majordomo/provider/llamaswap/faceswap_test.go

package llamaswap

import (
	"context"
	"encoding/base64"
	"errors"
	"io"
	"mime"
	"mime/multipart"
	"net/http"
	"net/http/httptest"
	"strings"
	"testing"

	"gitea.stevedudenhoeffer.com/steve/majordomo/imagegen"
	"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)

// parseParts pulls the multipart form a handler received.
func parseParts(t *testing.T, r *http.Request) (files map[string][]byte, fields map[string]string) {
	t.Helper()
	_, params, err := mime.ParseMediaType(r.Header.Get("Content-Type"))
	if err != nil {
		t.Fatalf("content type: %v", err)
	}
	mr := multipart.NewReader(r.Body, params["boundary"])
	files, fields = map[string][]byte{}, map[string]string{}
	for {
		p, err := mr.NextPart()
		if err == io.EOF {
			break
		}
		if err != nil {
			t.Fatalf("next part: %v", err)
		}
		body, _ := io.ReadAll(p)
		if p.FileName() != "" {
			files[p.FormName()] = body
		} else {
			fields[p.FormName()] = string(body)
		}
	}
	return files, fields
}

// TestFaceSwapSendsBothFiles pins the two-file wire shape. A face swap is the
// first endpoint in this provider taking more than one file, so buildMultipart
// grew a sibling; getting the field NAMES wrong would reach the shim as a
// missing-argument 422 rather than anything self-explanatory.
func TestFaceSwapSendsBothFiles(t *testing.T) {
	var gotPath string
	var files map[string][]byte
	var fields map[string]string
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		gotPath = r.URL.Path
		files, fields = parseParts(t, r)
		w.Header().Set("Content-Type", "image/png")
		raw, _ := base64.StdEncoding.DecodeString(onePixelPNG)
		_, _ = w.Write(raw)
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, err := p.FaceSwapModel("faceswap")
	if err != nil {
		t.Fatalf("model: %v", err)
	}
	img := editInit(t)
	res, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img},
		imagegen.WithFaceIndex(2))
	if err != nil {
		t.Fatalf("faceswap: %v", err)
	}
	if len(res.Images) != 1 {
		t.Fatalf("images = %d, want 1", len(res.Images))
	}
	if !strings.HasSuffix(gotPath, "/upstream/faceswap/v1/faceswap") {
		t.Errorf("path = %q", gotPath)
	}
	for _, want := range []string{"target", "source"} {
		if len(files[want]) == 0 {
			t.Errorf("no %q file part — the shim requires both", want)
		}
	}
	if fields["index"] != "2" {
		t.Errorf("index = %q, want 2", fields["index"])
	}
	if _, ok := fields["all"]; ok {
		t.Error("all sent alongside index — the shim ignores index under all=true, so sending both implies a precedence the caller cannot see")
	}
}

// TestFaceSwapAllSuppressesIndex: same reasoning from the other side.
func TestFaceSwapAllSuppressesIndex(t *testing.T) {
	var fields map[string]string
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		_, fields = parseParts(t, r)
		w.Header().Set("Content-Type", "image/png")
		raw, _ := base64.StdEncoding.DecodeString(onePixelPNG)
		_, _ = w.Write(raw)
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	img := editInit(t)
	if _, err := m.FaceSwap(context.Background(),
		imagegen.FaceSwapRequest{Target: img, Source: img, Index: new(int), All: true}); err != nil {
		t.Fatalf("faceswap: %v", err)
	}
	if fields["all"] != "true" {
		t.Errorf("all = %q, want true", fields["all"])
	}
	if _, ok := fields["index"]; ok {
		t.Error("index sent under all=true")
	}
}

// TestFaceSwapRejectsMissingImages: both are required, and the error should
// name which one rather than surfacing a shim 422.
func TestFaceSwapRejectsMissingImages(t *testing.T) {
	p := New(WithBaseURL("http://example.invalid"))
	m, _ := p.FaceSwapModel("faceswap")
	img := editInit(t)
	for _, tc := range []struct {
		name string
		req  imagegen.FaceSwapRequest
		want string
	}{
		{"no target", imagegen.FaceSwapRequest{Source: img}, "target"},
		{"no source", imagegen.FaceSwapRequest{Target: img}, "source"},
	} {
		_, err := m.FaceSwap(context.Background(), tc.req)
		if err == nil || !strings.Contains(err.Error(), tc.want) {
			t.Errorf("%s: err = %v, want one naming %q", tc.name, err, tc.want)
		}
	}
}

// TestFaceSwapRejectsNonImageResponse: the shim answers JSON on a semantic
// miss (no face found). Returning those bytes as an "image" would hand the
// caller a file that is not a picture and call it success.
func TestFaceSwapRejectsNonImageResponse(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
		w.Header().Set("Content-Type", "application/json")
		_, _ = w.Write([]byte(`{"detail":{"error":"no_face_in_source"}}`))
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	img := editInit(t)
	_, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img})
	if err == nil {
		t.Fatal("a JSON body was accepted as an image")
	}
	var apiErr *llm.APIError
	if !errors.As(err, &apiErr) {
		t.Errorf("err = %T, want *llm.APIError so callers can classify it", err)
	}
	if !strings.Contains(err.Error(), "no_face_in_source") {
		t.Errorf("err = %v, want it to relay the shim's reason", err)
	}
}

// TestListFacesParsesOrdering: the shim's left-to-right index is the contract
// callers select against, so it must survive decoding intact.
func TestListFacesParsesOrdering(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		if !strings.HasSuffix(r.URL.Path, "/upstream/faceswap/v1/faces") {
			t.Errorf("path = %q", r.URL.Path)
		}
		w.Header().Set("Content-Type", "application/json")
		_, _ = w.Write([]byte(`{"count":2,"faces":[
			{"index":0,"box":[10,20,30,40],"score":0.9,"width":20,"height":20},
			{"index":1,"box":[50,20,90,60],"score":0.8,"width":40,"height":40}]}`))
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	faces, err := m.ListFaces(context.Background(), editInit(t))
	if err != nil {
		t.Fatalf("list: %v", err)
	}
	if len(faces) != 2 || faces[0].Index != 0 || faces[1].Index != 1 {
		t.Fatalf("faces = %+v", faces)
	}
	if faces[1].Box != [4]int{50, 20, 90, 60} {
		t.Errorf("box = %v", faces[1].Box)
	}
}

// TestListFacesRejectsShortBox: a malformed box would send a caller at the
// wrong face, which is worse than an error.
func TestListFacesRejectsShortBox(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
		w.Header().Set("Content-Type", "application/json")
		_, _ = w.Write([]byte(`{"count":1,"faces":[{"index":0,"box":[1,2],"score":0.9}]}`))
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	if _, err := m.ListFaces(context.Background(), editInit(t)); err == nil {
		t.Fatal("a 2-element box was accepted")
	}
}

// TestFaceSwapRejectsHeaderlessNonImage is the regression for gadfly's
// blocking finding on #23, agreed by both models. sniffImageMIME falls back
// to image/png when detection is inconclusive, and the original guard only
// looked at Content-Type — so a JSON error body sent WITHOUT a Content-Type
// header was labelled a PNG and returned as a successful image. The shim
// answers JSON on a semantic miss, which is precisely the body that would
// have sailed through.
func TestFaceSwapRejectsHeaderlessNonImage(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
		// Explicitly no Content-Type — Go only sets one if we write before
		// deleting it, so clear it to model a bare upstream response.
		w.Header()["Content-Type"] = nil
		_, _ = w.Write([]byte(`{"detail":{"error":"no_face_in_target"}}`))
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	img := editInit(t)
	_, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img})
	if err == nil {
		t.Fatal("a headerless JSON body was accepted and would have been returned as image/png")
	}
	if !strings.Contains(err.Error(), "no_face_in_target") {
		t.Errorf("err = %v, want it to relay what actually came back", err)
	}
}

// TestFaceSwapAllowsNegativeIndexUnderAll: index is documented as ignored
// when all=true, so validating it there would reject a well-formed request.
func TestFaceSwapAllowsNegativeIndexUnderAll(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
		w.Header().Set("Content-Type", "image/png")
		raw, _ := base64.StdEncoding.DecodeString(onePixelPNG)
		_, _ = w.Write(raw)
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, _ := p.FaceSwapModel("faceswap")
	img := editInit(t)
	neg := -1
	if _, err := m.FaceSwap(context.Background(),
		imagegen.FaceSwapRequest{Target: img, Source: img, Index: &neg, All: true}); err != nil {
		t.Fatalf("negative index rejected under all=true, where it is ignored: %v", err)
	}
	// ...but still rejected when it WOULD be sent.
	if _, err := m.FaceSwap(context.Background(),
		imagegen.FaceSwapRequest{Target: img, Source: img, Index: &neg}); err == nil {
		t.Error("negative index accepted when it would actually be sent")
	}
}

// TestFaceSwapParsesSwapReport: the measured outcome is the whole reason the
// header exists — a caller that cannot tell "the likeness transferred" from
// "an image came back" goes and asks a vision model, which is wrong in
// exactly the cases that matter.
func TestFaceSwapParsesSwapReport(t *testing.T) {
	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
		w.Header().Set("Content-Type", "image/png")
		w.Header().Set("X-Swap-Report",
			`{"image":[1010,1200],"faces":[{"index":2,"size":[138,172],"yaw":-82.2,"identity_similarity":0.791}]}`)
		raw, _ := base64.StdEncoding.DecodeString(onePixelPNG)
		_, _ = w.Write(raw)
	}))
	defer srv.Close()

	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
	m, err := p.FaceSwapModel("faceswap")
	if err != nil {
		t.Fatalf("model: %v", err)
	}
	img := editInit(t)
	res, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img})
	if err != nil {
		t.Fatalf("FaceSwap: %v", err)
	}
	if len(res.SwappedFaces) != 1 {
		t.Fatalf("SwappedFaces = %d, want 1 — the measurement was dropped", len(res.SwappedFaces))
	}
	f := res.SwappedFaces[0]
	if f.Index != 2 || f.Width != 138 || f.Height != 172 {
		t.Errorf("face = %+v, want index 2 at 138x172", f)
	}
	if f.Yaw == nil || *f.Yaw != -82.2 {
		t.Errorf("yaw = %v, want -82.2 — the pose signal is how a caller knows a profile swap will not read", f.Yaw)
	}
	if f.IdentitySimilarity == nil || *f.IdentitySimilarity != 0.791 {
		t.Errorf("identity_similarity = %v, want 0.791", f.IdentitySimilarity)
	}
	// 138/1010 — the number that says "correct, and invisible at a glance".
	if got := f.FractionOfImage(); got < 0.13 || got > 0.14 {
		t.Errorf("FractionOfImage = %.3f, want ~0.137", got)
	}
}

// TestFaceSwapSurvivesMissingReport: an older shim sends no header at all. A
// swap that produced a good image must not fail because the diagnostics
// beside it were absent or malformed.
func TestFaceSwapSurvivesMissingReport(t *testing.T) {
	for name, hdr := range map[string]string{
		"absent":    "",
		"garbage":   "not json at all",
		"wrongtype": `{"faces":"nope"}`,
	} {
		t.Run(name, func(t *testing.T) {
			srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
				w.Header().Set("Content-Type", "image/png")
				if hdr != "" {
					w.Header().Set("X-Swap-Report", hdr)
				}
				raw, _ := base64.StdEncoding.DecodeString(onePixelPNG)
				_, _ = w.Write(raw)
			}))
			defer srv.Close()

			p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
			m, err := p.FaceSwapModel("faceswap")
			if err != nil {
				t.Fatalf("model: %v", err)
			}
			img := editInit(t)
			res, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img})
			if err != nil {
				t.Fatalf("a %s report failed the whole swap: %v", name, err)
			}
			if len(res.Images) != 1 {
				t.Fatal("image lost")
			}
			if res.SwappedFaces != nil {
				t.Errorf("SwappedFaces = %+v, want nil for a %s report", res.SwappedFaces, name)
			}
		})
	}
}