mirrored 15 minutes ago
0
yuanmengqifeat: standardize configuration fields across all evaluation examples - Add `fixed_ip` field to all 369 JSON files in examples directory - Set to `true` for 8 files listed in google_chrome.json multi_apps - Set to `false` for remaining 361 files - Add `possibility_of_env_change` field to 363 JSON files missing this field - Set to "low" for newly added fields - Preserve existing values (4 medium, 2 high) for 6 files that already had this field This ensures consistent configuration schema across all evaluation examples while maintaining backward compatibility with existing settings. e433f35
{
  "id": "e1e75309-3ddb-4d09-92ec-de869c928143",
  "snapshot": "chrome",
  "instruction": "Computer, can you turn the webpage I'm looking at into a PDF file, save it to my Desktop with the default filename and set the margins to none?",
  "source": "https://in5stepstutorials.com/google-chrome/save-web-page-as-pdf-in-chrome.php",
  "config": [
    {
      "type": "launch",
      "parameters": {
        "command": [
          "google-chrome",
          "--remote-debugging-port=1337"
        ]
      }
    },
    {
      "type": "launch",
      "parameters": {
        "command": [
          "socat",
          "tcp-listen:9222,fork",
          "tcp:localhost:1337"
        ]
      }
    },
    {
      "type": "chrome_open_tabs",
      "parameters": {
        "urls_to_open": [
          "https://lilianweng.github.io/posts/2023-06-23-agent/"
        ]
      }
    }
  ],
  "trajectory": "trajectories/",
  "related_apps": [
    "chrome"
  ],
  "evaluator": {
    "func": "compare_pdfs",
    "result": {
      "type": "vm_file",
      "path": "/home/user/Desktop/LLM Powered Autonomous Agents _ Lil'Log.pdf",
      "dest": "LLM Powered Autonomous Agents _ Lil'Log.pdf"
    },
    "expected": {
      "type": "pdf_from_url",
      "path": "https://lilianweng.github.io/posts/2023-06-23-agent/",
      "dest": "LLM Powered Autonomous Agents _ Lil'Log_gold.pdf"
    }
  },
  "proxy": true,
  "fixed_ip": false,
  "possibility_of_env_change": "low"
}