fix: review findings — clone-route audio sniffing, zip caps, filename sanitization, WAV response caps
- speakWithReference now validates the response IS audio via the same audioResultMIME sniff the sfx/enhance surfaces use — a 2xx JSON soft error or HTML proxy page was previously wrapped up as audio/wav bytes. - audioResultMIME moves to audio.go (next to speechMIME; it was defined in sfx.go but shared by enhance/clone) and learns the Ogg container normalization (application/ogg -> audio/ogg). - Stems zip unpack gains entry-count (16) and total-decompressed (1GB) caps on top of the existing per-entry cap — the per-entry bound alone still let a many-entry bomb multiply up. - sanitizeFilename drops NUL and both path separators too, so upload metadata can never smuggle directory structure to a file-writing shim. - New maxAudioResponseBytes (256MB) for bodies that ARE one audio clip (clone, enhance, sfx): a long WAV legitimately passes the 64MB JSON cap. - speakWithReference local renamed path -> upPath (naming parity with stems/enhance). Co-Authored-By: Claude Fable 5 <[email protected]> Claude-Session: https://claude.ai/code/session_01WWCQcYStWXBYUy5sZWnbLT
This commit is contained in:
+38
-14
@@ -83,12 +83,12 @@ func (m *speechModel) Speak(ctx context.Context, req audio.SpeechRequest, opts .
|
||||
// speakWithReference performs zero-shot voice cloning via the upstream
|
||||
// passthrough clone route. The reference sample rides as the `voice_file`
|
||||
// part and the text as an `input` field; voice/format/speed still go on the
|
||||
// wire when set (upstreams ignore fields they don't understand). The route's
|
||||
// default container is WAV, so MIME resolution falls back to audio/wav (not
|
||||
// the JSON route's mp3) when neither the response header nor the requested
|
||||
// format decides.
|
||||
// wire when set (upstreams ignore fields they don't understand). The result
|
||||
// MIME comes from the response header or content sniffing (audioResultMIME,
|
||||
// same validation as the sfx/enhance surfaces) — a JSON soft error or an
|
||||
// HTML proxy page must never be wrapped up as audio bytes.
|
||||
func (m *speechModel) speakWithReference(ctx context.Context, req audio.SpeechRequest) (*audio.SpeechResult, error) {
|
||||
path, err := upstreamPath(m.id, "/v1/audio/speech/upload")
|
||||
upPath, err := upstreamPath(m.id, "/v1/audio/speech/upload")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -107,18 +107,17 @@ func (m *speechModel) speakWithReference(ctx context.Context, req audio.SpeechRe
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
audioBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, formType, body, maxResponseBytes)
|
||||
audioBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, upPath, m.id, formType, body, maxAudioResponseBytes)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if len(audioBytes) == 0 {
|
||||
return nil, &llm.APIError{Provider: m.p.name, Model: m.id, Message: "speech clone response contained no audio"}
|
||||
}
|
||||
mimeType := "audio/wav"
|
||||
if mt := mimeFromContentType(contentType, "audio/"); mt != "" {
|
||||
mimeType = mt
|
||||
} else if req.Format != "" {
|
||||
mimeType = speechMIME("", req.Format)
|
||||
mimeType := audioResultMIME(contentType, audioBytes)
|
||||
if mimeType == "" {
|
||||
return nil, &llm.APIError{Provider: m.p.name, Model: m.id,
|
||||
Message: fmt.Sprintf("speech clone response is not audio (Content-Type %q): %s", contentType, truncateForError(audioBytes))}
|
||||
}
|
||||
return &audio.SpeechResult{Audio: audioBytes, MIME: mimeType}, nil
|
||||
}
|
||||
@@ -144,6 +143,28 @@ func speechMIME(contentType, format string) string {
|
||||
}
|
||||
}
|
||||
|
||||
// audioResultMIME resolves an audio body's MIME type: the response
|
||||
// Content-Type when it is a concrete audio type, else content sniffing
|
||||
// (RIFF/WAVE, Ogg and friends), else "" — the caller treats undetectable as
|
||||
// an upstream error, mirroring videoMIME. Sniffed "audio/wave" is normalized
|
||||
// to the conventional "audio/wav", and Ogg's container type
|
||||
// "application/ogg" to "audio/ogg". Shared by the clone, sfx, and enhance
|
||||
// surfaces, which all answer raw audio bodies.
|
||||
func audioResultMIME(contentType string, data []byte) string {
|
||||
if mt := mimeFromContentType(contentType, "audio/"); mt != "" {
|
||||
return mt
|
||||
}
|
||||
switch mt := http.DetectContentType(data); {
|
||||
case mt == "audio/wave":
|
||||
return "audio/wav"
|
||||
case mt == "application/ogg":
|
||||
return "audio/ogg"
|
||||
case strings.HasPrefix(mt, "audio/"):
|
||||
return mt
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// TranscriptionModel implements audio.TranscriptionProvider, binding a
|
||||
// speech-to-text model served by llama-swap (routed to a whisper.cpp-style
|
||||
// upstream).
|
||||
@@ -241,10 +262,13 @@ func transcriptionFilename(filename, mimeType string) string {
|
||||
}
|
||||
|
||||
// sanitizeFilename strips characters that would corrupt or inject into the
|
||||
// multipart Content-Disposition header. Quotes and backslashes are escaped
|
||||
// by mime/multipart itself; CR/LF are not — they must go.
|
||||
// multipart Content-Disposition header, or smuggle directory structure to
|
||||
// the receiving side. Quotes and backslashes are escaped by mime/multipart
|
||||
// itself, but a file-writing shim decodes them right back — so CR/LF/NUL
|
||||
// and both path separators are dropped: an upload-metadata filename must
|
||||
// never traverse ("../x", "a/b", "C:\x").
|
||||
func sanitizeFilename(name string) string {
|
||||
name = strings.NewReplacer("\r", "", "\n", "").Replace(name)
|
||||
name = strings.NewReplacer("\r", "", "\n", "", "\x00", "", "/", "", "\\", "").Replace(name)
|
||||
return strings.TrimSpace(name)
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user