Codex on a laptop

description.yaml is AWML 0.4, as it was pushed. The fit reads it converted to AWML 0.8.

# Codex on a person's own laptop, started on a schedule by the ChatGPT desktop app's scheduled tasks
# on a local project, or by cron or launchd running `codex exec`. This describes a kind of platform,
# not anyone's machine; AWML's example codex-laptop is a different one, where the laptop runs the
# workflow's own code. Checked against OpenAI's documentation on 22 October 2026.
awml: "0.4"
platform: { id: codex-agent-laptop, label: "Codex on a laptop" }

# A laptop may be shut for a fortnight's holiday, as in the AWML spec's own example. Scheduled tasks
# on a local project need the computer on and the desktop app running. A laptop that never sleeps
# can say less.
# https://github.com/chrismdp/awml/blob/main/SPEC.md#placing-a-workflow-where-it-can-run
# https://learn.chatgpt.com/docs/automations
off_for_up_to: P14D

# Each run is a Codex session that carries out the task's prompt.
# https://learn.chatgpt.com/docs/automations
# https://learn.chatgpt.com/docs/non-interactive-mode
steps: agent

# Codex's own agent, signed in with ChatGPT or an OpenAI API key. Routed through Amazon Bedrock, it
# is processed on Amazon's terms instead: list amazon here then.
# https://learn.chatgpt.com/docs/auth
# https://learn.chatgpt.com/docs/amazon-bedrock
agents: [openai]

# Codex runs commands in a sandbox with network access off by default, and `codex exec` starts
# read-only. So the workflow's own code cannot call a model company until you turn on
# sandbox_workspace_write.network_access, or choose full access: say any here then.
# https://learn.chatgpt.com/docs/agent-approvals-security#network-access
# https://learn.chatgpt.com/docs/non-interactive-mode
calls: []

# A laptop holds its owner's folders. A shared description cannot know their names, so it says
# notes, as AWML's examples do: keep a workflow's contexts under notes, or name your own folders
# when you describe your own laptop.
# https://github.com/chrismdp/awml/blob/main/SPEC.md#placing-a-workflow-where-it-can-run
holds: [notes]