<!-- provider-gap-audit: openai-videos-create -->
Summary
The OpenAI Node SDK (openai npm package, >=6.2.0) exposes a GA client.videos.create() API for text-to-video and image-to-video generation using the Sora 2 / Sora 2 Pro models. This is a distinct generative execution surface — separate from chat completions, the Responses API, and images.generate() — and is completely uninstrumented in this repo. Users generating video with Sora through the JS SDK get no Braintrust spans.
This repo already treats the analogous gaps for other providers/modalities as in-scope and trackable:
The OpenAI videos.* resource is the same category of gap (a dedicated generative media API, distinct from the text/chat path) but for OpenAI specifically, and it is not covered by any of those issues or any other open issue in this repo.
What instrumentation is missing
- Wrapper (
js/src/wrappers/oai.ts): No proxy for the videos resource. Only chat.completions, embeddings, moderations, and responses are wrapped (confirmed by reading the file — no video references at all).
- Auto-instrumentation config (
js/src/auto-instrumentations/configs/openai.ts): No config entry for videos.create (or videos.remix/videos.retrieve). The file only instruments chat.completions.create, embeddings.create, chat.completions.parse, moderations.create, chat.completions.stream, and the responses.* family.
- Channels (
js/src/instrumentation/plugins/openai-channels.ts): No channel definitions for video generation (confirmed — no video references).
- Plugin (
js/src/instrumentation/plugins/openai-plugin.ts): No handler for video generation calls.
- Vendor types (
js/src/vendor-sdk-types/openai.ts): No Videos/VideoCreateParams types.
- e2e: No test scenario under
e2e/scenarios/openai-instrumentation/ exercises video generation.
Upstream reference
- OpenAI Videos API reference: https://developers.openai.com/api/reference/resources/videos/methods/create
- Video generation guide: https://developers.openai.com/api/docs/guides/video-generation
client.videos.create({ model, prompt, size, seconds, input_reference }) — model accepts sora-2 / sora-2-pro; returns a video job object (object: "video", with id, status, created_at, model) that is polled via videos.retrieve(id) until the render completes, then downloaded via videos.downloadContent(id).- This is a stable, GA, production API available in
openai Node SDK >=6.2.0 — well within this repo's already-supported openai version range (>=4.0.0, and the repo's own dev-pin is openai@6.25.0, which already includes this resource).
- Similar to
models.generateVideos() in Google GenAI, this uses a long-running-operation/polling pattern rather than a single synchronous response — instrumentation will likely need to decide whether to span just the initial create() call or track the full poll-to-completion lifecycle (the existing google-genai-generate-videos issues note the same design question).
Braintrust docs status
not_found — Fetched https://www.braintrust.dev/docs/integrations/ai-providers/openai directly: it documents chat completions, embeddings (via gateway), audio transcriptions, images, structured outputs, and function calling as traced via wrapOpenAI, but does not mention videos.create, Sora, or any video generation capability anywhere.
Local repo files inspected
js/src/wrappers/oai.ts — no video referencesjs/src/auto-instrumentations/configs/openai.ts — full method list confirmed (chat completions, embeddings, parse, moderations, stream, responses create/stream/parse/compact); no videos entryjs/src/instrumentation/plugins/openai-channels.ts — no video referencesjs/src/vendor-sdk-types/openai.ts — no video/Video referencese2e/scenarios/openai-instrumentation/ — no video generation scenario- Full repo grep for
video/Video under js/src/ — only unrelated matches in attachment-utils.ts, google-genai.ts vendor types, and strands-agent-sdk files; none reference OpenAI's videos resource
<!-- provider-gap-audit: openai-videos-create -->
Summary
The OpenAI Node SDK (
openainpm package,>=6.2.0) exposes a GAclient.videos.create()API for text-to-video and image-to-video generation using the Sora 2 / Sora 2 Pro models. This is a distinct generative execution surface — separate from chat completions, the Responses API, andimages.generate()— and is completely uninstrumented in this repo. Users generating video with Sora through the JS SDK get no Braintrust spans.This repo already treats the analogous gaps for other providers/modalities as in-scope and trackable:
images.generate()/images.edit()— open gap OpenAIimages.generate()andimages.edit()not instrumented (wrapper and auto-instrumentation) #1628models.generateVideos()(Veo) — open gaps [bot] Instrument @google/genai models.generateVideos() #2030 / [bot] Google GenAImodels.generateVideos()(Veo) not instrumented #2176The OpenAI
videos.*resource is the same category of gap (a dedicated generative media API, distinct from the text/chat path) but for OpenAI specifically, and it is not covered by any of those issues or any other open issue in this repo.What instrumentation is missing
js/src/wrappers/oai.ts): No proxy for thevideosresource. Onlychat.completions,embeddings,moderations, andresponsesare wrapped (confirmed by reading the file — novideoreferences at all).js/src/auto-instrumentations/configs/openai.ts): No config entry forvideos.create(orvideos.remix/videos.retrieve). The file only instrumentschat.completions.create,embeddings.create,chat.completions.parse,moderations.create,chat.completions.stream, and theresponses.*family.js/src/instrumentation/plugins/openai-channels.ts): No channel definitions for video generation (confirmed — novideoreferences).js/src/instrumentation/plugins/openai-plugin.ts): No handler for video generation calls.js/src/vendor-sdk-types/openai.ts): NoVideos/VideoCreateParamstypes.e2e/scenarios/openai-instrumentation/exercises video generation.Upstream reference
client.videos.create({ model, prompt, size, seconds, input_reference })—modelacceptssora-2/sora-2-pro; returns a video job object (object: "video", withid,status,created_at,model) that is polled viavideos.retrieve(id)until the render completes, then downloaded viavideos.downloadContent(id).openaiNode SDK>=6.2.0— well within this repo's already-supportedopenaiversion range (>=4.0.0, and the repo's own dev-pin isopenai@6.25.0, which already includes this resource).models.generateVideos()in Google GenAI, this uses a long-running-operation/polling pattern rather than a single synchronous response — instrumentation will likely need to decide whether to span just the initialcreate()call or track the full poll-to-completion lifecycle (the existing google-genai-generate-videos issues note the same design question).Braintrust docs status
not_found— Fetched https://www.braintrust.dev/docs/integrations/ai-providers/openai directly: it documents chat completions, embeddings (via gateway), audio transcriptions, images, structured outputs, and function calling as traced viawrapOpenAI, but does not mentionvideos.create, Sora, or any video generation capability anywhere.Local repo files inspected
js/src/wrappers/oai.ts— novideoreferencesjs/src/auto-instrumentations/configs/openai.ts— full method list confirmed (chat completions, embeddings, parse, moderations, stream, responses create/stream/parse/compact); no videos entryjs/src/instrumentation/plugins/openai-channels.ts— novideoreferencesjs/src/vendor-sdk-types/openai.ts— novideo/Videoreferencese2e/scenarios/openai-instrumentation/— no video generation scenariovideo/Videounderjs/src/— only unrelated matches inattachment-utils.ts,google-genai.tsvendor types, andstrands-agent-sdkfiles; none reference OpenAI's videos resource