fix: address review — fail loud on non-video bodies, dedupe form plumbing, doc parity

- videoMIME no longer hard-falls-back to video/mp4: a 2xx body that is
  neither declared nor sniffable as video (JSON job envelope, HTML error
  page) is now an APIError instead of a 'successful' corrupt clip.
- Resolution rides the wire as width/height AND the OpenAI-style size
  string, so either upstream convention honors an explicit request.
- writeFormFields + mimeFromContentType shared helpers replace the
  copied multipart loop (audio.go/video.go) and Content-Type branch.
- ADR-0019 indexed in docs/adr/README.md; README gains the videogen
  section + support-matrix mention (docs-parity rule).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AXQxVhXBw8PwFAtsVrXSmj

README.md

@@ -266,6 +266,24 @@ tr, err := tm.Transcribe(ctx, audio.TranscriptionRequest{
 voices, err := ls.ListVoices(ctx, "kokoro") // []string of voice ids
 ```
 
+## Video: text-to-video + image-to-video
+
+Video generation lives in the `videogen` package (ADR-0019), mirroring
+imagegen/audio: one small `Model` contract, zero values mean backend
+defaults, bytes in/out. Text-to-video and image-to-video are one surface —
+a nil `InitImage` is a pure text prompt; setting it conditions generation
+on that frame (hybrid checkpoints like Wan 2.2 TI2V serve both). First
+backend: llama-swap (blocking `/v1/videos/sync`, vLLM-Omni style — the
+response body is the encoded clip, so `Result` carries a single `Video`).
+Generation runs for minutes; bound the call with a context deadline.
+
+```go
+vm, _ := ls.VideoModel("videogen-wan22-5b")
+res, err := vm.Generate(ctx, videogen.Request{Prompt: "a cat surfing"},
+    videogen.WithSize("1280x704"), videogen.WithNumFrames(81))
+// res.Video.Data ([]byte) + res.Video.MIME ("video/mp4")
+```
+
 ## Tool calls
 
 ```go
@@ -398,7 +416,8 @@ response as a single delta plus final event.
 capabilities are present at the client level; whether a given call succeeds
 depends on the llama.cpp model llama-swap loads. llama-swap also provides
 **image generation + editing** (`imagegen`), **speech synthesis +
-transcription** (`audio`) — separate axes, not shown above — plus a `Health`
+transcription** (`audio`), **video generation** (`videogen`) — separate
+axes, not shown above — plus a `Health`
 probe and management methods on `*llamaswap.Provider`.
 
 Notes: Ollama has no native tool_choice — `"none"` drops the tools;