shen-joe (#1399) wants images and videos from magpie in PI-Desktop and
WorkBuddy. Neither app sends video generation to a custom provider: PI-Desktop
has no video generation at all, and WorkBuddy's VideoGen/ImageGen post to
copilot.tencent.com's /v2/videos|images/generations with the account token.
So the way those agents get videos is Library → MCP → Magpie Image
(`magpie mcp image`). Its generate_video tool told the agent it works only
"with a Grok subscription signed in to Magpie (it has no other video model
yet)", and the Library card said the same, while gateway.Videomakers also
makes videos with a preset plan's videos (Volcengine Ark Agent Plan's
Seedance), another magpie, and a custom provider whose model list marks video
models (#1446). An agent reading that can tell a Seedance user they need Grok.
- imagemcp.go: generate_video's description and the package doc name each
kind of video model.
- library/market.go: the Magpie Image card says "a video model set up in
Magpie (Grok Imagine, Seedance)"; zh, zh-TW, ja and de follow.
- Tests: TestVideoToolSaysEveryVideoModel and TestMagpieImageSaysVideoModels
fail on the old text and pass now.
Run: go test -tags nogui ./internal/imagemcp ./internal/library ./internal/gui
./internal/gateway (ok) and ./... (only TestNoCommandBypassesProc red, from
2da8fbe4, fixed on main by b934d64a); gofmt -l; GOOS=linux and GOOS=windows
go vet of imagemcp and library. A built magpie's `mcp image` answered
tools/list with the new description. A sandbox gateway (scratch HOME,
127.0.0.1:3591, a real OpenRouter key) answered PI-Desktop's exact request,
POST /v1/images/generations {"model":"openrouter/google/gemini-2.5-flash-image",
"prompt":…,"n":1}, with 200 and data[0].b64_json, a PNG.