wdx usage

Show how much of each AI coding agent’s account’s limits is used.

wdx usage [flags]

As each AI coding agent last told through one of its agents: a row per window of its limits and bucket of models, with the window’s key and the bucket’s name as the AI coding agent gives them, when it resets and when that was told. Usage is the account’s, not an agent’s: every agent of one AI coding agent on this machine draws on the same one. A window used 100% or more is limited, and a bucket can be used while none of its windows is. Nothing is shown until an AI coding agent has told something; one on a plan without limits never does. With --node, the usage is the other node’s.

Flags

Flag	Default	Description
--node <name>		run the command on the node of this name, another of your account, through a session

Examples

# Every limit
wdx usage

# As JSON, for a script
wdx usage --json

Output

Each AI coding agent: whether it can be used, then its windows: label, bucket, used, when it resets and as of when. With --json: {“usage”: [{“aca”: …, “window”: …, “bucket”: …, “used_percent”: …, “resets_at”: …, “limited”: …, “observed_at”: …}, …]}

Errors

Code	Exit	When
daemon_unavailable	3	the daemon is not running or not answering
usage	2	the request, command line or a setting is invalid
internal	3	an unexpected failure: database, filesystem or git

With --node, also: code_not_set_up, code_wrong, connection_lost, daemon_unavailable, hub_unreachable, hub_version_unsupported, node_key_mismatch, node_not_found, node_offline, node_version_unsupported, not_logged_in, remote_access_off, remote_not_for_agents, route_not_allowed, session_closed, session_required, too_many_streams.