feat: add grok-4.6 xhigh reasoning effort - #901
Merged
Conversation
Grok 4.6 accepts xhigh as a real thinking level. Keep it on the Build request path and generate grok-4.6-xhigh aliases instead of downgrading unknown-model xhigh to high. Unverified max stays guarded.
RIERS
marked this pull request as ready for review
August 13, 2026 01:13
|
大佬可以把Console 账号也添加grok4.6模型吗， |
Contributor
Author
|
这个得马圣先支持才行 |
Closed
3 tasks
# Conflicts: # frontend/src/shared/i18n/index.ts
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
grok-4.6as a model that actually acceptslow / medium / high / xhigh.reasoning.effort: "xhigh"tohighfor this model.grok-4.6-low|medium|high|xhighaliases from/v1/modelswhen the base model is available.Why
Grok 4.6 supports extra-high thinking. Before this change it was treated as an unknown model, so client
xhigh/grok-4.6-xhighrequests were defensively downgraded tohigh. That made Codex-stylereasoning.effort=xhighsilently weaker than requested.Related: #897
Impact
model: "grok-4.6"withreasoning.effort: "xhigh"(orgrok-4.6-xhigh) and the upstream Build payload keepsxhigh.grok-4.5and unknown models still downgradexhigh/maxtohigh.maxon grok-4.6 still maps tohigh.Validation
go testshowedgrok-4.6levels=noneand Build normalizexhigh→high.go test ./internal/domain/model ./internal/infra/provider/cli ./internal/infra/provider/console ./internal/transport/http/inference -count=1go veton the same packages