Feat: Keep coding agents working when the Cortex proxy stops
Los mantenedores suelen responder en 1 día
@huang195 ya está trabajando en esto.
Desde el 9/11/2026.
Evaluación
Este issue todavía no se ha evaluado.
Descripción
Problem
When the Cortex proxy is not running, every agent that agentop configure wired to it stops working. Claude Code and OpenCode send all traffic to HTTPS_PROXY=http://127.0.0.1:47600. If nothing listens there, each request fails.
The agent shows a plain network error. The error does not name Cortex and does not tell the user how to fix it.
What Cortex does now
- macOS: launchd starts a supervisor (
cortex --supervise). The supervisor restarts the proxy, with a backoff (cmd/cortex/supervise.go). - Linux: the systemd unit uses
Restart=on-failure. agentop service uninstall: it only warns that "Claude Code and OpenCode stop working whenever the proxy is not running".
Gaps
- A killed supervisor stays dead.
cmd/cortex/supervise.go:32says: "What this does NOT cover: the supervisor itself being killed. Nothing restarts it". launchd does not restart it in agui/<uid>domain, so agents fail until the next login or a manual start. - Crash recovery is not tested from start to end on macOS.
cmd/agentop/cmd_service_platform.go:55-58says that restart-after-crash was "NOT verified end to end". - A bad config at boot stops all agents. A config error is fatal at startup. The supervisor then restarts the proxy into the same error, again and again. A hot reload keeps the last good config, but a boot does not. So one bad edit followed by a restart, or a reboot, cuts off every agent until the user repairs the file.
- The failure is hard to understand. The user sees "connection refused" in the agent, not "Cortex is not running".
Proposal
- Claude Code SessionStart hook that starts Cortex.
agentop configure claude-code enableinstalls a SessionStart hook.- The hook probes
127.0.0.1:47600. If nothing answers, it runsagentop service startand prints one line that says so. - The hook must never remove
HTTPS_PROXY. See Non-goals. - This also covers gap 1: the next session start brings back a dead supervisor.
- Open question: does the hook run before the first API request of the session? Test this before the design is final.
- Boot with the last good config.
- When startup validation fails, Cortex starts with the last config that it loaded with success.
- It reports the error in
/reload/statusand inagentop doctor, in the same way as a failed reload. - If no last good config exists, Cortex keeps the current behavior and exits.
- A clear message.
- When the proxy does not answer,
agentopandagentop execprint:Cortex is not running on 127.0.0.1:47600. Run: agentop service start. agentop doctoralready checks that the proxy serves. Make its fix line give the same command.
- When the proxy does not answer,
- A manual crash test on macOS, from a real GUI login:
kill -9the proxy. Check that the supervisor restarts it, and that a running agent session continues after the restart.kill -9the supervisor. Record what happens, then check that item 1 brings Cortex back.- Write the results in
docs/laptop-service.md.
Non-goals
- No automatic fail-open. Cortex must not remove
HTTPS_PROXY, and it must not send traffic directly to the provider when the proxy is down. A fail-open does these things without a message:- It turns off guardrails (IBAC, OPA) and the egress allow list.
- It stops session recording.
- It fires during each normal restart, which takes only seconds.
- A user who wants to stop using Cortex keeps the manual path:
agentop configure claude-code disable.
Acceptance
- A killed supervisor comes back at the next Claude Code session start.
- A config with a startup error does not stop agents when a last good config exists.
agentop doctorreports the error. - A dead proxy gives a message that names Cortex and the command that fixes it.
-
docs/laptop-service.mdrecords thekill -9results for the proxy and for the supervisor.
Assisted-By: Claude (Anthropic AI) [email protected]
- Lenguaje dominante
- Go
- Estrellas
- 26
- Forks
- 46
- Merge medio
- 13 h 49 min
- PR fusionados (30 d)
- 244
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.
Más de rossoctl/cortex
-
enhancement
Dificultad 4/5 3-5 días Aptitud para principiantes 48/100
Los mantenedores suelen responder en 1 día
-
enhancement ux
Dificultad 5/5 Más de una semana Aptitud para principiantes 25/100
rossoctl/cortex#1739 · 1 comentario ·
Los mantenedores suelen responder en 1 día
-
Phase C: Let Praxis core accept CONNECT and decrypt, and remove the Go front doorPosiblemente ocupada @huang195 la tomó hace 2 días. Abiertolaptop
rossoctl/cortex#1728 · 1 asignado ·
Los mantenedores suelen responder en 1 día
-
Phase D: Move the Cortex store, pricing, session API and attribution into the binaryPosiblemente ocupada @huang195 la tomó hace 2 días. Abiertolaptop
rossoctl/cortex#1727 · 1 asignado ·
Los mantenedores suelen responder en 1 día
-
Phase B: Send absolute-form requests to Praxis and remove the egress listenerPosiblemente ocupada @huang195 la tomó hace 2 días. Abiertolaptop
rossoctl/cortex#1726 · 1 asignado ·
Los mantenedores suelen responder en 1 día
Todos los issues de rossoctl/cortex
Issues similares
-
bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 68/100
php/frankenphp#2829 ·
Los mantenedores suelen responder en 1 día
-
bug
Dificultad 1/5 Menos de una hora Aptitud para principiantes 88/100
Los mantenedores suelen responder en 1 día
-
tech-debt
Dificultad 2/5 1-3 horas Aptitud para principiantes 82/100
Los mantenedores suelen responder en 1 día
-
kind/bug
Dificultad 2/5 1-3 horas Aptitud para principiantes 78/100
Los mantenedores suelen responder en 2 días
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 62/100
teradata-labs/loom#624 ·
Los mantenedores suelen responder en 1 día