Add native Responses API passthrough#1
Merged
Conversation
werbenhu
approved these changes
Jul 22, 2026
werbenhu
marked this pull request as ready for review
July 22, 2026 06:51
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Why
GrokProxy already uses the xAI Responses endpoint internally, but its public API only exposed Chat Completions and Anthropic Messages. Native Responses clients therefore had to pass through an external Responses-to-Chat bridge before reaching GrokProxy.
For multimodal tool results, that extra conversion can serialize structured image content into text. Large base64 image payloads are then counted as text tokens, causing extreme context growth and upstream disconnects. Direct Responses passthrough avoids that conversion and keeps the original multimodal structure intact.
The compact route is included so Codex-style clients can continue using automatic server-side context compaction through the same Responses-compatible base URL.
Validation