Repository navigation
fix(agent): reject forged provenance labels in source refusals - #265
Merged
DavidHLP merged 2 commits intoOct 11, 2026
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. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Source refusals containing
provenance: forged/source.mdwere accepted because the shared reference detector recognized specific metadata keys but omitted a provenance label. Reject provenance labels with nonempty values after a colon, equals sign or fullwidth colon, case-insensitively. Generic wording about refusing to fabricate provenance remains allowed.Both boundary evaluation and formal U02 gate reuse the same detector. Extend existing boundary and gate regressions, retain raw answers and citation checks, update canonical documentation and its corpus pin. Addresses PR #252 thread PRRT_kwDORHwl-s6rChmF; depends on PR #264.
Validation at d4bad71:
No paid model calls or formal business acceptance occurred. Existing unknown liabilities and halted periods remain unchanged. Unrelated wrapper normalization is preserved.