Smarter finish: review the turn's changes before saying it is done
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 5/5
- Tiempo estimado
- Más de una semana
- Aptitud para principiantes
- 38/100
- Tipo de issue
- Nueva funcionalidad
- Claridad
- Bastante claro
- Estado de actividad
- Activo
- Stack tecnológico
- typescript
- Área
- ai-infra-agents
Línea de trabajo
Start by reading the turn completion flow and the edit-tool/Patch Undo change tracking, then inspect how subagents, oracle or READ_ONLY_TOOLS, and per-turn cost reporting work. Check the handling of AGENTS.md and the benchmark referenced by #49. Done means file-changing turns can use the requested off/multi-file/always settings, perform at most one read-only review, address concrete findings before finishing, and report its cost and time.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Today
When the model decides it has finished, it writes a summary and the turn ends. Nothing checks the changes against what the user asked. Missed requirements, a leftover debug line or an edit to the wrong file show up only when the user reads the diff.
Proposal
For turns that changed files, run a short self-review before the final answer:
- Collect the turn's changes: the diffs from the edit tools, which Patch already keeps for Undo.
- Ask a read-only reviewer, the
oraclerole or a newreviewerwithREAD_ONLY_TOOLS, to compare them with the user's request and the project's conventions (AGENTS.md). It should answer with concrete problems only: missing parts, wrong behavior, unrelated changes, failing checks. - If it finds problems, the main agent fixes them in the same turn; if not, it finishes. At most one review round, so it can't loop.
Settings: off / on for multi-file changes / always. The review's cost and time show on the turn like any subagent.
Measure
Benchmark success rate (#49) against the extra cost per task. If it doesn't pay for itself on the cheaper reviewer model (#78), keep it off by default.
- Lenguaje dominante
- TypeScript
- Estrellas
- 2
- Forks
- 2
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Preparar el entorno
- Sin Dockerfile ni archivo de Docker Compose
- Sin plantilla de pull request
- Leer la guía de contribución
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Issues similares
-
area: cli bug flake ready-for-agent
Dificultad 2/5 1-3 horas Aptitud para principiantes 62/100
gazetta-studio/gazetta-studio#1772 ·
Los mantenedores suelen responder en 1 día
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 82/100
-
needs-triage
Dificultad 2/5 1-3 horas Aptitud para principiantes 66/100
microsoft/playwright#43875 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
README translations: ja, ko, deAbiertodocumentation good first issue
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
Los mantenedores suelen responder en 1 día
-
feature
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
calagopus/panel#285 · 1 comentario ·
Los mantenedores suelen responder en 1 día