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>

Services/ChatService.cs

@@ -84,7 +84,7 @@ Nur deine finale Text-Antwort wird weiterverwendet. Formuliere sie vollständig
     /// <summary>
     /// Baut den vollständigen ChatContext auf: Agent, Model, SystemPrompt, Chain, Workspace etc.
     /// </summary>
-    public async Task<ChatContext> PrepareContext(string sessionId, string userId, int maxIterations = 100, bool planMode = false, bool hasRemoteConnection = false, string remoteOs = null)
+    public async Task<ChatContext> PrepareContext(string sessionId, string userId, int maxIterations = 100, bool planMode = false, string multiModelMode = null, bool hasRemoteConnection = false, string remoteOs = null)
     {
         var session = await _db.GetSession(sessionId);
         if (session == null || (userId != null && session.UserId != userId) || string.IsNullOrEmpty(session.AgentId))
@@ -167,10 +167,14 @@ Nur deine finale Text-Antwort wird weiterverwendet. Formuliere sie vollständig
         var finalizerContext = await BuildSubAgentContext(
             session.FinalizerAgentId, sessionId, workspace, session, user);
 
-        // Multi-Modell-Panel (Fusion): Panel-Agenten (Proposer) bauen, falls aktiviert.
-        // Jeder Panel-Agent ist ein vollwertiger SubAgentContext (Modell/Provider/Key/Prompt/Effort).
+        // Multi-Modell-Panel (Fusion/MoA): Panel-Agenten (Proposer) bauen, falls aktiviert.
+        // Der Modus ist on-demand (transient pro Request, wie Plan-/Ultracode-Modus) → er kommt
+        // aus dem Request-Flag, NICHT mehr aus der Session. Die Panel-Mitglieder bleiben persistent
+        // (session.PanelAgentIds), nur ob/wie das Panel läuft entscheidet die einzelne Anfrage.
+        // Nur "fusion"/"moa" sind gültig; alles andere (leer/"off"/Müll) → kein Panel.
+        var effectiveMultiModelMode = (multiModelMode == "fusion" || multiModelMode == "moa") ? multiModelMode : "off";
         var panelContexts = new List<SubAgentContext>();
-        if (!string.IsNullOrEmpty(session.MultiModelMode) && session.MultiModelMode != "off"
+        if (effectiveMultiModelMode != "off"
             && !string.IsNullOrWhiteSpace(session.PanelAgentIds))
         {
             var panelIds = session.PanelAgentIds
@@ -251,7 +255,7 @@ Für welche Plattform soll die App entwickelt werden? Web, Mobile oder Desktop?
             Preparer = preparerContext,
             Review = reviewContext,
             Finalizer = finalizerContext,
-            MultiModelMode = session.MultiModelMode,
+            MultiModelMode = effectiveMultiModelMode,
             PanelAgents = panelContexts,
             MoaLayers = session.MoaLayers,
             PlanMode = planMode