Skip to content

fix(inference): add Max effort for Databricks GPT-5.6 - #3442

Open
Inference1 wants to merge 1 commit into
different-ai:devfrom
Inference1:fix/inference-gpt-5-6-max-thinking
Open

fix(inference): add Max effort for Databricks GPT-5.6#3442
Inference1 wants to merge 1 commit into
different-ai:devfrom
Inference1:fix/inference-gpt-5-6-max-thinking

Conversation

@Inference1

@Inference1 Inference1 commented Aug 3, 2026

Copy link
Copy Markdown

Fixes #3393

Summary

  • expose the max reasoning effort for Databricks GPT-5.6 Luna and Terra
  • add a catalog regression test covering all Databricks GPT-5.6 variants

Screenshots

GPT-5.6 Luna

GPT-5.6 Luna Thinking options

GPT-5.6 Terra

GPT-5.6 Terra Thinking options

Verification

  • node .opencode/skills/openwork-models/scripts/openwork-models.mjs validate
  • NODE_OPTIONS=--conditions=development pnpm --dir ee/apps/inference exec tsx --test test/model-catalog.test.ts
  • pnpm --filter @openwork-ee/inference build

@vercel

vercel Bot commented Aug 3, 2026

Copy link
Copy Markdown
Contributor

@Guohuan-Feng is attempting to deploy a commit to the Different AI Team on Vercel.

A member of the Team first needs to authorize it.

@vercel

vercel Bot commented Aug 3, 2026

Copy link
Copy Markdown
Contributor

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
openwork-landing Ready Ready Preview, v0 Aug 3, 2026 9:13am

@Inference1

Copy link
Copy Markdown
Author

@benjaminshafii Would you please review this pr

@Inference1

Copy link
Copy Markdown
Author

@johnnyshields Would you please review this pr

@johnnyshields

Copy link
Copy Markdown
Contributor

@Inference1 I'm not an admin/reviewer here. It looks good to me tho! @benjaminshafii ?

@Inference1

Copy link
Copy Markdown
Author

@benjaminshafii Would you please review this pr

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug]: Thinking options

2 participants