feat(azure): support reasoning models via Responses API routing - #3173
Open
yttrium400 wants to merge 2 commits into
Open
feat(azure): support reasoning models via Responses API routing#3173yttrium400 wants to merge 2 commits into
yttrium400 wants to merge 2 commits into
Conversation
themavik
reviewed
Mar 23, 2026
themavik
left a comment
There was a problem hiding this comment.
request() now assigns api_version from env twice back-to-back in the BYOK branch (duplicate line) — looks accidental and should be one assignment. If a payload could ever include both input and messages you would take the chat path; fine if impossible, otherwise worth an explicit guard or comment.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #3169. This PR implements dynamic routing for Azure OpenAI 'Responses API' requests (used by reasoning models like o1/o3). When
inputis present in the request payload, now utilizes the standardOpenAI(orAsyncOpenAI) client with a modified base URL (/openai/v1) as required by Azure.