Go

Add Bench using https://docs.usebench.ai/sdk/go and my Bench SDK setup prompt.
Use the install command on this page, plus my API endpoint and server-side key. Start with
metadata-only capture in staging. Wrap a real request and its tools with
bench.Trace and propagate the returned context. Flush a synthetic interaction,
confirm receipt in Bench, and show changed files and remaining setup steps.

go get github.com/trybench/bench-sdk/go@v0.2.3

package main

import (
    "context"
    "log"
    "os"

    bench "github.com/trybench/bench-sdk/go"
)

func main() {
    client, err := bench.New(bench.Options{
        APIKey: os.Getenv("BENCH_API_KEY"),
        Repository: os.Getenv("BENCH_REPOSITORY"),
        Branch: os.Getenv("BENCH_BRANCH"),
        Endpoint: os.Getenv("BENCH_API_BASE_URL"),
        SystemName: "Support agent",
        Environment: "staging",
    })
    if err != nil { log.Fatal(err) }
    ctx := context.Background()
    _, err = bench.Trace(ctx, client,
        bench.SpanInput{Name: "connection-check", Kind: "AGENT"},
        func(context.Context) (bool, error) { return true, nil },
    )
    client.Shutdown(ctx)
    if err != nil { log.Fatal(err) }
}

report, err := client.EvaluateSystem(ctx, bench.SystemEvaluationOptions{
    SourceRevision: os.Getenv("GIT_COMMIT_SHA"), // Full 40-character commit SHA
    ContextRevision: "refund-policy-v1",
    Cases: []bench.SystemCase{{
        ID: "outside-refund-policy", Split: "regression",
        Input: map[string]any{"days": 45},
        ExpectedOutput: bench.Expect(map[string]any{"refunded": false}),
        ForbiddenTools: []string{"issue-refund"},
    }},
    Run: handleRequest, // func(context.Context, any) (any, error)
})
if err != nil { return err }
if !report.Passed() { return fmt.Errorf("application checks failed or are incomplete") }
// Explicit upload when desired:
err = client.PublishSystemEvaluation(ctx, systemID, report)