Chirag0123 commited on
Commit
5567f49
ยท
1 Parent(s): 35f712a

feat(ui): add comprehensive Quick Start guide to Gradio dashboard

Browse files
Files changed (1) hide show
  1. app.py +33 -0
app.py CHANGED
@@ -539,6 +539,39 @@ with gr.Blocks(title="Codebase Navigation & Repair โ€” OpenEnv v4") as demo:
539
 
540
  with gr.Tabs():
541
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
542
  # โ”€โ”€ Tab 1: Interactive โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
543
  with gr.TabItem("๐ŸŽฎ Interactive"):
544
  with gr.Row():
 
539
 
540
  with gr.Tabs():
541
 
542
+ # โ”€โ”€ Tab 0: Quick Start Guide โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
543
+ with gr.TabItem("๐Ÿ“– Quick Start Guide"):
544
+ gr.Markdown("""
545
+ ### Welcome to Codebase Navigation & Repair โ€” OpenEnv v4
546
+
547
+ This interactive dashboard allows you to experience the environment infrastructure, run simulations, and analyze advanced agent logic.
548
+
549
+ #### ๐Ÿš€ Step-by-Step Evaluation Guide:
550
+
551
+ 1. **Initialize an Episode**
552
+ - Navigate to the **๐Ÿค– Run Agent** tab.
553
+ - Select a task (`task1`, `task2`, or `task3`) and click **"Run Agent"**.
554
+ - *This simulates an AI executing an episode dynamically against the environment and stores the trajectory.*
555
+
556
+ 2. **Trigger Advanced Intelligence Diagnostics (v3/v4 Features)**
557
+ - Go to **๐Ÿงช Causal Probe** and click it to evaluate if the agent truly understood the bug, or if it was just pattern-matching.
558
+ - Go to **๐ŸŽญ Counterfactual** to run mutation tests and analyze the brittleness of the agent's logic.
559
+ - Go to **๐Ÿ“ Confidence** to see if the agent over-explored or submitted too early.
560
+ - Go to **๐Ÿง  Intelligence** to execute failure classification and strategy detection.
561
+
562
+ 3. **Visualize the Thought Process**
563
+ - Head over to the **๐ŸŒ 3D Visualizer** tab.
564
+ - Click **"Load / Refresh Visualizer"**.
565
+ - Using Three.js, this generates a dynamic 3D web of exactly how the agent traversed the repository files (cubes) and tests (prisms).
566
+
567
+ 4. **Experiment Manually**
568
+ - Want to play the game yourself? Go to the **๐ŸŽฎ Interactive** tab.
569
+ - Click **Reset Environment**, then use the dropdowns to `read_file`, `write_file`, and finally `submit` to grade yourself.
570
+
571
+ 5. **REST API / CLI Runner**
572
+ - The entire platform operates out of incredibly fast, natively compliant REST endpoints. Check the **๐Ÿ“– API** tab for standard cURL routing.
573
+ """)
574
+
575
  # โ”€โ”€ Tab 1: Interactive โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
576
  with gr.TabItem("๐ŸŽฎ Interactive"):
577
  with gr.Row():