feat: Add advanced quick action buttons for agent chat

- Add 'Multi-Tool Analysis' button: chains analyze_leaderboard → compare_runs → estimate_cost
- Add 'Generate Synthetic Data' button: chains generate_synthetic_dataset → generate_prompt_template → push_dataset_to_hub
- Organize quick actions into Basic and Advanced sections
- Demonstrates multi-step autonomous agent workflows

app.py

@@ -3812,6 +3812,18 @@ Result: {result}
             outputs=[chat_components['message']]
         )
 
+        chat_components['quick_multi_tool'].click(
+            fn=lambda: on_quick_action("multi_tool"),
+            inputs=[],
+            outputs=[chat_components['message']]
+        )
+
+        chat_components['quick_synthetic'].click(
+            fn=lambda: on_quick_action("synthetic"),
+            inputs=[],
+            outputs=[chat_components['message']]
+        )
+
         # Compare button handler
         compare_components['compare_button'].click(
             fn=lambda run_a, run_b: handle_compare_runs(run_a, run_b, leaderboard_df_cache, compare_components),

screens/chat.py

@@ -554,10 +554,15 @@ def create_chat_ui():
 
                 # Quick actions
                 gr.Markdown("### ⚡ Quick Actions")
+                gr.Markdown("**Basic:**")
                 components['quick_analyze'] = gr.Button("🔍 Analyze Leaderboard", size="sm")
                 components['quick_costs'] = gr.Button("💰 Compare Costs", size="sm")
                 components['quick_recommend'] = gr.Button("🎯 Get Recommendations", size="sm")
 
+                gr.Markdown("**Advanced:**")
+                components['quick_multi_tool'] = gr.Button("🔗 Multi-Tool Analysis", size="sm")
+                components['quick_synthetic'] = gr.Button("🧪 Generate Synthetic Data", size="sm")
+
     return chat_screen, components
 
 
@@ -587,6 +592,8 @@ def on_quick_action(action_type):
     prompts = {
         "analyze": "Analyze the current leaderboard and show me the top performing models with their costs",
         "costs": "Compare the costs of the top 3 models - which one offers the best value?",
-        "recommend": "Based on the leaderboard data, which model would you recommend for a production system that needs both good accuracy and reasonable cost?"
+        "recommend": "Based on the leaderboard data, which model would you recommend for a production system that needs both good accuracy and reasonable cost?",
+        "multi_tool": "Analyze the leaderboard with focus on cost and accuracy, identify the top 2 models, compare them, and estimate the cost of running 500 evaluations on the cheaper one",
+        "synthetic": "Generate a synthetic test dataset with 100 tasks for the food-delivery domain using these tools: search_restaurants, view_menu, place_order, track_delivery, apply_promo, rate_restaurant, contact_driver. Then create a prompt template for the same domain and tools, and push the dataset to MCP-1st-Birthday/smoltrace-food-delivery-tasks-v2"
     }
     return prompts.get(action_type, "")