Document AI agent sandbox conflicts in server-AGENTS.md

Codex CLI seccomp filters block nix daemon access.
Workaround: disable redundant sandbox since server provides isolation.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Dan 2026-01-09 23:33:19 -08:00
parent 51e657d43b
commit 026f82e697

View file

@ -88,6 +88,26 @@ Simple Unix isolation - no containers, VMs, or complex sandboxing:
This is a learning environment, not a hostile multi-tenant system.
## AI Agent Sandbox Conflicts
Some AI coding agents (Codex, etc.) run commands in their own sandbox with seccomp
filters. This can block nix daemon access even though the server allows it.
**Symptom**: `nix store ping` or `nix develop` fails with "Operation not permitted"
from within the agent, but works from your regular SSH session.
**Fix for Codex CLI**: Disable redundant sandboxing (server already provides isolation):
```bash
# One-off
codex -s danger-full-access
# Permanent (~/.codex/config.toml)
sandbox_mode = "danger-full-access"
```
Other agents may have similar sandbox settings - check their docs if nix commands fail.
## Do NOT
- Run `sudo` (you don't have access)