Support multi-turn reasoning for xAI (reasoning_content only)
#5989
+682
−20
Conversation
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
Member
Author
|
/merge-queue |
Contributor
|
🚀 Merge queue workflow triggered! View the run: https://github.com/tensorzero/tensorzero/actions/runs/21497851446 |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
Bugbot Autofix is OFF. To automatically fix reported issues with Cloud Agents, enable Autofix in the Cursor dashboard.
Member
Author
|
/merge-queue |
Contributor
|
🚀 Merge queue workflow triggered! View the run: https://github.com/tensorzero/tensorzero/actions/runs/21498830853 |
shuyangli
approved these changes
Jan 30, 2026
github-merge-queue bot
pushed a commit
that referenced
this pull request
Jan 30, 2026
* Support multi-turn reasoning for xAI * Support multi-turn reasoning for xAI * Support multi-turn reasoning for xAI * Support multi-turn reasoning for xAI * Support multi-turn reasoning for xAI
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Outdated suggestions cannot be applied.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.
Fix #5971.
This required relying less on the OpenAI types and methods, and instead migrating them to xAI-specific ones (inevitable).
For now we'll only support
reasoning_content. We don't support encrypted reasoning as that requires the Responses API (we use the legacy Chat Completions API). See the issue above for more details.Note
Medium Risk
Medium risk because it changes how xAI chat requests are constructed (message splitting, JSON-mode system injection, and thought/tool handling), which could affect correctness across tool and multi-turn flows.
Overview
Enables multi-turn reasoning for xAI by introducing xAI-specific request message types (including assistant
reasoning_content) intensorzero-types-providersand switching the xAI provider off the shared OpenAI message builder.Adds
prepare_xai_messages/conversion helpers to map TensorZeroRequestMessageblocks into xAI Chat Completions messages, including concatenating assistantThoughttext intoreasoning_content, enforcing tool-call/result placement rules, and preserving JSON-mode system instructions.Updates tests and tooling: expands xAI unit/E2E coverage around
reasoning_contentand thought filtering behavior, and adds a nextest timeout override for slow xAI multi-turn reasoning tests.Written by Cursor Bugbot for commit 79118e2. This will update automatically on new commits. Configure here.