Skip to main content

​
Resume

cmd/crewship/cmd_resume.go continues a previous session by threading --chat <id> into the standard run flow against the agent that owns the chat. Four resolution paths:
InputResolution
(no arg)Interactive huh picker over the 10 most recent CLI-origin chats. Requires a TTY on stdin and stderr.
c_…Treated as a chat ID.
r_… / run_…Looked up via client.GetRun; the run’s chat_id is followed.
https://github.com/owner/repo/pull/<n>Searches the journal for the PR identifier and reuses the chat that produced it (best-effort — only works if an agent journaled the PR creation).
If the agent slug isn’t part of the resolved object, the chat detail is fetched from GET /api/v1/chats/{id} to recover it.

​
crewship resume [chat-id | run-id | pr-url]

No flags of its own — all flags belong to crewship run (it’s the dispatch target). The two flags that get forced are --chat <id> and --interactive=true.

​
Examples

crewship resume                                          # interactive picker
crewship resume c_abc123                                 # explicit chat
crewship resume r_xyz789                                 # via run
crewship resume https://github.com/foo/bar/pull/42       # via journal lookup

​
Common errors

  • interactive picker requires a TTY; pass a chat-id or run-id — running without a TTY but no argument.
  • run <id> has no associated chat to resume — the run pre-dates chat threading or was created without one.
  • could not determine agent for chat <id> — chat detail lookup did not surface an agent.
  • no recent sessions to resume — the workspace has no CLI-origin chats in the last 10 entries.
  • no session found for PR <owner/repo#n> — pass a chat-id directly — journal search came up empty; fall back to the chat-id form.
  • list recent: chats endpoint: <err>; fallback runs: <err> — both /api/v1/chats and the /runs fallback failed; both errors are surfaced to make the actual problem identifiable.

​
See also