fix(core): include 'low' effort for deepseek-v4-flash - #3732
Merged
Conversation
The official Thinking Mode guide accepts reasoning_effort low/high/max and states the effort mapping is identical for deepseek-v4-flash and deepseek-v4-pro; the deepseek-v4-pro entry here already pins the full set. The pinned ['high','max'] predates the 0731 refresh of this model.
Updates the thinking-variants assertion to the corrected catalog set ['low','high','max'], asserts reasoningEffort passthrough for 'low', and drops 'low' from the unsupported-effort loop.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
'low'todeepseek-v4-flashthinking efforts:['high', 'max']->['low', 'high', 'max'], withlastUpdated: '2026-08-24'.This surfaced during review of #3605: the vision-exp entry inherited its pinned set from this sibling, whose value predates the model's 0731 refresh.
Evidence
reasoning_effortoflow/high/maxand states the effort mapping table is "identical for deepseek-v4-flash and deepseek-v4-pro": https://api-docs.deepseek.com/guides/thinking_mode/deepseek-v4-proentry directly below already pins['low', 'high', 'max'].Test plan
test