docs(openrouter-video): sync with openrouter-web changes - #165
docs(openrouter-video): sync with openrouter-web changes#165devin-ai-integration[bot] wants to merge 1 commit into
Conversation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Original prompt from Automation
|
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
Summary
POST /api/v1/videosnow validates input modalities before dispatch (openrouter-web#32040, openrouter-web#32063), and the skill said nothing about it, so an agent hitting one of the new 400s would most likely retry the same payload.Three gates, all pre-dispatch 400s with the standard
{ error: { message } }body:input_references/frame_imagesentry's modality must be accepted by the model (frame_images/image_urlcount as image,audio_urlas audio,video_urlas video);video_urlreference; required text is satisfied by a non-emptyprompt.The requirement metadata is not exposed on
GET /api/v1/videos/models, so the error message is the only source of truth for what is missing. That is the reason the new section tells the agent to fix the payload (add the reference, drop the unsupported input, or switch model/provider) rather than retry.Link to Devin session: https://openrouter.devinenterprise.com/sessions/898c97dc4b6b45abb203df1a32f76143