Diff
cmd/crewship/cmd_diff.go takes two existing run IDs, fetches their state plus the last assistant message of each linked chat, and renders a terse before/after view. Distinct from eval compare, which re-runs an eval scenario on two tiers — diff works strictly on what already happened.
Use cases:
- “Did v2 of my routine actually fix the bug?” → diff before/after
- “What changed between Friday’s prod run and Monday’s regression?”
- “Did the agent give two different answers to the same prompt?”
run-a <id>: <err> or run-b <id>: <err>.
crewship diff <run-a> <run-b>
Examples
diff compares agent runs — msg_… (legacy r_…) IDs from
crewship history. The run_… / prn_… IDs printed by
crewship routine runs <slug> are routine (pipeline) runs and live in a
different namespace; there is no routine-run equivalent of diff, so
inspect them individually with crewship routine report <run-id>.
Passing a run_… ID on either side fails fast (exit code 3) instead of
returning a bare 404.Output
Side-by-side headers (agent, status, started, finished) with status colours (green/red/yellow), then a minimal line-by-line diff of the assistant output:See also
crewship eval compare— re-run an eval scenario on two model tiers.crewship history— find the two run IDs.crewship explain <run-id>— explain what one run did, with journal context.