cell codex

Run Codex in a devcell container

Synopsis

Starts an OpenAI Codex session inside an isolated devcell container.

The current working directory is mounted as /workspace. All additional args are forwarded to the codex binary unchanged.

When use_ollama = true in the [llm] section of devcell.toml (or —ollama is passed), Codex is started with —oss —local-provider ollama and CODEX_OSS_BASE_URL pointing at the host ollama instance. The model from llm.models.default is also passed when set.

Without ollama configured, Codex runs normally against the cloud provider (requires OPENAI_API_KEY or equivalent).

Examples:

cell codex
cell codex --ollama
cell codex --model o3
cell codex [args...] [flags]

Options

  -h, --help   help for codex

Options inherited from parent commands

      --base-image string         core image for scaffold Dockerfile (default: ghcr.io/dimmkirr/devcell:core-local)
      --build                     rebuild image before running (forces --no-cache)
      --debug                     plain-text mode plus stream full build log to stdout
      --dry-run                   print docker run argv and exit without running
      --engine string             execution engine: docker or vagrant (default "docker")
      --format string             output format: text, yaml, or json (default "text")
      --macos                     use macOS VM via Vagrant (alias for --engine=vagrant)
      --plain-text                disable spinners, use plain log output (for CI/non-TTY)
      --session-name string       session name for persistent home (~/.devcell/<name>)
      --vagrant-box string        Vagrant box name override
      --vagrant-provider string   Vagrant provider (e.g. utm) (default "utm")

SEE ALSO