perf: skip VLM thinking on image inspection - #158
Merged
Conversation
Inspect is OCR and provenance boxes, not multi-step reasoning. Qwen 3.5 Flash thinks by default and that was 20–40s; turning thinking off dropped it to ~8–11s without a clear quality loss. Co-authored-by: Cursor <cursoragent@cursor.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
1 Skipped Deployment
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
enableThinking: false. Gemini 3 Flash:thinkingLevel: "minimal"(lowest it allows).Test plan
chat: image inspection request→responseis closer to ~8–15s than ~30s.main) via the usual staging → main PR.Made with Cursor