`cortex run`

Execute code files in sandboxed environments with resource limits, or as direct subprocesses. Supports auto-fix loop for failed executions.

Usage

cortex run <file>                    # Run in sandbox (auto-detect language)
cortex run script.py --no-sandbox    # Run as direct subprocess
cortex run script.py --fix           # Enable LLM auto-fix loop on failure
cortex run script.py --fix --max-fix 6  # Up to 6 fix attempts

Options

Option	Description
`--no-sandbox`	Run as direct subprocess instead of Docker sandbox
`--fix`	Enable LLM auto-fix loop when code fails
`--max-fix`	Maximum number of fix attempts (default: 4)
`--help`	Show help for this command

Supported Languages

Language	Extension	Sandbox Image
Python	`.py`	`python:3.12-slim`
JavaScript	`.js`	`node:22-slim`
TypeScript	`.ts`	`node:22-slim`
Bash	`.sh`	`ubuntu:24.04`
Ruby	`.rb`	`ruby:3.3-slim`
Go	`.go`	`golang:1.23-bookworm`
Rust	`.rs`	`rust:1.78-slim`

Docker Sandbox

When running in sandbox mode, Docker containers are created with:

Constraint	Value
Network	`--network=none` (no network access)
Memory	256MB limit
CPU	0.5 cores
Process limit	64 PIDs
Security	`no-new-privileges`
Timeout	30 seconds
Max output	64KB

Subprocess fallback is used when docker info fails.

Auto-Fix Loop

When --fix is enabled:

runInSandbox(code)
  → exit != 0?
     → LLM: "Fix this error: <stderr>\n\nCode:\n<code>"
     → extract fixed code from LLM response
     → runInSandbox(fixedCode)
     → repeat up to maxRounds

Examples

# Run a Python script in Docker sandbox
cortex run analyze.py

# Run a shell script as direct subprocess
cortex run deploy.sh --no-sandbox

# Run with auto-fix enabled
cortex run buggy-code.py --fix

# Run with aggressive auto-fix
cortex run complex.js --fix --max-fix 8