Repository navigation
Conversation
Codex's automatic approval reviewer falls back to its built-in "codex-auto-review" id when the catalog does not override it. Moon Bridge does not route that id, so the reviewer fails closed and every escalated action is denied. Point each catalog entry at its own slug so review requests follow the same route as normal turns.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Codex's automatic approval reviewer (
approvals_reviewer = "auto_review", the desktop app default) uses the built-in model idcodex-auto-reviewunless the model catalog overrides it. A Moon Bridge instance doesn't route that id, so the review request fails, and because the reviewer fails closed, every escalated action gets denied.The generated
models_catalog.jsonnow setsauto_review_model_overrideto each entry's own slug, so review requests follow the same route as normal turns.Two tests cover the builder and the written catalog, and
go test ./...passes.Upstream reports for the same behavior: openai/codex#31255 and openai/codex#47917.