Skip to main content

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?”
Both runs are fetched in parallel; partial failures surface as run-a <id>: <err> or run-b <id>: <err>.

crewship diff <run-a> <run-b>

Examples

diff compares agent runsmsg_… (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:
The diff is intentionally not Myers — for run comparison users want the gist, not patch-applicable hunks.

See also