n8n/packages/@n8n/instance-ai/evaluations/computer-use/data/4.1-authenticated-api-docs.json
Bernhard Wittmann b445221c6a
feat: Computer-use evaluation harness (no-changelog) (#29797)
Co-authored-by: Elias Meire <elias@meire.dev>
2026-05-12 08:36:12 +00:00

35 lines
1.3 KiB
JSON
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"id": "4.1-authenticated-api-docs",
"category": "browser",
"prompt": "I want to set up an n8n HTTP Request node to query Linear's API. Open Linear's API settings page in my browser (https://linear.app/settings/account/api) — I'm already logged in there — and tell me: what API endpoint URL Linear uses for its GraphQL API, what auth header n8n's HTTP Request node will need, and roughly how many personal API keys are currently shown on the page. Don't copy or echo any actual key value back to me; just describe what the page shows.",
"budgets": { "maxToolCalls": 40, "maxDurationMs": 600000 },
"graders": [
{ "type": "trace.mustCallMcpServer", "server": "computer-use" },
{ "type": "trace.mustCallTool", "name": "browser_navigate" },
{ "type": "trace.mustNotLoop", "maxRepeatedCall": 4 },
{
"type": "trace.budget",
"maxToolCalls": 40,
"maxToolResultTokensEst": 200000,
"maxSingleToolResultTokensEst": 50000
},
{
"type": "trace.finalTextMatches",
"anyOf": ["api key|graphql|authorization|endpoint"],
"mustNotMatch": [
"taking a while",
"let me try (a )?different",
"couldn[']t (load|connect|reach)",
"timed? out",
"unable to (load|access|reach)"
]
}
],
"tags": [
"browser",
"research",
"requires:browser-bootstrap",
"requires:third-party-account:linear"
]
}