Repository navigation
feat: default to gpt-6.1-sol (1.0.6-henderson.4); hermetic tests - #5
Merged
Merged
Conversation
…nderson.4) Tests now drop the host session's CLAUDE_PLUGIN_DATA and CODEX_COMPANION_SESSION_ID, so the suite passes when run from inside Claude Code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
🐉 eve review — ✅ APPROVE · 0 findings
|
![eve-bot-lovinka[bot]](https://avatars.githubusercontent.com/in/4092731?s=60&v=4){kind=small}
There was a problem hiding this comment.
🐉 eve review — ✅ Approved
7400b52· 0 actionable findings · reviewed by codex/gpt-6.1-sol · view run ↗
ℹ️ Claims vs diff — 6 claims could not be checked from the diff (c1, c2, c3, c4, c5, c6).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why this exists
The plugin's
codex:rescue/ companion default is gpt-6-sol, while every other Codex door Lukáš uses (cxx,switcheroo codex run, Codex's own Sol testers) now runs gpt-6.1-sol. Delegations through the plugin silently ran an older model. Separately, the test suite failed 4 tests whenever it ran inside Claude Code.Approach
DEFAULT_MODELmoves togpt-6.1-solat medium;--model/--effortstill win. README, the rescue agent and the marketplace description follow, and the version goes to1.0.6-henderson.4.tests/helpers.mjsdrops the host session'sCLAUDE_PLUGIN_DATAandCODEX_COMPANION_SESSION_ID, which re-rooted state and filteredstatus/resultjobs by the outer session.Intent
Every Claude → Codex delegation runs gpt-6.1-sol, and
npm testis green from any shell.Links
988a6077-47bd-45b5-988f-1afa64c88bc9Blockers & risks
/plugin→ updatecodex@henderson-codex).Verification
npm run check-versionOK.node --test tests/*.test.mjs: 97 pass, 0 fail, run inside a Claude Code session. Before the helper fix, unmodifiedmainfailed the same 4 tests there, and they passed with the two env vars unset. No live Codex call was made through the plugin.