Safety prompts recur across run_skill and transfer_task sub-sessions
Los mantenedores suelen responder en 1 día
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 45/100
Línea de trabajo
Start by tracing how run_skill classifies read-only operations and how safety approvals are scoped when transfer_task creates a child session; the issue does not name source files or tests. Reproduce the reported flow, confirm both behaviors from the source, then add a focused regression test for a read-only skill crossing the sub-session boundary while preserving write confirmations and safety hooks.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Problem
A prior session using Docker Agent dev build bbe70f53 observed repeated safety prompts across delegated work: 10/10 runs in the surviving log window prompted again. This report is about runtime safety-state/tool classification, not agent prompt design.
Working hypothesis from the observed behavior: launching a skill with run_skill does not mark its execution read-only, so the default safety mode prompts; an approve-autonomous decision appears scoped to the current sub-session, while transfer_task creates a new sub-session that prompts again. These details need source-level confirmation and a minimal reproduction by maintainers; the surviving observations alone do not establish the mechanism.
Reproduction to investigate
- In default safety mode, run a skill via
run_skillthat performs only read operations. - Observe whether the tool launch prompts for approval despite being read-only.
- Grant the applicable autonomous/safety approval in that session, then delegate via
transfer_taskto a child session that performs the same read-only operation. - Observe whether the new sub-session prompts again.
Reported observation: repeated prompts occurred in 10/10 runs visible in the surviving log window. This count is limited to that window and is not a broader rate estimate. No raw logs, private content, local paths, or credentials are attached.
Expected
Provide safe, explicit, least-privilege handling for read-only operations and/or scoped reuse of a user-granted safety policy across related sub-sessions, with clear visibility of scope. Preserve safety hooks and their enforcement. Reuse must not automatically authorize writes or bypass explicit confirmation for external, irreversible, or production-reaching writes.
Actual observation / uncertainty
Prompts recurred across skill/delegation runs. The proposed run_skill classification and per-sub-session approval scope are hypotheses, not independently verified source conclusions.
Environment / limitations
- Docker Agent dev build:
bbe70f53 - macOS arm64
- Prior-session observation; exact source revision and a standalone reproduction were not retained.
Please confirm the classification and approval-scope behavior, then add a focused regression test for a read-only skill crossing a transfer_task sub-session boundary.
- Lenguaje dominante
- Go
- Estrellas
- 4.7k
- Forks
- 565
- Merge medio
- 18 h 52 min
- PR fusionados (30 d)
- 221
Preparar el entorno
Inicia el contenedor de desarrollo del proyecto en tu navegador, con tu propia cuenta de GitHub.
- Incluye un Dockerfile o un archivo de Docker Compose
- Sin plantilla de pull request
- Sin 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.
Más de docker/docker-agent
-
edit_file diff rendering panics on invalid UTF-8 textPosiblemente ocupada @TDnorthgarden la tomó hoy. Abiertoarea/tui
Dificultad 2/5 1-3 horas Aptitud para principiantes 85/100
docker/docker-agent#4955 ·
Los mantenedores suelen responder en 1 día
-
A setting to turn off the models.dev catalog download (offline and strict-network use)Posiblemente ocupada @3431481073 la tomó hace 19 días. Abiertoarea/config area/models
Dificultad 2/5 1-3 horas Aptitud para principiantes 72/100
docker/docker-agent#4714 ·
Los mantenedores suelen responder en 1 día
-
Error when trying to run sandbox example?Quizá libre de nuevo @dgageot la tomó hace 28 días y no hay ningún pull request abierto. Abiertoarea/cli
Dificultad 2/5 1-3 horas Aptitud para principiantes 62/100
docker/docker-agent#4672 · 1 comentario · 1 reacción · 1 asignado ·
Los mantenedores suelen responder en 1 día
-
`edit_file` silently edits the first match when `oldText` occurs more than oncePosiblemente ocupada @dwin-gharibi la tomó hace 103 días. Abiertoarea/tools
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
docker/docker-agent#3929 · 2 comentarios ·
Los mantenedores suelen responder en 1 día
-
area/api area/runtime
Dificultad 4/5 3-5 días Aptitud para principiantes 48/100
docker/docker-agent#4951 ·
Los mantenedores suelen responder en 1 día
Todos los issues de docker/docker-agent
Issues similares
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
IBM-Cloud/terraform-provider-ibm#7115 ·
Los mantenedores suelen responder en 2 días
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 86/100
fluxcd/notification-controller#1441 ·
Los mantenedores suelen responder en 1 día
-
bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 66/100
volcengine/volcengine-go-sdk#163 · 1 comentario ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
OneBusAway/maglev#2145 ·
Los mantenedores suelen responder en 2 días
-
priority/medium status/ready type/chore
Dificultad 2/5 1-3 horas Aptitud para principiantes 84/100
discobox-ai/discobox#1357 ·
Los mantenedores suelen responder en 1 día