fix(openai): don't auto-use Responses API on compatible apiBase#13002
Open
Solaris-star wants to merge 1 commit into
Open
fix(openai): don't auto-use Responses API on compatible apiBase#13002Solaris-star wants to merge 1 commit into
Solaris-star wants to merge 1 commit into
Conversation
Auto-routing gpt-5 / o-series models to /responses is only appropriate for the official OpenAI API. Custom OpenAI-compatible bases typically only implement /chat/completions. Align core canUseOpenAIResponses with the openai-adapters guard, keep useResponsesApi true/false overrides, and document the flag. Fixes continuedev#12995.
dosubot
Bot
added
the
size:S
Contributor
|
All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #12995: using
provider: openaiwith a customapiBaseand a gpt-5-like model name was still auto-routed toPOST /responses, which many OpenAI-compatible proxies do not implement (they only have/chat/completions).Change
BaseLLM.canUseOpenAIResponsesnow only auto-enables Responses for the official OpenAI API base (matchingpackages/openai-adaptersshouldUseResponsesEndpoint)useResponsesApi: falsestill hard-opts outuseResponsesApi: truestill hard-opts in even on a custom baseTest plan
gpt-5*still uses/responsesby defaultapiBase+gpt-5.5uses/chat/completionsby defaultapiBase+useResponsesApi: trueforces/responsesuseResponsesApi: falseforces/chat/completionsFixes #12995.