From 8e513ba43e2383d0d354d7afec60d54b46f6665f Mon Sep 17 00:00:00 2001 From: toki Date: Sun, 31 May 2026 16:30:06 +0900 Subject: [PATCH] sync: agent-ops from agentic-framework v1.1.119 --- agent-ops/.version | 2 +- agent-ops/skills/common/code-review/SKILL.md | 2 ++ agent-ops/skills/common/plan/SKILL.md | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/agent-ops/.version b/agent-ops/.version index 08b766a..51f88d3 100644 --- a/agent-ops/.version +++ b/agent-ops/.version @@ -1 +1 @@ -1.1.116 +1.1.119 diff --git a/agent-ops/skills/common/code-review/SKILL.md b/agent-ops/skills/common/code-review/SKILL.md index adac6d3..fdaa668 100644 --- a/agent-ops/skills/common/code-review/SKILL.md +++ b/agent-ops/skills/common/code-review/SKILL.md @@ -235,6 +235,7 @@ If the user-review gate does not trigger, write new routed plan/review files usi - Base the follow-up scope directly on the archived review findings. Keep it narrow and actionable. - Choose lane/grade again; preserve the prior route only when it was adequate, otherwise raise `GNN` and/or move `local -> cloud`. - If the finding is only missing or untrusted verification evidence that an appropriate follow-up lane can produce by rerunning commands or collecting artifacts, do not write `USER_REVIEW.md` solely for that reason. Write a follow-up plan that reruns the exact commands in an appropriate lane and records actual stdout/stderr. +- If follow-up verification involves mobile/UI hangs, timeouts, or no progress for 2 minutes, stop blind retries; require focused rerun output plus screenshot/window/UI-tree evidence path, or the exact reason capture is impossible. - Before choosing the follow-up route, apply this escalation gate: - If the archived plan was `local-*` and the verdict is `FAIL` for correctness, completeness, test coverage, or verification trust, move the follow-up build lane to `cloud` unless the issue is trivially deterministic and review-detectable without live environment behavior. - If the follow-up work is terminal-agent work (shell/CLI workflow implementation, bin script orchestration, process control, stdout/stderr parsing, exit-status contracts, long-running command diagnosis, or terminal benchmark-style tasks), use `cloud-G07` or higher. @@ -348,6 +349,7 @@ _구현 에이전트가 각 중간 검증 및 최종 검증 명령 실행 후 - 대체가 필요하면 `계획 대비 변경 사항`에 이유와 대체 명령을 기록한다. - `검증 결과`에는 실제 stdout/stderr를 붙여 넣는다. - 사용자 리뷰 요청으로 명령을 끝까지 실행하지 못했다면 `사용자 리뷰 요청`에 실행한 명령, 실제 출력, 미실행 명령의 사유를 기록한다. +- mobile/UI hang, timeout, 또는 2분 무진행은 blind retry를 중단하고 focused rerun 명령과 screenshot/window/UI-tree evidence path를 남기며, 불가능하면 정확한 사유를 남긴다. ### {TAG}-1 중간 검증 ``` diff --git a/agent-ops/skills/common/plan/SKILL.md b/agent-ops/skills/common/plan/SKILL.md index c4a5e1f..be26d0e 100644 --- a/agent-ops/skills/common/plan/SKILL.md +++ b/agent-ops/skills/common/plan/SKILL.md @@ -395,7 +395,7 @@ _구현 에이전트가 각 중간 검증 및 최종 검증 명령 실행 후 - 대체가 필요하면 `계획 대비 변경 사항`에 이유와 대체 명령을 기록한다. - `검증 결과`에는 실제 stdout/stderr를 붙여 넣는다. - 사용자 리뷰 요청으로 명령을 끝까지 실행하지 못했다면 `사용자 리뷰 요청`에 실행한 명령, 실제 출력, 미실행 명령의 사유를 기록한다. -- mobile/UI hang 또는 timeout은 focused rerun 명령과 screenshot/window/UI-tree evidence path를 남기고, 불가능하면 정확한 사유를 남긴다. +- mobile/UI hang, timeout, 또는 2분 무진행은 blind retry를 중단하고 focused rerun 명령과 screenshot/window/UI-tree evidence path를 남기며, 불가능하면 정확한 사유를 남긴다. ### {TAG}-1 중간 검증 ```