pansy/internal/vision/vision_test.go

package vision

import (
	"bytes"
	"context"
	"image"
	"image/jpeg"
	"testing"

	"gitea.stevedudenhoeffer.com/steve/majordomo"
	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
	"gitea.stevedudenhoeffer.com/steve/majordomo/provider/fake"
)

// tinyJPEG returns a real, sniffable JPEG. The chain runs media.Normalize before
// the provider, which checks the image's magic bytes, so a string literal won't
// do — the bytes must actually be a JPEG.
func tinyJPEG(t *testing.T) []byte {
	t.Helper()
	var b bytes.Buffer
	if err := jpeg.Encode(&b, image.NewRGBA(image.Rect(0, 0, 8, 8)), nil); err != nil {
		t.Fatalf("encode jpeg: %v", err)
	}
	return b.Bytes()
}

// extractVia is Extract with a caller-supplied registry, so the test can point it
// at a fake provider instead of resolving a live model. It mirrors Extract's body
// exactly apart from where the model comes from.
func extractVia(t *testing.T, m llm.Model, jpeg []byte) (SeedPacket, error) {
	t.Helper()
	return majordomo.Generate[SeedPacket](context.Background(), m, majordomo.Request{
		Messages: []majordomo.Message{
			majordomo.UserParts(majordomo.Text(extractPrompt), majordomo.Image("image/jpeg", jpeg)),
		},
	})
}

// TestExtractParsesModelJSON is the hermetic proof that the extraction path works
// end to end without a live model: a fake vision model returns canned packet JSON
// and Generate[SeedPacket] unmarshals it into the struct, image and schema
// included.
func TestExtractParsesModelJSON(t *testing.T) {
	reg := majordomo.New(majordomo.WithoutEnvProviders())
	fp := fake.New("fp") // default caps advertise structured output + images
	reg.RegisterProvider(fp)
	fp.Enqueue("vision", fake.Reply(`{
		"species": "garlic",
		"variety": "Music",
		"category": "vegetable",
		"vendor": "Johnny's",
		"sku": "2761",
		"lotCode": "L-42",
		"packedForYear": 2026,
		"daysToMaturity": 240,
		"spacingCm": 15,
		"seedCount": 8
	}`))

	m, err := reg.Parse("fp/vision")
	if err != nil {
		t.Fatalf("parse: %v", err)
	}

	got, err := extractVia(t, m, tinyJPEG(t))
	if err != nil {
		t.Fatalf("extract: %v", err)
	}
	if got.Variety != "Music" || got.Species != "garlic" || got.Category != "vegetable" {
		t.Errorf("unexpected packet: %+v", got)
	}
	if got.SpacingCM == nil || *got.SpacingCM != 15 {
		t.Errorf("spacingCm = %v, want 15", got.SpacingCM)
	}
	if got.PackedForYear == nil || *got.PackedForYear != 2026 {
		t.Errorf("packedForYear = %v, want 2026", got.PackedForYear)
	}

	// The image and the derived schema really reached the model.
	call := fp.Calls()[0]
	if call.Request.SchemaName != "seedpacket" {
		t.Errorf("schema name = %q, want seedpacket", call.Request.SchemaName)
	}
	var sawImage bool
	for _, p := range call.Request.Messages[0].Parts {
		if _, ok := p.(llm.ImagePart); ok {
			sawImage = true
		}
	}
	if !sawImage {
		t.Error("the image part didn't reach the model")
	}
}

// TestExtractLeavesMissingFieldsNil: a packet that only prints a species comes
// back with nil pointers for the numbers, not invented zeros — the whole reason
// the numeric fields are pointers.
func TestExtractLeavesMissingFieldsNil(t *testing.T) {
	reg := majordomo.New(majordomo.WithoutEnvProviders())
	fp := fake.New("fp")
	reg.RegisterProvider(fp)
	fp.Enqueue("vision", fake.Reply(`{"species":"basil","category":"herb"}`))
	m, _ := reg.Parse("fp/vision")

	got, err := extractVia(t, m, tinyJPEG(t))
	if err != nil {
		t.Fatalf("extract: %v", err)
	}
	if got.SpacingCM != nil || got.DaysToMaturity != nil || got.PackedForYear != nil || got.SeedCount != nil {
		t.Errorf("missing numeric fields should be nil, got %+v", got)
	}
}

// TestExtractRejectsEmptyImage: no bytes, no call.
func TestExtractRejectsEmptyImage(t *testing.T) {
	if _, err := Extract(context.Background(), "k", "fp/vision", nil); err == nil {
		t.Error("Extract accepted an empty image")
	}
}