Thanks to visit codestin.com
Credit goes to github.com

Skip to content

fix: skip image understanding when primary model has vision #1747

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
tyler6204 wants to merge 1 commit into from
Closed

fix: skip image understanding when primary model has vision #1747

tyler6204 wants to merge 1 commit into from

Conversation

@tyler6204
Copy link
Member

@tyler6204 tyler6204 commented Jan 25, 2026

Summary

  • Skip image understanding API call entirely when the primary model supports vision natively
  • Saves API cost and latency - no point describing an image when the model will see it directly

Changes

  • model-catalog.ts: Add input field to track model capabilities, plus modelSupportsVision() and findModelInCatalog() helpers
  • runner.ts: Check if primary model has vision before running image understanding; skip if it does

Test plan

  • Send image to vision-capable model (Claude Opus 4.5) → no image description API call, image passed natively
  • Send image to non-vision model → media understanding runs as before

🤖 Generated with Claude Code

@tyler6204 @claude
fix: skip image understanding when primary model has vision
7aa5c0b 
When the primary model supports vision natively (e.g., Claude Opus 4.5),
skip the image understanding call entirely. The image will be injected
directly into the model context instead, saving an API call and avoiding
redundant descriptions.

Co-Authored-By: Claude Opus 4.5 <[email protected]>
steipete added a commit that referenced this pull request Jan 25, 2026
@steipete @tyler6204
fix: skip image understanding for vision models (#1747)
5f98630 
Thanks @tyler6204.

Co-authored-by: Tyler Yust <[email protected]>
@steipete
Copy link
Contributor

steipete commented Jan 25, 2026

Rebased onto main, added attachment-scoped skip decision for vision models + regression test + changelog.
Ran pnpm lint && pnpm build && pnpm test.
Landed commits:

Thanks @tyler6204!

@steipete steipete closed this Jan 25, 2026
mcinteerj pushed a commit to mcinteerj/moltbot that referenced this pull request Jan 25, 2026
@steipete @tyler6204
fix: skip image understanding for vision models (openclaw#1747)
0f05927 
Thanks @tyler6204.

Co-authored-by: Tyler Yust <[email protected]>
rodrigouroz pushed a commit to rodrigouroz/moltbot that referenced this pull request Jan 26, 2026
@steipete @tyler6204 @rodrigouroz
fix: skip image understanding for vision models (openclaw#1747)
f2658ca 
Thanks @tyler6204.

Co-authored-by: Tyler Yust <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@tyler6204 @steipete