Repository navigation
fix(evals): preserve compound disclaimers and gate claims - #181
Merged
Merged
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b21a049e86
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Qualification rejected a truthful deferred handoff because it said
No independent review or completion is claimed. The same answer exposed a separate gap: a gate result after preceding prose could escape command evidence checks.What changed
Scope
Evaluator parsing and focused regression fixtures only. Product package bytes, policy, catalog, case instructions, sampling, and passing requirements stay unchanged.
Tradeoffs
The parser recognizes the observed wrapper while retaining both source clauses. The existing command parser and native evidence checks evaluate the result. It does not discard preceding claims or infer facts from review disclaimers.
Blast Radius
Delivery grading accepts the supported handoff and rejects altered command claims. The stopped campaign remains failed and supplies no qualification credit.
Verification
RED reproduction precedes GREEN. The unchanged actual native input passes after the fix, while incorrect exits, unknown commands, contradictory tails, and unsupported completion claims reject.
Focused delivery checks passed with 652 tests and zero failures. Typecheck passed. The reported apostrophe and colon cases reject incorrect exit claims, and quoted and unquoted command arguments retain their binding.
Diagnostic replay covers 348 attempts from 11 byte-identical original reports. It accepts 346, preserves one genuine disclosure failure, and excludes one host failure.
Full push preflight passed on the final head with 2,903 tests passing, 20 existing skips, and zero failures. Independent exact-head, native-evidence, package, and comment reviews passed.