fix(llamaswap): a headerless non-image response was returned as a PNG
CI / Tidy (pull_request) Successful in 9m26s
CI / Build & Test (pull_request) Successful in 10m4s

Gadfly on #23, blocking, 2/2 agreement — and it is the exact defect this
whole line of work has been about: a call that succeeds while handing back
the wrong bytes.

sniffImageMIME falls back to image/png when detection is inconclusive, and
the guard only consulted Content-Type. A response with NO Content-Type
therefore skipped the check entirely and was labelled a PNG. The shim answers
JSON on a semantic miss (no face found in the source or target), which is
precisely the body that would have sailed through as a successful image.

The check now validates the BYTES — http.DetectContentType must say image/ —
and the reported MIME prefers the server's own label only when that label is
itself an image type. Break-checked by restoring the header-only condition,
which fails the new test.

Also from that review:
  - index is documented as ignored under all=true, so a negative one is no
    longer rejected there; it is still rejected when it would actually be
    sent, and both halves are tested.
  - initImageFilename (video.go) was imageFilename with the base fixed to
    "frame" and now delegates to it — two copies of one extension table is
    how they drift.
  - DetectedFace carried Width/Height alongside Box, two sources of truth for
    one fact that can disagree after any transform. Now a Size() method
    derived from Box.
  - a dead `apiErr` in the test (declared, then `_ = apiErr`) was an
    abandoned errors.As check; it is wired up and now asserts callers can
    classify the error.
  - swapImg duplicated editInit verbatim; removed.

Not taken: adding a FaceSwapProvider/ModelOption surface to match the other
optional imagegen capabilities (single-model finding). There are no options
to carry yet, and inventing an empty option type to look symmetrical would be
API surface with nothing behind it. Worth revisiting when a real knob exists.
This commit is contained in:
2026-07-31 12:34:58 -04:00
parent 0ff90d80f6
commit 372bf826aa
4 changed files with 96 additions and 47 deletions
+63 -16
View File
@@ -3,6 +3,7 @@ package llamaswap
import (
"context"
"encoding/base64"
"errors"
"io"
"mime"
"mime/multipart"
@@ -15,15 +16,6 @@ import (
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)
func swapImg(t *testing.T) imagegen.Image {
t.Helper()
raw, err := base64.StdEncoding.DecodeString(onePixelPNG)
if err != nil {
t.Fatalf("decode fixture: %v", err)
}
return imagegen.Image{MIME: "image/png", Data: raw}
}
// 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()
@@ -73,7 +65,7 @@ func TestFaceSwapSendsBothFiles(t *testing.T) {
if err != nil {
t.Fatalf("model: %v", err)
}
img := swapImg(t)
img := editInit(t)
res, err := m.FaceSwap(context.Background(), imagegen.FaceSwapRequest{Target: img, Source: img},
imagegen.WithFaceIndex(2))
if err != nil {
@@ -111,7 +103,7 @@ func TestFaceSwapAllSuppressesIndex(t *testing.T) {
p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
m, _ := p.FaceSwapModel("faceswap")
img := swapImg(t)
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)
@@ -129,7 +121,7 @@ func TestFaceSwapAllSuppressesIndex(t *testing.T) {
func TestFaceSwapRejectsMissingImages(t *testing.T) {
p := New(WithBaseURL("http://example.invalid"))
m, _ := p.FaceSwapModel("faceswap")
img := swapImg(t)
img := editInit(t)
for _, tc := range []struct {
name string
req imagegen.FaceSwapRequest
@@ -157,16 +149,18 @@ func TestFaceSwapRejectsNonImageResponse(t *testing.T) {
p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
m, _ := p.FaceSwapModel("faceswap")
img := swapImg(t)
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)
}
_ = apiErr
}
// TestListFacesParsesOrdering: the shim's left-to-right index is the contract
@@ -185,7 +179,7 @@ func TestListFacesParsesOrdering(t *testing.T) {
p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
m, _ := p.FaceSwapModel("faceswap")
faces, err := m.ListFaces(context.Background(), swapImg(t))
faces, err := m.ListFaces(context.Background(), editInit(t))
if err != nil {
t.Fatalf("list: %v", err)
}
@@ -208,7 +202,60 @@ func TestListFacesRejectsShortBox(t *testing.T) {
p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
m, _ := p.FaceSwapModel("faceswap")
if _, err := m.ListFaces(context.Background(), swapImg(t)); err == nil {
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")
}
}