cli+dashboard: --panel flag, panel dict keys, TF-dialog panel section

main.py: --panel runs the agent panel on demand (force bypasses
enabled/surface/quality toggles; daily budget + LLM cap still apply),
prints the verdict + persona takes, and report_to_dict carries the four
panel keys — which auto-propagates them into the dashboard's
snapshot.json via report_to_webapp_dict. dashboard_publisher attaches
in scan_tf gated by agent_panel.dashboard (default off); dashboard.html
renders an "AI panel (advisory)" section in the TF detail dialog.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SisdfkxnXNL9iZsXxN3T15

test_all.py

@@ -7282,6 +7282,25 @@ def _():
         ap.reset_panel_state()
 
 
+@test("report_to_dict carries panel keys → dashboard snapshot propagation")
+def _():
+    from main import report_to_dict as _rtd
+    from dashboard_publisher import report_to_webapp_dict as _rtw
+    report = _panel_report()
+    d = _rtd(report)
+    assert d["panel_verdict"] == "" and d["panel_takes"] == []
+    report.panel_verdict = "AGREE"
+    report.panel_confidence = 77.5
+    report.panel_rationale = "solid confluence"
+    report.panel_takes = [{"persona": "risk", "stance": "support",
+                           "confidence": 66.0, "note": "rr fine"}]
+    wd = _rtw(report)
+    assert wd["panel_verdict"] == "AGREE"
+    assert wd["panel_confidence"] == 77.5
+    assert wd["panel_takes"][0]["persona"] == "risk"
+    json.dumps(wd, allow_nan=False)
+
+
 @test("agent_panel: attach never raises (LLM explosion, garbage settings)")
 def _():
     class _Bomb: