Send response.create fields at the top level over WebSocket - #8
Merged
Merged
Conversation
The OpenAI WS endpoint expects response.create messages with model/input/etc
at the top level. Wrapping them in a 'response' key gets back:
{"type":"error","error":{"message":"[ObjectParam] [model]
[missing_required_parameter] Missing required parameter: 'model'."}}
Updated #call and #warmup to merge fields into the envelope, and adjusted
the specs that asserted the nested shape.
Owner
|
Thanks @lucas-domeij, this fix and the matching spec changes have been merged in 96d74fd. Much appreciated. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hit this trying to use the WS transport against
wss://api.openai.com/v1/responses. Everyresponse.createcame back with:The endpoint wants the response fields at the top level of the message, not nested under a
responsekey. Switching to a top-level layout makes the API accept the request and stream chunks back normally.Verified with a small repro against the live endpoint with
gpt-4.1-miniandgpt-5. Existing specs updated to match the shape that actually goes over the wire.