Files
BrowserOS/packages/browseros-agent/apps/eval/configs/test_gemini-computer-use.json
shivammittal274 65547c60c0 fix(eval): clean up eval configs and add test-clado-api script (#540)
Consolidate 13 configs down to 7 with uniform settings:
- 3 weekly (CI): browseros-agent, browseros-oe-agent, browseros-oe-clado
- 4 test (local): test_gemini-computer-use, test_yutori-navigator, test_webvoyager, test_mind2web
- All configs: headless=false, captcha block, full browseros ports, restart_server_per_task

Deleted: debug-test, mind2web-test, tool-loop-test, orchestrator-executor-test,
orchestrator-executor-clado-test, fireworks-minimax-m2, webvoyager-test

Added: test-clado-api.ts script, browseros-oe-agent-weekly.json (OE with AI SDK executor)
2026-03-24 01:28:05 +05:30

31 lines
735 B
JSON
Vendored

{
"agent": {
"type": "gemini-computer-use",
"apiKey": "GOOGLE_AI_API_KEY",
"screenSize": {
"width": 1440,
"height": 900
},
"turnLimit": 100
},
"dataset": "../data/test-set.jsonl",
"num_workers": 1,
"restart_server_per_task": true,
"browseros": {
"server_url": "http://127.0.0.1:9110",
"base_cdp_port": 9010,
"base_server_port": 9110,
"base_extension_port": 9310,
"load_extensions": false,
"headless": false
},
"captcha": {
"api_key_env": "NOPECHA_API_KEY"
},
"graders": ["performance_grader"],
"grader_api_key_env": "OPENROUTER_API_KEY",
"grader_base_url": "https://openrouter.ai/api/v1",
"grader_model": "openai/gpt-4.1",
"timeout_ms": 1200000
}