플러그인

에이전트의 테스트·타입체크·lint·빌드 주장에 대한 신선도 게이트: 각 검증 실행이 tools/post-execute에서 영수증이 되고 파일 편집이 추적되며, agent/turn-stopping 시 최신 영수증이 오래되었거나 실패했거나 읽을 수 없는 주장은 영수증과 그 이후 편집된 파일을 명시해 한 단계 더 진행하도록 유도합니다.

다음 행동을 말만 하고 도구를 호출하지 않은 채 끝난 에이전트 턴을 재개합니다: 가드가 agent/turn-stopping에서 턴 로그를 재생하고, 판정 모델에 참/거짓 질문 하나를 던지며, 같은 턴을 한 단계 더 실행하도록 유도합니다.

Blocks the end of a turn while temporary files from that turn are still lying around: it registers a listener on the serial agent/turn-stopping hook and, if anything is left, steers the model with the file list and two ways out — delete them, or justify each one and move it somewhere deliberate. Candidates come from two narrow temp-file sources, plus a backup-retention channel that is on by default and flags excess .bak copies of files touched this turn. The first is the .agent-tmp/ convention directory under the session cwd: whatever is left in it is reported outright, because that directory exists only for throwaway files. The second is the paths this turn actually wrote, captured through the fs/write-intent hook; those are reported only when they sit under that cwd, fall outside .git, node_modules, .tmp-sessions and out, match a temp-file pattern, and the file is still present — which is what keeps junk already sitting in the workspace from being resurrected as a complaint about this turn. One steer per turn, subagent sessions skipped, nothing deleted by the plugin in the default steer mode (only the opt-in mode: prune deletes backups), and the check is readdir plus stat only.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

DeepSeek Harness 에이전트 루프 게이트(pre-step, pre-execute, post-execute, turn-stopping)에서 Jev(TypeSafe System One) 판정을 수행합니다. UI 의존성이 없으며 어떤 Harness 구성에도 연결할 수 있습니다.

턴 종료를 가로채 각 턴이 끝난 뒤 에이전트가 멈추기 전에 비평과 개선을 한 차례 수행하게 합니다.