Skip to main content

crewship approvals

Manage the Harbormaster approval queue — list pending human-in-the-loop requests and decide them.
list is safe for any workspace member; approve, deny, and cancel require OWNER or ADMIN role server-side (403 otherwise).

Subcommands


crewship approvals list

Sample output:
Columns: ID, status chip (colored), kind, crew, agent, reason (truncated).

crewship approvals approve <id>

Sample output:

crewship approvals deny <id>


crewship approvals cancel <id>

Withdraw a still-pending request without approving or denying it. The request moves to the cancelled status. Use this when the gated action is no longer relevant (mission aborted, agent retired, duplicate request). Only pending requests can be cancelled — an already-decided or already-cancelled request returns a conflict.
Sample output:

crewship approvals get <id>

Fetch one approval request and render its full detail (kind, args, reason, decision metadata). The entry is workspace-scoped — IDs from other workspaces return 404.
Text mode prints canonical fields (id, status, kind, reason, crew_id, agent_id, mission_id, requested_by, decided_by, decided_at, comment, created_at, updated_at) up top, then any extra keys verbatim so an evolving server payload still renders something useful.

crewship approvals reset-auto-tuning <tool>

Wipe the reward history used by Harbormaster gate auto-tuning for the given tool. Auto-tuning downgrades sync→async after 90%+ approvals and upgrades async→sync after 70%+ denials, over the last 20 decisions per tool+args shape. When that window gets skewed (e.g. automation approving on humans’ behalf for a stretch), reset to make the gate respect the configured mode again until humans re-train it naturally.
Permanently wipes the rolling reward history for the tool (no confirmation). Requires OWNER or ADMIN on the caller’s workspace.
Output reports rows_deleted from gate_reward_history.

Errors