Repository navigation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Coding turns spend extra model calls collecting context, repairing patches and declaring completion. This ports the Round 032 winning strategy onto current main: bounded Jev context selection, a Muse small-edit path, literal substitutions, explicit whole-task completion, and finite error/diagnostic feedback.
The optimized build is opt-in through
scripts/build-jev-muse.sh(Jevjev-1.13.0, small-edit Musemuse-spark-1-3; configure the primary writer as Muse too). Normal completion/recovery improvements also apply to plain builds. Build/use and integration details are in docs/jev-muse.md.Review map
5f853c3(374 added lines, mostly tests).faecac3. This retains main's architecture notes, read-by-pattern, search pre-reading and rejected-patch logging. The winner router supersedes/preselectin the optimized build, avoiding duplicate selection calls. The stricter normaltask_completecontract replaces main's completion flag.Validation and limits
go test ./...,go test -race ./..., andgo vet ./...pass.The evaluation harness (#8) and historical evidence (#9, stacked on #8) are separate review PRs.
stagingwas absent and was created at main23f5fce; no merge was performed.GitHub CI status
Linux/macOS tests, formatting and shellcheck pass. Windows record-isolation tests already fail on the unchanged main revision (
TestTheNewestRecordComesFirst,TestNoRecordsIsNotAnError,TestAnUnwritableHomeIsSurvived): their HOME-only setup does not isolate Windows USERPROFILE. The product PR Windows job is in progress; Windows success is not claimed.