Repository navigation
fix: release 1.0.1 with GPT-6.1 Sol token-saving preset - #5
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
This branch had an error being deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Token-saving mode in 1.0.0 pins BA to the previous GPT-6 Sol model. Version 1.0.1 updates the preset to GPT-6.1 Sol/high, retains inherited PM and GPT-6 Luna/xhigh for backend, web/mobile frontend, and QC, and requires the matching runtime before applying it.
Existing projects reapply the preset after upgrading; saved runs keep their original model snapshots. Host capability validation still rejects unavailable models without an implicit fallback. Release documentation and upload materials explain the separate plugin/runtime upgrade steps.
The lockfile also moves fast-uri from 3.1.7 to patched 3.1.8; a clean install reports zero vulnerabilities.
Validation: 183 tests across 20 files, TypeScript checks, build, all eight skill validations, and a fresh tarball/restored-launcher check for preset preview, save, idempotent reapplication, and normal reset. The added migration test verifies old run preservation and rejection when GPT-6.1 Sol is unavailable. Real-agent quality and token savings are not claimed.
Vercel completed the package build but its separate website preview failed because the project configuration expects a
publicoutput directory. The website preview setup is unchanged by this release.