Skip to main content

​
Sandbox CLI

Manage sandbox runtimes for isolated agent execution.

​
Overview

FluffBuzz can run agents in isolated sandbox runtimes for security. The sandbox commands help you inspect and recreate those runtimes after updates or configuration changes. Today that usually means:
  • Docker sandbox containers
  • SSH sandbox runtimes when agents.defaults.sandbox.backend = "ssh"
  • OpenShell sandbox runtimes when agents.defaults.sandbox.backend = "openshell"
For ssh and OpenShell remote, recreate matters more than with Docker:
  • the remote workspace is canonical after the initial seed
  • fluffbuzz sandbox recreate deletes that canonical remote workspace for the selected scope
  • next use seeds it again from the current local workspace

​
Commands

​
fluffbuzz sandbox explain

Inspect the effective sandbox mode/scope/workspace access, sandbox tool policy, and elevated gates (with fix-it config key paths). 
fluffbuzz sandbox explain
fluffbuzz sandbox explain --session agent:main:main
fluffbuzz sandbox explain --agent work
fluffbuzz sandbox explain --json

​
fluffbuzz sandbox list

List all sandbox runtimes with their status and configuration. 
fluffbuzz sandbox list
fluffbuzz sandbox list --browser  # List only browser containers
fluffbuzz sandbox list --json     # JSON output
Output includes:
  • Runtime name and status
  • Backend (docker, openshell, etc.)
  • Config label and whether it matches current config
  • Age (time since creation)
  • Idle time (time since last use)
  • Associated session/agent

​
fluffbuzz sandbox recreate

Remove sandbox runtimes to force recreation with updated config. 
fluffbuzz sandbox recreate --all                # Recreate all containers
fluffbuzz sandbox recreate --session main       # Specific session
fluffbuzz sandbox recreate --agent mybot        # Specific agent
fluffbuzz sandbox recreate --browser            # Only browser containers
fluffbuzz sandbox recreate --all --force        # Skip confirmation
Options:
  • --all: Recreate all sandbox containers
  • --session <key>: Recreate container for specific session
  • --agent <id>: Recreate containers for specific agent
  • --browser: Only recreate browser containers
  • --force: Skip confirmation prompt
Important: Runtimes are automatically recreated when the agent is next used.

​
Use Cases

​
After updating a Docker image

# Pull new image
docker pull fluffbuzz-sandbox:latest
docker tag fluffbuzz-sandbox:latest fluffbuzz-sandbox:bookworm-slim

# Update config to use new image
# Edit config: agents.defaults.sandbox.docker.image (or agents.list[].sandbox.docker.image)

# Recreate containers
fluffbuzz sandbox recreate --all

​
After changing sandbox configuration

# Edit config: agents.defaults.sandbox.* (or agents.list[].sandbox.*)

# Recreate to apply new config
fluffbuzz sandbox recreate --all

​
After changing SSH target or SSH auth material

# Edit config:
# - agents.defaults.sandbox.backend
# - agents.defaults.sandbox.ssh.target
# - agents.defaults.sandbox.ssh.workspaceRoot
# - agents.defaults.sandbox.ssh.identityFile / certificateFile / knownHostsFile
# - agents.defaults.sandbox.ssh.identityData / certificateData / knownHostsData

fluffbuzz sandbox recreate --all
For the core ssh backend, recreate deletes the per-scope remote workspace root on the SSH target. The next run seeds it again from the local workspace.

​
After changing OpenShell source, policy, or mode

# Edit config:
# - agents.defaults.sandbox.backend
# - plugins.entries.openshell.config.from
# - plugins.entries.openshell.config.mode
# - plugins.entries.openshell.config.policy

fluffbuzz sandbox recreate --all
For OpenShell remote mode, recreate deletes the canonical remote workspace for that scope. The next run seeds it again from the local workspace.

​
After changing setupCommand

fluffbuzz sandbox recreate --all
# or just one agent:
fluffbuzz sandbox recreate --agent family

​
For a specific agent only

# Update only one agent's containers
fluffbuzz sandbox recreate --agent alfred

​
Why is this needed?

Problem: When you update sandbox configuration:
  • Existing runtimes continue running with old settings
  • Runtimes are only pruned after 24h of inactivity
  • Regularly-used agents keep old runtimes alive indefinitely
Solution: Use fluffbuzz sandbox recreate to force removal of old runtimes. They’ll be recreated automatically with current settings when next needed. Tip: prefer fluffbuzz sandbox recreate over manual backend-specific cleanup. It uses the Gateway’s runtime registry and avoids mismatches when scope/session keys change.

​
Configuration

Sandbox settings live in ~/.fluffbuzz/fluffbuzz.json under agents.defaults.sandbox (per-agent overrides go in agents.list[].sandbox): 
{
  "agents": {
    "defaults": {
      "sandbox": {
        "mode": "all", // off, non-main, all
        "backend": "docker", // docker, ssh, openshell
        "scope": "agent", // session, agent, shared
        "docker": {
          "image": "fluffbuzz-sandbox:bookworm-slim",
          "containerPrefix": "fluffbuzz-sbx-",
          // ... more Docker options
        },
        "prune": {
          "idleHours": 24, // Auto-prune after 24h idle
          "maxAgeDays": 7, // Auto-prune after 7 days
        },
      },
    },
  },
}

​
See Also