imagegen/background.go

@@ -15,9 +15,9 @@ type BackgroundRemovalRequest struct {
 	Net string
 
 	// OnlyMask returns the black/white segmentation mask instead of the
-	// cutout — white where the subject is. Useful as an inpainting mask
-	// (EditRequest.Mask semantics after inversion: the mask marks the
-	// FOREGROUND, an inpaint mask marks the region to REPAINT).
+	// cutout — WHITE marks the SUBJECT. To inpaint (repaint) the subject,
+	// use it directly as EditRequest.Mask; to repaint the BACKGROUND,
+	// invert it first (EditRequest.Mask is white-means-repaint).
 	OnlyMask bool
 }
 

provider/llamaswap/audio.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"io"
 	"mime"
-	"mime/multipart"
 	"net/http"
 	"net/url"
 	"strings"
@@ -119,28 +118,19 @@ func (m *transcriptionModel) Transcribe(ctx context.Context, req audio.Transcrip
 		return nil, fmt.Errorf("%w: transcription requires audio bytes", llm.ErrUnsupported)
 	}
 
-	var buf bytes.Buffer
-	w := multipart.NewWriter(&buf)
-	fw, err := w.CreateFormFile("file", transcriptionFilename(req))
+	buf, formType, err := buildMultipart("build transcription form",
+		filePart{field: "file", filename: transcriptionFilename(req.Filename, req.MIME), data: req.Audio},
+		[]formField{
+			{"model", m.id, true},
+			{"response_format", "json", true},
+			{"language", req.Language, false},
+			{"prompt", req.Prompt, false},
+		})
 	if err != nil {
-		return nil, fmt.Errorf("llama-swap: build transcription form: %w", err)
-	}
-	if _, err := fw.Write(req.Audio); err != nil {
-		return nil, fmt.Errorf("llama-swap: build transcription form: %w", err)
-	}
-	if err := writeFormFields(w, "build transcription form", []formField{
-		{"model", m.id, true},
-		{"response_format", "json", true},
-		{"language", req.Language, false},
-		{"prompt", req.Prompt, false},
-	}); err != nil {
 		return nil, err
 	}
-	if err := w.Close(); err != nil {
-		return nil, fmt.Errorf("llama-swap: build transcription form: %w", err)
-	}
 
-	raw, _, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/transcriptions", m.id, w.FormDataContentType(), &buf, maxResponseBytes)
+	raw, _, err := m.p.doRaw(ctx, http.MethodPost, "/v1/audio/transcriptions", m.id, formType, buf, maxResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -158,11 +148,11 @@ func (m *transcriptionModel) Transcribe(ctx context.Context, req audio.Transcrip
 // headers), else one derived from the MIME subtype ("audio.mp3"), else
 // "audio". MIME parameters ("audio/ogg; codecs=opus") are stripped before
 // matching.
-func transcriptionFilename(req audio.TranscriptionRequest) string {
-	if name := sanitizeFilename(req.Filename); name != "" {
+func transcriptionFilename(filename, mimeType string) string {
+	if name := sanitizeFilename(filename); name != "" {
 		return name
 	}
-	mt := strings.ToLower(strings.TrimSpace(req.MIME))
+	mt := strings.ToLower(strings.TrimSpace(mimeType))
 	if parsed, _, err := mime.ParseMediaType(mt); err == nil {
 		mt = parsed
 	}

provider/llamaswap/diarize.go

@@ -79,7 +79,7 @@ func (m *diarizationModel) Diarize(ctx context.Context, req audio.DiarizationReq
 	}
 
 	body, contentType, err := buildMultipart("build diarization form",
-		filePart{field: "audio_file", filename: diarizationFilename(req), data: req.Audio},
+		filePart{field: "audio_file", filename: transcriptionFilename(req.Filename, req.MIME), data: req.Audio},
 		nil)
 	if err != nil {
 		return nil, err
@@ -111,12 +111,3 @@ func (m *diarizationModel) Diarize(ctx context.Context, req audio.DiarizationReq
 	}
 	return res, nil
 }
-
-// diarizationFilename mirrors transcriptionFilename for the diarization
-// request shape (same untrusted-metadata sanitization rules).
-func diarizationFilename(req audio.DiarizationRequest) string {
-	return transcriptionFilename(audio.TranscriptionRequest{
-		Filename: req.Filename,
-		MIME:     req.MIME,
-	})
-}

provider/llamaswap/mediautil.go

@@ -22,6 +22,12 @@ import (
 	"gitea.stevedudenhoeffer.com/steve/majordomo/videogen"
 )
 
+// maxImageResponseBytes caps the raw-image bodies from the upscale and
+// background-removal endpoints. The 64MB maxResponseBytes is a JSON cap;
+// a 4x-upscaled PNG legitimately exceeds it. Bounded (not video-sized)
+// because a single still image past this is an upstream bug, not data.
+const maxImageResponseBytes = 256 << 20
+
 // --- upscale ---
 
 // UpscaleModel implements imagegen.UpscaleProvider against the mediautils
@@ -62,7 +68,7 @@ func (m *upscaleModel) Upscale(ctx context.Context, req imagegen.UpscaleRequest,
 	if err != nil {
 		return nil, err
 	}
-	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxResponseBytes)
+	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxImageResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -112,23 +118,31 @@ func (m *backgroundModel) RemoveBackground(ctx context.Context, req imagegen.Bac
 	if err != nil {
 		return nil, err
 	}
-	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxResponseBytes)
+	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxImageResponseBytes)
 	if err != nil {
 		return nil, err
 	}
 	return singleImageResult(m.p.name, m.id, "background removal", raw, respType)
 }
 
-// singleImageResult wraps one raw image body into an imagegen.Result,
-// rejecting empty or non-image payloads (a proxy error page must not become
-// "the image").
+// singleImageResult wraps one raw image body into an imagegen.Result.
+// Acceptance requires positive evidence of image-ness — sniffed magic
+// bytes or a declared image/* Content-Type — so a proxy error page with
+// an empty Content-Type can never become "the image" (sniffImageMIME's
+// PNG default is a labelling fallback, not a validator).
 func singleImageResult(provider, model, verb string, raw []byte, contentType string) (*imagegen.Result, error) {
 	if len(raw) == 0 {
 		return nil, &llm.APIError{Provider: provider, Model: model, Message: verb + " response contained no image"}
 	}
-	mimeType := sniffImageMIME(raw)
-	if ct := strings.TrimSpace(contentType); ct != "" && !strings.HasPrefix(ct, "image/") && !strings.HasPrefix(http.DetectContentType(raw), "image/") {
-		return nil, &llm.APIError{Provider: provider, Model: model, Message: fmt.Sprintf("%s response is not an image (Content-Type %q)", verb, ct)}
+	sniffed := http.DetectContentType(raw)
+	declared := strings.TrimSpace(contentType)
+	if !strings.HasPrefix(sniffed, "image/") && !strings.HasPrefix(declared, "image/") {
+		return nil, &llm.APIError{Provider: provider, Model: model,
+			Message: fmt.Sprintf("%s response is not an image (Content-Type %q, sniffed %q)", verb, declared, sniffed)}
+	}
+	mimeType := sniffed
+	if !strings.HasPrefix(mimeType, "image/") {
+		mimeType = declared
 	}
 	return &imagegen.Result{Images: []llm.ImagePart{{MIME: mimeType, Data: raw}}}, nil
 }

provider/llamaswap/mediautil_test.go

@@ -251,3 +251,32 @@ func TestUpstreamPathRejectsSeparators(t *testing.T) {
 		t.Errorf("path prefix wrong: %q", got)
 	}
 }
+
+func TestUpscaleRejectsEmptyContentTypeNonImage(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header()["Content-Type"] = nil // suppress auto-detection: NO Content-Type at all
+		_, _ = w.Write([]byte("502 bad gateway"))
+	}))
+	defer srv.Close()
+
+	p := New(WithBaseURL(srv.URL), WithHTTPClient(srv.Client()))
+	up, _ := p.UpscaleModel("mediautils")
+	_, err := up.Upscale(context.Background(),
+		imagegen.UpscaleRequest{Image: imagegen.Image{Data: pngFixture(t)}})
+	var apiErr *llm.APIError
+	if !errors.As(err, &apiErr) {
+		t.Fatalf("err = %v, want APIError for headerless non-image body", err)
+	}
+}
+
+func TestUpstreamPathRejectsDotDot(t *testing.T) {
+	if _, err := upstreamPath("..", "/x"); err == nil {
+		t.Error("model '..' accepted")
+	}
+	if _, err := upstreamPath("m", "/v1/audio?path=../../api/models/unload"); err == nil {
+		t.Error("dot-dot rest accepted")
+	}
+	if _, err := upstreamPath("m", "/v1/audio?path=https://evil.example/x"); err == nil {
+		t.Error("absolute-URL rest accepted")
+	}
+}

provider/llamaswap/mesh.go

@@ -102,7 +102,7 @@ func (m *meshModel) Generate(ctx context.Context, req meshgen.Request, opts ...m
 	if err != nil {
 		return nil, fmt.Errorf("llama-swap: encode mesh request: %w", err)
 	}
-	raw, _, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, "application/json", bytes.NewReader(encoded), maxMeshResponseBytes)
+	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, "application/json", bytes.NewReader(encoded), maxMeshResponseBytes)
 	if err != nil {
 		return nil, err
 	}
@@ -110,8 +110,16 @@ func (m *meshModel) Generate(ctx context.Context, req meshgen.Request, opts ...m
 		return nil, &llm.APIError{Provider: m.p.name, Model: m.id, Message: "mesh response contained no data"}
 	}
 	// A JSON body on the success path is the server reporting a soft error
-	// (or an API drift) — never hand it back as "the mesh".
-	if first := strings.TrimLeft(string(raw[:min(len(raw), 64)]), " \t\r\n"); strings.HasPrefix(first, "{") || strings.HasPrefix(first, "[") {
+	// (or an API drift) — never hand it back as "the mesh". Two signals:
+	// the declared Content-Type, and a whitespace-tolerant peek at the
+	// leading bytes (512 covers any indented error envelope; a binary STL
+	// header theoretically CAN start with '{', but a real one also won't
+	// be all-whitespace-then-brace).
+	if strings.Contains(strings.ToLower(respType), "application/json") {
+		return nil, &llm.APIError{Provider: m.p.name, Model: m.id,
+			Message: "mesh response is JSON, not mesh bytes: " + truncateForError(raw)}
+	}
+	if first := strings.TrimLeft(string(raw[:min(len(raw), 512)]), " \t\r\n"); strings.HasPrefix(first, "{") || strings.HasPrefix(first, "[") {
 		return nil, &llm.APIError{Provider: m.p.name, Model: m.id,
 			Message: "mesh response is JSON, not mesh bytes: " + truncateForError(raw)}
 	}
@@ -120,9 +128,9 @@ func (m *meshModel) Generate(ctx context.Context, req meshgen.Request, opts ...m
 
 // truncateForError bounds a payload quoted into an error message.
 func truncateForError(b []byte) string {
-	const cap = 500
-	if len(b) > cap {
-		return string(b[:cap]) + "..."
+	const maxErrLen = 500
+	if len(b) > maxErrLen {
+		return string(b[:maxErrLen]) + "..."
 	}
 	return string(b)
 }

provider/llamaswap/upstream.go

@@ -21,12 +21,19 @@ func upstreamPath(model, rest string) (string, error) {
 	if strings.TrimSpace(model) == "" {
 		return "", fmt.Errorf("llama-swap: upstream call requires a model id")
 	}
-	if strings.ContainsAny(model, "/?#") {
+	if strings.ContainsAny(model, "/?#") || strings.Contains(model, "..") {
 		return "", fmt.Errorf("llama-swap: invalid model id %q for upstream call (contains a path separator)", model)
 	}
 	if !strings.HasPrefix(rest, "/") {
 		rest = "/" + rest
 	}
+	// rest may embed SERVER-SUPPLIED components (e.g. ACE-Step's result
+	// file URL) — refuse dot-dot segments and absolute-URL smuggling so a
+	// hostile/buggy upstream cannot redirect the follow-up request at
+	// another proxy endpoint (/api/models/unload, ...).
+	if strings.Contains(rest, "..") || strings.Contains(rest, "://") {
+		return "", fmt.Errorf("llama-swap: invalid upstream path %q (dot-dot or scheme)", rest)
+	}
 	return "/upstream/" + model + rest, nil
 }