Fix progress bar stuck status, improve Assets sidebar visualization/file extraction, better response formatting cleanup

FRRONTEEEND/components/ChatInterface.tsx

@@ -88,11 +88,22 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
           const progressData = await progressResponse.json();
           const steps = progressData.steps || [];
           
-          // Find the most recent running step
+          // Find the most recent running step, or last completed step
           const runningSteps = steps.filter((s: any) => s.status === 'running');
           if (runningSteps.length > 0) {
             const lastStep = runningSteps[runningSteps.length - 1];
             setCurrentStep(lastStep.tool);
+          } else if (steps.length > 0) {
+            // No running steps - check if there are completed steps
+            const completedSteps = steps.filter((s: any) => s.status === 'completed');
+            if (completedSteps.length > 0) {
+              // Only show if very recent (workflow still in progress)
+              const lastCompleted = completedSteps[completedSteps.length - 1];
+              const timeSinceCompletion = Date.now() - (lastCompleted.timestamp * 1000 || 0);
+              if (timeSinceCompletion < 2000) {  // Show for 2 seconds after completion
+                setCurrentStep('');
+              }
+            }
           }
         }
       } catch (err) {
@@ -698,37 +709,85 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
               {(() => {
                 const allPlots: Array<{title: string, url: string, type?: string}> = [];
                 const allReports: Array<{name: string, path: string}> = [];
+                const allDataFiles: Array<{name: string, path: string}> = [];
+                const seenModels = new Set<string>();
                 const allModels: string[] = [];
                 
                 activeSession.messages.forEach(msg => {
-                  if (msg.plots) allPlots.push(...msg.plots);
-                  if (msg.reports) allReports.push(...msg.reports);
-                  // Extract model references from content
-                  if (msg.content.includes('xgboost') || msg.content.includes('model')) {
-                    const modelMatch = msg.content.match(/\b(xgboost|random_forest|catboost|lightgbm)[^\s]*/gi);
-                    if (modelMatch) allModels.push(...modelMatch);
+                  // Collect plots
+                  if (msg.plots) {
+                    allPlots.push(...msg.plots.filter(p => p && p.title && p.url));
+                  }
+                  
+                  // Collect reports
+                  if (msg.reports) {
+                    allReports.push(...msg.reports.filter(r => r && r.name && r.path));
                   }
+                  
+                  // Extract data files from content (look for CSV mentions)
+                  const csvMatch = msg.content.match(/cleaned.*dataset|encoded.*dataset|prepared.*data/gi);
+                  if (csvMatch && !allDataFiles.some(f => f.name.includes('encoded'))) {
+                    allDataFiles.push({
+                      name: 'Cleaned & Encoded Dataset',
+                      path: '/outputs/data/encoded.csv'
+                    });
+                  }
+                  
+                  // Extract model names - look for baseline models only
+                  const baselineModels = ['xgboost', 'random_forest', 'catboost', 'lightgbm', 'ridge', 'lasso', 'logistic'];
+                  baselineModels.forEach(model => {
+                    if (msg.content.toLowerCase().includes(model) && !seenModels.has(model)) {
+                      seenModels.add(model);
+                      allModels.push(model);
+                    }
+                  });
                 });
                 
-                const uniqueModels = [...new Set(allModels)];
+                // Remove duplicates from plots
+                const uniquePlots = Array.from(new Map(allPlots.map(p => [p.title + p.url, p])).values());
                 
                 return (
                   <>
-                    {/* Models Section */}
-                    {uniqueModels.length > 0 && (
+                    {/* Visualizations Section - Show FIRST */}
+                    {uniquePlots.length > 0 && (
+                      <div>
+                        <div className="flex items-center gap-2 mb-3">
+                          <BarChart3 className="w-4 h-4 text-emerald-400" />
+                          <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Visualizations ({uniquePlots.length})</h4>
+                        </div>
+                        <div className="space-y-2">
+                          {uniquePlots.map((plot, idx) => (
+                            <button
+                              key={idx}
+                              onClick={() => setReportModalUrl(plot.url)}
+                              className="w-full p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-emerald-500/10 hover:border-emerald-500/30 transition-all text-left group"
+                            >
+                              <div className="flex items-center justify-between">
+                                <span className="text-sm text-white/80 truncate flex-1">{plot.title}</span>
+                                <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-emerald-400 transition-all" />
+                              </div>
+                              <span className="text-xs text-white/40 mt-1 block">{plot.type || 'interactive'}</span>
+                            </button>
+                          ))}
+                        </div>
+                      </div>
+                    )}
+                    
+                    {/* Data Files Section */}
+                    {allDataFiles.length > 0 && (
                       <div>
                         <div className="flex items-center gap-2 mb-3">
                           <FileText className="w-4 h-4 text-blue-400" />
-                          <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Models ({uniqueModels.length})</h4>
+                          <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Data Files ({allDataFiles.length})</h4>
                         </div>
                         <div className="space-y-2">
-                          {uniqueModels.slice(0, 5).map((model, idx) => (
+                          {allDataFiles.map((file, idx) => (
                             <div 
                               key={idx}
                               className="p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-white/10 transition-all cursor-pointer group"
                             >
                               <div className="flex items-center justify-between">
-                                <span className="text-sm text-white/80 truncate flex-1">{model}</span>
+                                <span className="text-sm text-white/80 truncate flex-1">{file.name}</span>
                                 <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-white/80 transition-all" />
                               </div>
                             </div>
@@ -737,26 +796,24 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
                       </div>
                     )}
                     
-                    {/* Plots Section */}
-                    {allPlots.length > 0 && (
+                    {/* Models Section */}
+                    {allModels.length > 0 && (
                       <div>
                         <div className="flex items-center gap-2 mb-3">
-                          <BarChart3 className="w-4 h-4 text-emerald-400" />
-                          <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Visualizations ({allPlots.length})</h4>
+                          <FileText className="w-4 h-4 text-purple-400" />
+                          <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Models ({allModels.length})</h4>
                         </div>
                         <div className="space-y-2">
-                          {allPlots.map((plot, idx) => (
-                            <button
+                          {allModels.map((model, idx) => (
+                            <div 
                               key={idx}
-                              onClick={() => setReportModalUrl(plot.url)}
-                              className="w-full p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-emerald-500/10 hover:border-emerald-500/30 transition-all text-left group"
+                              className="p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-purple-500/10 hover:border-purple-500/30 transition-all cursor-pointer group"
                             >
                               <div className="flex items-center justify-between">
-                                <span className="text-sm text-white/80 truncate flex-1">{plot.title}</span>
-                                <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-emerald-400 transition-all" />
+                                <span className="text-sm text-white/80 truncate flex-1 capitalize">{model.replace(/_/g, ' ')}</span>
+                                <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-purple-400 transition-all" />
                               </div>
-                              <span className="text-xs text-white/40 mt-1 block">{plot.type || 'interactive'}</span>
-                            </button>
+                            </div>
                           ))}
                         </div>
                       </div>
@@ -766,7 +823,7 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
                     {allReports.length > 0 && (
                       <div>
                         <div className="flex items-center gap-2 mb-3">
-                          <FileText className="w-4 h-4 text-purple-400" />
+                          <FileText className="w-4 h-4 text-orange-400" />
                           <h4 className="text-xs font-bold uppercase tracking-wider text-white/60">Reports ({allReports.length})</h4>
                         </div>
                         <div className="space-y-2">
@@ -774,11 +831,11 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
                             <button
                               key={idx}
                               onClick={() => setReportModalUrl(report.path)}
-                              className="w-full p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-purple-500/10 hover:border-purple-500/30 transition-all text-left group"
+                              className="w-full p-3 rounded-lg bg-white/5 border border-white/10 hover:bg-orange-500/10 hover:border-orange-500/30 transition-all text-left group"
                             >
                               <div className="flex items-center justify-between">
                                 <span className="text-sm text-white/80 truncate flex-1">{report.name}</span>
-                                <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-purple-400 transition-all" />
+                                <ChevronRight className="w-4 h-4 text-white/40 group-hover:text-orange-400 transition-all" />
                               </div>
                             </button>
                           ))}
@@ -787,7 +844,7 @@ export const ChatInterface: React.FC<{ onBack: () => void }> = ({ onBack }) => {
                     )}
                     
                     {/* Empty State */}
-                    {allPlots.length === 0 && allReports.length === 0 && uniqueModels.length === 0 && (
+                    {uniquePlots.length === 0 && allReports.length === 0 && allDataFiles.length === 0 && allModels.length === 0 && (
                       <div className="flex flex-col items-center justify-center h-full text-center p-8">
                         <Package className="w-12 h-12 text-white/10 mb-3" />
                         <p className="text-sm text-white/40 mb-1">No assets yet</p>

src/orchestrator.py

@@ -2305,25 +2305,37 @@ You are a DOER. Complete workflows based on user intent."""
                         )
                         summary_text = enhanced_summary["text"]
                         
-                        # 🧹 POST-PROCESS: Remove any file paths that slipped through
+                        # 🧹 POST-PROCESS: Clean file paths and broken formatting
                         import re
-                        # Remove file path patterns
-                        summary_text = re.sub(r'\./outputs/[^\s\)]+', '[generated file]', summary_text)
-                        summary_text = re.sub(r'/outputs/[^\s\)]+', '[generated file]', summary_text)
-                        summary_text = re.sub(r'outputs/[^\s\)]+', '[generated file]', summary_text)
-                        # Remove common file path mentions
-                        summary_text = re.sub(r'saved to:?\s*[^\s]+', 'generated', summary_text, flags=re.IGNORECASE)
-                        summary_text = re.sub(r'output file:?\s*[^\s]+', 'output generated', summary_text, flags=re.IGNORECASE)
-                        summary_text = re.sub(r'file path:?\s*[^\s]+', 'file generated', summary_text, flags=re.IGNORECASE)
-                        # Remove filename patterns in parentheses and backticks
-                        summary_text = re.sub(r'\([^\)]*\.(csv|pkl|html|png|json)[^\)]*\)', '', summary_text)
-                        summary_text = re.sub(r'`[^`]*\.(csv|pkl|html|png|json)[^`]*`', '', summary_text)
-                        # Clean up table separators that mention paths
-                        summary_text = re.sub(r'\|\s*[^\|]*\.(csv|pkl|html|png)[^\|]*\s*\|', '| [see artifacts] |', summary_text)
+                        # Remove file path patterns BEFORE they create [generated file]
+                        summary_text = re.sub(r'`\./outputs/[^\s`]+`', '', summary_text)  # Backtick wrapped paths
+                        summary_text = re.sub(r'\./outputs/[^\s\)]+', '', summary_text)   # Direct paths
+                        summary_text = re.sub(r'/outputs/[^\s\)]+', '', summary_text)     # Absolute paths
+                        summary_text = re.sub(r'outputs/[^\s\)]+', '', summary_text)      # Relative paths
+                        
+                        # Remove broken table rows with empty content
+                        summary_text = re.sub(r'\|\s*\|[^\|]*\|', '', summary_text)  # Clean malformed tables
+                        summary_text = re.sub(r'\|\s*\[\s*[^\]]*\]\([^\)]*\)\s*\|', '', summary_text)  # Remove link-only cells
+                        
+                        # Remove leftover [generated file] brackets
+                        summary_text = re.sub(r'\s*\[\s*generated file\s*\]\s*', ' ', summary_text)
+                        summary_text = re.sub(r'\[\s*see artifacts\s*\]', '', summary_text)
+                        
+                        # Remove broken parentheses and backticks
+                        summary_text = re.sub(r'`\[generated[^\]]*\]`', '', summary_text)
+                        summary_text = re.sub(r'\(\s*\[\s*generated[^\]]*\]\s*\)', '', summary_text)
+                        
+                        # Clean up "generated file" text patterns
+                        summary_text = re.sub(r'\[generated file\]', '', summary_text)
+                        summary_text = re.sub(r'saved to:?\s*[^\s]+', '', summary_text, flags=re.IGNORECASE)
+                        summary_text = re.sub(r'output file:?\s*[^\n]+', '', summary_text, flags=re.IGNORECASE)
+                        
+                        # Remove excessive whitespace
+                        summary_text = re.sub(r'\n\s*\n\s*\n+', '\n\n', summary_text)  # Multiple blank lines
+                        summary_text = re.sub(r' {2,}', ' ', summary_text)  # Multiple spaces
                         
                         metrics_data = enhanced_summary.get("metrics", {})
                         artifacts_data = enhanced_summary.get("artifacts", {})
-                        artifacts_data = enhanced_summary.get("artifacts", {})
                         plots_data = enhanced_summary.get("plots", [])
                         print(f"✅ Enhanced summary generated with {len(plots_data)} plots, {len(metrics_data)} metrics")
                     except Exception as e: