Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/dd60633f-2c72-42ba-8547-6f2c8cb0fdb0.json
yuanmengqi e433f35c1f feat: 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.
2025-07-16 13:45:34 +00:00

58 lines
1.6 KiB
JSON

{
"id": "dd60633f-2c72-42ba-8547-6f2c8cb0fdb0",
"snapshot": "multiapps",
"instruction": "Please extract all Python code and comments from Karpathy's GPT colab code cells (skip markdown parts), merge into \"gpt_dev_pure_code.py\" in Home directory. Include all Python code and # comments from code cells, but exclude markdown docstrings and file headers.",
"source": "authors",
"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://colab.research.google.com/drive/1JMLa53HDuA-i7ZBmqV7ZnA3c_fvtXnx-?usp=sharing#scrollTo=h5hjCcLDr2WC"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome",
"os",
"writer"
],
"evaluator": {
"func": "compare_python_pure_text",
"result": {
"type": "vm_file",
"path": "/home/user/gpt_dev_pure_code.py",
"dest": "gpt_dev_pure_code.py"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/dd60633f-2c72-42ba-8547-6f2c8cb0fdb0/gpt_dev_pure_code_gold.py",
"dest": "gpt_dev_pure_code_gold.py"
}
},
"proxy": true,
"env_may_change": true,
"fixed_ip": false,
"possibility_of_env_change": "low"
}