تعليق وكلاء الويب

instance_display:
  fields:
    - key: steps
      type: web_agent_trace
      label: "Agent Browsing Trace"
      display_options:
        show_overlays: true
        show_filmstrip: true
        show_thought: true
        show_observation: true
        show_element_info: true
        screenshot_max_width: 800
        screenshot_max_height: 600
        filmstrip_size: 80

{
  "id": "trace_001",
  "task_description": "Find and add a blue wool sweater to cart",
  "site": "amazon.com",
  "steps": [
    {
      "step_index": 0,
      "screenshot_url": "screenshots/step_000.png",
      "action_type": "click",
      "element": {
        "tag": "input",
        "text": "Search",
        "bbox": [340, 45, 680, 75]
      },
      "coordinates": {"x": 510, "y": 60},
      "mouse_path": [[200, 300], [350, 200], [510, 60]],
      "thought": "I need to search for blue wool sweaters",
      "observation": "Search box is focused",
      "timestamp": 1.2,
      "viewport": {"width": 1280, "height": 720}
    }
  ]
}

annotation_schemes:
  - annotation_type: radio
    name: step_correctness
    per_step: true
    labels:
      - name: correct
      - name: incorrect
      - name: unnecessary
  - annotation_type: text
    name: step_notes
    per_step: true
    label: "Notes on this step"

instance_display:
  fields:
    - key: browsing_session
      type: web_agent_recorder
      display_options:
        start_url: "https://www.google.com"
        proxy_mode: auto
        record_mouse_path: true
        record_viewport: true
        screenshot_method: server
        max_steps: 50

pip install playwright
playwright install chromium

# Convert from a specific format
python -m potato.trace_converter -i traces.json -f web_agent -o output.jsonl
 
# Auto-detect format
python -m potato.trace_converter -i traces.json --auto-detect -o output.jsonl

task_name: "Web Agent Evaluation"
task_dir: "."
 
data_files:
  - "traces.jsonl"
 
instance_display:
  fields:
    - key: task_description
      type: text
      label: "Task"
    - key: steps
      type: web_agent_trace
      label: "Agent Trace"
      display_options:
        show_overlays: true
        show_filmstrip: true
        show_thought: true
 
annotation_schemes:
  - annotation_type: radio
    name: task_success
    question: "Did the agent complete the task successfully?"
    labels:
      - name: "Yes"
      - name: "Partially"
      - name: "No"
  - annotation_type: radio
    name: step_correctness
    question: "Was this step correct?"
    per_step: true
    labels:
      - name: correct
      - name: incorrect
      - name: unnecessary
  - annotation_type: text
    name: error_description
    question: "Describe any errors in the agent's behavior"
 
output_annotation_dir: "output/"
output_annotation_format: "jsonl"

# Review Mode
python potato/flask_server.py start examples/agent-traces/web-agent-review/config.yaml -p 8000
 
# Creation Mode
python potato/flask_server.py start examples/agent-traces/web-agent-creation/config.yaml -p 8000