Route model-initiated reviews through hosted workflows - #1393
Open
bobzhang wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Model-initiated worktree reviews now use the same hosted
mbtxworkflow path as scouts. Remove the dedicatedreviewtool fromrunandserve, together with its live-goal mirror and per-turn budget wiring, and teach the model to callwf.agent_call(kind="review", input={"goal": ...}).Audit criteria and optional baseline are explicit. Hosted delegation requires a durable session, uses the existing 32-child reservation and 10-minute child deadline, and returns the full report instead of a digest/error flag. The reviewer still validates its submission.
--review-deadlinenow documents only the automatic gate.The standalone
openseek reviewcommand still callsagent_review.run_reviewdirectly without workflow. The automatic--review-gateandsubrun reviewengine remain available.Validation: an offline hosted-process regression verifies criteria, baseline, step envelope, report decoding, and journal/lifecycle output. No live model calls are required.
Passed
just check,just test(3241 native tests, 3213 JS tests, 24 cram cases, and the CLI lifecycle regressions),just build,moon info, andmoon fmt. No generated public interface changes.