fix: give DeepSeek V4 models a 1M last-resort context window - #226
Merged
Conversation
Flash and v4.1 ids were falling through to the V3 128K default, so trim and the ctx gauge used 131k against a 1M-class model. Co-authored-by: Cursor <cursoragent@cursor.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
deepseek-v4*family is now 1M (flash, pro, and v4.1 preview ids).deepseek-chat/deepseek-reasonerstay at 128K.maxContextTokensuse — Flash was incorrectly capped at 131k.Test plan
TestLastResortContextcovers flash, pro, v4.1, and V3 ids/api/modelsasserts 1M fordeepseek-v4-flashand the v4.1 preview idmake vet && make lint(0 issues)go test -short -race ./internal/llmclient/ ./cmd/odek/Made with Cursor