Files
magnus919_agent-skills/vercel-eve/evals/evals.json
T
Magnus HedemarkGitHubmagnus919 <magnus919>
a617ccaf2d feat: validate eval manifest coverage states (#129)
* feat: validate eval manifest coverage states

* test: create fixture directory explicitly

---------

Co-authored-by: magnus919 <magnus919>
2026-07-24 18:13:32 -04:00

36 lines
1.7 KiB
JSON

{
"schema_version": 1,
"skill_name": "vercel-eve",
"evals": [
{
"id": "self-hosted-durable-agent",
"prompt": "Deploy our Eve agent behind Traefik on a Node VM. It must survive restart and run a nightly schedule.",
"expected_output": "A deployment plan that requires persistent Workflow storage, both proxy prefixes, an explicit sandbox backend, host authentication, schedule execution, and an authenticated session-plus-resume verification path.",
"assertions": [
"Names both /eve/ and /.well-known/workflow/ proxy prefixes",
"Requires persistent workflow state rather than ephemeral container storage",
"Does not treat a health check as sufficient verification"
]
},
{
"id": "direct-provider-without-gateway",
"prompt": "Use Eve on our own server with Anthropic directly. We do not want requests routed through Vercel AI Gateway.",
"expected_output": "Instructions to use an AI SDK Anthropic provider model object and ANTHROPIC_API_KEY rather than a string Gateway model ID.",
"assertions": [
"Distinguishes a direct provider model object from a string model ID",
"Does not claim BYOK bypasses the Gateway",
"Keeps credentials out of source files"
]
},
{
"id": "near-miss-ai-sdk",
"prompt": "Add a ToolLoopAgent to our AI SDK app and make it durable.",
"expected_output": "Routes to an AI SDK-specific workflow rather than treating ToolLoopAgent as an Eve API.",
"assertions": [
"States that ToolLoopAgent belongs to the separate AI SDK API",
"Does not invent an Eve-specific ToolLoopAgent configuration"
]
}
]
}