diff --git a/examples/catalog_test.go b/examples/catalog_test.go index 918372b5..01eeaf8d 100644 --- a/examples/catalog_test.go +++ b/examples/catalog_test.go @@ -185,7 +185,7 @@ func TestTaskUsesRunnerOwnedLimitsAndReviewLoop(t *testing.T) { if code.Edges["success"] != "Review" || review.Edges["rejected"] != "Code" || ui.Edges["rejected"] != "Code" { t.Fatal("task must route implementation and review findings through Code", code.Edges, review.Edges, ui.Edges) } - if review.Limits == nil || review.Limits.MaxVisits != 3 || !slices.Equal(review.Limits.On, []string{"rejected", "error"}) { + if review.Limits == nil || review.Limits.MaxVisits != 5 || !slices.Equal(review.Limits.On, []string{"rejected", "error"}) { t.Fatalf("review must cap rejected/error loops with runner-owned limits: %+v", review.Limits) } } diff --git a/examples/task.md b/examples/task.md index f8bc5f2b..b0c7aae6 100644 --- a/examples/task.md +++ b/examples/task.md @@ -5,7 +5,7 @@ ``` ```prompt -Implement the task and any supplied plan. Follow the repository's AGENTS.md and area guidance; reuse existing code and conventions and keep the change focused. On a re-entry, fix only must-fix findings in the handoff; do not redo the task or re-review it. Verify with focused checks appropriate to the repository, never the full suites. Report the commands and results and the changed files. Do not commit, push or deploy. Use blocked_retryable only for an evidenced transient prerequisite; otherwise blocked. +Implement the task and any supplied plan. First merge the current base branch and resolve conflicts keeping both intents. Follow the repository's AGENTS.md and area guidance; reuse existing code and conventions and keep the change focused. Rendered work must meet the repository's UI guidance (a design or UI quality checklist, if it has one): aligned layout, consistent spacing, no bad wrapping, theme colours and standard controls. If the preview fixture cannot show a state the task changes, extend it so UIReview can capture it. On a re-entry, fix the must-fix findings in the handoff; after a failed delivery, merge the base branch again and fix the listed checks. Do not redo the task. Verify with focused checks appropriate to the repository, never the full suites. Report the commands and results and the changed files. Do not commit, push or deploy. Use blocked_retryable only for an evidenced transient prerequisite; otherwise blocked. ``` ```tools @@ -38,11 +38,11 @@ error -> Code # stage Review ```limits -{"max_visits":3,"on":["rejected","error"]} +{"max_visits":5,"on":["rejected","error"]} ``` ```prompt -Review this run's change against the task by reading the diff, not the whole repository. Start from the changed files, git status and a diff against the base branch, then read only code around changed hunks. Run no test suites, builds or analyzers: judge the checks Code reported and name missing coverage. Check correctness, regressions, duplication and performance. Rendered acceptance belongs to UIReview. On a revisit, confirm only that previous must-fix findings are fixed and that new hunks introduced no defect. Return rejected only for a must-fix defect with file, line, evidence and fix; advisory when only non-blocking notes remain; otherwise success. Do not edit or commit. +Review this run's change against the task by reading the diff, not the whole repository. Start from the changed files, git status and a diff against the base branch, then read only code around changed hunks. Run no test suites, builds or analyzers: judge the checks Code reported and name missing coverage. Check correctness, regressions, duplication, performance and UI code that breaks the repository's UI guidance (hard-coded colours or sizes, ad-hoc styles, layout that cannot align). Rendered acceptance belongs to UIReview. On a revisit, confirm only that previous must-fix findings are fixed and that new hunks introduced no defect. Return rejected only for a must-fix defect with file, line, evidence and fix; advisory when only non-blocking notes remain; otherwise success. Do not edit or commit. ``` ```tools @@ -73,11 +73,11 @@ error -> Review # stage UIReview ```limits -{"max_visits":3,"on":["rejected","error"]} +{"max_visits":5,"on":["rejected","error"]} ``` ```prompt -Verify the rendered result of this run's change against the task and platform conventions. When the change has no rendered effect, return skipped with the reason. Otherwise use the repository's documented capture or preview workflow to inspect affected states at relevant sizes and themes, saving evidence where the task requires it. Run no test suites. Do not edit or commit. Return rejected for a concrete visual defect with evidence and a fix; advisory for non-blocking notes; blocked only for an evidenced capture failure; otherwise approved. If the available fixture cannot render a needed state, return advisory naming the unverified state. Return blocked only when the application cannot be built or opened at all. +Judge the rendered result against the task and the repository's UI guidance as a demanding product designer: approve only what you would ship. When the change has no rendered effect, return skipped with the reason. Otherwise use the repository's documented capture or preview workflow to capture every affected state at small and large sizes, light and dark, including popups, focus, empty and long content; inspect every image you cite and save evidence where the task requires it. Run no test suites. Do not edit or commit. Return rejected for any visual or interaction defect with evidence, location and a fix; a state the fixture cannot show is rejected too, naming the fixture data Code must add. Return advisory only for minor polish, blocked only when the application cannot be built or opened at all, otherwise approved. ``` ```tools