Add workflow-status telemetry view and make panel modes on-demand

Workflow-status: a new WorkflowProgressTracker singleton taps the
suppressed dynamic-workflow subagent events (those carrying
parent_tool_use_id) into per-session telemetry without altering the
existing guard; the snapshot is serialized into the new chains.workflow_info
column on FinalizeChain (ChainId-matched so a panel member of the same
session cannot clear it) and exposed via GET /api/sessions/{id}/workflow-status
(live -> persisted -> none). The header menu gains a 'Workflow-Status' entry
with a modal that live-polls every 2s while running and self-stops on close.

Panel on-demand: Fusion/MoA is now a transient per-request multiModelMode
flag (like plan/ultracode) instead of a persisted session column. Session
settings keep only the panel members + moa_layers; the mode <select> was
removed and the composer dropdown drives the mode per request.

Docs: ARCHITECTURE.md, ARCHITECTURE_QUICK.md and README.md updated for both
features plus the already-shipped z.ai/GLM provider, GLM 5.2+ effort
passthrough, web-search-prime MCP and the ultracode toggle.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Models/ChatModels.cs

@@ -158,4 +158,13 @@ public class ChatRequest
     /// </summary>
     [JsonPropertyName("ultracode")]
     public bool Ultracode { get; set; }
+
+    /// <summary>
+    /// On-demand Panel-Modus für genau diese Anfrage (transient, NICHT persistent):
+    /// "" / "off" / "fusion" / "moa". Wie Plan-/Ultracode-Modus pro Request gewählt.
+    /// Die Panel-Mitglieder kommen weiterhin aus der persistierten Session (PanelAgentIds),
+    /// nur der Modus (ob/wie das Panel läuft) wird hier pro Anfrage gesetzt.
+    /// </summary>
+    [JsonPropertyName("multiModelMode")]
+    public string MultiModelMode { get; set; } = "";
 }