- videogen.LipSyncer/LipsyncProvider: SadTalker talking heads via
  POST /upstream/<id>/v1/talking_head (multipart image+audio parts,
  still/enhance/preprocess flags) -> mp4.
- videogen.VideoBackgroundRemover/VideoBackgroundRemovalProvider:
  POST /upstream/<id>/v1/video/matte (output greenscreen_mp4|alpha_webm).
- videogen.VideoUpscaler/VideoUpscaleProvider:
  POST /upstream/<id>/v1/video/upscale (scale 2|4).
- videogen.Chainer/ChainerProvider: async long-video chain-job client —
  SubmitChain (JSON POST /v1/video/chain, init_image_b64), ChainStatus
  (GET /v1/jobs/{id}, tolerant segment-id decode), ChainResult,
  ChainSegmentResult (partial delivery after mid-chain failure); hostile
  job-id path rejection.
- Shared singleVideoResult validation (positive video evidence) + a
  videoInputFilename hint helper; httptest contract tests per surface;
  ADR-0025 (index row deferred — MJ-A backfills the ADR index table and
  parallel edits would conflict).

Co-Authored-By: Claude Fable 5 <[email protected]>

@@ -0,0 +96,4 @@
+	return singleVideoResult(m.p.name, m.id, "lipsync", raw, respType)
+}
+
+// singleVideoResult wraps one raw video body into a videogen.Result,

@@ -0,0 +100,4 @@
+// requiring positive evidence of video-ness (declared video/* Content-Type
+// or sniffed mp4/webm magic) so a proxy error page can never become "the
+// clip" — the video sibling of singleImageResult.
+func singleVideoResult(provider, model, verb string, raw []byte, contentType string) (*videogen.Result, error) {

@@ -0,0 +1,295 @@
+package llamaswap

@@ -0,0 +60,4 @@
+
+// SubmitChain implements videogen.Chainer.
+func (m *chainerModel) SubmitChain(ctx context.Context, req videogen.ChainRequest) (string, error) {
+	if len(req.Segments) == 0 {

@@ -0,0 +71,4 @@
+		if strings.TrimSpace(seg.Prompt) == "" {
+			return "", fmt.Errorf("%w: video chain segment %d requires a prompt", llm.ErrUnsupported, i)
+		}
+		if seg.Seconds < 0 {

@@ -0,0 +135,4 @@
+	}
+	for _, entry := range out.Segments {
+		var s string
+		if json.Unmarshal(entry, &s) == nil {

@@ -0,0 +143,4 @@
+			ID        string `json:"id"`
+			SegmentID string `json:"segment_id"`
+		}
+		if json.Unmarshal(entry, &obj) == nil {

@@ -0,0 +197,4 @@
+	if strings.TrimSpace(jobID) == "" {
+		return "", fmt.Errorf("llama-swap: chain job call requires a job id")
+	}
+	if strings.ContainsAny(jobID, "/?#") || strings.Contains(jobID, "..") {

@@ -0,0 +116,4 @@
+// video: the caller's (sanitized — upload metadata is untrusted), else one
+// derived from the MIME subtype ("video.mp4"), else "video". Mirrors
+// transcriptionFilename.
+func videoInputFilename(filename, mimeType string) string {

@@ -0,0 +42,4 @@
+	Segment int
+	Total   int
+
+	// SegmentIDs are the COMPLETED per-segment artifacts, fetchable via

@@ -0,0 +60,4 @@
+// LipSyncer animates still portraits into talking-head clips. Its own small
+// interface rather than a method on Model: lip-syncers are not text-to-video
+// generators — they bind to a different backend id entirely.
+type LipSyncer interface {