST] Denying script {eid}")
+    requests.post(f"http://127.0.0.1:8999/api/confirm/{eid}", json={"approved": False})
+    denied = True
+    break
   if denied: break
   time.sleep(0.5)
  assert denied, "No ask_received event to deny"