test(doc-slop): pin judge codex-home staging contract - #661
Merged
Conversation
shunk031
force-pushed
the
fix/doc-slop-review-codex-home
branch
from
August 20, 2026 02:14
9e65311 to
2c544e1
Compare
Co-authored-by: Codex <noreply@openai.com>
shunk031
force-pushed
the
fix/doc-slop-review-codex-home
branch
from
August 20, 2026 02:34
2c544e1 to
ec7f5e5
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This is a regression-pinning PR, not a production bug fix. Current main already delegates judge-home staging to agent_guidance_eval.initialize_codex_home.
The new tests exercise that path through doc_slop_review.review_with_model and pin the contract:
The investigation also clarified an empirical source of confusion: sqlite state and related files seen in leftover staged homes can be created at runtime by the judge Codex process. Their presence does not prove that the runner copied the source home wholesale. In the live environment, auth.json is absent because authentication uses the configured command helper.
Validation
Coordination
PR #655 changes the judge prompt, and PR #658 changes the deterministic textlint area in the same script. Whichever of those three PRs lands last must update-branch from current main, rerun the complete validation, and re-verify the staging contract.
Do not claim this PR fixes the original bug; it pins the already-correct current-main behavior.