liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
64 lines
2.3 KiB
JSON
64 lines
2.3 KiB
JSON
{
|
|
"schema_version": 1,
|
|
"experiment": "6-8",
|
|
"acceptance_scope": "provider-portable-computer-use-trajectory",
|
|
"status": "complete",
|
|
"started_at": "2026-08-01T03:11:50.348098+00:00",
|
|
"ended_at": "2026-08-01T03:14:24.560745+00:00",
|
|
"api": {
|
|
"api_protocol": "openai-compatible-chat-completions",
|
|
"api_key_env": "OPENROUTER_API_KEY",
|
|
"base_url": "https://openrouter.ai/api/v1",
|
|
"requested_model": "qwen/qwen3-vl-32b-instruct",
|
|
"schema_mode": "native"
|
|
},
|
|
"provider_models_reported": [
|
|
"qwen/qwen3-vl-32b-instruct"
|
|
],
|
|
"browser_use_version": "0.9.5",
|
|
"task": "Open Google, search for San Francisco weather today, and report the temperature and conditions. Do not sign in or change any external data.",
|
|
"max_steps": 25,
|
|
"steps_executed": 16,
|
|
"agent_reported_success": true,
|
|
"final_result": "The current weather in San Francisco is 64°F, with conditions described as 'Sunny'. The temperature feels like 62°F, with a high of 74°F and a low of 55°F for the day. There is a 3% chance of rain and 0 inches of precipitation expected. This information was retrieved from weather.com after successfully navigating to the correct location and selecting today's forecast.",
|
|
"urls": [
|
|
"about:blank",
|
|
"https://www.google.com/",
|
|
"https://www.google.com/",
|
|
"https://www.google.com/",
|
|
"https://www.google.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/",
|
|
"https://weather.com/us/california/city/san-francisco/tenday",
|
|
"https://weather.com/us/california/city/san-francisco/tenday",
|
|
"https://weather.com/us/california/city/san-francisco/today",
|
|
"https://weather.com/us/california/city/san-francisco/today"
|
|
],
|
|
"errors": [
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
null,
|
|
"Failed to click element <div index=9207>. The element may not be interactable or visible. If the page changed after navigation/interaction, the index [9207] may be stale. Get fresh browser state before retrying.",
|
|
null,
|
|
null,
|
|
null,
|
|
null
|
|
],
|
|
"screenshots_retained": 15,
|
|
"credential_retained": false,
|
|
"qualification": "This is a separate open-model arm, not an Anthropic-equivalent result."
|
|
}
|