#agent failed to reply

1 messages · Page 1 of 1 (latest)

crude dagger
#

⚠️ Agent failed before reply: Sandbox mode requires Docker, but the "docker" command was not found in PATH. Install Docker (and ensure "docker" is available), or set agents.defaults.sandbox.mode=off to disable sandboxing. | spawn docker ENOENT.
Logs: openclaw logs --follow

restive furnaceBOT
thorn wingBOT
#

That one is pretty direct: sandboxing is enabled, but Docker is missing.

Most likely you have agents.defaults.sandbox.mode: "non-main" or "all", and since channel/thread sessions count as non-main, this thread tried to start in Docker and failed.

Try these first:

openclaw --version
openclaw status
openclaw doctor

If you do not want sandboxing, disable it:

openclaw config set agents.defaults.sandbox.mode off
#
openclaw status
openclaw sandbox explain

I can tell you exactly which config is causing it. 🦐

crude dagger
#

what would sandboxing do?

thorn wingBOT
#

Sandboxing puts agent tool execution in an isolated environment instead of on your host.

In practice, that means things like:

  • exec runs in a container
  • file reads/writes are limited to the sandbox workspace
  • installed host binaries/files are not automatically visible
  • you get a safer boundary for untrusted chats or multi-user/group setups

Good reasons to use it:

  • the agent is exposed in public/group chats
  • you want command/file access fenced off from your real machine
  • you want stricter isolation between agents/sessions

Reasons to leave it off:

  • personal/local setup
  • you want the agent to use host tools directly
  • you do not want the Docker dependency
#

Short version: safer, but more setup and a bit more friction. If this is just your own assistant on your own machine, I’d probably turn it off.