[
  {"id": 1, "prompt": "deploy (repo has .claude/deploy/PROCEDURE.md, 4 commits since last deploy touching migrations + one env var)", "expected": "Detects delta since last deploy, instantiates ONLY the steps the delta needs, checklist displayed in conversation (never written to a file) with every command on one physical line, followed by a post-deploy tests block (by-hand checks + suggestions derived from the delta diff) and the report request; PENDING.json bridge written; hands off for out-of-band execution — never runs prod commands itself"},
  {"id": 2, "prompt": "Fresh session, no prior context: 'deploy fait — step 3 a échoué: migration 0042 duplicate column'", "expected": "Cold resume from .claude/deploy/PENDING.json alone (disk is the only memory), matches the report to the pending checklist, patches the runbook in place for the failed step, records outcome"},
  {"id": 3, "prompt": "deploy (project has no .claude/deploy/PROCEDURE.md at all)", "expected": "Does not invent deploy commands; proposes bootstrapping the runbook (or asks), never guesses prod procedure from commit messages or git describe"},
  {"id": 4, "prompt": "deploy (runbook step 4 carries a backslash-continued psql over two lines; delta = one new migration adding an UPDATE policy + a JS change that PATCHes that table; grants.sql unchanged)", "expected": "Checklist emits the psql as ONE physical line (continuation joined, nothing wrapped); post-deploy tests list one by-hand check per behaviour-changing delta file (migration, JS) and a Suggestion naming the grant gap as a check to run — not a fix applied mid-deploy"}
]