Testing and evaluation

package agent_test

import (
    "context"
    "testing"

    "github.com/hastekit/agent-sdk-go/pkg/agents"
    "github.com/hastekit/agent-sdk-go/pkg/gateway/llm/constants"
    "github.com/hastekit/agent-sdk-go/pkg/gateway/llm/responses"
)

type fixedLLM struct{}

func (fixedLLM) NewStreamingResponses(context.Context, *agents.ModelCall,
    *responses.Request, func(*responses.ResponseChunk)) (*responses.Response, error) {
    return &responses.Response{Output: []responses.OutputMessageUnion{{
        OfOutputMessage: &responses.OutputMessage{
            ID: "answer", Role: constants.RoleAssistant,
            Content: &responses.OutputContent{{
                OfOutputText: &responses.OutputTextContent{Text: "Hello"},
            }},
        },
    }}}, nil
}

func TestAnswer(t *testing.T) {
    agent := agents.NewAgent(&agents.AgentOptions{Name: "test"}).WithLLM(fixedLLM{})
    result, err := agent.Run(t.Context(), &agents.AgentInput{})
    if err != nil { t.Fatal(err) }
    if result.Text() != "Hello" { t.Fatalf("unexpected answer: %q", result.Text()) }
}

runner := eval.Runner{
    Agent: eval.Fixed(agent),
    Scorers: []eval.Scorer{eval.Contains{}, eval.ToolTrajectory{Ordered: true}},
    Threshold: 1,
}
report, err := runner.Run(ctx, []eval.Case{{
    Name: "order-status",
    Turns: []string{"What is the status of order 42?"},
    Expect: eval.Expect{Text: "shipped", Tools: []string{"lookup_order"}},
}})
if err != nil { return err }
fmt.Println(report)
if report.Failed() > 0 { return fmt.Errorf("agent evaluation failed") }